Layout method and device of in-vehicle settings, processor and computer readable storage medium thereof

Abstract

The application relates to a layout method and device of in-vehicle settings, a processor and a computer readable storage medium thereof. The method adopts the application, determines the basic weight of each setting based on the historical operation data of a user within a preset time period, determines the correction weight of each setting based on the intention type reflected by the historical operation data of the user and / or the environment data of the user, and determines the sorting priority of each setting based on the basic weight and the correction weight of each setting to sort and layout each setting. The above method dynamically calculates the sorting priority based on the historical operation data (including intention and environment) of the user, intelligently sorts the menu layout, does not need to find the frequently used function through multiple levels, shortens the sight line transfer time, reduces the driving risk, permanently takes effect once, greatly reduces the long-term operation cost compared with a pure voice scheme, avoids the listening distraction of voice interaction, and returns to the touch habit in daily life.

Description

Technical Field

[0001] This invention relates to the field of in-vehicle icon display, specifically to a method, apparatus, processor, and computer-readable storage medium for laying out in-vehicle settings. Background Technology

[0002] With the rapid development of intelligent connected vehicle technology, vehicle functions are becoming increasingly rich, and the number of system settings on the central control screen is growing exponentially. Traditional in-vehicle settings menus use a factory-preset static layout, with all function items arranged in a fixed position. This static design has the following technical drawbacks: (1) Difficulty in finding function entry points and lengthy operation paths. The screen output of the existing graphical user interface adopts a fixed layout organization method. The position and style of functions cannot be dynamically adjusted. When users need to use a function that is not frequently used, they may not be able to find the corresponding function entry point. They may also need to perform multi-level menu navigation to reach the target setting item. The operation path is long and inefficient. Studies have shown that the existing host page layout adopts a fixed design and cannot be dynamically optimized and adjusted according to the external environment and user behavior, making it difficult to meet the personalized needs of users. (2) Prominent driving safety hazards. In particular, frequently used functions (such as seat heating, air conditioning temperature, driving mode switching, etc.) are buried in multi-level sub-menus due to the static design of the menu. Users have to shift their eyes for a long time to search for the function location during driving, which significantly distracts driving attention and poses serious safety hazards. The existing vehicle-machine interaction mainly relies on touch control. Drivers need to frequently shift their eyes from the road to the screen. The operation steps are cumbersome and easy to distract attention. (3) Although voice interaction is a supplement, the cost per use is high. Although voice interaction technologies (such as ASR and TTS) are relatively mature, they have the advantages of not occupying the user's visual focus and improving driving safety in the field of vehicle systems. However, voice interaction has the following limitations: each time a user uses a function, they need to wake up the voice assistant, say the complete command, and wait for the system to parse and respond, with each interaction taking 2 to 5 seconds. In noisy environments while the vehicle is in motion (such as high-speed wind noise, tire noise, engine noise) or in scenarios where the driver uses dialects, the voice recognition rate drops significantly, resulting in delayed or incorrect command responses. Voice interaction is a "speak once per use" mechanism, which cannot fundamentally reduce the number of operation steps, and users still face high interaction costs in the long term. (4) Existing adaptive layout schemes lack voice active intervention channels. Some technologies have attempted to dynamically and adaptively adjust the central control screen page by collecting data from the in-vehicle cabin and external environment. Other technologies determine the display position and layout order based on the correlation between modules by obtaining the attribute information and priority of the interface modules. There are also human-computer interaction interface technologies that can allocate the application interface proportion based on the current scenario and user characteristics and automatically generate the layout. However, existing solutions are all based on passive learning using user behavior data, which has the following shortcomings: 1. Cold start problem: The adaptive mechanism cannot work effectively when new users have no historical operation data. 2. Response lag: Behavioral data requires an accumulation period and cannot respond to instantaneous changes in user preferences. 3. Lack of interpretability and controllability: Users cannot actively inform the system of their preferences, and it is difficult to intervene in and correct the results of layout adjustments. 4. Ignoring intent-level intervention: Natural language interaction is not used as a channel for actively specifying layout intentions. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, apparatus, processor and computer-readable storage medium for the layout of in-vehicle settings.

