Scene generation method and device and electronic equipment

Abstract

The invention provides a scene generation method and apparatus, and an electronic device, belongs to the technical field of computers, and aims to solve the problem of tedious operation caused by manual scene configuration by using a scene arrangement tool in related technologies. The method comprises the following steps: identifying a language input by a user to obtain a scene configuration instruction; according to the scene configuration instruction, a configuration file of a target scene service is generated, and the configuration file comprises a trigger condition; and sending the configuration file to a vehicle end for storage, so that the vehicle end sets the target scene service according to the configuration file under the condition that the vehicle use scene conforms to the trigger condition.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a scene generation method, device and electronic device. Background Art

[0002] With the development of 5G and Internet of Vehicles technology, technology, intelligence, and humanity are redefining the new experience of human-machine interaction in the future, and cars are becoming smarter. In the smart cockpit solution, the car use scenario needs to be deeply integrated with the vehicle, user, environment, ecology, and traffic data to form settings that match various scenarios, provide services during driving, simplify driving operations, increase driving safety, optimize the smart experience, and drive smart driving life.

[0003] Related art proposes to use scene arrangement tools to arrange vehicle scenes. However, scene arrangement tools are often cumbersome to operate and require users to complete them through complex interface operations, which is difficult for most users to use. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a scene generation method, device and electronic device. The technical solution of the present disclosure is as follows: According to a first aspect of an embodiment of the present disclosure, a scene generation method is provided, which is applied to a scene editing platform, comprising: Identify the language input by the user and obtain the scene configuration instructions; Generate a configuration file for a target scenario service according to the scenario configuration instruction, wherein the configuration file includes a trigger condition; The configuration file is sent to the vehicle side for storage, so that when the vehicle usage scenario meets the trigger condition, the vehicle side sets the target scenario service according to the configuration file.

[0005] Optionally, generating a configuration file for a target scenario service according to the scenario configuration instruction includes: According to the scenario configuration instruction, determine the target scenario service from the service library; the target scenario service includes hardware service and software service; According to the scenario configuration instruction, the target scenario service is configured to obtain a corresponding configuration file; the configuration file includes a conditional text, a trigger text and an execution text.

[0006] Optionally, identifying the language input by the user and obtaining a scene configuration instruction includes: Preprocessing the voice data corresponding to the configuration voice input by the user to obtain the preprocessed voice data; the preprocessing includes filtering and noise reduction; Extracting representative features from the preprocessed speech data, and obtaining target text through the representative features; The target text is semantically understood to determine the configuration instruction corresponding to the configuration voice.

[0007] Optionally, performing semantic understanding on the target text to determine the configuration instruction corresponding to the configuration voice includes: In the case where a unique configuration instruction cannot be determined according to the target text, determining each initial configuration instruction obtained by semantic understanding of the target text; Sending each of the initial configuration instructions to the vehicle end to obtain a user's confirmation voice for the initial configuration instructions; Performing voice understanding on the confirmation voice to obtain a confirmation instruction; According to the confirmation instruction, determining a target configuration instruction from each of the processing configuration instructions; The target configuration instruction is determined to be the configuration instruction corresponding to the configuration voice.

[0008] According to a second aspect of an embodiment of the present disclosure, a scene generation method is provided, which is applied to a vehicle side and includes: Receive and store a configuration file sent by the scene arrangement platform, wherein the configuration file includes a trigger condition; When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file.

[0009] Optionally, the configuration file includes a conditional text, a trigger text, and an execution text. When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file, including: Determine a trigger condition according to the trigger text; Detecting the vehicle usage scenario in real time to determine whether the vehicle usage scenario meets the conditional text; When the vehicle use scenario satisfies the condition text, determining whether the trigger condition is met; When the trigger condition is met, the target scenario service is set according to the execution text in the configuration file.

[0010] Optionally, the configuration file includes a conditional text, a trigger text, and an execution text. When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file, including: Determine a trigger condition according to the trigger text; Detecting the vehicle usage scenario in real time to determine whether the vehicle usage scenario meets the conditional text; When the vehicle use scenario satisfies the condition text, determining whether the trigger condition is met; When the trigger condition is met, the target scenario service is set according to the execution text in the configuration file.

[0011] Optionally, it also includes: Receiving the initial configuration instruction sent by the scene arrangement platform, and broadcasting the initial configuration instruction; Collect the user's confirmation voice for the initial configuration instruction, and send the confirmation voice to the scene arrangement platform, so that the scene arrangement platform can understand the confirmation voice and obtain the confirmation instruction; according to the confirmation instruction, determine the target configuration instruction from each of the disposal configuration instructions; determine the target configuration instruction as the configuration instruction corresponding to the configuration voice.

