Rapid scene generation method based on cockpit system

Abstract

The invention discloses a rapid scene generation method based on a cockpit system, and belongs to the technical field of Internet of Vehicles. Comprising the following steps: S1, defining a scene type through a user behavior mode and establishing a scene model; s2, analyzing a scene demand of a user, and optimizing the scene model according to an analysis result; s3, constructing a scene adaptability algorithm, and performing priority ranking on the scenes based on the scene adaptability algorithm to obtain a ranked scene list; and S4, generating an initial service scene based on the sorted scene list, and then performing optimization to obtain an intelligent service scene. The technical scheme has the beneficial effects that seamless connection between the cabin system and the external application is realized, the user experience and the driving safety are improved, the operation burden of a driver is reduced, and the requirements of the intelligent cabin system are met.

Description

Technical Field

[0001] The present invention relates to the field of vehicle networking technology, and in particular to a quick scene generation method based on a cockpit system. Background Art

[0002] With the growing demand for smart transportation, it is particularly important to implement a true cross-platform zero-adaptation solution. A zero-adaptation solution means that the vehicle cockpit system can seamlessly connect with a wide range of third-party applications without additional configuration or modification. This solution significantly lowers the threshold for technology integration, speeds up the launch of new features and services, and improves the user's interactive experience in different application scenarios.

[0003] Although there are some preliminary solutions on the market that attempt to solve the cross-platform problem, these solutions are usually limited to specific ecosystems or rely on complex middleware and conversion layers. This not only increases the complexity of the system architecture, but may also introduce additional performance overhead and security risks. In addition, existing solutions often seem to be unable to cope with emerging technology trends such as 5G communications, edge computing, and artificial intelligence algorithms, and are difficult to meet the needs of future smart cockpit systems. Summary of the invention

[0004] The purpose of the present invention is to provide a quick scene generation method based on a cockpit system to solve the above technical problems.

[0005] A quick scene generation method based on a cockpit system, comprising:

[0006] Step S1, defining the scenario type and establishing a scenario model based on the user behavior pattern;

[0007] Step S2, analyzing the user's scenario requirements and optimizing the scenario model according to the analysis results;

[0008] Step S3, constructing a scene adaptability algorithm, and prioritizing the scenes based on the scene adaptability algorithm to obtain a prioritized scene list;

[0009] Step S4, generating an initial service scenario based on the sorted scenario list and then optimizing it to obtain an intelligent service scenario.

[0010] Preferably, step S3 comprises:

[0011] Step S31, calculating the initial priority based on the user's preference coefficient for the scene type;

[0012] Step S32, sorting all scenes according to the initial priority scores to obtain an initial list;

[0013] Step S33, the user interacts with the in-vehicle assistant to extract key information input by the user;

[0014] Step S34, sorting the initial list according to the extracted key information to obtain the sorted scene list.

[0015] Preferably, the calculation formula of the initial priority in step S31 is:

[0016]

[0017] Among them, P i Indicates the initial priority, Indicates scene S i The inherent score of Indicates the preference coefficient for the scene type according to user preference.

[0018] Preferably, step S33 includes:

[0019] Step S331, receiving user input;

[0020] Step S332: the in-vehicle assistant performs natural language processing on the user input to extract key information from the user input.

[0021] Preferably, the sorting process in step S34 includes:

[0022] Start traversing from the first scene in the initial list, compare the priorities of adjacent scenes in turn, and when the priority of the latter scene is higher than that of the former scene according to the priority adjustment parameter, exchange the scene positions until there is no position exchange after traversal, and output the sorted scene list.

[0023] Preferably, the priority adjustment parameter includes preferences directly input by a user or environmental data collected by a sensor.

[0024] Preferably, the method further includes step S0, designing a rule engine framework and developing a cross-platform adaptation layer according to a cross-platform interface document to connect third-party applications to the cockpit system.

[0025] Preferably, the scene types in step S1 include at least a navigation scene, an entertainment scene and an emergency call scene.

[0026] Preferably, the scenario model optimized in step S2 includes scenario triggering conditions, corresponding service processes and expected outputs.

[0027] Preferably, the cross-platform interface document in step S0 includes an interface data format, an interface calling method and an error handling mechanism.

