Intelligent cabin scene automatic generation method and device

Abstract

The invention relates to the technical field of vehicles, in particular to an intelligent cabin scene automatic generation method and device, and the method comprises the steps: generating a character string sequence according to vehicle use information, environment information and user preference information; generating a demand scene code according to the character string sequence; judging whether a demand scene matched with the demand scene code exists in a scene set or not, if yes, displaying and adjusting the demand scene, and storing the adjusted demand scene into a scene library and the scene set at the same time; on the contrary, whether a demand scene matched with the demand scene code exists in the scene library or not is judged, if the demand scene matched with the demand scene code does not exist, multiple demand features in the demand scene code are extracted, an expected scene is generated according to the multiple demand features, and the expected scene is stored in the scene library and the scene set at the same time; and otherwise, storing the required scene into the scene set. Therefore, the problems that new functions are added to scenes of an existing intelligent cabin system, coding needs to be carried out in advance, and the functions enjoyed by a user are too limited are solved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method and device for automatically generating a smart cockpit scene. Background Art

[0002] The current smart cockpit systems on the market mostly rely on programmers to code in advance and integrate them into the system through OTA. Although this method ensures the stability and reliability of the system to a certain extent, it also brings many limitations. First, the functions that users can enjoy are often limited by the developers' pre-planning and coding, resulting in relatively single functions that may not meet the diverse needs of users. Secondly, since the development and integration of functions takes a long time, the introduction of new functions is often slow, and it is difficult for users to enjoy the latest technological achievements in a timely manner. Furthermore, the scenario services provided by the system may not be what users really like or need, and lack personalization and customization, resulting in poor user experience. Summary of the invention

[0003] The present invention provides a method and device for automatically generating a smart cockpit scene, so as to solve the problems that if new functions are to be added to the scenes of the existing smart cockpit system, they need to be encoded in advance, the functions enjoyed by users are too limited, and the real needs of users cannot be met.

[0004] The first aspect of the present invention provides a method for automatically generating a smart cockpit scene, comprising the following steps: obtaining vehicle usage information, environmental information around the vehicle, and preference information of a target user in the vehicle; performing word segmentation processing on the vehicle usage information, the environmental information, and the preference information to generate a string sequence; inputting the string sequence into a target scene designer to generate a demand scene code; judging whether there is a demand scene matching the demand scene code in the user scene set, if there is a demand scene matching the demand scene code, displaying and adjusting the demand scene, and storing the adjusted demand scene in both the target scene library and the user scene set, otherwise the demand scene code is input into the target scene library; judging whether there is a demand scene matching the demand scene code in the target scene library, if there is no demand scene matching the demand scene code, extracting multiple demand features in the demand scene code, generating an expected scene based on the multiple demand features, and storing the expected scene in both the target scene library and the user scene set, otherwise the demand scene is stored in the user scene set.

[0005] Optionally, the word segmentation processing is performed on the vehicle usage information, the environmental information and the preference information to generate a string sequence, including: using a multimodal word segmenter to perform word segmentation processing on the vehicle usage information, the environmental information and the preference information to obtain multiple strings; assigning an embedded vector to each string, and concatenating each embedded vector to generate a combined embedding matrix; inputting the combined embedding matrix into an MLLM multimodal large language model to generate the string sequence.

[0006] Optionally, inputting the combined embedding matrix into the MLLM multimodal large language model to generate the string sequence includes: inputting the combined embedding matrix into the MLLM multimodal large language model, using a self-attention mechanism to capture long-distance dependencies in the combined embedding matrix to generate position information of each string; performing a linear transformation on the position information to generate the string sequence, and converting the string sequence into a vehicle status code, an environment identification code, and an intended target code.

[0007] Optionally, inputting the string sequence into the target scenario designer to generate a required scenario code includes: inputting the string sequence into the target scenario designer, performing bit operations on the string sequence according to current time data to obtain a first weight of the vehicle status code, a second weight of the environment identification code and a third weight of the intended target code; and generating the required scenario code according to the first weight, the second weight and the third weight.