[0012] According to a third aspect of an embodiment of the present disclosure, a scene generation device is provided, which is applied to a scene editing platform, including: The recognition module is used to recognize the language input by the user and obtain the scene configuration instructions; A generating module, used to generate a configuration file of a target scenario service according to the scenario configuration instruction, wherein the configuration file includes a trigger condition; The sending module is used to send the configuration file to the vehicle end for storage, so that the vehicle end can set the target scene service according to the configuration file when the vehicle use scene meets the trigger condition.

[0013] According to a fourth aspect of an embodiment of the present disclosure, a scene generation device is provided, which is applied to a vehicle side, and includes: A receiving module, used to receive and store a configuration file sent by the scene arrangement platform, wherein the configuration file includes a trigger condition; An execution module is used to set the target scenario service according to the configuration file when the vehicle usage scenario meets the trigger condition.

[0014] According to a fifth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the scene generation method described in the first aspect or the second aspect are implemented.

[0015] According to a sixth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the scene generation method described in the first aspect or the second aspect are implemented.

[0016] According to a seventh aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the scene generation method described in the first aspect or the second aspect are implemented.

[0017] The present disclosure generates scene configuration instructions by recognizing natural language input by users, which greatly simplifies the complex interface operation process in traditional scene arrangement tools. Users no longer need to have an in-depth understanding of complex setting options or interface layouts. They only need to describe the required scenes in everyday language to quickly implement configuration, which can improve user convenience and satisfaction. By pre-setting trigger conditions, the corresponding scene services are automatically executed when the vehicle meets these conditions, effectively reducing the driver's manual operations during driving, thereby improving driving safety. With the continuous changes in user needs and the development of new technologies, the system can flexibly adjust and optimize the scene configuration to ensure that the latest needs of users are always met. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the description of the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a schematic diagram of a scene generation system shown in an embodiment of the present disclosure; Figure 2 is a schematic diagram of the steps of a scene generation method shown in an embodiment of the present disclosure; Figure 3 is a schematic diagram of the steps of a scene generation method shown in an embodiment of the present disclosure; Figure 4 is a scene generation flow chart shown in an embodiment of the present disclosure; Figure 5 is a schematic diagram of a scene generation device shown in an embodiment of the present disclosure; Figure 6 is a schematic diagram of a scene generation device shown in an embodiment of the present disclosure; Figure 7 It is a schematic diagram of an electronic device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0021] The terms "first", "second", etc. in the specification and claims of the present disclosure are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present disclosure can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0022] With the development of 5G and Internet of Vehicles technology, technology, intelligence, and humanity are redefining the new experience of human-machine interaction in the future, and cars are becoming smarter. In the smart cockpit solution, the car use scenario needs to be deeply integrated with the vehicle, user, environment, ecology, and traffic data to form settings that match various scenarios, provide services during driving, simplify driving operations, increase driving safety, optimize the smart experience, and drive smart driving life.

[0023] It is mentioned in the related art that a scene arrangement tool can be used to arrange vehicle scenes. However, the operation of the scene arrangement tool is often cumbersome and requires users to complete it through complex interface operations, which is difficult for most users to use.

[0024] Therefore, the present disclosure proposes a scenario generation system to solve the problem of cumbersome operation of scenario editing tools. A corresponding configuration file for generating a scenario can be directly generated through user voice, and the configuration file can be executed when the requirements are met to obtain the required vehicle use scenario.

[0025] Figure 1 Schematic diagram of a scene generation system shown in an embodiment of the present disclosure. Figure 1As shown, the system includes a vehicle end and a scene arrangement platform. The vehicle end receives the user's voice and transmits the user's voice to the scene arrangement platform for processing. The scene arrangement platform obtains the corresponding scene configuration instruction according to the user's voice; generates a configuration file for the target scene service according to the scene configuration instruction, and sends the configuration file to the vehicle end. After the vehicle end receives the configuration file, it stores the configuration file. The configuration file can provide a trigger condition. When the vehicle use scene meets the trigger condition, the configuration file is executed to set the target scene service.

[0026] Figure 2 Schematic diagram of the steps of a scene generation method shown in an embodiment of the present disclosure. Figure 2 As shown, the scene generation method is applied to the scene arrangement platform, and may specifically include the following steps: Step S11: Identify the language input by the user and obtain scene configuration instructions.

[0027] The user inputs the requirements for vehicle scenario configuration through natural language. The system uses natural language processing to identify specific scenario configuration instructions, including service type, time conditions, location conditions, event trigger conditions, etc.

