Cabin control method, electronic equipment and vehicle

Abstract

The invention relates to the technical field of vehicles, in particular to a cabin control method, electronic equipment and a vehicle, and the method comprises the steps: obtaining the current data of a user and the current environment data of a cabin; according to the current data and the current environment data, calculating an emotion adaptation degree score and an environment adaptation degree score respectively, and according to the current data and the current environment data, calculating a conflict punishment score; determining respective weights according to the emotion adaptation degree score, the environment adaptation degree score and the conflict penalty score, and calculating a comprehensive adaptation score according to the emotion adaptation degree score, the environment adaptation degree score, the conflict penalty score and the respective weights; and controlling corresponding actions of the cabin according to the comprehensive adaptation score. According to the method, the actions of the cockpit can be matched with the emotion and the environment cooperatively, the adjustment actions of the user on the cockpit system and conflicts occurring when the user emotion or the cockpit environment changes are quantified, it is ensured that the final actions of the cockpit are the result of multi-target comprehensive consideration, resource allocation in the cockpit is optimized, and the use experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a cockpit control method, electronic equipment, and vehicle. Background Technology

[0002] Intelligent cockpits have become a core carrier for improving driving experience and safety. Their core requirement is to achieve precise matching between cockpit status and user needs. Currently, cockpit adjustment is gradually evolving from traditional single environmental parameter control to an integrated approach of emotional perception, environmental optimization, and interactive adaptation.

[0003] However, cockpit systems in related technologies generally treat emotion recognition and environmental regulation as independent modules, and there is a lack of dynamic correlation between the modules, which makes it impossible for the control strategy of the cockpit system to take into account both the emotional needs of the user and the environmental needs of the cockpit. Summary of the Invention

[0004] This application provides a cockpit control method, electronic device, and vehicle to solve the problem that cockpit execution strategies in related technologies cannot simultaneously meet the emotional needs of users and the environmental needs of the cockpit.

[0005] The first aspect of this application provides a cockpit control method, comprising the following steps: acquiring current user data and current cockpit environmental data; calculating the user's emotional fit score based on the current data, calculating the cockpit's environmental fit score based on the current environmental data, and calculating a conflict penalty score based on the current data and the current environmental data; determining the respective weights of the emotional fit score, environmental fit score, and conflict penalty score; calculating a comprehensive fit score based on the emotional fit score, environmental fit score, conflict penalty score, and their respective weights; and controlling corresponding cockpit actions based on the comprehensive fit score.

[0006] Based on the aforementioned technical means, this application embodiment can calculate the emotional fit score and environmental fit score based on the user's current data and the current environment data of the cockpit, respectively. It can also calculate a conflict penalty score based on the user's current data and the current environment data of the cockpit. The weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, and a comprehensive fit score is calculated based on these scores and their respective weights. Finally, the cockpit's corresponding actions are controlled based on the comprehensive fit score. This allows the cockpit's actions to coordinate with emotions and the environment, quantifies the user's adjustments to the cockpit system, and addresses conflicts arising from changes in user emotions or the cockpit environment. This ensures that the final cockpit actions are a result of comprehensive consideration of multiple objectives, avoiding the pursuit of emotional or environmental fit at the expense of potential risks. It improves user satisfaction with the cockpit environment and driving safety, enhances the user experience, and optimizes in-cockpit resource allocation, preventing resource waste.

[0007] Optionally, the emotional fit score of the user is calculated based on the current data, including: obtaining the user's first reference data; calculating the first difference data between the first reference data and the current data; and calculating the emotional fit score based on the first difference data and the corresponding weight.

[0008] Based on the above technical means, the embodiments of this application can obtain the user's first reference data, calculate the first difference data between the first reference data and the current data, calculate the emotional fit score based on the first difference data and the corresponding weight, and determine the fit of the cabin environment to the user's emotional needs by comparing the user's reference data and the user's current data.

[0009] Optionally, the environmental fit score of the cockpit is calculated based on the current environmental data, including: obtaining second reference data of the cockpit; calculating second difference data between the current environmental data and the second reference data; and calculating the environmental fit score based on the second difference data and the corresponding weights.

[0010] Based on the above technical means, the embodiments of this application can obtain the user's second reference data, calculate the second difference data between the second reference data and the current data, calculate the environmental adaptability score based on the second difference data and the corresponding weight, and determine the environmental adaptability of the cabin environment by comparing the environmental reference data and the current environmental data.

[0011] Optionally, the conflict penalty score is calculated based on the current data and the current environment data, including: identifying the conflict action type based on the current data and the current environment data; determining the score and weight of the conflict action based on the type of conflict action; and calculating the conflict penalty score based on the weight and score of the conflict action.

[0012] Based on the aforementioned technical means, this application embodiment can accurately determine the types of conflict actions that may be caused by adjustment actions based on the user's current data and the current environmental data of the cockpit, and assign corresponding scores and weights to different types of conflict actions to clarify the severity and priority of the conflict. Then, by weighted summation of the weights and scores of the conflict actions, an overall conflict penalty score is obtained. Through conflict identification and quantification, the cockpit system can consider potential negative impacts when making decisions and comprehensively consider the final cockpit actions.

[0013] Optionally, the score and weight of the conflicting action are determined according to the type of conflicting action, including: obtaining a first correspondence table of conflicting action types, scores and weights; and querying the first correspondence table using the type of conflicting action as an index to obtain the score and weight of the conflicting action.

[0014] Optionally, the weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, including: obtaining a second correspondence table between the emotional fit score, environmental fit score, conflict penalty score, and weights; and querying the second correspondence table using the emotional fit score, environmental fit score, and conflict penalty score as indexes to obtain the respective weights of the emotional fit score, environmental fit score, and conflict penalty score.

[0015] Based on the above technical means, the embodiments of this application can use the emotional fit score, environmental fit score and conflict penalty score as indexes to query the second correspondence table to obtain the respective weights of the emotional fit score, environmental fit score and conflict penalty score, so as to calculate the comprehensive fit score in the future.

[0016] Optionally, the cockpit actions are controlled according to the overall adaptation score, including: generating cockpit control commands based on the overall adaptation score; querying pre-set cockpit control strategies based on the cockpit control commands to obtain the target control actions of the cockpit; and controlling the cockpit to execute the target control actions.

[0017] Optionally, after controlling the corresponding cockpit actions based on the comprehensive adaptation score, the method further includes: identifying user feedback data; and updating the cockpit control strategy based on the adjusted target control actions and cockpit control commands when the user adjusts the target control actions based on the feedback data.