[0004] To achieve the above objectives, the present invention provides a method, apparatus, processor, and computer-readable storage medium for laying out in-vehicle installations as follows: The layout method for in-vehicle settings is characterized by the following steps: (1) Determine the basic weight of each setting item based on the user's historical operation data within a preset time period; (2) Determine the correction weight of each setting based on the type of intent reflected by the user's historical operation data and / or the user's environmental data; (3) Determine the sorting priority of each setting item based on its basic weight and modified weight, so as to sort and arrange each setting item. Wherein, the base weight is positively correlated with the sorting priority, the upward adjustment of the modified weight is positively correlated with the sorting priority, and the downward adjustment of the modified weight is negatively correlated with the sorting priority.

[0005] Preferably, the historical operation data includes at least one of the user's historical operation frequency, historical operation duration, and recent operation time interval; The historical operation frequency is positively correlated with the basic weight, the historical operation duration is positively correlated with the basic weight, and the most recent operation time interval is negatively correlated with the basic weight.

[0006] Preferably, step (1) specifically includes: (1.1) Determine the operation frequency sub-score of each setting item based on the historical operation frequency, determine the operation duration sub-score of each setting item based on the historical operation duration, and determine the operation time interval score of each setting item based on the operation time interval. (1.2) Determine the basic weight of each setting item based on the first basic sub-weight, the second basic sub-weight, the third basic sub-weight, the operation frequency sub-score, the operation duration sub-score, and the operation time interval score; Wherein, the first basic sub-weight corresponds to the operation frequency sub-score, the second basic sub-weight corresponds to the operation duration sub-score, and the third basic sub-weight corresponds to the operation time interval score.

[0007] Preferably, step (2) specifically includes: (2.1) Determine the first sub-correction weight of each setting item based on the intent type; And / or, (2.2) determine the second sub-correction weight of each setting item based on the environmental data and the historical operation data; (2.3) Determine the correction weight of each setting item based on the first sub-correction weight and / or the second sub-correction weight.

[0008] Preferably, the first sub-correction weight corresponding to each setting item is obtained by weighted accumulation based on the first historical sub-correction weight determined by the historical operation data of the setting item. The smaller the current time interval of the historical operation data, the higher the weight of the first historical sub-correction weight.

[0009] Preferably, the intent type includes usage intent, positive ranking intent, and negative ranking intent, and step (2.1) specifically includes: (2.1.1) Identify at least one of the user's usage intent, positive ranking intent, and negative ranking intent based on historical operation data; (2.1.2) Determine the first sub-correction weight based on at least one of the usage intention score, positive ranking intention score, and negative ranking intention score; Wherein, the usage intention score is obtained based on the usage intention, the positive ranking intention score is obtained based on the positive ranking intention, and the negative ranking intention score is obtained based on the negative ranking intention; When the number of times usage intent, positive ranking intent, and negative ranking intent are identified is the same, the score of positive ranking intent is greater than the score of usage intent, and the score of usage intent is greater than the score of negative ranking intent.

[0010] Preferably, step (2.2) specifically includes: (2.2.1) Obtain the preset conditions of each external environment and the target settings corresponding to the preset conditions of the external environment; (2.2.2) When the environmental data meets the preset conditions of the external environment, determine the second sub-correction weight of the target setting item.

[0011] Preferably, step (3) specifically includes: (3.1) Determine the sorting priority of each setting item based on its base weight and adjusted weight; (3.2) In response to the preset triggering condition, sort and arrange each setting item according to the sorting priority.

[0012] Preferably, the sorting layout includes accommodating low-priority settings that are lower than a preset sorting priority, and after step (3), it further includes: (4) Obtain user operation feedback data for each setting item after sorting and layout, determine the correction feedback weight of each setting item based on the operation feedback data, and update the sorting priority of each setting item based on the basic weight, the correction weight and the correction feedback weight of each setting item.

