Scene generation method and device, equipment, medium and product

Abstract

The invention provides a scene generation method and device, equipment, a medium and a product. The method comprises the steps of obtaining target input of a user; a first data set and a second data set are obtained, and the first data set comprises state data of all modules of the system; the second data set comprises functional data of each module of the system; determining a first scene theme and a first scene triggering condition according to the target input, the first data set and the second data set; inputting the first scene theme and the first scene triggering condition into a target scene generation model to obtain first scene execution data; and generating a first scene according to the first scene theme, the first scene triggering condition and the first scene execution data. The technical problem of low scene editing efficiency caused by tedious scene editing operation in related technologies is solved.

Description

Technical Field

[0001] The present application belongs to the field of machine learning technology, and in particular, relates to a scene generation method, device, equipment, medium and product. Background Art

[0002] In the traditional technical field, scene editing functions mainly rely on users to perform pure manual operations on the user interface. However, this operation method is not only cumbersome but also prone to errors, which greatly increases the user's learning cost and operation difficulty.

[0003] Specifically, traditional scene editing functions lack intelligent and automated support, and users need to manually adjust every detail. The cumbersome operation process reduces the user experience.

[0004] Therefore, in order to improve the user's editing efficiency and experience, the traditional scene editing function can be improved and optimized to stimulate the user's enthusiasm for use and improve the user's operating experience. Summary of the invention

[0005] The embodiments of the present application provide a scene generation method, apparatus, device, storage medium and computer program product, which solve the technical problem in the related art that the scene editing efficiency is low due to the cumbersome scene editing operation.

[0006] In a first aspect, an embodiment of the present application provides a scene generation method, the method comprising:

[0007] Get the user's target input;

[0008] Acquire a first data set and a second data set, wherein the first data set includes status data of each module of the system; and the second data set includes function data of each module of the system;

[0009] Determine a first scene theme and a first scene trigger condition according to the target input, the first data set and the second data set;

[0010] Inputting the first scene theme and the first scene trigger condition into the target scene generation model to obtain the first scene execution data;

[0011] A first scene is generated according to a first scene theme, a first scene trigger condition and first scene execution data.

[0012] In a second aspect, an embodiment of the present application provides a scene generation device, the device comprising:

[0013] The acquisition module is used to obtain the user's target input;

[0014] The acquisition module is further used to acquire a first data set and a second data set, wherein the first data set includes status data of each module of the system; and the second data set includes function data of each module of the system;

[0015] A determination module, used to determine a first scene theme and a first scene trigger condition according to a target input, a first data set and a second data set;

[0016] An input module, used for inputting a first scene theme and a first scene trigger condition into a target scene generation model to obtain first scene execution data;

[0017] A generation module is used to generate a first scene according to a first scene theme, a first scene trigger condition and first scene execution data.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:

[0019] A processor and a memory storing programs or instructions;

[0020] The above method is implemented when the processor executes the program or instruction.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored, and the program or instruction implements the above method when executed by a processor.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the above method.

[0023] In an embodiment of the present application, by obtaining user input and system-related data, and then determining the first scene theme and the first scene trigger condition based on the user input and the system-related data, the first scene theme and the first scene trigger condition are input into the target scene generation model to generate the first scene execution data, and finally the first scene is generated based on the first scene theme, the first scene trigger condition and the first scene execution data. This solution can generate a scene that matches the user input using the target scene generation model based on the user input when receiving the user input, and push it to the user for use, without the need for the user to manually edit the scene, thus solving the technical problem in the related technology that the scene editing operation is cumbersome and leads to low efficiency of scene editing, and improves the user's operating experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] Figure 1 is a flow chart of a scene generation method according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of a scene generation model training method according to an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of the overall process of a scene generation method according to an embodiment of the present invention;

[0028] Figure 4 is a structural block diagram of a scene generation device according to an embodiment of the present invention;

[0029] Figure 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0031] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0032] In addition, it should be noted that the acquisition, storage, use, and processing of data in the embodiments of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, and they should be considered as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0033] In order to solve the problems of the prior art, an embodiment of the present application provides a scene generation method, which can be applied to a vehicle cockpit system for vehicle scene setting. Figure 1 is a flow chart of a scene generation method according to an embodiment of the present invention. Figure 1 As shown, the scene generation method may include the following steps:

[0034] S110, obtaining a target input from a user.