[0018] Based on the above technical means, the embodiments of this application identify user feedback data, and when it is determined that the user is adjusting the target control action based on the feedback data, the cockpit control strategy is updated according to the adjusted target control action and cockpit control command. By driving the strategy library update through user feedback, the cockpit control strategy gradually adapts to the user's personalized preferences, improves long-term user satisfaction, and avoids the solidification of the cockpit control strategy. It can cope with the differences in needs of different users and the changes in needs of the same user.

[0019] A second aspect of this application provides a cockpit control device, comprising: an acquisition module for acquiring current user data and current cockpit environmental data; a first calculation module for calculating the user's emotional fit score based on the current data, calculating the cockpit's environmental fit score based on the current environmental data, and calculating a conflict penalty score based on the current data and the current environmental data; a second calculation module for determining the respective weights of the emotional fit score, environmental fit score, and conflict penalty score, and calculating a comprehensive fit score based on the emotional fit score, environmental fit score, conflict penalty score, and their respective weights; and a control module for controlling corresponding cockpit actions based on the comprehensive fit score.

[0020] Optionally, the first calculation module is further configured to: obtain the user's first reference data; calculate the first difference data between the first reference data and the current data; and calculate the sentiment fit score based on the first difference data and the corresponding weight.

[0021] Optionally, the first calculation module is further configured to: acquire second reference data of the cockpit; calculate second difference data between the current environmental data and the second reference data; and calculate an environmental adaptability score based on the second difference data and the corresponding weights.

[0022] Optionally, the first calculation module is further configured to: identify conflict action types based on user data and cabin environment data; determine the score and weight of the conflict action based on the type of conflict action; and calculate the conflict penalty score based on the weight and score of the conflict action.

[0023] Optionally, the first calculation module is further configured to: obtain a first correspondence table of conflict action types, scores, and weights; and query the first correspondence table using the conflict action type as an index to obtain the score and weight of the conflict action.

[0024] Optionally, the second calculation module is further used to: obtain a second correspondence table between the emotional fit score, the environmental fit score, the conflict penalty score and the weights; and use the emotional fit score, the environmental fit score and the conflict penalty score as indexes to query the second correspondence table to obtain the respective weights of the emotional fit score, the environmental fit score and the conflict penalty score.

[0025] Optionally, the control module is further configured to: generate cockpit control commands based on the comprehensive adaptation score; query a pre-set cockpit control strategy based on the cockpit control commands to obtain the target control action of the cockpit, and control the cockpit to execute the target control action.

[0026] Optionally, it also includes: an update module, used to identify user feedback data after controlling the corresponding cockpit action based on the comprehensive adaptation score; and to update the cockpit control strategy based on the adjusted target control action and cockpit control commands when the user adjusts the target control action based on the feedback data.

[0027] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the cockpit control method as described above.

[0028] A fourth aspect of this application provides a vehicle that includes the electronic devices described in the above embodiments.

[0029] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a cockpit control method provided according to an embodiment of this application; Figure 2 This is a flowchart of a cockpit control method provided according to a specific embodiment of this application; Figure 3 This is an example diagram of a cockpit control device provided according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0031] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0032] Before describing the solution of this application, the technical problems existing in the cockpit system of the related art will be introduced first. The main problems existing in the related art are as follows: 1. The disconnect between emotion, environment, and interaction: Cockpit systems in related technologies generally treat emotion recognition, environmental adjustment, and interaction strategies as independent modules, lacking dynamic correlation. For example, a traditional cockpit may only automatically adjust the air conditioning based on temperature, but it cannot simultaneously adjust the seat massage intensity and voice feedback style based on the driver's fatigue level.

[0033] 2. Limitations of static weight allocation: Using a fixed weight allocation strategy (such as 50% for emotional needs and 50% for environmental needs) cannot dynamically adjust priorities according to real-time scenarios. For example, when a driver is in a state of high fatigue, the system in related technologies may still allocate resources according to fixed weights, resulting in the core need (fatigue relief) not being responded to first.

[0034] 3. Lack of closed-loop feedback mechanism: Related technologies generally lack user feedback-driven self-learning capabilities, making it impossible to optimize strategies using historical data. For example, if a user is allergic to a specific fragrance, the system cannot continuously learn to avoid repeatedly recommending that fragrance.

[0035] 4. Insufficient multimodal data fusion: Many related technologies rely on single-modal data (such as facial expressions or voice signals alone) for emotion recognition, resulting in a high false positive rate. For example, when there is a lot of noise inside the car, the accuracy of voice emotion recognition drops significantly, and related technologies lack robust optimization through multimodal data fusion.

[0036] This application provides a cockpit control method, comprising: acquiring current user data and current cockpit environmental data; calculating the user's emotional fit score based on the current data, calculating the cockpit's environmental fit score based on the current environmental data, and calculating a conflict penalty score based on the current data and the current environmental data; determining the respective weights of the emotional fit score, environmental fit score, and conflict penalty score; calculating a comprehensive fit score based on the emotional fit score, environmental fit score, conflict penalty score, and their respective weights; and controlling corresponding cockpit actions based on the comprehensive fit score.

[0037] This application embodiment can calculate the emotional fit score and environmental fit score based on the user's current data and the current cabin environment data, respectively. It also calculates a conflict penalty score based on the user's current data and the current cabin environment data. The weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, and a comprehensive fit score is calculated based on these scores and their respective weights. Finally, the corresponding cabin actions are controlled based on the comprehensive fit score. This allows the cabin actions to adapt to both emotions and the environment, quantifies the user's adjustments to the cabin system, and addresses conflicts arising from changes in user emotions or the cabin environment. This ensures that the final cabin actions are a result of considering multiple objectives comprehensively, avoiding the pursuit of emotional or environmental fit at the expense of potential risks. It improves user satisfaction with the cabin environment, enhances the user experience and driving safety, and optimizes cabin resource allocation, preventing resource waste.

[0038] Specifically, Figure 1 This is a schematic flowchart of a cockpit control method provided in an embodiment of this application.

[0039] like Figure 1 As shown, the cockpit control method includes steps S101-S104.

[0040] Step S101: Obtain the user's current data and the cockpit's current environmental data.

[0041] The user's current data includes emotion-related data and interaction data. Emotion-related data includes facial images, voice data, and physiological data (heart rate, blink frequency, etc.). Interaction data includes user actions. Environmental data includes temperature, noise, and light intensity.

[0042] In this application embodiment, user data and cabin environmental data can be collected based on multiple sensors, such as cameras, temperature sensors, etc.

[0043] Step S102: Calculate the user's emotional fit score based on the current data, calculate the cabin's environmental fit score based on the current environmental data, and calculate the conflict penalty score based on the current data and the current environmental data.