[0013] The device for the layout of in-vehicle installations is characterized in that the device comprises: A processor is configured to execute computer-executable instructions; The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described method for laying out in-vehicle settings.

[0014] The processor for implementing the layout of in-vehicle settings is characterized in that the processor is configured to execute computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described method for laying out in-vehicle settings.

[0015] The computer-readable storage medium is characterized in that it stores a computer program thereon, which can be executed by a processor to implement the various steps of the above-described method for laying out vehicle-mounted installation items.

[0016] The in-vehicle settings layout method of this invention calculates the basic and corrective weights of settings based on user historical operation data (including intent type and environmental data), dynamically sorting and arranging the menu to significantly improve operational efficiency. Frequently used functions no longer require lengthy searches through multi-level menus, greatly reducing single-eye shift time and lowering driving risks; moreover, users only need one operation to permanently change the menu position for direct access later, significantly reducing long-term operational costs. Simultaneously, daily operations rely on touch muscle memory, avoiding secondary distractions caused by listening confirmation in voice interaction. Furthermore, it enables personalized adaptive layouts for each user, improving satisfaction. Users can also directly modify menus via natural language, breaking the "black box" nature of traditional algorithms and combining interpretability and interventionability. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the first architecture of the layout method for vehicle-mounted settings according to the present invention.

[0018] Figure 2 This is a schematic diagram of the second architecture of the layout method for vehicle-mounted settings according to the present invention.

[0019] Figure 3 This is a flowchart illustrating the layout method of the vehicle-mounted installation items according to the present invention. Detailed Implementation

[0020] To more clearly describe the technical content of the present invention, the following description is provided in conjunction with specific embodiments.

[0021] Please see Figure 1 as well as Figure 2The present invention provides a method for arranging in-vehicle settings, comprising the following steps: (1) Determine the basic weight of each setting item based on the user's historical operation data within a preset time period (corresponding to Figure 1 The "operational behavior data" and "behavior weight calculation unit" in the text. Figure 2 (the "perception layer" in the text) (2) Determine the correction weight of each setting based on the user's historical operation data reflecting the type of intent and / or the user's environmental data (corresponding to...). Figure 1 (including the "voice weight increment unit" and the "scene correction factor unit"). (3) Determine the sorting priority of each setting item based on its base weight and adjusted weight, so as to sort and arrange each setting item accordingly. Figure 1 The “fusion unit” and “composite weight value” in the text.

[0022] In the above steps (2) and (3) corresponding to Figure 2 The decision-making and execution levels within the organization.

[0023] Among them, the basic weight is positively correlated with the ranking priority, the upward adjustment of the modified weight is positively correlated with the ranking priority, and the downward adjustment of the modified weight is negatively correlated with the ranking priority.

[0024] In some embodiments, the preset time period is 30 days; historical operation data includes user actions on various function items in the vehicle settings menu, including the number of clicks, click frequency, distribution of single usage duration, usage time period (time period labels, such as morning, noon, evening), and contextual information such as geographical location. The aforementioned behavioral data is recorded locally using a data tracking method and is stored only on the vehicle terminal, without being uploaded to the cloud to protect user privacy.

[0025] In some embodiments, a user's historical operation data may include operation data from touch operations and voice operations. For voice operations, the system receives user-input voice commands, converts the speech to text using ASR (Automatic Speech Recognition), and then uses an NLU (Natural Language Understanding) unit for intent recognition and slot filling, parsing out the following intent types: usage intent, positive prioritization intent, and negative prioritization intent. For example, "Put the seat heating on the first page" is a positive prioritization intent for the "seat heating" setting. "I don't often use driving modes, put it away" is identified as a negative prioritization intent for the "driving mode" setting. "Lock navigation to the top" is a positive prioritization intent for "navigation." If "Turn on seat heating" or "Set driving mode to standard" is recognized, then a usage intent is identified.

