Method, electronic device and vehicle for responding to vehicle demand

Abstract

The application relates to the technical field of vehicles, and provides a method for responding to a vehicle demand, an electronic device and a vehicle. The method for responding to the vehicle demand comprises the following steps: in response to receiving a vehicle demand instruction, determining atomic capabilities required to be executed in response to the vehicle demand instruction and execution logic between the atomic capabilities; generating an execution script according to the atomic capabilities required to be executed and the execution logic between the atomic capabilities; and running the execution script to respond to the vehicle demand instruction. According to the vehicle demand of a user, an automatic script for responding to the vehicle demand can be automatically generated, the vehicle demand of the user can be satisfied by executing the automatic script, the problem that the operation amount is large and the learning cost is high in realizing the vehicle demand of the user is solved, and the use experience of the user is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, and particularly relates to a method for responding to vehicle demand, an electronic device and a vehicle. BACKGROUND

[0002] In the current vehicle use scenario, if a driver or a passenger generates a vehicle use demand, such as hoping that the vehicle machine system executes certain specific vehicle machine functions under certain specific conditions, the driver or the passenger needs to enter a function setting, manually selects corresponding conditions and function actions and performs logical splicing, and then the vehicle machine system can understand and execute. For example, the user hopes to close the window when it rains. The user needs to enter the function setting, manually selects the condition "when it rains and the window is open", and the function action "close the window" associated with the condition.

[0003] In such a function setting, because there are many functions and the concepts are complex, the user needs to pay additional learning cost to understand the use method. In addition, if the user's demand is more complex, it will also bring more operation amount to the user, causing inconvenience in use.

[0004] Therefore, the present application is proposed. SUMMARY

[0005] Therefore, the present application is proposed.

[0006] In order to achieve the above purpose, in a first aspect, the present application provides a method for responding to vehicle demand, comprising:

[0007] In response to receiving a vehicle demand instruction, determining an atomic ability required to be executed in response to the vehicle demand instruction and an execution logic between atomic abilities;

[0008] Generating an execution script according to the atomic ability required to be executed and the execution logic between atomic abilities;

[0009] Running the execution script to respond to the vehicle demand instruction.

[0010] Further, the determining the atomic ability required to be executed in response to the vehicle demand instruction and the execution logic between atomic abilities comprises:

[0011] determining whether a target script matching the vehicle use demand instruction exists in a script content library, the script content library including scripts corresponding to various vehicle use demands, and each script including atomic capabilities required to be executed in response to the vehicle use demand and execution logic between the atomic capabilities;

[0012] in response to the target script matching the vehicle use demand instruction existing in the script content library, determining the atomic capabilities involved in the target script and the execution logic between the atomic capabilities as the atomic capabilities required to be executed in response to the vehicle use demand instruction and the execution logic between the atomic capabilities.

[0013] Further, the generating an execution script according to the atomic capabilities required to be executed and the execution logic between the atomic capabilities includes:

[0014] determining name information of the atomic capabilities involved in the target script;

[0015] determining real-time parameters corresponding to each atomic capability according to the name information and the vehicle use demand instruction;

[0016] replacing historical parameters corresponding to each atomic capability in the target script with the real-time parameters to obtain the execution script.

[0017] Further, the determining the name information of the atomic capabilities involved in the target script includes:

[0018] matching name information of each preset atomic capability in an atomic capability library with content of the target script respectively, and determining name information of a preset atomic capability with a matching degree reaching a first threshold as the name information of the atomic capabilities involved in the target script;

[0019] or, determining information associated with a preset keyword in the target script as the name information of the atomic capabilities involved in the target script.

[0020] Further, the determining the real-time parameters corresponding to each atomic capability according to the name information and the vehicle use demand instruction includes:

[0021] determining a parameter name matching the name information, and identifying an information segment in the vehicle use demand instruction corresponding to the name information;

[0022] determining information in the information segment matching the parameter name as a real-time parameter of the corresponding atomic capability.

[0023] Further, the determining whether a target script matching the vehicle use demand instruction exists in a script content library includes:

[0024] The content of the vehicle use demand instruction is compared with the function summary information of each script in the script content library to perform similarity calculation.

[0025] In response to the existence of a target script with a similarity reaching a second threshold value, it is determined that a target script matching the vehicle use demand instruction exists in the script content library.

[0026] Further, the atomic capabilities required to be executed in response to the vehicle use demand instruction and the execution logic between the atomic capabilities further include:

[0027] In response to the absence of a target script matching the vehicle use demand instruction in the script content library, the vehicle use demand instruction is understood to determine the atomic capabilities required to be executed and the execution logic between the atomic capabilities.

[0028] Further, the method further includes:

[0029] The vehicle use demand instruction and the execution script are added to the script content library as a new script.