[0044] Among them, the emotional fit score can be represented by Em, which is used to quantify the degree to which the user's emotional needs are met in the current cabin environment. The higher the score, the more the user's emotional needs are met. The environmental fit score can be represented by En, which is used to quantify the degree of improvement of the cabin environment from an uncomfortable state to a comfortable state. The higher the score, the better the environmental optimization effect. The conflict penalty score can be represented by U3, which is used to quantify the severity of new conflicts (such as energy waste, impact on driving safety, etc.) caused by adjustment actions, changes in user emotions, and changes in the environment in the cabin system.

[0045] The embodiments of this application can comprehensively determine the user's emotional fit score and the cabin environment fit score by combining data from multiple modalities, thereby improving the accuracy of judging the user's emotions and the cabin environment.

[0046] Step S103: Determine the weights of the emotional fit score, environmental fit score, and conflict penalty score, and calculate the comprehensive fit score based on the emotional fit score, environmental fit score, conflict penalty score, and their respective weights.

[0047] It is understood that the embodiments of this application can determine the weights of the emotional fit score, environmental fit score and conflict penalty score to adapt to the user's needs in different situations, ensure that core needs are responded to first, and calculate the comprehensive fit score based on the emotional fit score, environmental fit score, conflict penalty score and their respective weights.

[0048] The comprehensive adaptation score formula in this application embodiment can be: U = α×Em + β×En - γ×U3; Wherein, U is the overall fit score (the higher the better, measuring the overall fit effect of the current cabin environment); Em is the emotional fit score (0-10, the higher the value, the higher the emotional satisfaction); En is the environmental improvement score (0-10, the higher the value, the better the environmental optimization effect); U3 is the conflict penalty value (0-5, the higher the value, the more serious the conflict, which needs to be deducted); α, β, and γ are their respective weights.

[0049] Step S104: Control the corresponding cockpit actions based on the comprehensive adaptation score.

[0050] The cabin controls include increasing the intensity of seat massage, adjusting the air conditioning temperature, and turning on the ambient lighting.

[0051] This application embodiment can calculate the emotional fit score and environmental fit score based on the user's current data and the current cabin environment data, respectively. It also calculates a conflict penalty score based on the user's current data and the current cabin environment data. The weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, and a comprehensive fit score is calculated based on these scores and their respective weights. Finally, the corresponding cabin actions are controlled based on the comprehensive fit score. This allows the cabin actions to adapt to both emotions and the environment, quantifies the user's adjustments to the cabin system, and addresses conflicts arising from changes in user emotions or the cabin environment. This ensures that the final cabin actions are a result of considering multiple objectives comprehensively, avoiding the pursuit of emotional or environmental fit at the expense of potential risks. It improves user satisfaction with the cabin environment, enhances the user experience and driving safety, and optimizes cabin resource allocation, preventing resource waste.

[0052] In addition, it should be noted that there are situations where there is no conflict in the actions performed by the current cockpit system. In this case, the overall fit score is calculated based on the emotional fit score, the environmental fit score, and their corresponding weights.

[0053] In some embodiments of this application, calculating a user's emotional fit score based on current data includes: obtaining the user's first reference data; calculating the first difference data between the first reference data and the current data; and calculating the emotional fit score based on the first difference data and the corresponding weight.

[0054] The first reference data can be the initial data collected when the user gets into the vehicle, or the initial data collected before the cockpit control process is executed for the first time when the user's data reaches the trigger threshold set by the user.

[0055] It is understood that the embodiments of this application can obtain the user's first reference data, calculate the first difference data between the first reference data and the current data, calculate the emotional fit score based on the first difference data and the corresponding weight, and determine the fit of the cabin environment to the user's emotional needs by comparing the user's reference data and the user's current data.

[0056] The formula for calculating the emotional fit score in this application embodiment can be: Em = w1×S1 + w2×S2 +... + wn×Sn; S1, S2...Sn are the scores of the emotional sub-dimensions (0-10 points), such as the physiological fatigue dimension and the emotional recovery dimension; the sub-dimension scores are generated through multimodal fusion (e.g., S1 = 0.4 × facial fatigue feature + 0.3 × voice fatigue feature + 0.3 × physiological fatigue feature); the scores of individual modal features are determined by mapping from sensor data (e.g., the mapping relationship is set as heart rate 85 beats / min → 3 points, decreasing to 75 beats / min → 8 points); w1, w2...wn are the sub-dimension weights (the sum is 1, e.g., w1 = 0.6, w2 = 0.4, because physiological fatigue has a higher priority).

[0057] In some embodiments of this application, calculating the cabin's environmental fit score based on current environmental data includes: obtaining second reference data for the cabin; calculating second difference data between the current environmental data and the second reference data; and calculating the environmental fit score based on the second difference data and its corresponding weight.

[0058] The second reference data can be the initial environmental data collected when the user gets into the vehicle, or the initial environmental data collected before the cockpit control process is executed for the first time when the environmental data reaches the trigger threshold set by the user. The second reference data also includes ideal cockpit environmental parameters.

[0059] It is understood that the embodiments of this application can obtain the user's second reference data, calculate the second difference data between the second reference data and the current data, calculate the environmental adaptability score based on the second difference data and the corresponding weight, and determine the environmental adaptability of the cabin environment by comparing the environmental reference data and the current environmental data.

[0060] The formula for calculating the environmental adaptability in this application embodiment can be: En = k1×I1 + k2×I2 + ... +km×Im; Wherein, I1, I2...Im are the improvement indices (0-10 points) for a single environmental indicator, I = (current state - initial discomfort state) ÷ (ideal comfort state - initial discomfort state) × 10 (if the current state is better than the ideal state, it is counted as 10 points); the initial discomfort state is the environmental parameter collected for the first time or the parameter that exceeds the ideal value by 20% (such as temperature > 28℃); the ideal comfort state is 24℃ (temperature) and ≤50dB (noise) by default, which can be manually set by the user (if a user has been setting it to 26℃ for a long time, then the ideal value will be updated to 26℃); k1, k2...km are the environmental indicator weights (the sum is 1, such as temperature k1=0.4, noise k2=0.3).

[0061] For example, the second reference data is set as a temperature of 24℃ and a noise level of 50dB (temperature weight 0.7, noise weight 0.3). The current cabin environment data is a temperature of 30℃ and a noise level of 65dB. Calculating the second difference data, the temperature deviation is 6℃ (improvement index 10 points), and the noise deviation is 5dB (improvement index 3.3 points). The environmental adaptability score En = 0.7 × 10 + 0.3 × 3.3 ≈ 8.0, indicating that the temperature optimization effect is significant, but the noise still needs further improvement.