[0026] In the above embodiments, the identification of intent type can be based on slot identification and application interface prediction scheme of large language model, and the voice request can be identified and parameters filled according to the prompt information template; or a sentence segmentation processing scheme based on the degree of semantic unit relevance can be adopted, which first segments the sentences and then performs interface prediction and parameter filling sentence by sentence to improve the accuracy of natural language understanding of complex voice commands.

[0027] The user's environmental data includes in-vehicle cabin data (such as in-vehicle temperature and seat occupancy status) and current external environmental data (such as time, weather, and air quality).

[0028] In some optional embodiments, historical operation data includes at least one of the user's historical operation frequency, historical operation duration, and recent operation time interval; Historical operation frequency is positively correlated with basic weight, historical operation duration is positively correlated with basic weight, and recent operation time interval is negatively correlated with basic weight.

[0029] In some optional embodiments, step (1) specifically includes: (1.1) Determine the operation frequency sub-score for each setting item based on historical operation frequency, determine the operation duration sub-score for each setting item based on historical operation duration, and determine the operation time interval score for each setting item based on operation time interval. (1.2) Determine the basic weight of each setting item based on the first basic sub-weight, the second basic sub-weight, the third basic sub-weight, the operation frequency sub-score, the operation duration sub-score, and the operation time interval score; Among them, the first basic sub-weight corresponds to the operation frequency sub-score, the second basic sub-weight corresponds to the operation duration sub-score, and the third basic sub-weight corresponds to the operation time interval score.

[0030] In some embodiments, the first basic sub-weight is 0.5, the second basic sub-weight is 0.3, and the third basic sub-weight is 0.2. The operation frequency sub-score is positively correlated with historical operation frequency and is obtained by normalizing the historical operation frequency; the operation duration sub-score... The score is obtained by normalizing historical operation durations; operation time interval score. In some embodiments, the operation time interval score is obtained based on the most recent operation time interval. equal , where t is the time interval between the most recent operations and λ is a constant. In other words, the basic weights... The first basic sub-weight is... The second basic sub-weight is The third basic sub-weight is .

[0031] In some optional embodiments, step (2) specifically includes: (2.1) Determine the first sub-correction weight of each setting item based on the intent type; In some embodiments, historical operation data includes voice commands, in which case step (2.1) corresponds to Figure 1 The “voice commands” and “voice weight increment units” in the text; And / or, (2.2) determine the second sub-correction weight (corresponding to) for each setting item based on environmental data and historical operation data. Figure 1 (The "scene context" and "scene correction factor unit" in the text). (2.3) Determine the correction weight of each setting item based on the first sub-correction weight and / or the second sub-correction weight.

[0032] The first sub-correction weight corresponding to each setting item is obtained by weighting and accumulating the first historical sub-correction weight determined by the historical operation data of each setting item. The smaller the current time interval of the historical operation data, the higher the weight of the first historical sub-correction weight.

[0033] In some optional embodiments, the intent type includes usage intent, positive ranking intent, and negative ranking intent, and step (2.1) specifically includes: (2.1.1) Identify at least one of the user's usage intent, positive ranking intent, and negative ranking intent based on historical operation data; (2.1.2) Determine the first sub-correction weight based on at least one of the use intention score, positive ranking intention score, and negative ranking intention score; Among them, the usage intention score is based on the usage intention, the positive ranking intention score is based on the positive ranking intention, and the negative ranking intention score is based on the negative ranking intention; When the number of times usage intent, positive ranking intent, and negative ranking intent are identified is the same, the score for positive ranking intent is greater than the score for usage intent, and the score for usage intent is greater than the score for negative ranking intent.