[0030] To achieve the above object, in a second aspect, the present application provides a device for responding to a vehicle use demand, comprising:

[0031] A determination module is configured to determine the atomic capabilities required to be executed in response to the vehicle use demand instruction and the execution logic between the atomic capabilities in response to receiving a vehicle use demand instruction;

[0032] A generation module is configured to generate an execution script according to the atomic capabilities required to be executed and the execution logic between the atomic capabilities;

[0033] A running module is configured to run the execution script to respond to the vehicle use demand instruction.

[0034] To achieve the above object, in a third aspect, the present application provides an electronic device, 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 responding to a vehicle use demand according to the first aspect.

[0035] To achieve the above object, in a fourth aspect, the present application provides a vehicle comprising the electronic device according to the third aspect.

[0036] To achieve the above object, in a fifth aspect, the present application provides a computer readable storage medium storing computer instructions for causing a computer to execute the method for responding to a vehicle use demand according to any one of the first aspect.

[0037] As can be seen from the above, the method for responding to vehicle usage needs provided in this application includes receiving the user's vehicle usage request command. This means the user only needs to issue the command based on their needs, without needing to manually configure anything, thus saving user time and effort. Users also do not need to learn how to configure the vehicle system to respond to their needs, reducing learning costs and improving the user experience. Upon receiving the user's vehicle usage request command, the method automatically determines the atomic capabilities required to respond to the command and the execution logic between these capabilities, automatically generating an execution script. Running this script enables automatic response to the user's request command. Compared to manually configuring the atomic capabilities and their execution logic, this solution automatically determines these capabilities based on the user's command, eliminating the need for manual configuration and solving the problem of excessive manual operations and high learning costs in fulfilling vehicle usage needs, thereby improving the user experience. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A flowchart illustrating a method for responding to vehicle usage demand according to an embodiment of this application. Figure 1 ;

[0040] Figure 2 A flowchart illustrating a method for responding to vehicle usage demand according to an embodiment of this application. Figure 2 ;

[0041] Figure 3 A flowchart illustrating a method for responding to vehicle usage demand according to an embodiment of this application. Figure 3 ;

[0042] Figure 4 A flowchart illustrating a method for responding to vehicle usage demand according to an embodiment of this application. Figure 4 ;

[0043] Figure 5 This is a schematic diagram of a device for responding to vehicle usage needs according to an embodiment of this application;

[0044] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0045] For the purpose of clarity, technical solution and advantages of the present application, the present application is further described in detail below with reference to specific embodiments and drawings.

[0046] It should be noted that, unless otherwise defined, technical or scientific terms used in the embodiments of the present application should be understood as their common meanings to those of ordinary skill in the art to which the present application belongs. The terms "first", "second" and similar terms used in the embodiments of the present application do not denote any order, quantity or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms encompass the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar terms do not mean physical or mechanical connection, but can include electrical connection, whether direct or indirect. The terms "upper", "lower", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute positions of the described objects are changed, the relative positional relationships can also be changed accordingly.

[0047] It should be noted that the method of the embodiments of the present application can be executed by a single device, such as a computer or a server, etc. The method of the embodiments of the present application can also be applied to a distributed scenario, and be completed by multiple devices cooperating with each other. In this distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiments of the present application, and the multiple devices can interact with each other to complete the method.

[0048] It should be noted that some embodiments of the present application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the order described above and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0049] In the current vehicle use scenario, if the driver or passenger has a vehicle use demand, such as hoping that the vehicle machine system performs certain specific vehicle machine functions under certain specific conditions (for example, if it is raining, please close the window, if it is sunny, please open the window), the user needs to enter the function setting, manually select the corresponding condition and function action and perform logical splicing, and then the vehicle machine system can understand and execute. For example, the user's vehicle use demand is "close the window when it rains", the user needs to enter the function setting, manually select the condition "when it rains and the window is open", and the function action "close the window" associated with the condition. In such a function setting, because there are many functions and complex concepts, the range of each function is not explicitly explained, therefore, the user needs to pay additional learning cost to understand the use method. In addition, if the user's demand is more complex, it will also bring more operation amount to the user, causing inconvenience in use. Therefore, a method for automatically setting vehicle machine related functions according to user demand is needed to be developed to solve the problem of large operation amount and large learning cost in realizing the user's vehicle use demand.

[0050] In some embodiments, Figure 1 A flowchart of a method for responding to a vehicle demand is shown, which can be executed by a device for responding to a vehicle demand. The device for responding to a vehicle demand can be realized in the form of software and / or hardware, and integrated in a vehicle machine.

[0051] As Figure 1 The method for responding to a vehicle demand includes the following steps:

[0052] S110, in response to receiving a vehicle use demand instruction, determining the atomic capabilities required to respond to the vehicle use demand instruction and the execution logic between the atomic capabilities.

[0053] The vehicle use demand instruction is issued by the user. The user can speak the specific vehicle use demand instruction in the form of voice, or input his own user demand instruction in the form of text through the interactive interface, or display some commonly used demand information on the interactive interface, and the user can directly select specific demand information to trigger the vehicle use demand instruction, so as to further simplify the user's operation and improve the user's operation convenience and use experience.