[0062] In some embodiments of this application, calculating a conflict penalty score based on current data and current environmental data includes: determining the conflict action type based on the current data and current environmental data; determining the score and weight of the conflict action based on the type of conflict action; and calculating the conflict penalty score based on the weight and score of the conflict action.

[0063] Among them, the conflict action type refers to the type of negative impact that may be caused when satisfying emotional or environmental needs, such as increased energy consumption, impact on driving safety, and functional incompatibility; the conflict action score is a score that quantifies the severity of a single conflict action, ranging from 0 to 10 points, with higher scores indicating greater conflict impact.

[0064] It is understood that the embodiments of this application can accurately determine the types of conflict actions that may be caused by adjustment actions based on the user's current data and the current environmental data of the cockpit, and assign corresponding scores and weights to different types of conflict actions, clarify the severity and priority of the conflict, and then obtain the overall conflict penalty score by weighted summation of the weights and scores of the conflict actions. Through conflict identification and quantification, the cockpit system can consider potential negative impacts when making decisions and comprehensively consider the final cockpit actions.

[0065] The conflict action types in this application embodiment may include: 1. Energy consumption conflict.

[0066] There is a conflict between emotional needs and low energy consumption. For example, when users are tired, they need to turn on the seat massage and high-temperature air conditioning, which causes energy consumption to exceed the vehicle's preset threshold (such as the range dropping rapidly in pure electric mode).

[0067] 2. Security conflict.

[0068] Environmental optimization conflicts with driving safety. For example, turning on strong ambient lighting to improve environmental adaptability can result in glare and affect the driver's ability to see the road conditions.

[0069] 3. Functional mutual exclusion conflict.

[0070] Emotional and environmental actions can interfere with each other. For example, turning on a massage chair to relieve fatigue (emotional need) while simultaneously turning on a strong air conditioner to cool down (environmental need) can reduce the comfort of the massage.

[0071] 4. User experience conflict.

[0072] Actions that conflict with users' implicit preferences, such as judging that users need to relax (emotional fit) and playing soothing music, but users actually prefer rock music (not captured by the initial data), lead to a decline in the experience.

[0073] The formula for calculating the conflict penalty score in this application embodiment can be: U3 = p1 × C1 + p2 × C2 + ... + pq × Cq; C1, C2, ..., Cq are the severity scores of a single conflict (ranging from 0 to 10, where 0 indicates no conflict and 10 indicates a serious conflict); p1, p2, ..., pq are the weights of the conflicts (summing up to 1), representing the priority of the conflicts (e.g., if the impact on driving safety is more serious than the increase in energy consumption, then p1 > p2).

[0074] For example, when a user is fatigued, the cabin system plans to perform a seat massage and low-temperature air conditioning adjustment. Based on user data (fatigue requires warmth) and environmental data (current temperature 28℃), the conflicting action type is identified as functional mutual exclusion (conflict between low temperature and warmth requirements) + increased energy consumption. A conflict score of 6 points (weight 0.7) is set for functional mutual exclusion and 2 points (weight 0.3) for increased energy consumption. The conflict penalty score is calculated as U3 = 0.7 × 6 + 0.3 × 2 = 4.8, indicating that the adjustment scheme has a serious conflict under the current situation and needs to be adjusted.

[0075] In some embodiments of this application, determining the score and weight of a conflicting action based on its type includes: obtaining a first correspondence table of conflicting action types, scores, and weights; and querying the first correspondence table using the conflicting action type as an index to obtain the score and weight of the conflicting action.

[0076] The first correspondence table is a pre-defined mapping table containing conflict action types, corresponding scores, and weights. It serves as the basis for calculating conflict penalty scores and can be updated based on scenario requirements and user feedback.

[0077] It is understood that the embodiments of this application can obtain a first correspondence table of conflict action types, scores and weights, and use the conflict action type as an index to query the first correspondence table to obtain the conflict action score and weight. The correspondence table can make the determination of conflict scores and weights more efficient.

[0078] In some embodiments of this application, the weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, including: obtaining a second correspondence table between the emotional fit score, environmental fit score, conflict penalty score, and weights; and querying the second correspondence table using the emotional fit score, environmental fit score, and conflict penalty score as indexes to obtain the respective weights of the emotional fit score, environmental fit score, and conflict penalty score.

[0079] The second correspondence table stores a pre-defined correspondence between emotional fit score, environmental fit score, conflict penalty score and their respective weights. The lower the fit score, the higher the weight, to ensure that core needs are responded to first.

[0080] It is understood that, in the embodiments of this application, the emotional fit score, environmental fit score, and conflict penalty score can be used as indexes to query the second correspondence table to obtain the respective weights of the emotional fit score, environmental fit score, and conflict penalty score, so as to calculate the comprehensive fit score in the future.

[0081] In some embodiments of this application, controlling the corresponding cockpit actions based on the comprehensive adaptation score includes: generating cockpit control commands based on the comprehensive adaptation score; querying a pre-set cockpit control strategy based on the cockpit control commands to obtain the target control action of the cockpit; and controlling the cockpit to execute the target control action.

[0082] It is understood that, in the embodiments of this application, cockpit control commands can be generated based on the comprehensive adaptation score, and pre-set cockpit control strategies can be queried based on the cockpit control commands to obtain the target control action of the cockpit and control the cockpit to execute the target control action.

[0083] Specifically, in this application embodiment, a score range of the comprehensive adaptation score can be preset. Based on the score range in which the comprehensive adaptation score is located, the corresponding control command is determined. Then, based on the cockpit control command, the preset cockpit control strategy is queried to obtain the target control action of the cockpit and control the cockpit to execute the target control action.

[0084] For example, when U≥7 (adaptation effect is excellent), maintain the current action (such as continuing seat massage); When 4 ≤ U < 7 (adaptation effect is average): Select environment or emotion enhancement operation from the strategy library. Within this range, further compare the proportions of Em and En in U. If the proportion of Em is higher than the proportion of En, select emotion enhancement operation (such as increasing seat massage intensity or playing soothing music). If the proportion of Em is lower than the proportion of En, select environment optimization operation (such as adjusting the air conditioning temperature to the ideal value or reducing in-car noise). If the proportion of Em is equal to the proportion of En, select both environment optimization and emotion enhancement operation simultaneously. When U < 4 points (poor adaptation effect): trigger emergency adjustment (such as pausing the current action and switching to the user's historical preference operation).

[0085] Specifically, the cockpit control process in this application embodiment may or may not involve conflict, and the two situations will be described separately below.

[0086] 1. Conflict-free algorithm.