[0034] In some embodiments, the first sub-correction weight can be obtained by adding the usage intent score, the positive ranking intent score, and the negative ranking intent score. For ease of explanation, the following intent types are all identified as one type, and each identification is performed only once. In some embodiments, when the user's intent type is identified as "positive ranking intent" (e.g., the identified voice is "push driving mode to the top" or "adjust driving mode to the front"), the positive ranking intent score corresponding to "driving mode" is 50 points. If the identified voice is "adjust driving mode to standard mode", then the user's intent type is "usage intent". The usage intent score corresponding to "driving mode" is 10 points. In other embodiments, if the same setting (e.g., "driving mode") is activated multiple times on the same day, the usage intent score for that setting will gradually converge. If the identified voice is "hide driving mode" or "adjust driving mode to the back", then the negative ranking intent score is -80% of the base weight of "driving mode" (i.e., the base weight of "driving mode" multiplied by 0.2).

[0035] In other embodiments, a first historical sub-correction weight can be determined based on the intent type obtained from the user's operation data. The first sub-correction weight is then obtained by weighting and accumulating these first historical sub-correction weights. In some embodiments, the first sub-correction weight is: .in, Indicates the first historical sub-correction weight. This represents the weight corresponding to the first historical sub-correction weight at a given time. Indicates the current time interval.

[0036] In some optional embodiments, step (2.2) specifically includes: (2.2.1) Obtain the preset conditions of each external environment and the target settings corresponding to the preset conditions of the external environment; (2.2.2) When the environmental data meets the preset conditions of the external environment, the second sub-correction weight of the target setting item is determined.

[0037] In some embodiments, if the preset external environmental conditions are during the morning period (e.g., 6:00 AM to 9:00 AM) and the outside temperature is below zero degrees Celsius, the setting corresponding to these preset external environmental conditions is "seat heating". If the environmental data meets the preset external environmental conditions, the second sub-correction weight for the "seat heating" setting is determined to be 15 points. In some embodiments, the second sub-correction weight can be expressed as follows.

[0038] In some embodiments, the weights are adjusted as follows: .

[0039] in, It is a correction factor for the external environment.

[0040] In some optional embodiments, step (3) specifically includes: (3.1) Determine the sorting priority of each setting item based on its base weight and adjusted weight; (3.2) In response to the preset triggering conditions, sort and arrange each setting item according to the sorting priority.

[0041] In some embodiments, preset triggering conditions may include: the change in the correction weight of a certain setting exceeds a preset change threshold (e.g., ±15 minutes), the user explicitly requests layout adjustment via voice command (instant triggering), the user's cumulative number of data operations reaches a preset threshold (e.g., cumulative number of operations ≥ 50 times), and preset timed triggering strategies (e.g., every Sunday at midnight).

[0042] In some embodiments, the sorting layout may specifically include: placing frequently used settings at the top of the primary menu or in easily accessible areas (such as the upper left corner as a visual hotspot) based on adjusted weights; and collapsing less frequently used settings to preset secondary menus (such as in the "More Functions" or "Other Settings" storage panel). In some embodiments, based on the correlation coefficient between settings (such as determined by frequent itemset mining or collaborative filtering), strongly related function items (such as "Seat Heating" and "Steering Wheel Heating") may be grouped together and displayed in the same area or form a quick switching panel. In some embodiments, when the menu layout is updated, identifying graphics (such as bubble prompts or "Recommended" badges) may be used at the function entry point of the parent menu level to indicate the movement position of frequently used settings; for settings "hidden" by voice, a floating icon may be used at the entry point of the "More" storage panel to indicate the number of stacked functions. In some embodiments, an appropriate layout style and grid partitioning strategy may be selected based on the current vehicle's central control screen size and resolution parameters.

[0043] In some optional embodiments, the sorting layout includes accommodating low-priority settings that are below a preset sorting priority, and after step (3), it further includes: (4) Obtain user feedback data on each setting item after sorting and layout, determine the correction feedback weight of each setting item based on the operation feedback data, and update the sorting priority of each setting item based on the basic weight, correction weight, and correction feedback weight (corresponding to) Figure 2 (The "feedback layer" in the middle).

[0044] The apparatus for implementing the layout of in-vehicle installations according to the present invention, wherein the apparatus includes: A processor is configured to execute computer-executable instructions; The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described method for laying out in-vehicle settings.

