Automobile functional part control method, computer device and storage medium

Abstract

The invention discloses an automobile function component control method and device and a storage medium, and the method can recognize first context information containing user function demand information according to first action information made by a detection object in a first time period, and can recognize user function demand information according to second action information made by a person in a vehicle in a second time period. Second context information containing the demand confirmation information is identified, so that a control instruction can be generated according to the first context information and the second context information; the first context information already contains rich user function demand information, so that a person on the vehicle only needs to make a simple action in the second time period to generate the second action information, the number limitation of automobile function parts capable of being operated and adjusted is reduced, and the user experience is improved. And the complexity of the action to be performed by the second action information is reduced, and the effects of improving the convenience degree of control of the automobile functional part and improving the user experience are achieved. The invention is widely applied to the technical field of automobiles.

Description

Technical Field

[0001] The present invention relates to the technical field of automobiles, and in particular to a method for controlling automobile functional components, a computer device, and a storage medium. Background Art

[0002] Automobiles are equipped with a rich variety and quantity of functional components, and users can enable and adjust the functional components according to their own needs. For the traditional use of automobile functional components, users need to operate interaction modules such as buttons, knobs, levers, or display screens to send control instructions to the automobile functional components. This method requires users to take their hands off the steering wheel to operate, which is inconvenient to operate and even affects traffic safety in the driving environment. With the development of speech recognition technology and motion capture technology, some automobiles apply the collection and recognition of information such as the user's voice, body movements, or head movements to generate control instructions to control automobile functional components, thus realizing the convenience of operating automobile functional components without the need for users to take their hands off the steering wheel, improving the usability, and ensuring traffic safety.

[0003] However, due to the large number of automobile functional components available for operation and adjustment, both the traditional automobile functional component control technology and the automobile functional component control technology applying speech recognition technology and motion capture technology require the user's voice or actions to specifically indicate the automobile functional component to be controlled. In this way, either the number of automobile functional components available for operation and adjustment must be reduced in order to maintain the simplicity of the voice or actions that the user needs to say or make, or the user needs to say or make long and complex voices or actions in order to maintain the number of automobile functional components available for operation and adjustment. Whichever way, it will reduce the convenience of controlling automobile functional components and the user experience. Summary of the Invention

[0004] Aiming at the technical problems such as the poor convenience and user experience of the current automobile functional component control technology, the purpose of the present invention is to provide a method, device, and storage medium for controlling automobile functional components.

[0005] On the one hand, an embodiment of the present invention includes a method for controlling automobile functional components, and the method for controlling automobile functional components includes the following steps:

[0006] Obtain first motion information detected in a first time period;

[0007] Obtain second motion information detected in a second time period; the second time period is a time period after the first time period;

[0008] Identify the first motion information to obtain first context information, and identify the second motion information to obtain second context information;

[0009] Obtain a control instruction according to the first context information and the second context information.

[0010] Further, the obtaining of the first action information detected in the first time period includes:

[0011] Continuously perform action detection on the first vehicle occupant or an external detection object to obtain continuous action information;

[0012] Determine the first time period;

[0013] Perform segment truncation on the continuous action information according to the first time period to obtain the first action information.

[0014] Further, the obtaining of the second action information detected in the second time period includes:

[0015] During the second time period, perform action detection on a second vehicle occupant to obtain the second action information; the second vehicle occupant is any vehicle occupant including the first vehicle occupant.

[0016] Further, the determining of the first time period includes:

[0017] Determine the duration of the third time period;

[0018] Take the start point of the second time period as the end point of the third time period;

[0019] Determine the start point of the third time period according to the duration and the end point of the third time period;

[0020] Take at least a part of the third time period as the first time period.

[0021] Further, the taking at least a part of the third time period as the first time period includes:

[0022] Divide the third time period into multiple unit time periods;

[0023] For any one of the unit time periods, perform semantic recognition on the part of the continuous action information corresponding to the unit time period to obtain a semantic segment corresponding to the unit time period;

[0024] Perform semantic clustering on each of the semantic segments;

[0025] Combine the unit time periods corresponding to the semantic segments grouped into the same class into a corresponding first time period.

[0026] Further, the obtaining of the control instruction according to the first context information and the second context information includes:

[0027] Run an artificial intelligence model;

[0028] Input the first context information into the artificial intelligence model for processing, and determine user function requirement information according to the output result of the artificial intelligence model;

[0029] Obtain the requirement intensity of the user function requirement information;

[0030] Obtain the target vehicle functional component pointed to by the user function requirement information;

[0031] Input the second context information into the artificial intelligence model for processing, and determine requirement confirmation information according to the output result of the artificial intelligence model;

[0032] In response to the requirement confirmation information, when the requirement intensity is greater than the intensity threshold, generate the control instruction according to the requirement intensity and the target vehicle functional component.

[0033] Further, the running of the artificial intelligence model includes:

[0034] Deploy and run a lightweight distilled model locally on the vehicle;

[0035] Use the lightweight distilled model as the artificial intelligence model.