[0008] Optionally, the determining whether there is a demand scenario matching the demand scenario code in the user scenario set, if there is a demand scenario matching the demand scenario code, displaying and adjusting the demand scenario, and storing the adjusted demand scenario in both the target scenario library and the user scenario set, otherwise inputting the demand scenario code into the target scenario library, includes:

[0009] Searching the user scenario set for a demand scenario that matches the demand scenario code;

[0010] If there is a demand scenario corresponding to the demand scenario code in the user scenario set, the demand scenario will be displayed to the target user for review. If the target user is not satisfied, the target user will be provided with an editing scenario to adjust the demand scenario, and the adjusted demand scenario will be stored in the target scenario library and the user scenario set as the expected scenario. Otherwise, the demand scenario will be given to the target user for use.

[0011] Optionally, the determining whether there is a demand scenario matching the demand scenario code in the target scenario library, if there is no demand scenario matching the demand scenario code, extracting multiple demand features in the demand scenario code, generating an expected scenario according to the multiple demand features, and storing the expected scenario in both the target scenario library and the user scenario set, otherwise storing the demand scenario in the user scenario set, includes:

[0012] Searching the target scenario library for a demand scenario that matches the demand scenario code;

[0013] If there is no demand scenario corresponding to the demand scenario code in the target scenario library, feature extraction is performed on the demand scenario code to obtain multiple demand features, and the multiple demand features are input into the target scenario generator to generate a new scene, and the new scene is displayed to the target user for review. If the target user is satisfied, the new scene is stored in the target scenario library and the user scenario set as the expected scene. Otherwise, an editing scene is provided to the target user to adjust the new scene, and the adjusted new scene is stored in the target scenario library and the user scenario set as the expected scene. If there is a demand scenario corresponding to the demand scenario code in the target scenario library, the demand scene is stored in the user scenario set.

[0014] The second aspect of the present invention provides an automatic generation device for intelligent cockpit scenes, including: an acquisition module for acquiring vehicle usage information, environmental information around the vehicle, and preference information of a target user in the vehicle; a word segmentation module for performing word segmentation processing on the vehicle usage information, the environmental information, and the preference information to generate a string sequence; a generation module for inputting the string sequence into a target scene designer to generate a demand scene code; a first judgment module for judging whether there is a demand scene matching the demand scene code in the user scene set, and if there is a demand scene matching the demand scene code, displaying and adjusting the demand scene, and storing the adjusted demand scene in the target scene library and the user scene set at the same time, otherwise the demand scene code is input into the target scene library. A second judgment module for judging whether there is a demand scene matching the demand scene code in the target scene library, and if there is no demand scene matching the demand scene code, extracting multiple demand features in the demand scene code, generating an expected scene according to the multiple demand features, and storing the expected scene in the target scene library and the user scene set at the same time, otherwise the demand scene is stored in the user scene set.

[0015] A third aspect of the present invention provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for automatically generating a smart cockpit scene as described in the above embodiment.

[0016] A fourth aspect of the present invention provides a computer program product, which implements the above-mentioned method for automatically generating smart cockpit scenes when the computer program / instructions are executed by a processor.

[0017] A fifth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for automatically generating a smart cockpit scene.

[0018] The method and device for automatically generating smart cockpit scenes proposed in the embodiments of the present invention can solve the problem of automatic scene generation. It no longer requires advance coding or pre-setting. It can collect user usage habits and preferences, the vehicle's surrounding environment, and the current vehicle usage status, and provide users with personalized services based on this information. It can fully match the user's operating habits and better meet the different needs of different users.

[0019] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A flow chart of a method for automatically generating a smart cockpit scene provided by an embodiment of the present invention;

[0022] Figure 2 A specific execution flow chart of the method for automatically generating a smart cockpit scene provided by an embodiment of the present invention;

[0023] Figure 3 A specific execution flow chart of generating a character string sequence provided by an embodiment of the present invention;

[0024] Figure 4 A specific execution flow chart of storing a user scenario set when there is a demand scenario matching the demand scenario code provided by an embodiment of the present invention;

[0025] Figure 5 A specific execution flow chart of storing a user scenario set when there is no demand scenario matching the demand scenario code provided by an embodiment of the present invention;

[0026] Figure 6 A block diagram of a device for automatically generating intelligent cockpit scenes provided by an embodiment of the present invention;

[0027] Figure 7 A schematic structural diagram of a vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0029] The following describes a method and device for automatically generating a smart cockpit scene according to an embodiment of the present invention with reference to the accompanying drawings.