[0045] The present invention discloses a processor for implementing the layout of in-vehicle settings, wherein the processor is configured to execute computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described method for laying out in-vehicle settings.

[0046] The computer-readable storage medium of the present invention stores a computer program thereon, which can be executed by a processor to implement the various steps of the above-described method for laying out in-vehicle settings.

[0047] Please see Figure 3 In a specific embodiment of the present invention, the layout method of the vehicle-mounted settings may include the following steps.

[0048] 1. Data Collection. Specifically, after user authorization, click-based operation data for the following settings were collected over 30 days: "Seat Heating" was the most frequently clicked, concentrated in the morning and winter weather scenarios; "Driving Mode" was clicked only twice in 30 days, with sparse usage records; "Navigation" was frequently used during evening commutes; and "Air Conditioning Temperature Adjustment" was frequently adjusted when children were in the car (when a child occupant was detected by the seat weight sensor). Voice commands from the user can also be continuously received via a microphone array: Voice Command 1: "Put the seat heating on the first page." Voice Command 2: "I rarely use Driving Mode, put it away." Voice Command 3: "Turn on the seat heating" (quick function activation).

[0049] 2. Sort priority calculation (i.e.) Figure 3 (The "2-weight calculation" in the text). The sorting priority can specifically include the following steps: Basic weight calculation: The basic weight of "seat heating" is calculated based on three factors: frequency, duration, and recent usage interval decay, resulting in a basic weight of 78 points; the basic weight of "navigation" is 65 points; and the basic weight of "driving mode" is 12 points.

[0050] The first sub-correction weight calculation: The command "Place seat heating on the first page" applies a first sub-correction weight of +50 points, and "Turn on seat heating" applies a first sub-correction weight of +10 points. After accumulation and decay with the current time interval, the seat heating obtains a first sub-correction weight of +52 points. The command "I rarely use driving mode, put it away" is identified as a negative sorting intention. At this time, the decay factor is triggered, and the base weight of driving mode is multiplied by 0.2 (or the first sub-correction weight of driving mode can be determined to be 80% of the base weight of driving mode multiplied).

[0051] Second sub-correction weight calculation: In the morning and cold weather conditions, add +15 points to "seat heating".

[0052] Corrected weight calculation: The final composite weight of seat heating is 78+52+15=145 points; the composite weight of navigation is 65 points; the composite weight of driving mode is 12×0.2=2.4 points (for ease of calculation, 12×0.2 can be approximately equal to 2 points).

[0053] 3. Layout trigger judgment. Layout trigger judgment may include the following steps.

[0054] The "Driving Mode" weight was detected to have dropped to 22 points, a decrease of more than 15 points compared to the previous iteration (20 points), and the user explicitly requested an adjustment via voice command, meeting the immediate triggering conditions. The layout decision steps are as follows: Sorting priority sorting: Sort according to sorting priority, the sequence is: seat heating (145), navigation (65), air conditioning temperature fine adjustment (52), in-vehicle Wi-Fi hotspot (18), driving mode (2).

[0055] 4. Location assignment (i.e.) Figure 3 In the "Generate New Layout" section: Seat heating is moved to the top left corner of the first-level menu (visual hotspot area); navigation remains in the second position on the first screen; fine-tuning of air conditioning temperature remains on the first screen; driving modes are folded and stored in the "More Settings" sub-panel.

[0056] Voice-activated visualization: If the system detects that the user has not clicked on the function item that has been brought to the home screen after using a voice command, it will automatically announce: "The 'seat heating' you previously specified by voice has been placed in the upper left corner of the home page. Please check it."

[0057] 5. Execution (i.e. Figure 3 "Load Display": The system generates a new menu layout and loads and displays it.