[0054] In summary, the vehicle use demand instruction is used to represent the user's vehicle use demand, such as "if it rains, please close the window, if it is sunny, please open the window", "every year in August at 5 pm, I want to play music as soon as I get on the car" and the like are specific vehicle use demands.

[0055] After receiving the car use demand instruction, the car use demand instruction is parsed, identified or other types of processing, the purpose is to determine the atomic ability required to be executed in response to the car use demand instruction and the execution logic between the atomic abilities. Among them, the essence of the atomic ability is the refined car function, and one atomic ability represents one specific car function. For example, "heating of the second row left seat" and "turning on the air conditioner" are two different atomic abilities.

[0056] By refining the car function into independent atomic abilities, a basis for realizing function individualization customization can be provided. The car system can flexibly combine various atomic abilities according to the needs and preferences of different users to provide personalized function configuration and services for users. For example, some users focus on entertainment functions, and the car system can combine atomic abilities such as "music playing", "video playing" and "online radio". Some users focus on auxiliary driving, and the car system can combine atomic abilities such as "adaptive cruise", "lane keeping" and "automatic parking" to meet the diverse and personalized needs of users.

[0057] The execution logic between the atomic abilities refers to the execution order and execution conditions of the atomic abilities. For example, for the car use demand instruction "if it rains, please close the window", two atomic abilities are involved, namely "determine whether it is raining" and "close the window", and the execution logic between the two atomic abilities is that if the execution result of the first atomic ability "determine whether it is raining" is "raining", the second atomic ability "close the window" is executed; if the execution result of the first atomic ability "determine whether it is raining" is "not raining", the second atomic ability "close the window" is not executed.

[0058] S120, generating an execution script according to the atomic abilities required to be executed and the execution logic between the atomic abilities.

[0059] Among them, the execution script is a specific computer program, and the car system runs the execution script, then the atomic abilities can be executed according to the execution logic between the atomic abilities, so as to respond to the user's demand and achieve the purpose of meeting the user's demand.

[0060] For example, an atomic ability library can be pre-set, which includes all atomic abilities that the car system can support, and corresponding execution scripts are pre-generated for different atomic abilities and their execution logic, and the scene functions that can be met by the execution script are summarized, and the corresponding relationship between the summary and the execution script is established. When receiving the user's demand instruction, the user's demand can be directly calculated with the similarities of the summaries, and the execution script corresponding to the summary with higher similarity is determined as the execution script for meeting the user's demand this time.

[0061] S130, run the execution script to respond to the vehicle demand instruction.

[0062] The method for responding to vehicle demand provided by the embodiment includes receiving a vehicle demand instruction of a user, that is, the user only needs to issue a vehicle demand instruction according to the user's own vehicle demand, without manually setting relevant settings, thereby saving the user's operation, and the user does not need to learn the relevant settings required to make the car respond to the user's vehicle demand, thereby reducing the user's learning cost and improving the user's vehicle experience. When the vehicle demand instruction of the user is received, the atomic capabilities required to respond to the demand instruction and the execution logic between the atomic capabilities are automatically determined, thereby automatically generating an execution script, and the automatic response to the user demand instruction is realized by running the execution script. Compared with the manual setting of the atomic capabilities required to be executed and the execution logic between the atomic capabilities, the present application can automatically determine the atomic capabilities required to respond to the demand instruction and the execution logic between the atomic capabilities according to the user's vehicle demand instruction, so that the user's demand can be met without manually operating any settings, solving the problem of large amount of operation and high learning cost in realizing the user's vehicle demand, and being beneficial to improving the user's experience.

[0063] On the basis of the above embodiment, Figure 2 A flowchart of a method for responding to vehicle demand is shown, and the present embodiment gives an optional embodiment mode for S110 "determining the atomic capabilities required to respond to the vehicle demand instruction and the execution logic between the atomic capabilities" in the above embodiment, that is, determining whether there is a target script matching the vehicle demand instruction in the script content library, if there is, determining the atomic capabilities involved in the target script and the execution logic between the atomic capabilities as the atomic capabilities required to respond to the vehicle demand instruction and the execution logic between the atomic capabilities. This kind of way of determining the atomic capabilities required to respond to the vehicle demand instruction and the execution logic between the atomic capabilities has the advantages of high precision and fast speed, thereby improving the speed and efficiency of responding to the user's vehicle demand, and being beneficial to bringing a better user experience.

[0064] As Figure 2 The method for responding to vehicle demand includes the following steps:

[0065] S210, in response to receiving a vehicle demand instruction, determining whether there is a target script matching the vehicle demand instruction in the script content library.

[0066] The script content library includes scripts corresponding to various vehicle use requirements, and each script includes atomic capabilities required to respond to the vehicle use requirement and execution logic between the atomic capabilities. A script is a presentation of a user-defined scene function, and each script is composed of related atomic capabilities and the logical relationship between them.