[0035] In S110, the user may input his / her target requirement through the user interface of the system or other interactive methods (such as voice input). For example, the user may input "help me design a scene for the front passenger to welcome the passenger on board", which is the user's target input.

[0036] S120, acquiring a first data set and a second data set, wherein the first data set includes status data of each module of the system; and the second data set includes function data of each module of the system.

[0037] In S120, the first data set mainly includes the status data of each module of the system. For example, it may include the current time, the air conditioning temperature in the car, whether the door is open, the seat position, the window status, etc. These data reflect the current actual status and environmental information of the vehicle. They are used to provide a comprehensive view of the current status of the system and provide the model with necessary context information to understand and predict the user's intentions and needs.

[0038] The second data set mainly includes the functional data of each module of the system. For example, it can include the air volume adjustment range of the air conditioner, the temperature setting range, the seat massage intensity, the speaker volume, etc. These data represent the various functions and operations that the system can perform. The model is provided with an executable atomic capability list, which can include multiple atomic capabilities, each of which corresponds to a functional data. Atomic capabilities are the basic elements for building recommended intelligent scenarios.

[0039] S130, determining a first scene theme and a first scene trigger condition according to the target input, the first data set and the second data set.

[0040] In S130, the system can calculate the matching degree between the target input and each data in the first data set and the second data set, respectively, usually by calculating a similarity score or a probability distribution. Based on the calculated matching degree, the system can filter out system status and function data whose matching degree with the semantic information exceeds a preset threshold.

[0041] For example, system states whose matching degree with “co-pilot, get on the car” exceeds a preset threshold may include “co-pilot door status”, “co-pilot seat status”, etc., while functional data whose matching degree with “welcome” exceeds a preset threshold may include “voice broadcast”.

[0042] By combining the target state data and the target function data, we can obtain the scene themes that the user wants to create (such as "nap mode", "welcome to the front passenger", etc.) and the conditions that trigger these scenes (such as specific time, door state changes, etc.).

[0043] S140, inputting the first scene theme and the first scene trigger condition into the target scene generation model to obtain the first scene execution data.

[0044] In S140, the acquired first scene theme and trigger condition are passed as input to a pre-trained target scene generation model.

[0045] The target scene generation model can generate execution data corresponding to the scene based on the input scene theme and trigger conditions combined with its learned knowledge. These execution data can include a series of actions or operations, such as "turn on the porch light" and "play welcome music".

[0046] S150, generating a first scene according to a first scene theme, a first scene trigger condition and first scene execution data.

[0047] In S150, according to the first scene theme, trigger conditions and scene execution data, the system can construct a complete scene. This scene not only includes the theme and trigger conditions, but also describes in detail which actions or operations should be performed in the scene.

[0048] Finally, the system pushes the generated first scene to the user. This can be presented to the user in an intuitive way through the system's user interface (such as mobile phone APP, smart central control screen, etc.), so that the user can clearly understand the content and execution effect of the scene. At the same time, the system can also provide options for users to choose whether to enable the scene.

[0049] In this way, the system can use the target scene generation model to quickly and accurately generate scenes that meet user needs, and push them to users for selection and activation, thereby greatly improving the system's intelligence level and user experience.

[0050] In an embodiment of the present application, by obtaining user input and system-related data, and then determining the first scene theme and the first scene trigger condition based on the user input and the system-related data, the first scene theme and the first scene trigger condition are input into the target scene generation model to generate the first scene execution data, and finally the first scene is generated based on the first scene theme, the first scene trigger condition and the first scene execution data. This solution can generate a scene that matches the user input using the target scene generation model based on the user input when receiving the user input, and push it to the user for use, without the need for the user to manually edit the scene, thus solving the technical problem in the related technology that the scene editing operation is cumbersome and leads to low efficiency of scene editing, and improves the user's operating experience.