[0058] 6. Feedback learning (i.e.) Figure 3 (The "feedback loop" in the system): The system detected that after entering "More Settings," the user consciously clicked "Driving Mode" again and adjusted it to "Sport Mode." The system recorded this as negative feedback—the user has a need for "Driving Mode" but it was previously over-restricted. Based on the negative feedback criterion that reflects the user's true needs, the corrective feedback weight for "Driving Mode" was determined to be +15 points, and it was restored to the bottom or edge of the primary menu in the next layout iteration.

[0059] In some embodiments, the base weights (including operation frequency sub-scores, operation duration sub-scores, and operation time interval scores) and correction weights (including first sub-correction weights, second sub-correction weights, and third sub-correction weights) can be calculated using a trained machine learning model. The model's input includes: passive behavior feature vectors, voice command interaction sequences (including timestamps and command types), and environmental context feature vectors. The model's training method includes: acquiring a large amount of historical interaction data from anonymous users as training samples to predict the Top-N most likely functions used by the target user in the next time period as supervision signals. After training, this method uses the prediction confidence of each setting in the model output as a correction weight. The advantage of using a machine learning model lies in its ability to capture implicit collaborative relationships between settings (e.g., users often tend to adjust "steering wheel heating" after adjusting "seat heating") and the dynamic preference shifting patterns of users in different time periods and scenarios, thereby improving the prediction accuracy of layout adjustments.

[0060] Compared to other methods, this approach calculates the base and adjusted weights of settings items based on users' historical operation data (including intent type and environmental data), dynamically sorting and arranging the menu to significantly improve operational efficiency. Frequently used functions no longer require lengthy searches through multi-level menus, greatly reducing single-look-shift time and lowering driving risks. Furthermore, users can permanently change menu positions with a single operation, allowing direct access later, significantly reducing long-term operational costs. Simultaneously, daily operations rely on touch muscle memory, avoiding secondary distractions caused by listening confirmation in voice interaction. In addition, it enables personalized adaptive layouts for each user, enhancing satisfaction. Users can also directly modify menus using natural language, breaking the "black box" nature of traditional algorithms and combining interpretability and operability.

[0061] For the specific implementation scheme of this embodiment, please refer to the relevant descriptions in the above embodiments, which will not be repeated here.

[0062] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0063] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0064] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0065] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0066] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The corresponding program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0067] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0068] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0069] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0070] Compared to other methods, this approach calculates the base and adjusted weights of settings items based on users' historical operation data (including intent type and environmental data), dynamically sorting and arranging the menu to significantly improve operational efficiency. Frequently used functions no longer require lengthy searches through multi-level menus, greatly reducing single-look-shift time and lowering driving risks. Furthermore, users can permanently change menu positions with a single operation, allowing direct access later, significantly reducing long-term operational costs. Simultaneously, daily operations rely on touch muscle memory, avoiding secondary distractions caused by listening confirmation in voice interaction. In addition, it enables personalized adaptive layouts for each user, enhancing satisfaction. Users can also directly modify menus using natural language, breaking the "black box" nature of traditional algorithms and combining interpretability and operability.

[0071] In this specification, the invention has been described with reference to specific embodiments thereof. However, it will be apparent that various modifications and variations can be made without departing from the spirit and scope of the invention. Therefore, the specification and drawings should be considered illustrative rather than restrictive.

Claims

1. A method for arranging in-vehicle settings, characterized in that, The method for laying out the in-vehicle settings menu includes the following steps: (1) Determine the basic weight of each setting item based on the user's historical operation data within a preset time period; (2) Determine the correction weight of each setting based on the type of intent reflected by the user's historical operation data and / or the user's environmental data; (3) Determine the sorting priority of each setting item based on its basic weight and modified weight, so as to sort and arrange each setting item. Wherein, the base weight is positively correlated with the sorting priority, the upward adjustment of the modified weight is positively correlated with the sorting priority, and the downward adjustment of the modified weight is negatively correlated with the sorting priority.

2. The layout method for vehicle-mounted installations according to claim 1, characterized in that, The historical operation data includes at least one of the user's historical operation frequency, historical operation duration, and recent operation time interval. The historical operation frequency is positively correlated with the basic weight, the historical operation duration is positively correlated with the basic weight, and the most recent operation time interval is negatively correlated with the basic weight.