[0028] The scene configuration instruction indicates the scene configuration required by the user, and is extracted based on the voice input by the user.

[0029] Step S12: Generate a configuration file for the target scenario service according to the scenario configuration instruction, wherein the configuration file includes a trigger condition.

[0030] Generate a configuration file for the target scene service according to the scene configuration instruction. The configuration file is used to set the target scene service so that the target scene service can provide sub-services that meet the needs of the user. In a specific implementation, the target scene service is the co-pilot screen, which can provide multiple sub-services such as unfolding the co-pilot screen, folding the co-pilot screen, and adjusting the unfolding angle of the co-pilot screen.

[0031] The configuration file can be for one or more target scene services, and multiple target scene services can be set at the same time through one configuration file. The configuration file includes trigger conditions, which are used to set each target scene service according to the configuration file when the vehicle scene meets the trigger conditions.

[0032] Among them, the structure and content of the configuration file can be optimized, such as merging duplicate configurations, optimizing execution logic, etc., to improve the processing efficiency and stability of the vehicle side.

[0033] For example, a corresponding configuration file is generated by the user voice "When there is someone in the passenger seat, expand the passenger screen". Then when there is someone in the passenger seat, it is the trigger condition.

[0034] Step S13: Send the configuration file to the vehicle side for storage, so that the vehicle side can set the target scenario service according to the configuration file when the vehicle usage scenario meets the trigger condition.

[0035] A configuration file for a certain vehicle usage scenario is generated through the scenario orchestration platform and sent to the vehicle side. The vehicle side stores the configuration file but does not immediately execute the operations corresponding to the configuration file.

[0036] When the user is using the car, the current usage of the user will be detected in real time. When the usage meets the trigger conditions, the vehicle will automatically set the target scene service according to the service parameters and logic in the configuration file. Specifically, the target scene services corresponding to the configuration file can be determined and set for each target scene service.

[0037] For example, the corresponding configuration file is generated by the user voice "When the passenger seat is occupied, expand the passenger screen". Then the target scene service is the passenger screen, and expanding the passenger screen is to make specific settings for the target scene service.

[0038] The embodiments of the present disclosure allow users to customize vehicle service scenarios according to their personal preferences and needs, enhancing the comfort and convenience of driving and riding. Through automated scenario configuration and execution, intelligent management of vehicle services is achieved, reducing user manual operations. Dynamic modification and updating of scenario configuration is supported to meet the diverse needs of users at different times and scenarios.

[0039] Among them, in an optional embodiment, a configuration file of the target scene service is generated according to the scene configuration instructions, including: determining the target scene service from a service library according to the scene configuration instructions; the target scene service includes hardware services and software services; configuring the target scene service according to the scene configuration instructions to obtain a corresponding configuration file; the configuration file includes conditional text, trigger text and execution text.

[0040] A service library containing various hardware services and software services can be built. The service library should fully cover all types of services that the vehicle may provide, such as audio control, air conditioning adjustment, seat heating / ventilation, navigation settings, entertainment system, safety system, etc. It is mainly divided into hardware services and software services. Hardware services include doors and windows, seats, seat belts, steering wheels, rearview mirrors, wipers, air conditioning, fragrances, exterior lights, reading lights, ambient lights, main driver's screen, co-driver's screen and HUD; software services include navigation, multimedia and sound. The service library can be updated regularly to include the latest service items and function upgrades to ensure the timeliness and integrity of the service library.

[0041] The service library is located on the scene orchestration platform. After parsing the scene configuration instructions, the scene orchestration platform determines the target scene service that needs to be configured from the service library. The determined target scene service can be a combination of one or more hardware services and software services, for example, all hardware services or all software services, or both hardware services and software services.

[0042] According to the conditional parameters and user preferences in the scene configuration instructions, the target scene service is configured in detail. It can include the specific parameters, trigger conditions and execution logic of the target scene service. Specific parameters can include volume, temperature setting, seat position, etc.; trigger conditions can include time, location, vehicle status, etc.; execution logic can include priority sorting, condition combination logic, etc.

[0043] Integrate the configured service parameters, trigger conditions, execution logic and other information into a configuration file. The configuration file needs to include three texts: condition text, trigger text and execution text. The condition text is used to describe: the prerequisites for triggering the execution of the configuration file; the trigger text is used to describe: the trigger conditions for executing the configuration file when the prerequisites are met; the execution text is used to describe: the specific actions set for the target scenario service.

[0044] The generated configuration file can be logically verified to ensure that all settings are reasonable and feasible. The configuration file targets one or more target scenario services. For example, the same configuration file can be used to configure hardware services and software services, or only software services, or only hardware services.