[0051] In some embodiments, determining the first scene theme and the first scene trigger condition according to the target input, the first data set and the second data set includes:

[0052] Extract semantic information of target input;

[0053] A first scene theme and a first scene trigger condition are determined according to the semantic information, the first data set and the second data set.

[0054] In this embodiment, when the user inputs a target instruction or description through the system's user interface, the system will first parse this input and extract the semantic information. This usually involves natural language processing techniques, such as word segmentation, part-of-speech tagging, named entity recognition, etc., to accurately understand the user's intentions and needs. For example, if the user's target input is "help me design a scene for welcoming the co-pilot on board", the extracted semantic information may include "co-pilot", "boarding" and "welcome".

[0055] The extracted semantic information can be used by the system to compare with the two data sets to determine the first scene theme and the first scene trigger condition. The first data set contains the status of each module that the system can currently obtain, while the second data set contains the functions of each module that the system can control.

[0056] For example, the system status may include "in-vehicle temperature", "passenger car door status", "passenger car seat status", "passenger car speaker status", etc., and the functional data may include related actions such as "adjustment", "broadcast", "massage", etc.

[0057] In some embodiments, determining the first scene theme and the first scene trigger condition according to the semantic information, the first data set and the second data set includes:

[0058] By respectively calculating the matching degree between the semantic information and the state data of each module of the system in the first data set, and the functional data of each module of the system in the second data set;

[0059] Determine target state data of multiple modules in the first data set whose matching degree with the semantic information is greater than a first preset threshold, and target function data of multiple modules in the second data set whose matching degree with the semantic information is greater than a second preset threshold;

[0060] According to the target state data and the target function data, the first scene theme and the first scene triggering condition are determined.

[0061] In this embodiment, the system can calculate the matching degree between the semantic information and each data in the two data sets, usually by calculating a similarity score or a probability distribution. Based on the calculated matching degree, the system can filter out the system state and function data whose matching degree with the semantic information exceeds a preset threshold.

[0062] For example, system states whose matching degree with “co-pilot, get on the car” exceeds a preset threshold may include “co-pilot door status”, “co-pilot seat status”, etc., while functional data whose matching degree with “welcome” exceeds a preset threshold may include “voice broadcast”.

[0063] By combining the target state data and the target function data, we can obtain the scene themes that the user wants to create (such as "nap mode", "welcome to the front passenger", etc.) and the conditions that trigger these scenes (such as specific time, door state changes, etc.).

[0064] In some embodiments, before inputting the first scenario theme and the first scenario trigger condition into the target scenario generation model to obtain the first scenario execution data, the method further includes:

[0065] Acquire a third data set, the third data set including a plurality of training scenarios pre-set according to the status data and function data of each module of the system, each training scenario including a training scenario theme, a training scenario triggering condition and corresponding training scenario execution data;

[0066] Extract features of the first data set and the second data set respectively, perform feature fusion and data enhancement, and obtain a fused data set;

[0067] The preset neural network model is trained according to the fused data set and the third data set to obtain a target scene generation model.

[0068] In this embodiment, the third data set includes several training scenarios pre-set according to the status data and functional data of each module of the system. For example, each training scenario includes a training scenario theme (such as nap mode, driving mode, etc.), a training scenario trigger condition (such as the vehicle speed reaches a specific value, the door is closed, etc.) and the corresponding training scenario execution data (such as adjusting the seat angle, lowering the air-conditioning temperature, etc.). The model is provided with sample data required for training. By learning and understanding these preset training scenarios, the model can gradually master how to generate recommended intelligent scenarios based on user intent and contextual information.

[0069] In this way, by obtaining the first, second and third data sets containing system status, functional data and preset training scenarios, comprehensive training materials are provided for the model, enabling it to accurately understand user intentions and generate intelligent scenario recommendations that meet needs.

[0070] In this embodiment, before feature fusion, the first data set and the second data set can be preprocessed, including data cleaning (removing duplicate, erroneous or missing data), data normalization or standardization (ensuring that different features are on the same scale), and possible feature selection (selecting the features that are most useful for subsequent tasks).