[0087] Total = Em × K1 + En × K2; Where Em is the emotional fit score; En is the environmental fit score; K1 and K2 are weight coefficients, which can be determined by referring to the second correspondence table, or the weights can be dynamically adjusted (K1+K2=1, which can be adjusted according to the thresholds of Em and En).

[0088] The dynamic adjustment rules for weight coefficients K1 and K2 can be as follows: K1=0.7 (when Em<6, emotional needs take priority), K1=0.3 (when En<6, environmental needs take priority), K1=0.5 (other cases, balanced distribution).

[0089] If Em < 6 and En < 6, then Em - En ≥ 1, and K1 = 0.4; if En - Em ≥ 1, then K1 = 0.6.

[0090] For example, given Em=5 and En=7, the weights are: since Em<6, K1=0.7 and K2=0.3.

[0091] Total = 5 × 0.7 + 7 × 0.3 = 5.6.

[0092] Emotional needs (fatigue relief) accounted for a higher proportion (3.5 / 5.6≈62.5%), and the cabin system prioritized responding to emotional needs by increasing actions that enhance these needs, such as turning on ambient lighting, playing music, and activating fragrances.

[0093] 2. Algorithms with conflicts.

[0094] In satisfying emotional needs or improving the environment, new conflicts may arise (such as low-temperature air conditioning + seat heating leading to energy waste). U3 is a weighted calculation of the negative impacts of these conflicts; the higher the score, the more severe the conflict, and the more comprehensive fit needs to be deducted.

[0095] Overall fit score, U = α × Em + β × En - γ × U³; Where U is the overall fit score, equivalent to Total above; Em is the emotional fit score; En is the environmental improvement score; U3 is the conflict penalty score; α, β, and γ are weighting coefficients (α+β+γ=1, which can be determined by querying the second correspondence table and adjusted according to the priority of the scenario, for example, α=0.6 when driving at high speed and α=0.3 when parking, α is equivalent to K1 above and β is equivalent to K2 above).

[0096] For example, if a user feels fatigued after driving for 1 hour (emotional need: fatigue relief), the interior temperature is 30℃ (ideal 24℃) and the noise level is 65 decibels (ideal 50 decibels), the cabin system will activate a fatigue relief strategy (play soothing music + lower the temperature to 24℃).

[0097] Step 1: Calculate the emotional fit Em.

[0098] The emotional sub-dimension (2 in total) includes: S1: "Relief of physiological fatigue" (heart rate decreased from 85 beats / min to 75 beats / min, corresponding to a score of 8). S2: "Behavioral relaxation" (sitting posture changes from tense to natural, corresponding to a score of 7 points).

[0099] Weights (physiological signals are more important in fatigue relief): w1=0.6, w2=0.4; Em = 0.6 × 8 + 0.4 × 7 = 4.8 + 2.8 = 7.6 (The emotional fit is good).

[0100] Step 2: Calculate the environment fit score En.

[0101] Environmental indicators (2), including: Temperature: Initial 30℃ → Current 24℃ (ideal 24℃), Improvement index I1 = (24-30) ÷ (24-30) × 10 = 10 points (fully met); Noise level: Initial 65 dB → Current 60 dB (ideal 50 dB), Improvement index I2 = (60-65) ÷ (50-65) × 10 = (-5) ÷ (-15) × 10 ≈ 3.3 points (partial improvement); Weights (temperature is more important for driving comfort): k1=0.7, k2=0.3; En=0.7×10+0.3×3.3≈7+1=8.0.

[0102] Step 3: Calculate the conflict penalty U3 (check if it causes new problems) (energy consumption, driving safety) Potential conflict (1), including: When the temperature is lowered, the air conditioner power increases, and the energy consumption rises from 1.2kW to 1.8kW (but does not exceed the "energy consumption threshold of 2.0kW"). The severity of the conflict is C1=2 points (minor conflict). Weight (energy conflicts have lower priority): p1=1.0 (only 1 conflict); U3 = 1.0 × 2 = 2.0 (small conflict impact, low penalty value).

[0103] Step 4: Calculate the overall fit score.

[0104] Assuming the weights (emotional safety is the most important factor in driving scenarios): α=0.5, β=0.3, γ=0.2; Overall fit score: U=0.5×7.6+0.3×8.0-0.2×2.0=3.8+2.4-0.4=5.8 (Overall fit is good).

[0105] Em is a score based on key signals of emotional needs being met, with the core being the improvement of the user's subjective / physiological state; En is a score based on the degree of improvement from discomfort to comfort in environmental indicators, with the core being the degree of optimization of the physical environment; U3 is a score based on the severity of new conflicts, with the core being avoiding side effects caused by system operation.

[0106] When these three factors are combined, the overall adaptability U can intuitively reflect whether the system solution truly adapts to user needs and scenarios. The higher the value, the better the adaptability.

[0107] The result U from the previous step is used to associate the corresponding strategy selection based on the optimal result U; the result is then output to the control layer to control the cabin hardware (such as light color temperature and seat massage intensity).

[0108] For example, when U≥7 (excellent adaptation effect): maintain the current operation (such as continuing seat massage); When 4 ≤ U < 7 (adaptation effect is average): Select environment or emotion enhancement operation from the strategy library. Within this range, further compare the proportions of Em and En in U. If the proportion of Em is higher than the proportion of En, select emotion enhancement operation (such as increasing seat massage intensity or playing soothing music). If the proportion of Em is lower than the proportion of En, select environment optimization operation (such as adjusting the air conditioning temperature to the ideal value or reducing in-car noise). If the proportion of Em is equal to the proportion of En, select both environment optimization and emotion enhancement operation simultaneously. When U < 4 points (poor adaptation effect): trigger emergency adjustment (such as pausing the current operation and switching to the user's historical preferred operation).

[0109] In some embodiments of this application, after controlling the corresponding cockpit actions based on the comprehensive adaptation score, the method further includes: identifying user feedback data; and when determining based on the feedback data that the user is adjusting the target control action, updating the cockpit control strategy based on the adjusted target control action and the cockpit control command.

[0110] The feedback data consists of user response data to cockpit control actions, including active feedback (such as ratings and voice evaluations) and passive feedback (such as manual adjustment operations and continuous on / off actions).

[0111] It is understood that the embodiments of this application identify user feedback data, and when it is determined that the user will adjust the target control action based on the feedback data, the cockpit control strategy is updated according to the adjusted target control action and cockpit control command. The strategy library is updated through user feedback, so that the cockpit control strategy gradually conforms to the user's personalized preferences, improves long-term user satisfaction, and avoids the solidification of the cockpit control strategy. It can cope with the differences in the needs of different users and the changes in the needs of the same user.