[0045] By adopting the embodiments of the present disclosure, users can freely combine and customize service scenarios according to their personal preferences and needs to achieve a highly personalized driving experience. Through automated service configuration and triggering mechanisms, intelligent management of vehicle services is achieved, reducing user manual operations. The scenario configuration process is simplified, the user operation difficulty is reduced, and user satisfaction is improved. Regular updates and expansions of the service library provide vehicles with more diverse service options, promoting service innovation and technology upgrades.

[0046] Among them, in an optional embodiment, identifying the language input by the user and obtaining the scene configuration instructions includes: preprocessing the voice data corresponding to the configuration voice input by the user to obtain the preprocessed voice data; the preprocessing includes filtering and noise reduction; extracting representative features from the preprocessed voice data, and obtaining the target text through the representative features; performing semantic understanding on the target text to determine the configuration instructions corresponding to the configuration voice.

[0047] The vehicle side will collect the user's configuration voice through the audio collection device, sample and quantize the configuration voice into a digital signal, and then encode it to form voice data in a specific format. After the vehicle side obtains the voice data corresponding to the configuration voice, it transmits the voice data to the scene arrangement platform.

[0048] The scene arrangement platform performs pre-processing such as filtering and noise reduction on the voice data corresponding to the configuration voice input by the user to obtain the pre-processed voice data.

[0049] Filtering processing means using a digital filter to remove high-frequency noise or unnecessary frequency components in the speech data and retain the main frequency band of the speech signal. For example, the frequency range of human speech is approximately between 300Hz and 3400Hz; the digital filter can be a low-pass filter or a band-pass filter.

[0050] Noise reduction processing means using more complex algorithms to further reduce background noise and improve the signal-to-noise ratio of speech signals. It can distinguish speech and noise more finely, thus removing noise more effectively. These algorithms include spectral subtraction, Wiener filtering, deep learning methods, etc.

[0051] Representative features can be extracted from the pre-processed speech data by extracting parameters that can represent the characteristics of speech signals, such as Mel frequency cepstral coefficients, linear prediction coefficients, etc. These parameters can capture key information such as the pitch and timbre of the speech.

[0052] The extracted representative features are matched with the acoustic model to find the most likely phoneme or word sequence. The acoustic model can be a statistical model trained based on a large amount of speech data. The candidate sequence output by the acoustic model is then decoded using the language model, and the sequence that best conforms to the grammatical and semantic rules is selected as the recognition result. The language model can be a statistical language model, a neural network language model, etc. By using the embodiments of the present disclosure, speech recognition technology can quickly convert the user's verbal instructions into text or perform corresponding operations, reducing the time and labor intensity of manual input. The voice interaction method is more intuitive and convenient than traditional manual input, allowing users to communicate with the machine more naturally. The filtering and noise reduction technology in the preprocessing stage effectively reduces the impact of noise on speech recognition and improves the accuracy of recognition.

[0053] Among them, in an optional embodiment, the target text is semantically understood to determine the configuration instruction corresponding to the configuration voice, including: when a unique configuration instruction cannot be determined based on the target text, each initial configuration instruction obtained by semantic understanding of the target text is determined; each initial configuration instruction is sent to the vehicle end to obtain the user's confirmation voice for the initial configuration instruction; the confirmation voice is voice understood to obtain a confirmation instruction; according to the confirmation instruction, a target configuration instruction is determined from each of the disposal configuration instructions; and the target configuration instruction is determined as the configuration instruction corresponding to the configuration voice.

[0054] Use the scenario orchestration platform to conduct in-depth analysis of the target text. Since the user's expression may be ambiguous or contain multiple possible intentions, in some cases, the scenario orchestration platform will identify all possible configuration intentions and cannot obtain a unique configuration instruction. For example, if the user voice command "When the car door is open, turn on the air conditioner" is received, since the car has four doors, the scenario orchestration platform cannot obtain a unique configuration instruction based on the user's voice.

[0055] Based on the results of multi-intent recognition, a series of initial configuration instructions are generated. Each initial configuration instruction represents a possible configuration requirement in the target text.

[0056] Each initial configuration instruction obtained through the target text is sent to the vehicle end, so that the vehicle end makes an announcement. For example, when the user configures the voice as "When the door is opened, turn on the air conditioner", each initial configuration instruction is converted into a short announcement voice "Which door should I open?" and this short voice is announced.

[0057] The vehicle side collects the user's confirmation voice, which is used to confirm or deny the initial configuration command. The vehicle side sends the collected confirmation voice to the scene arrangement platform, which performs voice recognition and semantic understanding on the user's confirmation voice.