[0071] For the first data set, key features that can reflect the current state of the system can be extracted, such as the current time, the temperature inside the car, the door switch status, etc. For the second data set, features that can describe the executable operations of the system can be extracted, such as the air conditioning volume adjustment range, the seat massage level, the speaker volume, etc.

[0072] After extracting features, you can select appropriate feature fusion strategies to fuse the extracted features according to task requirements and data characteristics. Examples include simple concatenation, weighted summation, feature interaction (such as product, polynomial expansion), and main cause analysis.

[0073] Apply the selected feature fusion strategy to combine the extracted features to form a new fused dataset. This dataset will contain the joint features from the original two datasets, as well as new features generated by feature interaction.

[0074] After feature fusion, the fused data set can be enhanced to increase the diversity and robustness of the data. Data enhancement can include a variety of methods, such as data expansion (generating new data samples by adding noise, transformation, etc.), data balancing (adjusting the proportion of different categories of data to improve the generalization ability of the model), etc.

[0075] In this way, through preprocessing, feature extraction, fusion and data enhancement, the system status and functional data are effectively integrated, the feature dimensions are enriched, the data diversity is enhanced, and a more comprehensive and robust fused data set is provided for subsequent model training.

[0076] In this embodiment, the preset neural network model can be a deep learning model, such as a convolutional neural network, a recurrent neural network, or a more complex variant, such as a Transformer, etc. The structure of the neural network model can be adjusted and optimized according to specific application scenarios and requirements, and there is no limitation on this.

[0077] Use the prepared data set to train the preset neural network model. The training process can include steps such as forward propagation, calculation of loss function, back propagation, and parameter update.

[0078] During the training process, some optimization algorithms and techniques are also used to improve training efficiency and model performance, such as learning rate adjustment, regularization, batch normalization, etc.

[0079] After a certain number of iterations of the above steps, a trained neural network model, namely the target scene generation model, can be obtained. This model can generate corresponding scene execution actions based on the input scene theme and scene trigger conditions.

[0080] It is understandable that in order to ensure that the target scene generation model can meet the needs of actual applications, the target scene generation model can also be verified and optimized. This includes using a test data set to evaluate the performance of the model, adjusting model parameters to improve accuracy, etc.

[0081] In this way, by iteratively training the preset neural network model and combining the fusion data set with the preset training scenario, a target scenario generation model was successfully constructed. This model can efficiently and accurately generate intelligent scenario execution actions based on the input conditions to meet actual application needs.

[0082] In some embodiments, a preset neural network model is trained according to the fused data set and the third data set to obtain a target scene generation model, including:

[0083] The preset neural network model is trained according to the fused data set and the third data set to obtain an initial scene generation model;

[0084] Acquire a fourth data set, the fourth data set including a plurality of verification scenarios pre-set according to the status data and function data of each module of the system, each verification scenario including a verification scenario subject, a verification scenario triggering condition and corresponding verification scenario execution data;

[0085] Extract verification scenario topics and verification scenario triggering conditions of several verification scenarios to obtain verification data;

[0086] Input the verification data into the initial scenario generation model to obtain the model scenario execution data;

[0087] Compare the model scenario execution data with the verification scenario execution data of several verification scenarios to obtain a comparison result;

[0088] The initial scene generation model is modified according to the comparison results to obtain the target scene generation model.

[0089] In this embodiment, first, the fused data set and the third data set can be used to train the preset neural network model. This training process is intended to allow the model to learn the mapping relationship from system status and function data to potential scene themes and trigger conditions.

[0090] After a certain number of rounds of training, an initial scenario generation model can be obtained. This model can initially generate corresponding scenario execution data based on the input scenario theme and trigger conditions, but its accuracy and generalization ability still need to be improved.

[0091] Next, in order to evaluate and further improve the performance of the model, a validation dataset (the fourth dataset) needs to be prepared. This dataset contains several pre-set validation scenarios, each of which defines the scenario theme, trigger conditions, and corresponding execution data in detail. These validation scenarios can be designed based on actual situations that the system may encounter to ensure that the model can perform well when facing real scenarios.