[0030] Figure 1 A schematic diagram of a flow chart of a method for automatically generating a smart cockpit scene provided in an embodiment of the present invention.

[0031] like Figure 1 As shown, the method for automatically generating a smart cockpit scene includes the following steps:

[0032] In step S101, vehicle usage information, vehicle surrounding environment information, and preference information of a target user in the vehicle are obtained.

[0033] In step S102, the vehicle use information, the environment information and the preference information are segmented to generate a character string sequence.

[0034] In some embodiments, the vehicle usage information, the environment information, and the preference information are segmented to generate a string sequence, including:

[0035] Using a multimodal word segmenter to segment vehicle usage information, environmental information, and preference information to obtain multiple character strings;

[0036] Assign an embedding vector to each string and concatenate each embedding vector to generate a combined embedding matrix;

[0037] The combined embedding matrix is ​​input into the MLLM multimodal large language model to generate string sequences.

[0038] In some embodiments, the combined embedding matrix is ​​input into an MLLM multimodal large language model to generate a string sequence, including:

[0039] The combined embedding matrix is ​​input into the MLLM multimodal large language model, and the self-attention mechanism is used to capture the long-distance dependencies in the combined embedding matrix to generate the position information of each string;

[0040] The position information is linearly transformed to generate a string sequence, and the string sequence is converted into a vehicle status code, an environment identification code, and an intended target code.

[0041] In the actual implementation process, Figure 2 As shown, preference information such as habits and hobbies of the target user in the car, the surrounding environment of the vehicle and the current vehicle usage are collected, and these data are converted into text that can be recognized by the machine to be input into the multimodal word segmenter for word segmentation processing to generate multiple string tokens; according to the type of each token (such as word, phrase, symbol, etc.), an embedded embedding vector is assigned to each token; the embedding vectors of all string tokens are concatenated into a combined embedding matrix and input into the encoder of the MLLM multimodal large language model; the MLLM encoder usually uses the Transformer architecture as a decoder to generate a token sequence, and the decoder stage uses a self-attention mechanism to capture the long-distance dependencies in the input combined embedding matrix, and the positional encoding in the decoder is used to capture the position information of each token in the array; when generating tokens, the decoder applies a linear transformation and then uses a softmax function to predict the next token one by one, and finally generates a string token sequence, and performs AI word segmentation on the string token sequence to finally generate the intent target code, environment identification code and vehicle status code.

[0042] In step S103, the character string sequence is input into the target scenario designer to generate a required scenario code.

[0043] In some embodiments, a string sequence is input into a target scenario designer to generate a required scenario code, including:

[0044] Inputting the string sequence into the target scenario designer, performing bit operations on the string sequence according to the current time data to obtain a first weight of the vehicle status code, a second weight of the environment identification code, and a third weight of the intended target code;

[0045] A demand scenario code is generated according to the first weight, the second weight, and the third weight.

[0046] In the actual implementation process, Figure 3As shown, the intention target code, environment identification code and vehicle status code are input into the target scenario designer to perform bit operations on the three codes according to the current time data to obtain the weights of the three codes, and the codes with large weights are used as the scene generation dependency information to be used in the end, and the required scenario code is generated according to the scene generation dependency information.

[0047] Furthermore, the demand scenario code is a 64-bit text string containing numbers and characters, and each digit of the string has a special meaning. For example, the last three digits of the demand scenario code contain the user's habit of operating the interface, such as whether the like button is in the upper left or lower left.

[0048] In step S104, it is determined whether there is a demand scenario matching the demand scenario code in the user scenario set. If there is a demand scenario matching the demand scenario code, the demand scenario is displayed and adjusted, and the adjusted demand scenario is stored in the target scenario library and the user scenario set at the same time. Otherwise, the demand scenario code is input into the target scenario library.