[0067] Optionally, the function summary information corresponding to each script in the script content library can be defined, and the function summary information is used to represent the scene function that can be implemented by the corresponding script, for example, it can be "please close the window in time if it rains". Therefore, the function summary information corresponding to each script in the script content library is equivalent to a specific vehicle use requirement, so when receiving a real-time vehicle use requirement instruction issued by the user, the semantic similarity calculation can be performed between the vehicle use requirement instruction and the function summary information corresponding to each script in the script content library. If there is function summary information with high similarity, it means that there is a target script in the script content library that can meet the vehicle use requirement, that is, it is determined that there is a target script in the script content library that matches the vehicle use requirement instruction. Further, the atomic capabilities involved in the target script and the execution logic between the atomic capabilities can be determined as the atomic capabilities required to respond to the vehicle use requirement instruction and the execution logic between the atomic capabilities. That is, the atomic capabilities required to respond to the vehicle use requirement instruction and the execution logic between the atomic capabilities are determined from the script content library. Since the atomic capabilities involved in each script in the script content library and the execution logic between the atomic capabilities are determined in advance, usually by the developer specially, or obtained through an authoritative channel, the atomic capabilities involved in each script in the script content library and the execution logic between the atomic capabilities have high precision and reliability. Therefore, by determining the atomic capabilities required to respond to the vehicle use requirement instruction and the execution logic between the atomic capabilities from the script content library, the atomic capabilities required to respond to the vehicle use requirement instruction and the execution logic between the atomic capabilities determined have high precision and reliability.

[0068] In general, the determination of whether there is a target script in the script content library that matches the vehicle use requirement instruction includes: performing similarity calculation on the content of the vehicle use requirement instruction and the function summary information of each script in the script content library; and in response to the existence of a target script with a similarity reaching a second threshold, determining that there is a target script in the script content library that matches the vehicle use requirement instruction. That is, only by similarity calculation, a target script that matches the vehicle use requirement instruction can be determined from the script content library, so that the determination of the target script is simpler, the determination method of the target script is simplified, the implementation difficulty is reduced, and higher determination speed and accuracy can be obtained, which lays a foundation for quickly and accurately responding to the vehicle use requirement instruction.

[0069] By pre-storing various scripts capable of realizing different scene functions in the script content library, when a user issues a car use demand instruction in real time, the script content library can be searched for matching, if the script content library has a target script matching the car use demand instruction, the atomic capabilities involved in the target script and the execution logic between the atomic capabilities are determined as the atomic capabilities required to be executed in response to the car use demand instruction and the execution logic between the atomic capabilities, thereby improving the accuracy, reliability and efficiency of determining the atomic capabilities required to be executed in response to the car use demand instruction and the execution logic between the atomic capabilities, and laying a foundation for accurately and quickly responding to the user demand instruction.

[0070] S220, in response to the script content library having a target script matching the car use demand instruction, the atomic capabilities involved in the target script and the execution logic between the atomic capabilities are determined as the atomic capabilities required to be executed in response to the car use demand instruction and the execution logic between the atomic capabilities.

[0071] Among them, the script content library includes various scripts corresponding to car use demands, and each script includes atomic capabilities required to be executed in response to the car use demand and the execution logic between the atomic capabilities. The script is the presentation of the user-defined scene function, and each script is composed of several related atomic capabilities and the logical relationship between them.

[0072] When it is determined that the script content library has a target script matching the car use demand instruction, the atomic capabilities involved in the target script and the execution logic between the atomic capabilities are directly determined as the atomic capabilities required to be executed in response to the car use demand instruction and the execution logic between the atomic capabilities, which is beneficial to improve the accuracy, reliability and efficiency of determining the atomic capabilities required to be executed in response to the car use demand instruction and the execution logic between the atomic capabilities, and lays a foundation for accurately and quickly responding to the user demand instruction.

[0073] S230, generating an execution script according to the atomic capabilities required to be executed and the execution logic between the atomic capabilities.

[0074] S240, running the execution script to respond to the car use demand instruction.

[0075] The method for responding to the car demand provided by the embodiment determines whether there is a target script in the script content library that matches the car demand instruction of the user when the car demand instruction of the user is received, and if there is a target script in the script content library that matches the car demand instruction, determines the atomic capabilities involved in the target script and the execution logic between the atomic capabilities as the atomic capabilities required to respond to the car demand instruction and the execution logic between the atomic capabilities. Since the atomic capabilities involved in each script in the script content library and the execution logic between the atomic capabilities are specially formulated by the developers or obtained through an authoritative channel, the atomic capabilities involved in each script in the script content library and the execution logic between the atomic capabilities have high precision, and therefore, the accuracy and reliability of the atomic capabilities required to respond to the car demand instruction and the execution logic between the atomic capabilities are improved by determining the atomic capabilities required to respond to the car demand instruction and the execution logic between the atomic capabilities from the script content library. Since the atomic capabilities required to respond to the car demand instruction and the execution logic between the atomic capabilities are determined from the script content library, only the content of the car demand instruction and the function summary information of each script in the script content library need to be calculated for similarity to determine the corresponding atomic capabilities and the execution logic between the atomic capabilities, and therefore, the determination efficiency is high, laying a foundation for accurately and quickly responding to the demand instruction of the user. The atomic capabilities required to respond to the demand instruction and the execution logic between the atomic capabilities are automatically determined, so that the execution script is automatically generated, the automatic response to the demand instruction of the user is realized by running the execution script, the demand of the user can be met without manual operation of any setting, the problem of large operation amount and high learning cost in realizing the car demand of the user is solved, and the use experience of the user is improved.