[0058] The scenario arrangement platform determines the target configuration instruction from all the initial configuration instructions according to the user's confirmation instruction. The target configuration instruction indicates the configuration operation that the user really wants to perform. The subsequent configuration operation is performed according to the target configuration instruction.

[0059] With the embodiments of the present disclosure, the system can understand and respond to the user's voice commands through natural language processing and semantic understanding technology. When faced with vague or ambiguous target text, the system does not simply ignore or execute it incorrectly, but attempts to generate multiple possible initial configuration instructions, which can improve the accuracy and flexibility of instruction parsing in the case of complex and changeable natural language. By sending the initial configuration instructions to the vehicle and requesting user confirmation, a user feedback loop is established, which can help the system confirm the user's true intentions and make corrections when necessary. It can be flexibly applied to a variety of vehicle configuration and control scenarios without relying on specific keywords or phrases.

[0060] Figure 3 Schematic diagram of the steps of a scene generation method shown in an embodiment of the present disclosure. Figure 3 As shown, the scene generation method is applied to the vehicle side, and may specifically include the following steps: Step S31: receiving and storing a configuration file sent by the scene editing platform, wherein the configuration file includes a trigger condition.

[0061] The configuration file is generated by the scenario orchestration platform. After the scenario orchestration platform generates the configuration file, it sends the configuration file to the vehicle end, and the vehicle end stores the configuration file. The configuration file is used to generate or activate the detailed information and instructions required for a specific vehicle scenario. The configuration file includes the corresponding trigger conditions.

[0062] After receiving the configuration file, the vehicle stores it in local storage for quick access and execution when needed. During the storage process, the format of the configuration file can be verified and the integrity checked to ensure the validity and security of the file.

[0063] Step S32: When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file.

[0064] The vehicle side parses the stored configuration files, extracts key information, and obtains the trigger conditions, which define when the corresponding vehicle scenarios should be activated or generated.

[0065] According to the analyzed trigger conditions, the vehicle sets up corresponding logic judgment or monitoring mechanism in the internal system. The logic judgment or monitoring mechanism is used to monitor the vehicle status, environmental parameters or user behavior in real time, so as to perform subsequent operations when the trigger conditions are met.

[0066] The vehicle side continuously detects whether the current state meets the trigger conditions defined in the configuration file. Specifically, it can conduct comprehensive analysis and judgment based on data from multiple sources such as vehicle sensor data, user input information, and vehicle location. Once the trigger conditions are detected, the vehicle side sets the target scene service according to the instructions in the configuration file.

[0067] After setting the target scene service, users will be able to feel the changes brought about by the scene, such as music playback, seat adjustment, ambient light changes, etc., thereby improving the driving or riding experience.

[0068] Using the embodiments of the present disclosure, the method enables the vehicle to dynamically adjust its services or behaviors according to the configuration files sent by the outside, such as the scene arrangement platform, thereby improving the intelligence level and adaptive ability of the vehicle. In certain scenarios, such as driving at night, bad weather, etc., the vehicle can automatically turn on the corresponding safety assistance function to reduce the driver's operating burden and improve driving safety. The trigger conditions in the configuration file can be set based on a variety of factors, so that the vehicle can be linked with other smart devices or services, such as smart homes, navigation systems, etc., to provide a more intelligent service experience.

[0069] Among them, in an optional embodiment, the configuration file includes conditional text, trigger text and execution text. When the vehicle use scenario meets the trigger condition, the target scenario service is set according to the configuration file, including: determining the trigger condition according to the trigger text; detecting the vehicle use scenario in real time to determine whether the vehicle use scenario meets the conditional text; when the vehicle use scenario meets the conditional text, judging whether the trigger condition is met; when the trigger condition is met, setting the target scenario service according to the execution text in the configuration file.

[0070] Parse the configuration file to ensure that the conditional text, trigger text, and execution text can be correctly identified and stored in the vehicle's memory or persistent storage medium.

[0071] The specific content of the trigger condition is clarified according to the trigger text. For example, time, location, and vehicle status can all be used as trigger conditions. Real-time detection of vehicle use scenarios can collect the current vehicle operating status and environmental information through the vehicle's sensors and environmental perception devices. Vehicle sensors include GPS, speed sensors, acceleration sensors, etc.; environmental perception devices include cameras, radars, etc.

[0072] The collected information is compared with the conditional text to determine whether the current vehicle usage scenario meets the conditional text provided in the configuration file.

[0073] When the vehicle usage scenario meets the condition text, it is further determined whether the trigger condition is met. If the trigger condition is met, the target scenario service is set according to the execution text in the configuration file. The execution text can clearly specify the target scenario service that needs to be adjusted, the specific parameter values ​​of the adjustment, and the execution order.