[0112] Specifically, the overall implementation process of the cockpit control method in this application includes: 1. First, based on the user's initial data and the initial environment data of the cockpit, select an initial cockpit control policy from the cockpit control policy library and execute it; 2. Secondly, during the execution of the initial cockpit control strategy, the user's current data and the current environment data of the cockpit are collected. The emotional fit score of the initial cockpit control strategy is calculated based on the user's current data, the environmental fit score of the initial cockpit control strategy is calculated based on the current environment data of the cockpit, and the conflict penalty score is calculated based on the user's current data and the current environment data of the cockpit. 3. Then, the overall fit score of the initial control strategy is calculated based on the emotional fit score, environmental fit score, and conflict penalty score. Finally, the initial cockpit control strategy is adjusted based on the overall fit score.

[0113] 4. Finally, repeat the above process to adjust the cockpit control strategy.

[0114] In addition to implementing the aforementioned control strategy adjustments, the cockpit system also has a self-learning module. Based on user feedback (such as manual adjustment records and satisfaction ratings), it updates the Q table through an experience playback mechanism to update the cockpit control strategy. Table 1 is a table showing the correspondence between user feedback and F-values ​​(quantitative indicators of user feedback). A positive F-value indicates that the user is satisfied with or prefers the operation, while a negative F-value indicates that the user is satisfied with or prefers the operation.

[0115]

[0116] In the process of adjusting the cockpit control strategy of the cockpit system, the core of reinforcement learning is to gradually learn a more precise adjustment scheme through a cycle of trying adjustments → obtaining feedback → optimizing the strategy. The following is a complete reinforcement learning process that incorporates user feedback.

[0117] 1. Strengthen the core elements of learning.

[0118] Before proceeding with the update, define five core elements, including: Intelligent agent: Cockpit system (responsible for deciding how to adjust); Environment: The state of the cabin (user's heart rate, body temperature; outside temperature, time, etc.); State (S): A detailed description of the environment and user state (e.g., S = [User heart rate 80 beats / min (relaxed), outside temperature 30℃ (summer), driving mode: commuting]); Action (A): The adjustment scheme selected by the system (e.g., A = [24℃ air conditioning, 110° seat, soft music]). Reward (R): Feedback score after the action, which combines objective adaptability and user feedback (R=R_total=λ×U+(1-λ)×F). Strategy (π): The system's decision-making habits.

[0119] 2. Reinforcement learning update steps.

[0120] The essence of reinforcement learning is to correct old knowledge with new experiences, which is carried out in 5 steps.

[0121] (1) Initialization strategy (random selection or use of standard scheme for the first time).

[0122] Principle: At the beginning, the system had no experience, and the adjustment scheme was random (in any state, all adjustment schemes have the same probability of being selected).

[0123] Example scenario: Initial state S0: [User's first time using the car (no historical data), outside temperature 25℃ (spring and autumn), driving mode: commuting]; Possible adjustment options (e.g., 3 options: A1 = 24℃ + 110° seat + light music; A2 = 22℃ + 105° seat + rock music; A3 = 26℃ + 115° seat + pop music). Initial strategy: Each option has a 1 / 3 probability of being selected (completely random, for example, A2 might be selected by chance on the first try).

[0124] (2) Perform actions and gain experience.

[0125] Principle: After the system executes an adjustment plan, the environment will provide a new state and reward, forming an experience (state S → action A → reward R → new state S).

[0126] Example scenario: The system executes action A2 (22℃ air conditioner, 105° seat, rock music); Feedback received: Objective compatibility: Users felt that 22℃ was a bit cold (U1=6 points), energy consumption was moderate (U2=4 points), and there were no conflicts (U3=0). User feedback: The user manually increased the temperature to 24℃ (passive feedback, twice in a row) → F=-1; Fusion bonus: R_total = 0.7 × (0.4 × 6 + 0.3 × 4 - 0.3 × 0) + 0.3 × (-1) = 0.7 × 3.6 - 0.3 = 2.22 (moderate to low effect); New Status S': [User raises temperature to 24℃, outside temperature remains 25℃, driving mode: commuting]; Record experience: (S0, A2, R=2.22, S').

[0127] (3) Update the value function with experience.

[0128] Q(S,A)←Q(S,A)+a×[R_total+b×max a 'Q(S',A') Q(S,A)]; Where a is the learning rate (0 < α < 1, controlling the update magnitude, such as 0.2); b is the discount factor (0 < γ < 1, such as 0.9, indicating that future rewards are not as important as current rewards); R_total is the fusion reward = λ × U + (1 - λ) × F (λ = 0.7, balancing objective adaptation and user feedback).

[0129] Example scenario: Initially, all Q values ​​are 0 (no experience); update Q(S0,A2) using the experience from step 2 (S0,A2,R=2.22,S'): The new state S' has not yet performed any actions, so for now we assume max... a 'Q(S',A')=0; Substituting into the formula (a=0.2, b=0.9): Q(S0,A2)=0+0.2×[2.22+0.9×0-0]=0.444; The system understands that A2 should be selected under S0, with a value of 0.444 (lower than the original example of 0.72 points, due to negative user feedback lowering the reward).

[0130] (4) Update the strategy based on the Q value.

[0131] Principle: The goal of the strategy is to prefer actions with higher Q values ​​in state S. An ε-greedy strategy is adopted: most of the time, the best known action is chosen (exploitation), and occasionally new actions are tried randomly (exploration, avoiding repetitive use of old methods).

[0132] Example scenario: After multiple attempts, in state S0, the Q values ​​of the three actions are: A1=0.5, A2=0.444, A3=0.6; ε-greedy strategy (ε=0.1, i.e., 10% probability of exploration, 90% probability of exploitation): There is a 90% probability of choosing A3, which has the highest Q value (because 0.6 > 0.5 > 0.444); there is a 10% probability of randomly choosing A1 or A2 (to avoid missing a better option).

[0133] (5) Repeated iteration.

[0134] Principle: Repeatedly perform actions → gain experience → update Q value → update strategy. As experience increases, the Q value gets closer and closer to the actual effect, and the strategy becomes more and more stable.

[0135] Scenario example (after 100 iterations): The system has recorded a lot of experience (e.g., when commuting in spring and autumn, users prefer 26°C and light music). Q value maturity: The Q value of A1 (26℃ + light music) is 8.2, which is much higher than that of A2 (5.1) and A3 (4.8). Stable strategy: In the ε-greedy strategy, A1 is selected with a 99% probability (almost no random trial and error), and the adjustment effect is always very good (the reward is stable at a high score).

[0136] 3. User feedback handling mechanism.

[0137] To make reinforcement learning more aligned with user needs, user feedback needs to be transformed into quantifiable reward signals.

[0138] (1) Feedback types and quantification rules are shown in Table 2.