3. The layout method for vehicle-mounted installations according to claim 2, characterized in that, Step (1) specifically includes: (1.1) Determine the operation frequency sub-score of each setting item based on the historical operation frequency, determine the operation duration sub-score of each setting item based on the historical operation duration, and determine the operation time interval score of each setting item based on the operation time interval. (1.2) Determine the basic weight of each setting item based on the first basic sub-weight, the second basic sub-weight, the third basic sub-weight, the operation frequency sub-score, the operation duration sub-score, and the operation time interval score; Wherein, the first basic sub-weight corresponds to the operation frequency sub-score, the second basic sub-weight corresponds to the operation duration sub-score, and the third basic sub-weight corresponds to the operation time interval score.

4. The layout method for vehicle-mounted installations according to claim 1, characterized in that, Step (2) specifically includes: (2.1) Determine the first sub-correction weight of each setting item based on the intent type reflected by the historical operation data; And / or, (2.2) determine the second sub-correction weight of each setting item based on the environmental data and the historical operation data; (2.3) Determine the correction weight of each setting item based on the first sub-correction weight and / or the second sub-correction weight.

5. The layout method for vehicle-mounted installations according to claim 4, characterized in that, The first sub-correction weight corresponding to each setting item is obtained by weighting and accumulating the first historical sub-correction weight determined by the historical operation data of each setting item. The smaller the current time interval of the historical operation data, the higher the weight of the first historical sub-correction weight.

6. The layout method for vehicle-mounted installations according to claim 4, characterized in that, The intent types include usage intent, positive ranking intent, and negative ranking intent, and step (2.1) specifically includes: (2.1.1) Identify at least one of the user's usage intent, positive ranking intent, and negative ranking intent based on historical operation data; (2.1.2) Determine the first sub-correction weight based on at least one of the usage intention score, positive ranking intention score, and negative ranking intention score; Wherein, the usage intention score is obtained based on the usage intention, the positive ranking intention score is obtained based on the positive ranking intention, and the negative ranking intention score is obtained based on the negative ranking intention; When the number of times usage intent, positive ranking intent, and negative ranking intent are identified is the same, the score of positive ranking intent is greater than the score of usage intent, and the score of usage intent is greater than the score of negative ranking intent.

7. The layout method for vehicle-mounted installations according to claim 4, characterized in that, Step (2.2) specifically includes: (2.2.1) Obtain the preset conditions of each external environment and the target settings corresponding to the preset conditions of the external environment; (2.2.2) When the environmental data meets the preset conditions of the external environment, determine the second sub-correction weight of the target setting item.

8. The layout method for vehicle-mounted installations according to claim 1, characterized in that, Step (3) specifically includes: (3.1) Determine the sorting priority of each setting item based on its base weight and adjusted weight; (3.2) In response to the preset triggering condition, sort and arrange each setting item according to the sorting priority.

9. The layout method for vehicle-mounted installations according to claim 1, characterized in that, The sorting layout includes accommodating low-priority settings that are lower than the preset sorting priority. After step (3), it also includes: (4) Obtain user operation feedback data for each setting item after sorting and layout, determine the correction feedback weight of each setting item based on the operation feedback data, and update the sorting priority of each setting item based on the basic weight, the correction weight and the correction feedback weight of each setting item.

10. A device for implementing the layout of in-vehicle installation items, characterized in that, The device includes: A processor is configured to execute computer-executable instructions; The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the steps of the layout method for the vehicle-mounted installations according to any one of claims 1 to 9.

11. A processor for implementing the layout of in-vehicle settings, characterized in that, The processor is configured to execute computer-executable instructions, which, when executed by the processor, implement the steps of the layout method for the in-vehicle installation item according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, It stores a computer program that can be executed by a processor to implement the various steps of the layout method of the in-vehicle settings as described in any one of claims 1 to 9.

Images