[0074] During the execution process, it is necessary to detect the interaction between the vehicle's control system, entertainment system, safety system and other subsystems to ensure the smooth execution of the task.

[0075] By adopting the embodiments of the present disclosure, precise control of service triggering can be achieved by subdividing the trigger conditions into conditional text and trigger text. The conditional text defines the basic characteristics of the scene, while the trigger text further specifies the conditions for triggering the service under these conditions, which can make the trigger logic clearer and more flexible. Real-time detection of the vehicle usage scenario and comparison with the conditional text ensures that the vehicle can dynamically adjust the service settings according to the current environment and status, so that the vehicle can better adapt to the complex and changeable vehicle usage environment and improve user satisfaction. After the vehicle usage scenario meets the conditional text, it is necessary to further determine whether the trigger condition is met, which reduces the service mis-triggering caused by inaccurate conditional judgment and improves the stability and reliability of the system. Once the trigger condition is met, the system will automatically set the target scenario service according to the execution text without manual intervention, which improves the efficiency and accuracy of service settings and reduces the user's operating burden.

[0076] Among them, in an optional embodiment, it also includes: receiving an initial configuration instruction sent by the scene arrangement platform, and broadcasting the initial configuration instruction; collecting the user's confirmation voice for the initial configuration instruction, and sending the confirmation voice to the scene arrangement platform, so that the scene arrangement platform can understand the confirmation voice and obtain a confirmation instruction; according to the confirmation instruction, determining a target configuration instruction from each of the handling configuration instructions; determining the target configuration instruction as the configuration instruction corresponding to the configuration voice.

[0077] Receive the initial configuration instructions sent by the scene arrangement platform, and use the audio output device in the vehicle, such as a speaker, and text-to-speech technology to convert the initial configuration instructions into voice form and play them to the user.

[0078] The vehicle end collects the user's confirmation voice for the initial configuration instruction through its microphone or other audio collection equipment. The confirmation voice is used to confirm or deny the initial configuration instruction. The user's confirmation voice is sent to the scene arrangement platform.

[0079] The scenario orchestration platform analyzes the confirmation voice, uses advanced speech recognition algorithms to convert the voice into text, and then uses natural language processing technology to understand the intent and semantics in the text, and finally generates a confirmation instruction. Based on the user's confirmation instruction, the scenario orchestration platform selects the target configuration instruction from multiple initial configuration instructions. Specifically, by comparing the user's confirmation instruction with the initial configuration instruction, the initial configuration instruction that best matches or best meets the user's needs can be found as the target configuration instruction.

[0080] By adopting the embodiments of the present disclosure, the method provides users with an intuitive and natural way of interaction by broadcasting the initial configuration instructions and collecting the user's confirmation voice. The user can confirm or modify the configuration instructions by voice, thereby improving the user-friendliness and interactivity of the system. The scene arrangement platform performs voice understanding on the user's confirmation voice, and can accurately identify the user's intention and instruction content, reduce configuration errors caused by misoperation or misunderstanding, and improve the accuracy of the configuration. The entire process from receiving the initial configuration instructions to finally determining the target configuration instructions is automated, which can improve the efficiency and response speed of the system. Compared with the traditional manual configuration method, this method reduces the steps of manual intervention. The user only needs to confirm or modify by voice, and the system can automatically complete the subsequent configuration process, reducing the complexity and error rate of manual operation.

[0081] Figure 4 is a scene generation flow chart shown in an embodiment of the present disclosure. Figure 4 As shown, the following is a specific scene generation process.

[0082] The user's voice is collected on the vehicle side, including the user's configuration voice. For example, the user's configuration voice is "When navigation ends and I navigate to the company, remind me to clock in for work", and the configuration voice is converted into voice data and transmitted to the scene arrangement platform.

[0083] The scene arrangement platform receives the voice data corresponding to the configuration voice, and then converts it into text to obtain the target text. The target text is semantically understood to determine the scene configuration instructions. In some cases, the scene arrangement platform cannot obtain a unique scene configuration instruction based on the target text, and may obtain multiple initial scene configuration instructions that may represent the user's intention.

[0084] The scene arrangement platform sends each initial scene configuration instruction to the vehicle end, and the vehicle end broadcasts the instruction by voice. The user gives feedback of confirmation voice based on the broadcast information. The vehicle end collects the confirmation voice and transmits the collected confirmation voice to the scene arrangement platform. The scene arrangement platform understands the confirmation voice and confirms the target scene configuration instruction from each initial scene configuration instruction.