[0049] In some embodiments, it is determined whether there is a demand scenario matching the demand scenario code in the user scenario set, and if there is a demand scenario matching the demand scenario code, the demand scenario is displayed and adjusted, and the adjusted demand scenario is stored in the target scenario library and the user scenario set at the same time, otherwise the demand scenario code is input into the target scenario library, including:

[0050] Search the user scenario set for the corresponding demand scenario that matches the demand scenario code;

[0051] If there is a demand scenario corresponding to the demand scenario code in the user scenario set, the demand scenario will be displayed to the target user for review. If the target user is not satisfied, the target user will be provided with an editing scenario to adjust the demand scenario, and the adjusted demand scenario will be stored in the target scenario library and the user scenario set as the expected scenario. Otherwise, the demand scenario will be given to the target user for use.

[0052] In the actual implementation process, Figure 4 As shown, the demand scenario corresponding to the demand scenario code is searched in the user scenario set. If there is a demand scenario corresponding to the demand scenario code in the user scenario set, the demand scenario will be displayed to the target user for review. If the target user is satisfied, the demand scenario will be used directly with the target user. If the target user is not satisfied, an editing scenario will be provided to the target user to adjust the demand scenario, and the adjusted demand scenario will be stored as an expected scenario in both the target scenario library and the user scenario set.

[0053] It should be noted that for the first time after startup, the demand scenario code is generated based on preference information such as user habits and hobbies, the vehicle's surrounding environment and the current vehicle usage. It is definitely impossible to obtain the scene from the user scenario set using the demand scenario code, because the user scenario set is an empty set at this time. It is necessary to directly enter step S105 and use the target scenario generator to generate the demand scenario.

[0054] In step S105, it is determined whether there is a demand scenario matching the demand scenario code in the target scenario library. If there is no demand scenario matching the demand scenario code, multiple demand features in the demand scenario code are extracted, and an expected scenario is generated based on the multiple demand features. The expected scenario is stored in both the target scenario library and the user scenario set. Otherwise, the demand scenario is stored in the user scenario set.

[0055] In some embodiments, searching the target scenario library for a demand scenario that matches the demand scenario code;

[0056] If there is no demand scenario corresponding to the demand scenario code in the target scenario library, feature extraction is performed on the demand scenario code to obtain multiple demand features, and the multiple demand features are input into the target scenario generator to generate a new scene, and the new scene is displayed to the target user for review. If the target user is satisfied, the new scene is stored in the target scenario library and the user scenario set as the expected scene at the same time. Otherwise, an editing scene is provided to the target user to adjust the new scene, and the adjusted new scene is stored in the target scenario library and the user scenario set as the expected scene at the same time;

[0057] If there is a demand scenario corresponding to the demand scenario code in the target scenario library, the demand scenario is stored in the user scenario set.

[0058] In the actual implementation process, Figure 4 As shown, the target scene library is searched for a required scene that matches the required scene code. If the match is successful, the required scene is stored in the user scene set, which is a collection of scenes that the user can use. After the smart cockpit system is started, the scene set that needs to be temporarily saved for all scenes will be initialized. In the vehicle system, the embodiment of the present invention will preset some scene resources according to the user's needs, and both the user and the system can optimize and adjust these scene resources later.

[0059] If the match fails, the required scenario code is input into the target scenario generator, features and other information are extracted based on the required scenario code, and these feature information is input into the target scenario generator. The target scenario generator generates a new scene based on multiple features, and sends the new scene to the target user for use. The target user determines whether the new scene is satisfactory. If satisfied, the new scene is stored as the expected scene in both the target scenario library and the user scenario set. Otherwise, the target user is provided with an editing scene to adjust the new scene. The adjusted new scene is stored as the expected scene in both the target scenario library and the user scenario set. The purpose of storing the scene in the target scene library is to facilitate subsequent direct matching and use, and the purpose of storing the scene in the user scene set is for use by the target user who is currently using the smart cockpit.

[0060] Furthermore, if Figure 5 As shown, the generated new scene is automatically displayed on the screen through an interface for user operation. The displayed interface provides editing capabilities. If the user is not satisfied with the generation of the new scene, he can re-edit the scene through the editing function, such as changing the operation button from the upper left to the lower left. After editing, it is automatically stored in the user scene set, so that it can be used directly when the scene is re-triggered after power-on. It also needs to be automatically stored in the user scene set so that it can be used directly from the memory during the current power-on to power-off cycle. There is no need to go through the scene generation process. That is, the newly generated scene, whether it is obtained from the scene library or automatically generated by AI, needs to be placed in the user scene set. If the scene is triggered again, it will be directly extracted from the user scene set, and the scene generation process will no longer be required.