[0076] On the basis of the above embodiment, Figure 3A flowchart of a method of responding to a vehicle demand is shown, and the embodiment is given for the optional embodiment of S120 "generating an execution script according to the atomic capabilities required to be executed and the execution logic between the atomic capabilities" in the above embodiment. Specifically, the script structure of the target script (i.e. the framework of the execution script) is followed, and the parameters corresponding to each atomic capability are identified from the current vehicle demand instruction, and the parameters in the target script are replaced with the parameters, thereby obtaining an execution script for responding to the current vehicle demand. Since the script structure of each script in the script library is prepared in advance, usually by the developers, it has high precision and reliability, so that by referring to the script structure of the target script (i.e. the framework of the execution script) to determine the execution script for responding to the current vehicle demand, the execution script for responding to the current vehicle demand has high precision and reliability; and by following the script structure of the target script (i.e. the framework of the execution script), only the parameters therein are replaced to obtain the execution script for responding to the current vehicle demand, so that the determination of the execution script for responding to the current vehicle demand is more efficient, more convenient, and easier to implement.

[0077] Alternatively, the execution script of the target script is directly determined as the execution script for responding to the current vehicle demand. By this way of determining the execution script for responding to the current vehicle demand, it has the advantages of easy implementation, high efficiency, high reliability and less online calculation.

[0078] As shown in Figure 3 The method of responding to a vehicle demand comprises the following steps:

[0079] S310, in response to the existence of a target script in the script content library that matches the vehicle demand instruction, the atomic capabilities involved in the target script and the execution logic between the atomic capabilities are determined as the atomic capabilities required to be executed and the execution logic between the atomic capabilities for responding to the vehicle demand instruction.

[0080] S320, the name information of the atomic capabilities involved in the target script is determined.

[0081] For example, the name information of the atomic capability can be "two-row seat heating", and the parameters corresponding to the atomic capability are "first gear, second gear, third gear, off", indicating that it can support the seat heating to be turned on to first gear, second gear, third gear or off.

[0082] The name information of the atomic capability involved in the target script is determined, which can be directly read from the name information of the atomic capability stored in association with the target script. Alternatively, the name information of each preset atomic capability in the atomic capability library is matched with the content of the target script respectively, and the name information of the preset atomic capability that reaches a first threshold in matching degree is determined as the name information of the atomic capability involved in the target script. For example, the name information of the preset atomic capability in the atomic capability library is "second-row seat heating", and the text information "second-row seat heating" is matched with the content of the target script to detect whether the text information is included in the content of the target script. If yes, it is determined that the name information of the atomic capability involved in the target script includes "second-row seat heating".

[0083] Alternatively, the information associated with the preset keyword in the target script is determined as the name information of the atomic capability involved in the target script. For example, a preset keyword (for example, action) is set in the target script, and the name information of the atomic capability is recorded after the preset keyword. Therefore, the name information of the atomic capability can be determined by identifying the preset keyword.

[0084] S330, determining the real-time parameter corresponding to each atomic capability according to the name information and the car use demand instruction.

[0085] For example, according to a preset mapping relationship, the parameter name matched with the name information is determined, for example, for the name information "second-row seat heating", the parameter name matched with it includes "first gear, second gear, third gear and off".

[0086] The information segment corresponding to the name information in the car use demand instruction is identified, which can be understood as an information segment composed of a few words before the position of the name information and a few words after the position of the name information together with the name information in the car use demand instruction. In addition to the name information, the information segment also includes the corresponding real-time parameter, such as "please heat the second-row seat to the second gear". The corresponding real-time parameter is usually close to the position of the name information. Based on this rule, the information segment corresponding to the name information in the car use demand instruction is identified first, and then the parameter name is matched in the information segment. The matched parameter name is determined as the real-time parameter of the corresponding atomic capability. That is, the information matched with the parameter name in the information segment is determined as the real-time parameter of the corresponding atomic capability.

[0087] S340, replacing the historical parameter corresponding to each atomic capability in the target script with the real-time parameter to obtain the execution script.

[0088] Furthermore, the vehicle usage request instruction and the execution script are added as new scripts to the script content library to enrich the scripts in the script content library and provide a basis for responding to vehicle usage requests in the future.

[0089] For this new script, the vehicle usage request instruction is its functional summary information, and the execution script is its script structure.

[0090] For example, when the car usage request instruction is: "Play music as soon as I get in the car; close the rear windows if it rains," the corresponding execution script, or script structure, is as follows:

[0091] Trigger (when the car's infotainment system starts), Action (play playlist {mediaSrc=**music, sheet=recommended playlist}); Condition (determine the weather {day=today, type=rain}), Action (second row left window {state=all closed}), Action (second row right window {state=all closed}).