[0085] According to the target scenario configuration instructions, a configuration file corresponding to the target scenario service is generated, and the configuration file is used to generate the corresponding vehicle scenario. The configuration file can include conditional text, trigger text, and execution text. For example, if the user's configuration voice is "When navigation ends and navigates to the company, remind me to punch in for work", then the target scenario service is "Device that can be used for reminders, such as audio or car computer, etc.", the conditional text is "Navigate to the company", the trigger text is "When navigation ends", and the execution text is "Remind me to punch in for work." The configuration file is sent to the vehicle end.

[0086] The vehicle receives the information and stores the configuration file. The vehicle usage scenario of the user is monitored in real time. When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file to present the corresponding vehicle scenario. For example, if the configuration file is generated based on the configuration voice "When navigation ends and I navigate to the company, remind me to clock in for work", if it is detected that the user has navigated to the company, then at the end of navigation, a speaker or other device is used to remind the user to clock in for work.

[0087] Figure 5 Schematic diagram of a scene generation device shown in an embodiment of the present disclosure. Figure 5 As shown, the scene generation device is applied to a scene editing platform, and the scene generation device includes: Identification module 510, used to identify the language input by the user and obtain scene configuration instructions; A generating module 520, configured to generate a configuration file for a target scenario service according to the scenario configuration instruction, wherein the configuration file includes a trigger condition; The sending module 530 is used to send the configuration file to the vehicle end for storage, so that the vehicle end can set the target scene service according to the configuration file when the vehicle use scene meets the trigger condition.

[0088] Optionally, the generating module is specifically used to execute: According to the scenario configuration instruction, determine the target scenario service from the service library; the target scenario service includes hardware service and software service; According to the scenario configuration instruction, the target scenario service is configured to obtain a corresponding configuration file; the configuration file includes a conditional text, a trigger text and an execution text.

[0089] Optionally, the identification module is specifically configured to execute: Preprocessing the voice data corresponding to the configuration voice input by the user to obtain the preprocessed voice data; the preprocessing includes filtering and noise reduction; Extracting representative features from the preprocessed speech data, and obtaining target text through the representative features; The target text is semantically understood to determine the configuration instruction corresponding to the configuration voice.

[0090] Optionally, the identification module is specifically configured to execute: In the case where a unique configuration instruction cannot be determined according to the target text, determining each initial configuration instruction obtained by semantic understanding of the target text; Sending each of the initial configuration instructions to the vehicle end to obtain a user's confirmation voice for the initial configuration instructions; Performing voice understanding on the confirmation voice to obtain a confirmation instruction; According to the confirmation instruction, determining a target configuration instruction from each of the processing configuration instructions; The target configuration instruction is determined to be the configuration instruction corresponding to the configuration voice.

[0091] Figure 6 Schematic diagram of a scene generation device shown in an embodiment of the present disclosure. Figure 6 As shown, the scene generation device is applied to a vehicle end, and the scene generation device includes: The receiving module 610 is used to receive and store the configuration file sent by the scene arrangement platform, wherein the configuration file includes a trigger condition; The execution module 620 is used to set the target scenario service according to the configuration file when the vehicle usage scenario meets the trigger condition.

[0092] Optionally, the configuration file includes a conditional text, a trigger text, and an execution text, and the execution module is specifically used to execute: Determine a trigger condition according to the trigger text; Detecting the vehicle usage scenario in real time to determine whether the vehicle usage scenario meets the conditional text; When the vehicle use scenario satisfies the condition text, determining whether the trigger condition is met; When the trigger condition is met, the target scenario service is set according to the execution text in the configuration file.

[0093] Optionally, the scene generating device further includes: A broadcasting module, used for receiving the initial configuration instruction sent by the scene arrangement platform, and broadcasting the initial configuration instruction; The collection module is used to collect the user's confirmation voice for the initial configuration instruction, and send the confirmation voice to the scene arrangement platform so that the scene arrangement platform can understand the confirmation voice and obtain the confirmation instruction; according to the confirmation instruction, determine the target configuration instruction from each of the disposal configuration instructions; determine the target configuration instruction as the configuration instruction corresponding to the configuration voice.

[0094] It should be noted that the device embodiment is similar to the method embodiment, so the description is relatively simple, and the relevant parts can be referred to the method embodiment.

[0095] The present disclosure also provides an electronic device, referring to Figure 7 , Figure 7 is a schematic diagram of an electronic device shown in an embodiment of the present disclosure. Figure 7 As shown, the electronic device 700 includes: a memory 710 and a processor 720. The memory 710 and the processor 720 are connected via a bus communication. A computer program is stored in the memory 710. The computer program can be run on the processor 720 to implement the steps in the scene generation method disclosed in the embodiment of the present disclosure.