[0061] The target scene library saves scene information to disk. After shutting down and restarting, the scene library information can be loaded from disk to memory for direct use. The user scene set saves the currently generated scene in memory, and the scene triggered during the current startup to shutdown cycle can be used directly.

[0062] It should be noted that the scenes in the target scene library and the user scene set will display different content on the interface according to the different operating habits of users. For example, if the current vehicle environment is in a supermarket, different users will see different supermarket content, and the buttons on the interface will also be displayed in different positions. For example, for the "place order" button, some users like the button to be in the upper left corner, while some users like the button to be in the lower left corner. At the same time, the scene is also affected by the vehicle status. For example, if the air conditioner is currently turned on and the air conditioner temperature is relatively suitable, then even if it is detected that the ambient temperature of the vehicle is too high, there is no need to turn on the air conditioner again.

[0063] In summary, the method for automatic generation of smart cockpit scenes proposed in an embodiment of the present invention can solve the problem of automatic scene generation. It no longer requires advance coding and pre-setting. It can collect user usage habits and preferences, the vehicle's surrounding environment and the current vehicle usage status, and provide users with personalized services based on this information. It can fully match the user's operating habits and better meet the different needs of different users.

[0064] Next, the device for automatically generating a smart cockpit scene according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0065] Figure 6 A block diagram of a device for automatically generating intelligent cockpit scenes according to an embodiment of the present invention.

[0066] like Figure 6 As shown, the intelligent cockpit scene automatic generation device 60 includes: an acquisition module 601, a word segmentation module 602, a generation module 603, a first judgment module 604 and a second judgment module 605.

[0067] Among them, the acquisition module 601 is used to obtain vehicle usage information, environmental information around the vehicle, and preference information of the target user in the vehicle. The word segmentation module 602 is used to perform word segmentation processing on the vehicle usage information, environmental information and preference information to generate a string sequence. The generation module 603 is used to input the string sequence into the target scenario designer to generate a demand scenario code. The first judgment module 604 is used to determine whether there is a demand scenario matching the demand scenario code in the user scenario set. If there is a demand scenario matching the demand scenario code, the demand scenario is displayed and adjusted, and the adjusted demand scenario is stored in the target scenario library and the user scenario set at the same time. Otherwise, the demand scenario code is input into the target scenario library. The second judgment module 605 is used to determine whether there is a demand scenario matching the demand scenario code in the target scenario library. If there is no demand scenario matching the demand scenario code, multiple demand features in the demand scenario code are extracted, and an expected scenario is generated according to multiple demand features, and the expected scenario is stored in the target scenario library and the user scenario set at the same time. Otherwise, the demand scenario is stored in the user scenario set.

[0068] In some embodiments, the acquisition module 601 includes:

[0069] A word segmentation unit, used for performing word segmentation processing on the vehicle use information, the environment information and the preference information by using a multimodal word segmenter to obtain a plurality of character strings;

[0070] A concatenation unit, which is used to assign an embedded vector to each string and concatenate each embedded vector to generate a combined embedding matrix;

[0071] The generation unit is used to input the combined embedding matrix into the MLLM multimodal large language model to generate a string sequence.

[0072] In some embodiments, the generating unit comprises:

[0073] The capture subunit is used to input the combined embedding matrix into the MLLM multimodal large language model and use the self-attention mechanism to capture the long-distance dependencies in the combined embedding matrix to generate the position information of each string;

[0074] The transformation subunit is used to perform linear transformation on the position information to generate a string sequence, and convert the string sequence into a vehicle status code, an environment identification code and an intended target code.

[0075] In some embodiments, the generation module 603 includes:

[0076] A bit operation unit, used for inputting the string sequence into the target scene designer, and performing bit operation on the string sequence according to the current time data to obtain a first weight of the vehicle status code, a second weight of the environment identification code, and a third weight of the intended target code;

[0077] A generating subunit is used to generate a demand scenario code according to the first weight, the second weight and the third weight.