[0028] The beneficial effects of the present invention are: achieving seamless connection between the cockpit system and external applications, improving user experience and driving safety, reducing the driver's operating burden, and meeting the needs of the intelligent cockpit system. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of a quick scene generation method based on a cockpit system of the present invention;

[0030] Figure 2 is a schematic diagram of step S3 of the present invention;

[0031] Figure 3 It is a schematic diagram of step S33 of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0034] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0035] A quick scene generation method based on cockpit system, such as Figure 1 As shown, including

[0036] Step S1, defining the scenario type and establishing a scenario model based on the user behavior pattern;

[0037] Step S2, analyzing the user's scenario requirements and optimizing the scenario model according to the analysis results;

[0038] Step S3, constructing a scene adaptability algorithm, and prioritizing the scenes based on the scene adaptability algorithm to obtain a prioritized scene list;

[0039] Step S4, generating an initial service scenario based on the sorted scenario list and then optimizing it to obtain an intelligent service scenario.

[0040] Specifically, the present invention provides a quick scene generation method based on a cockpit system, which realizes seamless connection between the cockpit system and external applications, improves user experience and driving safety, reduces the driver's operating burden, and meets the needs of an intelligent cockpit system.

[0041] A scenario refers to an environment in which a user performs a specific task. For example, when a user inputs "I want to go home and navigate the way home", a specific scenario is formed: the home-going scenario. The scenario includes the user's purpose (going home) and the required function (navigation). The user behavior pattern is the regular behavior of the user when using the product. In the implementation of the home-going scenario, the user's behavior pattern includes purpose orientation (the user explicitly expresses the need to go home), content recognition (recognizing the user's current location and destination), and function call (realizing the need to go home through the navigation function).

[0042] In a preferred embodiment, referring to Figure 2 , step S3 comprises:

[0043] Step S31, calculating the initial priority based on the user's preference coefficient for the scene type;

[0044] Step S32, sorting all scenes according to the initial priority scores to obtain an initial list;

[0045] Step S33, the user interacts with the in-vehicle assistant to extract key information input by the user;

[0046] Step S34, sorting the initial list according to the extracted key information to obtain a sorted scene list.

[0047] Specifically, the system optimizes scenarios based on the user's historical interactions and preferences, making each interaction more in line with user needs. By obtaining specific needs and scenarios through the interaction between the user and the in-car assistant, the system can instantly reflect the user's needs and make corresponding adjustments to make the interaction smoother. The initial list is finally sorted based on user input and priority scores to obtain a list of scenarios that meet the current user needs.

[0048] In a preferred embodiment, the calculation formula of the initial priority in step S31 is:

[0049]

[0050] Among them, P i Indicates the initial priority, Indicates scene S i The inherent score of Indicates the preference coefficient for scene type based on user preference.

[0051] Specifically, the inherent score is a default score number set based on the rule scenario engine, and the default value is 100.

[0052] In a preferred embodiment, referring to Figure 3 , step S33 comprises:

[0053] Step S331, receiving user input;

[0054] Step S332: The in-vehicle assistant performs natural language processing on the user input to extract key information from the user input.

[0055] Specifically, user input can be voice input or text input. Taking voice input as an example, the in-car assistant is a voice assistant, and the scenario is: play the most recently played music and find the most recently played music in the multi-music APP. Extract keywords from the user's voice, which can be commands, locations, time, etc. Establish a mapping table between keywords and application scenarios to achieve fast retrieval and matching.

[0056] Taking text input as an example, natural language processing divides continuous text into meaningful words or phrases, analyzes the structure of sentences, and identifies the relationship between words to understand the grammatical meaning of sentences. Understand the deeper meaning of the text, including context, sentiment analysis, and intent recognition. The in-car assistant then identifies the most important information or keywords from the text, and quickly retrieves and responds to user needs based on these keywords. Compare the extracted keywords with the preset rules to quickly find relevant application scenarios.

[0057] In a preferred embodiment, the sorting process in step S34 includes:

[0058] Start traversing from the first scene in the initial list, and compare the priorities of adjacent scenes in turn. When the priority of the latter scene is higher than that of the former scene according to the priority adjustment parameter, swap the scene positions until there is no position swap after traversal, and output the sorted scene list;

[0059] Priority adjustment parameters include preferences directly entered by the user or environmental data collected through sensors.

[0060] Specifically, the scenario adaptability algorithm is a model for dynamically adjusting the priority of scenario services. It dynamically adjusts the scenario ranking according to the user's preferences and needs, enabling the in-vehicle assistant to more intelligently understand the user's intentions and provide more relevant scenarios. The priority and service strategy of the scenario are updated in real time based on the user's personalized preferences and surrounding environmental conditions. The model is trained to understand the feature differences in different platforms and environments, so as to identify the optimal scenario service configuration.