[0096] The embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the scene generation method disclosed in the embodiment of the present disclosure are implemented.

[0097] The embodiments of the present disclosure also provide a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in the scene generation method disclosed in the embodiments of the present disclosure are implemented.

[0098] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0099] It should be understood by those skilled in the art that the embodiments of the present disclosure may be provided as methods, devices or computer program products. Therefore, the embodiments of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The embodiments of the present disclosure are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0103] Although some embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the present disclosure.

[0104] The scene generation method, device and electronic device provided by the present disclosure are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method of the present disclosure and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present disclosure, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present disclosure.

Claims

1. A scene generation method, characterized in that: Applied to scene arrangement platform, including: Identify the language input by the user and obtain the scene configuration instructions; Generate a configuration file for a target scenario service according to the scenario configuration instruction, wherein the configuration file includes a trigger condition; The configuration file is sent to the vehicle side for storage, so that when the vehicle usage scenario meets the trigger condition, the vehicle side sets the target scenario service according to the configuration file.

2. The method according to claim 1, characterized in that Generate a configuration file for the target scenario service according to the scenario configuration instruction, including: According to the scenario configuration instruction, determine the target scenario service from the service library; the target scenario service includes hardware service and software service; According to the scenario configuration instruction, the target scenario service is configured to obtain a corresponding configuration file; the configuration file includes a conditional text, a trigger text and an execution text.

3. The method according to claim 1, characterized in that Identify the language input by the user and obtain the scene configuration instructions, including: Preprocessing the voice data corresponding to the configuration voice input by the user to obtain the preprocessed voice data; the preprocessing includes filtering and noise reduction; Extracting representative features from the preprocessed speech data, and obtaining target text through the representative features; The target text is semantically understood to determine the configuration instruction corresponding to the configuration voice.

4. The method according to claim 2, characterized in that: Performing semantic understanding on the target text to determine the configuration instruction corresponding to the configuration voice includes: In the case where a unique configuration instruction cannot be determined according to the target text, determining each initial configuration instruction obtained by semantic understanding of the target text; Sending each of the initial configuration instructions to the vehicle end to obtain a user's confirmation voice for the initial configuration instructions; Performing voice understanding on the confirmation voice to obtain a confirmation instruction; According to the confirmation instruction, determining a target configuration instruction from each of the processing configuration instructions; The target configuration instruction is determined to be the configuration instruction corresponding to the configuration voice.

5. A scene generation method, characterized in that: Applied to the vehicle side, including: Receive and store a configuration file sent by the scene arrangement platform, wherein the configuration file includes a trigger condition; When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file.

6. The method according to claim 5, characterized in that The configuration file includes a conditional text, a trigger text, and an execution text. When the vehicle usage scenario meets the trigger condition, the target scenario service is set according to the configuration file, including: Determine a trigger condition according to the trigger text; Detecting the vehicle usage scenario in real time to determine whether the vehicle usage scenario meets the conditional text; When the vehicle use scenario satisfies the condition text, determining whether the trigger condition is met; When the trigger condition is met, the target scenario service is set according to the execution text in the configuration file.

7. The method according to claim 5, characterized in that Also includes: Receiving the initial configuration instruction sent by the scene arrangement platform, and broadcasting the initial configuration instruction; Collect the user's confirmation voice for the initial configuration instruction, and send the confirmation voice to the scene arrangement platform, so that the scene arrangement platform can understand the confirmation voice and obtain the confirmation instruction; according to the confirmation instruction, determine the target configuration instruction from each of the disposal configuration instructions; determine the target configuration instruction as the configuration instruction corresponding to the configuration voice.

8. A scene generation device, characterized in that: Applied to scene arrangement platform, including: The recognition module is used to recognize the language input by the user and obtain the scene configuration instructions; A generating module, used to generate a configuration file of a target scenario service according to the scenario configuration instruction, wherein the configuration file includes a trigger condition; The sending module is used to send the configuration file to the vehicle end for storage, so that the vehicle end can set the target scene service according to the configuration file when the vehicle use scene meets the trigger condition.

9. A scene generation device, characterized in that: Applied to the vehicle side, including: A receiving module, used to receive and store a configuration file sent by the scene arrangement platform, wherein the configuration file includes a trigger condition; An execution module is used to set the target scenario service according to the configuration file when the vehicle usage scenario meets the trigger condition.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the scene generation method according to any one of claims 1 to 4 or 5 to 7 are implemented.

Images