[0139]

[0140] (2) Formula for fusion reward.

[0141] R_total=λ×U+(1-λ)×F; Wherein, λ is the weighting coefficient (0.6≤λ≤0.8), which is dynamically adjusted according to the feedback intensity (e.g., λ=0.6 when the user operates continuously, and λ=0.8 when operating once).

[0142] Algorithm advantages: Explicit user preferences: The F-value directly expresses the user's subjective feelings, avoiding the system's reliance solely on objective indicators (such as temperature and heart rate); Timely feedback: Instant feedback (such as manual temperature adjustment) can immediately influence the strategy without waiting for multiple interactions; Abnormal feedback filtering: By using λ weights and continuity judgments (such as two consecutive operations), accidental touches are avoided from interfering with learning; Personalized acceleration: Preferences for specific users (such as 26℃) can converge quickly, reducing the number of explorations.

[0143] The reinforcement learning process deeply integrates user feedback into the Q-Learning algorithm. Through a closed loop of feedback quantification → reward fusion → strategy optimization, the system can adapt to objective environmental indicators and quickly learn personalized user preferences, ultimately achieving optimal synergy between emotion, environment, and interaction.

[0144] The implementation flow of the cockpit control method of this application embodiment is described below through a specific example, such as... Figure 2 As shown, it includes: 1. Multimodal data acquisition.

[0145] Emotion-related: Facial images (resolution ≥ 1280×720, frame rate ≥ 30fps), speech signals (sampling rate ≥ 16kHz), physiological signals (heart rate, skin conductance, sampling frequency ≥ 100Hz). Environmental factors: cabin temperature, noise (sampling rate ≥ 10 Hz), light intensity (sampling rate ≥ 5 Hz).

[0146] 2. Emotional fit calculation Em.

[0147] The degree to which a cockpit system meets a user's emotional needs is measured by physiological signals, behavioral data, or subjective feedback. Em is calculated by weighted summation of satisfaction scores for these signals; a higher score indicates that the cockpit system better matches the user's emotional needs.

[0148] Em = w1×S1 + w2×S2 + ... + wn×Sn.

[0149] 3. Calculation of environmental improvement degree (i.e., environmental adaptability) En.

[0150] Environmental indicators refer to the adjustment from an uncomfortable state to a comfortable state, and are the core of E. The calculation logic is a weighted sum of the improvement of each environmental indicator. The higher the score, the better the environmental optimization effect.

[0151] En = k1×I1 + k2×I2 + ... + km×Im.

[0152] 4. Conflict penalty calculation U3.

[0153] The penalty value for cockpit system operation causing new problems. When the cockpit system satisfies emotions or improves the environment, it may cause new conflicts (such as low temperature air conditioning + seat heating leading to energy waste). U3 is a weighted sum of the negative impacts of these conflicts. The higher the score, the more serious the conflict, and more comprehensive fit needs to be deducted.

[0154] U3 = p1×C1 + p2×C2 + ... + pq×Cq.

[0155] 5. Weighting and conflict resolution.

[0156] Conflict-free algorithm: Total = Em×K1 + En×K2.

[0157] Algorithm with conflict: U = α × Em + β × En - γ × U3.

[0158] 6. Hardware layer linkage.

[0159] Based on the result U from the previous step, the corresponding cockpit control strategy is selected by associating the optimal result U with the result U.

[0160] 7. Cockpit hardware operation.

[0161] The selected cockpit control strategy is output to the control layer, which then controls the cockpit hardware (such as light color temperature, seat massage intensity, etc.).

[0162] 8. User feedback collection.

[0163] Collect user feedback on the cockpit system's execution of control strategies, including manual adjustment records and satisfaction ratings, to facilitate subsequent self-learning of control strategies.

[0164] 9. Learn and update strategies.

[0165] By using reinforcement learning to update strategies, the cockpit system can achieve more precise adjustments.

[0166] In summary, the core of the cockpit control method in this application is to achieve dynamic collaborative optimization of user emotional state, cockpit environmental parameters, and interaction strategies through an environmental adaptive algorithm. This involves collecting data such as the driver's facial images, voice signals, and physiological signals, as well as data on cockpit temperature, noise, and light, using multimodal sensors. The emotion analysis module calculates the emotional adaptation requirement value Em based on the multimodal data, while the environmental assessment module calculates the environmental improvement degree En. The dynamic decision-making module, combined with the conflict penalty U3, generates an adaptation strategy through a comprehensive utility function. The execution module controls the cockpit hardware (seat massage, air conditioning, lighting, etc.) according to the strategy and optimizes the strategy through reinforcement learning driven by user feedback, forming a closed loop of perception-computation-decision-execution-feedback-learning.

[0167] This application embodiment uses multimodal fusion emotion recognition to integrate facial, voice, and physiological signals for emotion analysis, avoiding single emotion input; it can enhance driving safety by improving the closed-loop adaptation of emotion-environment-interaction and significantly reducing the risk of driver distraction; it quantifies the degree of conflict between emotion and environmental needs through mutual information entropy and dynamically adjusts resource allocation; it strengthens learning and self-optimization by dynamically updating strategies through user feedback, so that system satisfaction gradually increases with usage time, and the accuracy of personalized recommendations improves after long-term use.

[0168] The cockpit control method proposed in this application can calculate an emotional fit score and an environmental fit score based on the user's current data and the cockpit's current environmental data, respectively. It can also calculate a conflict penalty score based on the user's current data and the cockpit's current environmental data. The weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, and a comprehensive fit score is calculated based on these scores and their respective weights. Finally, the cockpit's corresponding actions are controlled based on the comprehensive fit score. This allows the cockpit's actions to adapt to both emotions and the environment, quantifies the user's adjustments to the cockpit system, and addresses conflicts arising from changes in user emotions or the cockpit environment. This ensures that the final cockpit actions are a result of considering multiple objectives, avoiding the pursuit of emotional or environmental fit at the expense of potential risks. It improves user satisfaction with the cockpit environment and driving safety, enhances the user experience, and optimizes cockpit resource allocation, preventing resource waste.

[0169] Next, the cockpit control device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0170] Figure 3 This is a block diagram of a cockpit control device according to an embodiment of this application.

[0171] like Figure 3 As shown, the cockpit control device 10 includes: an acquisition module 100, a first calculation module 200, a second calculation module 300, and a control module 400.