[0092] S350. Run the execution script to respond to the vehicle usage request instruction.

[0093] In some implementations, in response to the absence of a target script matching the ride request instruction in the script content library, the ride request instruction is understood to determine the atomic capabilities to be executed and the execution logic between these atomic capabilities. For example, a large language model can be used to perform semantic understanding on the ride request instruction to determine the atomic capabilities to be executed and the execution logic between these atomic capabilities.

[0094] Specifically, trigger classification models, atomic ability recognition models, parameter filling models, and script generation models can be trained using matched sample data. Among these, the atomic ability recognition models, parameter filling models, and script generation models are LLM (Large Language Models), implemented based on the Transformer architecture and attention mechanisms. The model architecture includes a multi-layered structure, consisting of multiple encoders and decoders, forming a hierarchical structure. The encoder is responsible for analyzing and processing the input text, extracting representations containing key information such as semantics, syntax, and context. The decoder generates coherent and context-sensitive responses based on the encoded representations. By progressively refining and improving response generation at each layer, the model can gradually grasp the subtle nuances of language and generate high-quality text. The attention mechanism is a core component of the model, assigning different weights to different words in a sentence, enabling the model to focus on key information within a given context and ignore irrelevant details, thus more accurately understanding the potential meaning of the text.

[0095] The trigger classification model is an NLP (Natural Language Processing) model in the form of BERT (Bidirectional Encoder Representations from Transformers). The model structure is a Transformer-based encoder composed of multiple stacked self-attention layers and feed-forward neural network layers. The self-attention mechanism can calculate the correlation between each word in the text and other words in parallel, effectively capturing long-distance semantic dependencies, which enables the model to better understand the context information of the text.

[0096] The trigger classification model is used to identify the trigger category contained in the car use demand instruction. The trigger is a type of atomic ability used to determine whether the corresponding trigger timing is met. When the trigger timing arrives, the subsequent content will be executed. For example, the car use demand instruction is "play music as soon as I get in the car", and the corresponding trigger category is "car machine startup". The input of the trigger classification model is the text information corresponding to the car use demand instruction, and the output is the trigger category.

[0097] The atomic ability recognition large model is used to identify all atomic abilities required to respond to the car use demand instruction. Its input is the trigger category output by the trigger classification model and the text information corresponding to the car use demand instruction, and its output is a list of all atomic abilities required to respond to the car use demand instruction. For example, the car use demand instruction is "when I say it's a little hot, if the weather is sunny, please help me open the car window", the trigger category is "voice instruction", and "when I say it's a little hot, if the weather is sunny, please help me open the car window" and "voice instruction" are input into the atomic ability recognition large model to obtain the atomic ability list "car window control", "voice instruction", and "weather judgment".

[0098] The parameter filling large model is used to identify the parameters corresponding to each atomic ability from the car use demand instruction. Its input is the text information of the car use demand instruction and the atomic ability list output by the atomic ability recognition large model, and its output is the atomic ability and the corresponding parameters. For example, the car use demand instruction is "play music as soon as I get in the car. If it rains, close the rear window." The corresponding atomic ability list is "car machine startup, play song list, weather judgment, second row left window, second row right window". These information are input into the parameter filling large model as input, and the output is "car machine startup, play song list, mediaSrc = **music, sheet = play song list; weather judgment, day = today, type = rain; second row left window, state = full close, second row right window, state = full close".

[0099] The script generation large model is used to generate an execution script, that is, to generate a script, the input of which is the output of the parameter filling large model, and the output of which is the final script, for example, the car demand instruction is "I will play music as soon as I get on the car. If it rains, close the rear car window". The output of the parameter filling large model is "Car machine starts, play the song list, mediaSrc = **music, sheet = play the song list; judge the weather, day = today, type = rain; second row left window, state = full close, second row right window, state = full close", the output of the parameter filling large model is taken as the input of the script generation large model, and the output of the script generation large model is:

[0100] Trigger (car machine starts), Action (play the song list {mediaSrc = **music, sheet = recommended song list}); Condition (judge the weather {day = today, type = rain}), Action (second row left window {state = full close}), Action (second row right window {state = full close}).

[0101] Based on the above large model, referring to a method flow diagram for responding to a car demand as shown in Figure 4 When the user inputs a car demand to the car machine voice, the voice function of the car machine converts it into a demand description in text form. Then, using a text similarity model, the user's demand description is matched with the function summary of all scripts in the script content library for similarity. If a script with high similarity can be matched, branch one is executed: the script structure is retained, and only the parameter values of the related atomic capabilities are re-determined; if a script with high similarity cannot be matched, branch two is executed: the script is generated from scratch using the model capability.