[0078] In some embodiments, the first determination module 604 includes:

[0079] Search the user scenario set for the corresponding demand scenario that matches the demand scenario code;

[0080] If there is a demand scenario corresponding to the demand scenario code in the user scenario set, the demand scenario will be displayed to the target user for review. If the target user is not satisfied, the target user will be provided with an editing scenario to adjust the demand scenario, and the adjusted demand scenario will be stored in the target scenario library and the user scenario set as the expected scenario. Otherwise, the demand scenario will be given to the target user for use.

[0081] In some embodiments, the second determination module 605 includes:

[0082] Search the target scenario library for the corresponding demand scenario that matches the demand scenario code;

[0083] If there is no demand scenario corresponding to the demand scenario code in the target scenario library, feature extraction is performed on the demand scenario code to obtain multiple demand features, and the multiple demand features are input into the target scenario generator to generate a new scene, and the new scene is displayed to the target user for review. If the target user is satisfied, the new scene is stored in the target scenario library and the user scenario set as the expected scene at the same time. Otherwise, an editing scene is provided to the target user to adjust the new scene, and the adjusted new scene is stored in the target scenario library and the user scenario set as the expected scene at the same time;

[0084] If there is a demand scenario corresponding to the demand scenario code in the target scenario library, the demand scenario is stored in the user scenario set.

[0085] It should be noted that the aforementioned explanation of the embodiment of the method for automatically generating a smart cockpit scene is also applicable to the device for automatically generating a smart cockpit scene of this embodiment, and will not be repeated here.

[0086] The intelligent cockpit scene automatic generation device proposed in the embodiment of the present invention can solve the problem of automatic scene generation. It no longer needs advance coding and pre-setting. It can collect user usage habits and user preferences, the vehicle's surrounding environment and the current vehicle usage status, and provide personalized services to users based on this information. It can fully match the user's operating habits and better meet the different needs of different users.

[0087] Figure 7 A schematic diagram of the structure of a vehicle provided in an embodiment of the present invention. The vehicle may include:

[0088] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0089] When the processor 702 executes the program, the method for automatically generating a smart cockpit scene provided in the above embodiment is implemented.

[0090] Furthermore, the vehicle also includes:

[0091] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0092] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0093] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0094] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0095] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0096] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0097] An embodiment of the present invention further provides a computer program product, which implements the above-mentioned method for automatically generating smart cockpit scenes when the computer program / instructions are executed by a processor.

[0098] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for automatically generating a smart cockpit scene.

[0099] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0100] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0101] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0102] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0103] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0104] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0105] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0106] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for automatically generating a smart cockpit scene, characterized in that: The following steps are involved: Obtain vehicle usage information, environmental information around the vehicle, and preference information of target users in the vehicle; Performing word segmentation processing on the vehicle usage information, the environment information, and the preference information to generate a character string sequence; Inputting the string sequence into a target scenario designer to generate a required scenario code; Determine whether there is a demand scenario matching the demand scenario code in the user scenario set; if there is a demand scenario matching the demand scenario code, display and adjust the demand scenario, and store the adjusted demand scenario in both the target scenario library and the user scenario set; otherwise, input the demand scenario code into the target scenario library; Determine whether there is a demand scenario matching the demand scenario code in the target scenario library. If there is no demand scenario matching the demand scenario code, extract multiple demand features in the demand scenario code, generate an expected scenario based on the multiple demand features, and store the expected scenario in both the target scenario library and the user scenario set. Otherwise, store the demand scenario in the user scenario set.

2. The method for automatically generating intelligent cockpit scenes according to claim 1, characterized in that: The performing word segmentation processing on the vehicle use information, the environment information and the preference information to generate a character string sequence includes: Using a multimodal word segmenter to perform word segmentation processing on the vehicle use information, the environmental information, and the preference information to obtain a plurality of character strings; Assign an embedding vector to each string and concatenate each embedding vector to generate a combined embedding matrix; The combined embedding matrix is ​​input into the MLLM multimodal large language model to generate the string sequence.