[0092] The subject and trigger conditions of the verification scenario are extracted from the verification data set and input into the initial scenario generation model obtained through preliminary training as verification data. The model will generate model scenario execution data based on the input verification data, that is, the actions or operations that should be performed in the scenario predicted by the model.

[0093] Compare the scenario execution data generated by the model with the corresponding verification scenario execution data in the verification data set to evaluate the accuracy of the model. According to the comparison results, if there is a large difference between the execution data generated by the model and the verification data, it means that the model is still insufficient in some aspects and needs to be corrected.

[0094] The correction process can include adjusting model parameters, optimizing network structure, increasing training data, etc. to improve the accuracy and generalization ability of the model.

[0095] Through multiple iterations of the above steps, the model is continuously corrected and optimized until the difference between the scenario execution data generated by the model and the verification data set reaches an acceptable range. At this time, the model obtained is the target scenario generation model.

[0096] In this way, by training and correcting the model, it is ensured that the target scenario generation model obtained can accurately generate scenario themes, trigger conditions and execution data that meet user expectations when faced with actual scenarios, thereby providing users with more intelligent and personalized services.

[0097] In some embodiments, after generating the first scene according to the first scene theme, the first scene trigger condition and the first scene execution data, the method further includes:

[0098] When the first scenario triggering condition is detected, the first scenario is executed according to the first scenario execution data.

[0099] In this embodiment, the system will continuously monitor the status of each module and external events to detect whether the triggering condition of the first scene previously pushed to the user is met.

[0100] For example, if the user accepts a recommended scenario whose trigger condition is "the front passenger door is open, and the front passenger seat occupancy signal changes from unoccupied to occupied", the system will monitor the door status and seat occupancy status in real time.

[0101] Once the trigger condition is detected, the system will execute the scenario according to the first scenario execution data generated previously. The execution data may include a series of execution actions. For example, in this example, the execution action may be "voice broadcast welcome words 'Welcome the distinguished hostess to take a seat'".

[0102] The system will execute these actions one by one in the order and requirements of the execution data to complete the execution of the entire intelligent scene.

[0103] After the execution is completed, the system can provide feedback to the user on the execution results, such as through UI display or voice broadcast, to inform the user that the scenario has been successfully executed, and can provide some additional information or prompts.

[0104] This ensures that the scenario is accurately executed under the correct conditions, thereby improving the user experience and the intelligence level of the system.

[0105] Figure 2 is a flow chart of a scene generation model training method according to an embodiment of the present invention;

[0106] S201, organize the states of each module that the system can obtain into a first data set. S202, organize the functions of each module that the system can control into a second data set. S203, define a batch of preset smart scenes according to the atomic capabilities as the third data set. S204, train the preset neural network model according to the first, second and third data sets. S205, define a batch of preset smart scenes according to the atomic capabilities as the fourth data set. S206, extract the themes and trigger conditions of the preset smart scenes. S207, input the extracted themes and trigger conditions into the preset neural network model. S208, the preset neural network model generates recommended scene execution actions. S209, compare the execution actions generated by the preset neural network model with the actions defined by the preset scenes. S210, correct the preset neural network model and obtain the corrected model. S211, repeat the above steps to train the target scene generation model.

[0107] Figure 3 This is a schematic diagram of the overall process of a scene generation method according to an embodiment of the present invention; S301, obtain the user's target input. S302, extract the semantic information of the target input. S303, the model scores the atomic capability matching one by one. S304, obtain the atomic capability with a matching degree greater than a preset threshold. S305, determine the scene theme and scene trigger condition of the scene based on the atomic capability. S306, generate execution data based on the scene theme and scene trigger condition of the scene. S307, generate the first scene and push it to the customer.

[0108] Figure 4 A schematic structural diagram of a scene generation device provided in another embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0109] Reference Figure 4 , the scene generation device 400 may include:

[0110] The acquisition module 401 is used to acquire the target input of the user;

[0111] The acquisition module 401 is further used to acquire a first data set and a second data set, wherein the first data set includes status data of each module of the system; and the second data set includes function data of each module of the system;

[0112] A determination module 402, configured to determine a first scene theme and a first scene trigger condition according to a target input, a first data set, and a second data set;

[0113] An input module 403, used to input the first scene theme and the first scene trigger condition into the target scene generation model to obtain the first scene execution data;

[0114] The generating module 404 is used to generate the first scene according to the first scene theme, the first scene triggering condition and the first scene execution data.