[0061] Prioritization parameters such as user preferences and environmental data enable the system to dynamically adapt to different users and environmental changes, thereby providing more personalized and relevant scenario recommendations.

[0062] The sorting process allows the system to optimize based on real-time data, so that the final output scene list always reflects the current actual situation and user needs. Adjustment based on user input and environmental data can improve the system's response speed and accuracy to user needs and enhance the user experience.

[0063] In a preferred embodiment, the method further includes step S0, designing a rule engine framework and developing a cross-platform adaptation layer according to a cross-platform interface document to connect a third-party application to the cockpit system;

[0064] In step S0, the cross-platform interface document includes an interface data format, an interface calling method, and an error handling mechanism.

[0065] Specifically, the rule engine architecture includes rule storage, rule execution, and rule update mechanisms. All rules are stored centrally for easy management and maintenance, ensuring the uniformity and consistency of the rules. Rules are efficiently retrieved and applied, improving the system's response speed and processing efficiency. New rules can be easily added or modified without rewriting the core logic of the system.

[0066] The rule engine automatically applies rules, reducing manual intervention and improving the degree of automation of decision-making. It can process input data and apply rules in real time, so as to make quick responses and decisions. It supports complex logical judgments and rule combinations, improving the system's ability to handle complex scenarios.

[0067] Ability to dynamically update rules without restarting the system or performing complex maintenance operations. Quickly respond to changes in the environment or user needs to ensure that the system always meets the latest requirements. Supports version management and rollback of rules to ensure stability and traceability during rule changes.

[0068] Specifically, we will write cross-platform interface documents and provide sample codes to facilitate third-party developers to access them.

[0069]

[0070]

[0071]

[0072] In a preferred embodiment, the scene types in step S1 include at least a navigation scene, an entertainment scene, and an emergency call scene, and also include other extended scenes, such as a user-defined scene.

[0073] Specifically, clear scenario classification helps the system to more effectively handle and manage different types of scenarios and improve the accuracy of responses. It can provide more appropriate services or functions for specific scenarios and improve the user experience.

[0074] Optimizing processing for different scenario types can reduce the complexity of system processing and improve overall operational efficiency. Classification enables the system to meet different user needs, such as navigation, entertainment or emergency situations, enhancing the flexibility and practicality of the system.

[0075] In a preferred embodiment, the optimized scenario model in step S2 includes scenario triggering conditions, corresponding service processes and expected outputs.

[0076] Specifically, clear scenario trigger conditions ensure that the system can accurately identify when to activate a specific scenario, improving the accuracy and timeliness of the response.

[0077] Clearly defined service processes ensure that each scenario is handled consistently and effectively, thereby optimizing service quality and user experience.

[0078] Setting expected outputs helps the system set clear goals and standards during processing, improving the predictability and consistency of results. The optimized model simplifies the complexity of scene processing and improves the system's operating efficiency and resource utilization.

[0079] The present invention solves the data synchronization problem between the cockpit and the APP through the interaction between the cockpit system and the APP, ensuring the consistency and real-time nature of the information. A two-way communication mechanism is implemented, allowing the APP to send instructions to the cockpit, and also supporting the cockpit to request data or services from the APP.

[0080] Specifically, the present invention is used to achieve seamless connection between the cockpit system and third-party applications, achieving a user experience of "what you say is what you get" and "what you write is what you get". Taking voice input as an example, the specific steps are as follows:

[0081] First, the owner inputs the voice behavior;

[0082] Then, the system determines the owner's behavior, retrieves local information, and opens the local application if the information is found. If it is not recognized, it searches the cloud, traverses all third-party applications, and provides personalized scenario services.

[0083] Among them, the key technologies are:

[0084] (1) Development of a cross-platform adaptation layer, creating a middleware or service layer to uniformly manage the communication between the cockpit system and multiple third-party applications, solving the technical pain points of cross-platform and cross-application connectivity;

[0085] (2) Natural language processing optimization, using NLP (natural language processing) for word segmentation, grammatical analysis, semantic understanding, etc., to optimize voice and text processing logic;

[0086] (3) Keyword extraction and matching: extract keywords from user input and quickly search and match corresponding application scenarios according to preset rules.

[0087] Suppose a user needs to quickly set up a home-coming scene, which includes turning on the air conditioner in the car, playing specific music, and notifying smart home devices in advance to prepare for the user to come home.