[0102] Branch one: directly obtain the matched script, keep its script structure unchanged, and extract all atomic capabilities therein. Take all atomic capabilities and the user's original demand description as the input of the parameter filling large model to obtain the parameter values of all atomic capabilities that meet the demand description this time. For example, the input of the parameter filling large model is: when I say it is a little hot, if the weather is sunny, please help me open the car window; car window control and voice instruction. The output data is: main driver window-1102672, state = full open; voice instruction-1102673, zone = arbitrary, value = a little hot; judge the weather-1102674, day = today, type = sunny. The atomic capabilities with updated parameters are filled into the script structure again to obtain the final script.

[0103] Branch two: obtain the trigger category to which the demand description belongs using the trigger classification model. Based on the results of the previous step and the pre-maintained atomic ability library, use the atomic ability identification large model to find all atomic abilities involved in the demand description. Fill in the input of the large model with all atomic abilities and the user's original demand description as parameters to obtain the parameter values of all atomic abilities that meet the demand description. Fill in the input of the script generation large model with all atomic abilities and the user's original demand description as parameters to generate the final script. After completing the above process, the new script is sorted into the script content library, and the number of scripts in the script content library is continuously enriched to provide a basis for subsequent response to vehicle demand.

[0104] The embodiment scheme combines a large language model, a traditional natural language processing model, a text similarity model, and a number of business logic rules to decompose a complex content understanding task into a plurality of relatively simple and direct subtasks, and trains the model to quickly and accurately understand user vehicle demand and structure to generate an automated script that can realize the vehicle demand. The problems of high learning cost and tedious operation of the user are solved.

[0105] Based on the same inventive concept, the present application also provides a device for responding to vehicle demand corresponding to any of the above-mentioned embodiment methods.

[0106] Reference Figure 5 The device for responding to vehicle demand includes a determination module 510 configured to determine atomic abilities required to be executed and execution logic between the atomic abilities in response to receiving a vehicle demand instruction; a generation module 520 configured to generate an execution script according to the atomic abilities required to be executed and the execution logic between the atomic abilities; and a running module 530 configured to run the execution script to respond to the vehicle demand instruction.

[0107] Further, the determination module 510 includes a first determination unit configured to determine whether a target script matching the vehicle demand instruction exists in a script content library, the script content library including scripts corresponding to a plurality of vehicle demands, and each script including atomic abilities required to be executed in response to a vehicle demand and execution logic between the atomic abilities, and in response to the target script matching the vehicle demand instruction existing in the script content library, the atomic abilities involved in the target script and the execution logic between the atomic abilities are determined as the atomic abilities required to be executed and the execution logic between the atomic abilities in response to the vehicle demand instruction.

[0108] Further, the generating module 520 comprises: a second determining unit, configured to determine name information of an atomic capability involved in the target script; a third determining unit, configured to determine real-time parameters corresponding to each atomic capability according to the name information and the car-using demand instruction; and a replacing unit, configured to replace historical parameters corresponding to each atomic capability in the target script with the real-time parameters, to obtain the execution script.

[0109] Further, the second determining unit is specifically configured to: match name information of each preset atomic capability in an atomic capability library with content of the target script respectively, and determine name information of a preset atomic capability with a matching degree reaching a first threshold as the name information of the atomic capability involved in the target script.

[0110] Or, determine information associated with a preset keyword in the target script as the name information of the atomic capability involved in the target script.

[0111] Further, the third determining unit is specifically configured to: determine a parameter name matched with the name information, and identify an information segment corresponding to the name information in the car-using demand instruction.

[0112] Determine information matched with the parameter name in the information segment as a real-time parameter of the corresponding atomic capability.

[0113] Further, the first determining unit is specifically configured to: perform similarity calculation on content of the car-using demand instruction and function summary information of each script in the script content library; and in response to a target script with a similarity reaching a second threshold existing, determine that the target script matching the car-using demand instruction exists in the script content library.

[0114] Further, the first determining unit is further configured to: in response to no target script matching the car-using demand instruction existing in the script content library, understand the car-using demand instruction, and determine atomic capabilities required to be executed and execution logic between the atomic capabilities.

[0115] Further, the apparatus further comprises an adding module, configured to add the car-using demand instruction and the execution script as a new script to the script content library.

[0116] For the convenience of description, the above apparatus is described in various modules respectively according to functions. Of course, functions of the modules can be implemented in one or more software and / or hardware in implementing the present application.

[0117] The apparatuses in the above embodiments are used to implement the corresponding method of responding to a car-using demand in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be described herein.

[0118] For the convenience of description, the above apparatus is described in various modules in terms of functions. Of course, the functions of the modules can be implemented in one or more software and / or hardware in the implementation of the present application.

[0119] The apparatus of the above embodiments is used to implement the method of responding to the vehicle demand in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0120] Based on the same inventive concept, the present application also provides a vehicle corresponding to the method of any of the above embodiments, which comprises the apparatus for responding to the vehicle demand.

[0121] Based on the same inventive concept, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of responding to the vehicle demand according to any of the above embodiments when executing the program.