3. The method for automatically generating intelligent cockpit scenes according to claim 2, characterized in that: The step of inputting the combined embedding matrix into the MLLM multimodal large language model to generate the string sequence comprises: Input the combined embedding matrix into the MLLM multimodal large language model, and use the self-attention mechanism to capture the long-distance dependencies in the combined embedding matrix to generate the position information of each string; The position information is linearly transformed to generate the string sequence, and the string sequence is converted into a vehicle status code, an environment identification code and an intended target code.

4. The method for automatically generating intelligent cockpit scenes according to claim 3, characterized in that: The step of inputting the character string sequence into a target scenario designer to generate a required scenario code includes: Inputting the string sequence into the target scenario designer, performing bitwise operation on the string sequence according to current time data to obtain a first weight of the vehicle status code, a second weight of the environment identification code, and a third weight of the intended target code; The demand scenario code is generated according to the first weight, the second weight and the third weight.

5. The method for automatically generating intelligent cockpit scenes according to claim 1, characterized in that: The determining whether there is a demand scenario matching the demand scenario code in the user scenario set, and if there is a demand scenario matching the demand scenario code, displaying and adjusting the demand scenario, and storing the adjusted demand scenario in both the target scenario library and the user scenario set; otherwise, inputting the demand scenario code into the target scenario library, includes: Searching the user scenario set for a demand scenario that matches the demand scenario code; If there is a demand scenario corresponding to the demand scenario code in the user scenario set, the demand scenario will be displayed to the target user for review. If the target user is not satisfied, the target user will be provided with an editing scenario to adjust the demand scenario, and the adjusted demand scenario will be stored in the target scenario library and the user scenario set as the expected scenario. Otherwise, the demand scenario will be given to the target user for use.

6. The method for automatically generating intelligent cockpit scenes according to claim 1, characterized in that: The determining whether there is a demand scenario matching the demand scenario code in the target scenario library, and if there is no demand scenario matching the demand scenario code, extracting multiple demand features in the demand scenario code, generating an expected scenario according to the multiple demand features, and storing the expected scenario in both the target scenario library and the user scenario set, otherwise storing the demand scenario in the user scenario set, includes: Searching the target scenario library for a demand scenario that matches the demand scenario code; If there is no demand scenario corresponding to the demand scenario code in the target scenario library, feature extraction is performed on the demand scenario code to obtain multiple demand features, and the multiple demand features are input into the target scenario generator to generate a new scene, and the new scene is displayed to the target user for review. If the target user is satisfied, the new scene is stored in the target scenario library and the user scenario set as the expected scene at the same time. Otherwise, an editing scene is provided to the target user to adjust the new scene, and the adjusted new scene is stored in the target scenario library and the user scenario set as the expected scene at the same time; If a demand scenario corresponding to the demand scenario code matches exists in the target scenario library, the demand scenario is stored in the user scenario set.

7. An automatic generation device for intelligent cockpit scenes, characterized in that: include: An acquisition module is used to acquire vehicle usage information, environmental information around the vehicle, and preference information of target users in the vehicle; A word segmentation module, used for performing word segmentation processing on the vehicle use information, the environmental information and the preference information to generate a character string sequence; A generating module, used for inputting the string sequence into a target scenario designer to generate a required scenario code; A first judgment module is used to judge whether there is a demand scenario matching the demand scenario code in the user scenario set. If there is a demand scenario matching the demand scenario code, the demand scenario is displayed and adjusted, and the adjusted demand scenario is stored in the target scenario library and the user scenario set at the same time. Otherwise, the demand scenario code is input into the target scenario library; The second judgment module is used to judge whether there is a demand scenario matching the demand scenario code in the target scenario library. If there is no demand scenario matching the demand scenario code, multiple demand features in the demand scenario code are extracted, an expected scenario is generated according to the multiple demand features, and the expected scenario is stored in the target scenario library and the user scenario set at the same time. Otherwise, the demand scenario is stored in the user scenario set.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for automatically generating a smart cockpit scene as described in any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program / instruction is executed by a processor, the method for automatically generating a smart cockpit scene according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for automatically generating a smart cockpit scene as described in any one of claims 1 to 6.

Images