[0172] The acquisition module 100 is used to acquire the user's current data and the current environment data of the cockpit; the first calculation module 200 is used to calculate the user's emotional fit score based on the current data, calculate the cockpit's environmental fit score based on the current environment data, and calculate the conflict penalty score based on the current data and the current environment data; the second calculation module 300 is used to determine the weights of the emotional fit score, environmental fit score, and conflict penalty score, and calculate the comprehensive fit score based on the emotional fit score, environmental fit score, conflict penalty score, and their respective weights; the control module 400 is used to control the corresponding actions of the cockpit based on the comprehensive fit score.

[0173] In some embodiments of this application, the first calculation module 200 is further configured to: obtain the user's first reference data; calculate the first difference data between the first reference data and the current data; and calculate the emotional fit score based on the first difference data and the corresponding weight.

[0174] In some embodiments of this application, the first calculation module 200 is further configured to: acquire second reference data of the cockpit; calculate second difference data between the current environmental data and the second reference data; and calculate an environmental adaptability score based on the second difference data and the corresponding weights.

[0175] In some embodiments of this application, the first calculation module 200 is further configured to: identify conflict action types based on current data and current environment data; determine the score and weight of the conflict action based on the type of conflict action; and calculate the conflict penalty score based on the weight and score of the conflict action.

[0176] In some embodiments of this application, the first calculation module 200 is further configured to: obtain a first correspondence table of conflict action types, scores, and weights; and query the first correspondence table using the conflict action type as an index to obtain the conflict action score and weight.

[0177] In some embodiments of this application, the second calculation module 300 is further configured to: obtain a second correspondence table of emotional fit score, environmental fit score, conflict penalty score and weight; and query the second correspondence table using the emotional fit score, environmental fit score and conflict penalty score as indexes to obtain the respective weights of the emotional fit score, environmental fit score and conflict penalty score.

[0178] In some embodiments of this application, the control module 400 is further configured to: generate cockpit control commands based on the comprehensive adaptation score; query a pre-set cockpit control strategy based on the cockpit control commands to obtain the target control action of the cockpit, and control the cockpit to execute the target control action.

[0179] In some embodiments of this application, the cockpit control device 10 of this application embodiment further includes: an update module.

[0180] The update module is used to identify user feedback data after controlling the corresponding cockpit actions based on the comprehensive adaptation score; when the user adjusts the target control actions based on the feedback data, the cockpit control strategy is updated based on the adjusted target control actions and cockpit control commands.

[0181] It should be noted that the foregoing explanation of the cockpit control method embodiment also applies to the cockpit control device of this embodiment, and will not be repeated here.

[0182] The cockpit control device proposed in this application can calculate an emotional fit score and an environmental fit score based on the user's current data and the current environmental data of the cockpit, respectively. It can also calculate a conflict penalty score based on the user's current data and the current environmental data of the cockpit. The weights of the emotional fit score, environmental fit score, and conflict penalty score are determined, and a comprehensive fit score is calculated based on these scores and their respective weights. Finally, the cockpit's corresponding actions are controlled based on the comprehensive fit score. This allows the cockpit's actions to be coordinated with emotions and the environment, and quantifies the user's adjustments to the cockpit system, as well as conflicts arising from changes in user emotions or the cockpit environment. This ensures that the final cockpit actions are a result of comprehensive consideration of multiple objectives, avoiding the pursuit of emotional or environmental fit at the expense of potential risks. It improves user satisfaction with the cockpit environment and driving safety, enhances the user experience, and optimizes in-cockpit resource allocation, avoiding resource waste.

[0183] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0184] When the processor 402 executes the program, it implements the cockpit control method provided in the above embodiments.

[0185] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0186] The memory 401 is used to store computer programs that can run on the processor 402.

[0187] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0188] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0189] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0190] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0191] This application also provides a vehicle that includes the above-described electronic equipment.

[0192] In the description of this specification, the 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 this application. 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. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0193] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0194] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application 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 should be understood by those skilled in the art to which embodiments of this application pertain.

[0195] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more 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 (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0196] 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 program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A cockpit control method, characterized in that, Includes the following steps: Obtain the user's current data and the current environmental data of the cockpit; Calculate the user's emotional fit score based on the current data, calculate the cabin's environmental fit score based on the current environmental data, and calculate the conflict penalty score based on the current data and the current environmental data; The weights of the emotional fit score, the environmental fit score, and the conflict penalty score are determined, and the overall fit score is calculated based on the emotional fit score, the environmental fit score, the conflict penalty score, and their respective weights. The cockpit actions are controlled based on the comprehensive adaptation score.

2. The cockpit control method according to claim 1, characterized in that, The step of calculating the user's emotional compatibility score based on the current data includes: Obtain the user's initial reference data; Calculate the first difference data between the first reference data and the current data; The emotional fit score is calculated based on the first difference data and the corresponding weights.

3. The cockpit control method according to claim 1, characterized in that, The calculation of the cabin's environmental adaptability score based on the current environmental data includes: Obtain second reference data for the cockpit; Calculate the second difference data between the current environmental data and the second reference data; The environmental adaptability score is calculated based on the second difference data and the corresponding weights.

4. The cockpit control method according to claim 1, characterized in that, The calculation of the conflict penalty score based on the current data and the current environment data includes: Identify conflict action types based on the current data and the current environment data; The score and weight of the conflicting action are determined based on the type of conflicting action; The conflict penalty score is calculated based on the weight and score of the conflict action.

5. The cockpit control method according to claim 4, characterized in that, The step of determining the score and weight of the conflict action based on its type includes: Obtain the first correspondence table of conflict action types, scores, and weights; Using the type of conflicting action as an index, the score and weight of the conflicting action are obtained by querying the first correspondence table.

6. The cockpit control method according to claim 1, characterized in that, The determination of the weights for the emotional fit score, the environmental fit score, and the conflict penalty score includes: Obtain a second correspondence table between the emotional fit score, the environmental fit score, the conflict penalty score, and their weights; Using the emotional fit score, the environmental fit score, and the conflict penalty score as indexes, the second correspondence table is queried to obtain the respective weights of the emotional fit score, the environmental fit score, and the conflict penalty score.

7. The cockpit control method according to claim 1, characterized in that, The method of controlling the corresponding cockpit actions based on the comprehensive adaptation score also includes: Cockpit control commands are generated based on the comprehensive adaptation score; The cockpit control commands are used to query the pre-set cockpit control strategy to obtain the target control action of the cockpit, and the cockpit is controlled to execute the target control action.

8. The cockpit control method according to claim 7, characterized in that, After controlling the corresponding cockpit actions based on the comprehensive adaptation score, the method further includes: Identify user feedback data; When the user adjusts the target control action based on the feedback data, the cockpit control strategy is updated based on the adjusted target control action and the cockpit control command.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the cockpit control method as described in any one of claims 1-8.

10. A vehicle, characterized in that, It includes the electronic device as described in claim 9.

Images