[0122] Based on the same inventive concept, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of responding to the vehicle demand according to any of the above embodiments when executing the program.

[0123] Figure 6 A more specific hardware structure of an electronic device provided by the present embodiment is shown, which can include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040 and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030 and the communication interface 1040 are connected to each other in the device through the bus 1050.

[0124] The processor 1010 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the present embodiment.

[0125] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0126] The input / output interface 1030 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0127] The communication interface 1040 is configured to connect a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as a USB, a network cable, etc.) or through a wireless manner (such as a mobile network, WIFI, Bluetooth, etc.).

[0128] The bus 1050 includes a channel for transmitting information between various components (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040) of the device.

[0129] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only include components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0130] The electronic device of the above embodiments is used to implement the method of responding to the vehicle demand in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here.

[0131] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the method of responding to the vehicle demand as described in any of the above embodiments.

[0132] The computer readable media of the embodiments can include permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0133] The storage medium of the above embodiments stores computer instructions for causing the computer to execute the method of responding to vehicle demand as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here.

[0134] Those skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present application (including claims) is limited to these examples; the above embodiments or technical features between different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of the different aspects of the embodiments of the present application as described above. In order to be brief, they are not provided in detail.

[0135] In addition, in order to simplify the description and discussion, and so as not to make the embodiments of the present application difficult to understand, the well-known power / ground connections of integrated circuit (IC) chips and other components can or can not be shown in the provided drawings. In addition, the devices can be shown in the form of block diagrams in order to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented the embodiments of the present application (i.e. these details should be fully within the understanding of those skilled in the art). Where specific details (e.g. circuits) are set forth in order to describe the exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than limiting.

[0136] While the present application has been described in connection with certain embodiments thereof, many modifications, substitutions, changes, and of forms will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0137] Embodiments of the present application are intended to cover all such alterations, modifications, and variations as they can come within the scope of the appended claims. Accordingly, although specific embodiments have been furthered in connection with the present application, any omission, substitution, change, improvement, etc. made by one of ordinary skill in the art to the disclosed embodiments should be considered to be within the scope of the present application.

Claims

1. A method for responding to vehicle usage demand, characterized in that, include: In response to receiving a car-use request instruction, determine whether there is a target script in the script content library that matches the car-use request instruction. The script content library includes scripts corresponding to various car-use requests. Determine the atomic capabilities required to respond to the vehicle usage request command and the execution logic between these atomic capabilities; In response to the existence of a target script in the script content library that matches the vehicle use request instruction, the name information of the atomic capabilities involved in the target script is determined; Based on the name information and the vehicle usage request instruction, determine the real-time parameters corresponding to each atomic capability; replace the historical parameters corresponding to each atomic capability in the target script with the real-time parameters to obtain the execution script; Run the execution script to respond to the vehicle request command.

2. The method for responding to vehicle demand according to claim 1, characterized in that, Each script includes atomic capabilities required to respond to a vehicle usage request and the execution logic between these atomic capabilities. Determining the atomic capabilities required to respond to the vehicle usage request instruction and the execution logic between these atomic capabilities includes: In response to the existence of a target script in the script content library that matches the vehicle use request instruction, the atomic capabilities involved in the target script and the execution logic between the atomic capabilities are determined as the atomic capabilities and the execution logic between the atomic capabilities required to respond to the vehicle use request instruction.

3. The method for responding to vehicle demand according to claim 1, characterized in that, The determination of the name information of the atomic capabilities involved in the target script includes: The name information of each preset atomic capability in the atomic capability library is matched with the content of the target script, and the name information of the preset atomic capability that reaches the first threshold of matching degree is determined as the name information of the atomic capability involved in the target script. Alternatively, the information in the target script associated with preset keywords can be determined as the name information of the atomic capabilities involved in the target script.

4. The method for responding to vehicle demand according to claim 1, characterized in that, The step of determining the real-time parameters corresponding to each atomic capability based on the name information and the vehicle usage request instruction includes: Determine the parameter name that matches the name information, and identify the information fragment in the vehicle use request instruction that corresponds to the name information; The information in the information fragment that matches the parameter name is determined as the real-time parameter of the corresponding atomic capability.

5. The method for responding to vehicle demand according to claim 1, characterized in that, Determining whether a target script matching the vehicle usage request exists in the script content library includes: The similarity of the content of the vehicle use request instruction with the functional summary information of each script in the script content library is calculated. In response to the existence of a target script with a similarity reaching a second threshold, it is determined that there is a target script in the script content library that matches the vehicle use request instruction.

6. The method for responding to vehicle demand according to claim 2, characterized in that, Also includes: In response to the absence of a target script in the script content library that matches the vehicle use request instruction, the vehicle use request instruction is understood to determine the atomic capabilities to be executed and the execution logic between the atomic capabilities.

7. The method for responding to vehicle demand according to claim 1, characterized in that, Also includes: The vehicle usage request instruction and the execution script are added as a new script to the script content library.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for responding to vehicle demand as described in any one of claims 1 to 7.

9. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 8.

Images