[0115] In some embodiments, the determination module 402 may include the following units:

[0116] An extraction unit, used to extract semantic information of the target input;

[0117] The determination unit is used to determine the first scene theme and the first scene trigger condition according to the semantic information, the first data set and the second data set.

[0118] In some embodiments, the determining unit may include the following subunits:

[0119] A calculation subunit, used to calculate the matching degree between the semantic information and the state data of each module of the system in the first data set, and the functional data of each module of the system in the second data set;

[0120] A determination subunit, configured to determine target state data of a plurality of modules in the first data set whose matching degree with the semantic information is greater than a first preset threshold, and target function data of a plurality of modules in the second data set whose matching degree with the semantic information is greater than a second preset threshold;

[0121] The determination subunit is also used to determine the first scene theme and the first scene trigger condition according to the target state data and the target function data.

[0122] In some embodiments, the scene generation device 400 may include:

[0123] The acquisition module 401 is further used to obtain a third data set before inputting the first scene theme and the first scene trigger condition into the target scene generation model to obtain the first scene execution data, the third data set including a plurality of training scenes pre-set according to the status data and function data of each module of the system, each training scene including a training scene theme, a training scene trigger condition and corresponding training scene execution data;

[0124] A processing module, used to extract features of the first data set and the second data set respectively, perform feature fusion and data enhancement, and obtain a fused data set;

[0125] The training module is used to train the preset neural network model according to the fused data set and the third data set to obtain a target scene generation model.

[0126] In some embodiments, the training module may include the following units:

[0127] A training unit, used to train a preset neural network model according to the fused data set and the third data set to obtain an initial scene generation model;

[0128] an acquisition unit, configured to acquire a fourth data set, the fourth data set comprising a plurality of verification scenarios pre-set according to the status data and function data of each module of the system, each verification scenario comprising a verification scenario subject, a verification scenario triggering condition and corresponding verification scenario execution data;

[0129] An extraction unit, used to extract verification scenario themes and verification scenario triggering conditions of a plurality of verification scenarios to obtain verification data;

[0130] An input unit, used to input verification data into the initial scenario generation model to obtain model scenario execution data;

[0131] A comparison unit, used to compare the model scenario execution data with the verification scenario execution data of several verification scenarios to obtain a comparison result;

[0132] The correction unit is used to correct the initial scene generation model according to the comparison result to obtain the target scene generation model.

[0133] In some embodiments, the scene generation device 400 may include:

[0134] The execution module is used to generate the first scene according to the first scene theme, the first scene trigger condition and the first scene execution data, and then execute the first scene according to the first scene execution data when the first scene trigger condition is detected.

[0135] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application, and are devices corresponding to the above-mentioned scene generation method. All implementation methods in the above-mentioned method embodiment are applicable to the embodiment of the device. Its specific functions and technical effects brought about can be found in the method embodiment part, which will not be repeated here.

[0136] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0137] Figure 5 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Figure 5 As shown:

[0138] The device may include a processor 501 and a memory 502 storing programs or instructions.

[0139] When the processor 501 executes the program, the steps in any of the above method embodiments are implemented.

[0140] Exemplarily, the program may be divided into one or more modules / units, one or more modules / units are stored in the memory 502, and executed by the processor 501 to complete the present application. One or more modules / units may be a series of program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the program in the device.

[0141] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0142] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0143] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0144] The processor 501 implements any one of the methods in the above embodiments by reading and executing the program or instruction stored in the memory 502 .

[0145] In one example, the electronic device may further include a communication interface 503 and a bus 504. The processor 501, the memory 502, and the communication interface 503 are connected via the bus 504 and communicate with each other.

[0146] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0147] Bus 504 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 504 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0148] In addition, in combination with the method in the above embodiment, the embodiment of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores a program or instruction; when the program or instruction is executed by a processor, any one of the methods in the above embodiment is implemented. The computer-readable storage medium can be read by a machine such as a computer.