[0088] The keyword "home mode" in this scenario is extracted through the user's voice "home mode" or text input "home mode". The rule engine recognizes "home mode" and matches the corresponding scenario service according to the preset rules. Automatically start the air conditioner in the car and adjust it to the preset temperature. Play specific music from the music app. Send instructions through the smart home app to turn on the preset home welcome songs such as lights, TV and air conditioner at home.

[0089] The cockpit system responds via voice: "Everything is ready for you to go home."

[0090] Through this implementation, users can enjoy a seamless intelligent experience, and the cockpit system can also more flexibly integrate third-party services to provide personalized scenario services. By using natural language processing technology, semantic understanding and customized rules, it can quickly respond to user needs without changing the existing system architecture, provide personalized services and experiences, and provide users with unprecedented convenient and safe travel experience, while injecting new vitality into the development of the entire intelligent transportation industry.

[0091] The present invention solves the problem of cross-platform communication and achieves zero adaptation. Any third-party application can access the smart cockpit ecosystem in the simplest way. It realizes seamless connection between the cockpit system and third-party applications, improves user experience and driving safety, reduces the operating burden of the driver, provides an open access platform for third-party applications, and meets the needs of the smart cockpit system.

[0092] In summary, this application provides a quick scene generation method based on the cockpit system, focusing on the fields of intelligent transportation systems (ITS) and vehicle-to-everything (V2X), with special attention to in-vehicle intelligent cockpit technology and its integration with the external application ecosystem. By using natural language processing, semantic understanding and customized rules, it aims to break the boundaries between the cockpit system and third-party applications and achieve deep integration. By enhancing intelligence and adaptability, it can quickly respond to user needs, provide personalized services, and improve the driving experience. At the same time, the technology covers cross-platform communication, data security and AI scene recognition, building a complete ecosystem and promoting the smart transportation industry to move towards a higher level of intelligence and personalized services.

[0093] The above description is only a preferred embodiment of the present invention, and does not limit the implementation mode and protection scope of the present invention. For those skilled in the art, it should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.

Claims

1. A quick scene generation method based on a cockpit system, characterized in that: include: Step S1, defining the scenario type and establishing a scenario model based on the user behavior pattern; Step S2, analyzing the user's scenario requirements and optimizing the scenario model according to the analysis results; Step S3, constructing a scene adaptability algorithm, and prioritizing the scenes based on the scene adaptability algorithm to obtain a prioritized scene list; Step S4, generating an initial service scenario based on the sorted scenario list and then optimizing it to obtain an intelligent service scenario.

2. The cockpit system-based quick scene generation method according to claim 1, characterized in that: Step S3 includes: Step S31, calculating the initial priority based on the user's preference coefficient for the scene type; Step S32, sorting all scenes according to the initial priority scores to obtain an initial list; Step S33, the user interacts with the in-vehicle assistant to extract key information input by the user; Step S34, sorting the initial list according to the extracted key information to obtain the sorted scene list.

3. The cockpit system-based quick scene generation method according to claim 2, characterized in that: The calculation formula of the initial priority in step S31 is: Among them, P i Indicates the initial priority, Indicates scene S i The inherent score of Indicates the preference coefficient for the scene type according to user preference.

4. The cockpit system-based quick scene generation method according to claim 2, characterized in that: Step S33 includes: Step S331, receiving user input; Step S332: the in-vehicle assistant performs natural language processing on the user input to extract key information from the user input.

5. The cockpit system-based quick scene generation method according to claim 2, characterized in that: The sorting process in step S34 includes: Start traversing from the first scene in the initial list, compare the priorities of adjacent scenes in turn, and when the priority of the latter scene is higher than that of the former scene according to the priority adjustment parameter, exchange the scene positions until there is no position exchange after traversal, and output the sorted scene list.

6. The cockpit system-based quick scene generation method according to claim 5, characterized in that: The priority adjustment parameters include preferences directly input by the user or environmental data collected by sensors.

7. The cockpit system-based quick scene generation method according to claim 1, characterized in that: It also includes step S0, designing a rule engine framework and developing a cross-platform adaptation layer according to the cross-platform interface document to connect third-party applications to the cockpit system.

8. The cockpit system-based quick scene generation method according to claim 1, characterized in that: The scenario types in step S1 include at least a navigation scenario, an entertainment scenario, and an emergency call scenario.

9. The cockpit system-based quick scene generation method according to claim 1, characterized in that: The optimized scenario model in step S2 includes scenario triggering conditions, corresponding service processes and expected outputs.

10. The cockpit system-based quick scene generation method according to claim 7, characterized in that: The cross-platform interface document in step S0 includes an interface data format, an interface calling method, and an error handling mechanism.

Images