[0149] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0150] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0151] An embodiment of the present application provides a computer program product, which is stored in a computer-readable storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0152] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0153] The functional modules shown in the above block diagram can be implemented as hardware, software, firmware or their combination. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments can be downloaded via computer grids such as the Internet, intranets, etc.

[0154] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0155] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by a computer program or instruction. These programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0156] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A scene generation method, characterized in that: The method comprises: Get the user's target input; Acquire a first data set and a second data set, wherein the first data set includes status data of each module of the system; and the second data set includes function data of each module of the system; Determining a first scene theme and a first scene trigger condition according to the target input, the first data set, and the second data set; Inputting the first scenario theme and the first scenario triggering condition into a target scenario generation model to obtain first scenario execution data; A first scene is generated according to the first scene theme, the first scene trigger condition and the first scene execution data.

2. The method according to claim 1, characterized in that The determining, according to the target input, the first data set, and the second data set, a first scene theme and a first scene trigger condition includes: Extracting semantic information of the target input; A first scene theme and a first scene trigger condition are determined according to the semantic information, the first data set, and the second data set.

3. The method according to claim 2, characterized in that The determining, according to the semantic information, the first data set, and the second data set, a first scene theme and a first scene trigger condition includes: respectively calculating the matching degree between the semantic information and the status data of each module of the system in the first data set, and the matching degree between the semantic information and the function data of each module of the system in the second data set; Determine target state data of a plurality of modules in the first data set whose matching degree with the semantic information is greater than a first preset threshold, and target function data of a plurality of modules in the second data set whose matching degree with the semantic information is greater than a second preset threshold; The first scene theme and the first scene trigger condition are determined according to the target state data and the target function data.

4. The method according to claim 1, characterized in that: Before inputting the first scenario theme and the first scenario trigger condition into the target scenario generation model to obtain the first scenario execution data, the method further includes: Acquire a third data set, the third data set comprising a plurality of training scenarios pre-set according to the status data and function data of each module of the system, each training scenario comprising a training scenario theme, a training scenario triggering condition and corresponding training scenario execution data; Extracting features of the first data set and the second data set respectively, performing feature fusion and data enhancement, and obtaining a fused data set; A preset neural network model is trained according to the fused data set and the third data set to obtain the target scene generation model.

5. The method according to claim 4, characterized in that The step of training a preset neural network model according to the fused data set and the third data set to obtain a target scene generation model includes: Training a preset neural network model according to the fused data set and the third data set to obtain an initial scene generation model; Acquire a fourth data set, the fourth data set comprising a plurality of verification scenarios pre-set according to the status data and function data of each module of the system, each verification scenario comprising a verification scenario subject, a verification scenario triggering condition and corresponding verification scenario execution data; Extracting verification scenario themes and verification scenario triggering conditions of the plurality of verification scenarios to obtain verification data; Inputting the verification data into the initial scenario generation model to obtain model scenario execution data; Comparing the model scenario execution data with the verification scenario execution data of the plurality of verification scenarios to obtain a comparison result; The initial scene generation model is modified according to the comparison result to obtain the target scene generation model.

6. The method according to claim 1, characterized in that After generating the first scene according to the first scene theme, the first scene trigger condition and the first scene execution data, the method further includes: When the first scenario triggering condition is detected, the first scenario is executed according to the first scenario execution data.

7. A scene generation device, characterized in that: The device comprises: The acquisition module is used to obtain the user's target input; The acquisition module is further used to acquire a first data set and a second data set, wherein the first data set includes status data of each module of the system; and the second data set includes function data of each module of the system; a determination module, configured to determine a first scene theme and a first scene trigger condition according to the target input, the first data set, and the second data set; An input module, used for inputting the first scenario theme and the first scenario triggering condition into a target scenario generation model to obtain first scenario execution data; A generation module is used to generate a first scene according to the first scene theme, the first scene trigger condition and the first scene execution data.

8. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method according to any one of claims 1 to 6.

Images