[0036] Further, the obtaining of the requirement intensity of the user function requirement information includes:

[0037] Obtain the own first context information, the synonymous first context information, and the antonymous first context information of the user function requirement information; wherein, the own first context information is the first context information obtained by the artificial intelligence model to process and obtain the user function requirement information, the synonymous first context information is the first context information with a semantics similar to that of the own first context information, and the antonymous first context information is the first context information with a semantics opposite to that of the own first context information;

[0038] Obtain a first duration, a second duration, and a third duration; the first duration is the duration of the first time period corresponding to the own first context information, the second duration is the duration of the first time period corresponding to the synonymous first context information, and the third duration is the duration of the first time period corresponding to the antonymous first context information;

[0039] Determine the requirement intensity in a positive correlation according to the sum of the first duration, the second duration, and the third duration.

[0040] On the other hand, an embodiment of the present invention further includes a computer device, including a memory and a processor. The memory is used to store at least one program, and the processor is used to load at least one program to execute the automotive functional component control method in the embodiment.

[0041] On the other hand, an embodiment of the present invention further includes a computer-readable storage medium, in which a program executable by a processor is stored. The program executable by the processor is used to execute the automotive functional component control method in the embodiment when executed by the processor.

[0042] The beneficial effects of the present invention are as follows: In the automotive functional component control method in the embodiment, the first context information including user functional requirement information can be identified according to the first action information made by the vehicle occupants and / or the external detection objects in the first time period. In the second time period after the first time period, the second context information including requirement confirmation information can be identified according to the second action information made by the vehicle occupants. Thus, a control instruction can be generated according to the first context information and the second context information. Since the first context information already contains rich user functional requirement information after the information accumulation in the first time period, the vehicle occupants only need to make simple actions in the second time period to generate the second action information and the second context information, which is used together with the first context information to generate the control instruction, so as to meet the subjective usage requirements of the vehicle occupants for the automotive functional components or meet the objective usage requirements of the driving environment for the automotive functional components. Since the control instruction is jointly obtained according to the second context information and the first context information, as long as the automotive functional components corresponding to the first context information are different, the use of different automotive functional components can also be controlled with the same second action information, thereby reducing the number limit of the automotive functional components that can be operated and adjusted, as well as reducing the complexity of the actions to be made for the second action information, achieving the effect of improving the convenience of automotive functional component control and enhancing the user experience. Description of the Drawings

[0043] Figure 1 Schematic diagram of an automotive system to which the automotive functional component control method can be applied in the embodiment;

[0044] Figure 2 Schematic diagram of the steps of the automotive functional component control method in the embodiment;

[0045] Figure 3 Schematic diagram of the principle of the automotive functional component control method in the embodiment;

[0046] Figure 4 Schematic diagram of the principle of determining the first time period in the embodiment;

[0047] Figure 5Schematic diagram of the principle for determining demand intensity in the embodiment. Specific implementation mode

[0048] In this embodiment, the control method for automotive functional components can be applied to Figure 1 the automotive system shown. Referring to Figure 1 , the automotive system includes a control module, automotive functional components, an in-vehicle motion detection module, and an out-of-vehicle motion detection module. Among them, the control module is a component with data acquisition, data processing, and control functions; the automotive functional components include components such as an audio-visual entertainment system, air conditioner, windows, and ambient lights that perform corresponding functions; the in-vehicle motion detection module can specifically be sensors such as a microphone, camera, or lidar to detect the actions of the vehicle occupants inside the vehicle. The detected actions can be speech, body movements, gestures, facial expressions, etc.; the out-of-vehicle motion detection module can specifically be sensors such as a microphone, camera, or lidar to detect the actions of out-of-vehicle detection objects such as pedestrians and adjacent vehicles outside the vehicle. The detected actions can be the speech, body movements, gestures, facial expressions of pedestrians, and driving actions such as the driving trajectory and lighting usage of adjacent vehicles.

[0049] In this embodiment, taking a vehicle (this vehicle) equipped with Figure 1 the automotive system shown as an example for illustration. The first vehicle occupant can specifically be the driver or passenger of this vehicle. The second vehicle occupant can be the same person as the first vehicle occupant or a different person from the first vehicle occupant. For example, if the first vehicle occupant is the driver of this vehicle, the second vehicle occupant is the passenger of this vehicle.

[0050] In this embodiment, referring to Figure 2 , the control method for automotive functional components includes the following steps:

[0051] S1. Obtain the first action information detected in the first time period;

[0052] S2. Obtain the second action information detected in the second time period;

[0053] S3. Identify the first action information to obtain the first context information, and identify the second action information to obtain the second context information;

[0054] S4. Obtain a control instruction according to the first context information and the second context information.

[0055] Steps S1 - S4 can be executed by the control module. When the control module executes some of these steps, it can call other modules or components to execute.

[0056] The principle of steps S1 - S4 is as shown in Figure 3 .

[0057] Referring to Figure 3 , in step S1, the control module calls the in-vehicle action detection module and / or the out-of-vehicle action detection module to perform detection in the first time period T1, so as to obtain the first action information; in step S2, the control module calls the in-vehicle action detection module to perform detection in the second time period T2, so as to obtain the second action information.

[0058] In step S3, the control module can run a semantic recognition algorithm to recognize the first action information, obtain the semantic information of the first action information as the first context information, run the semantic recognition algorithm to recognize the second action information, and obtain the semantic information of the second action information as the second context information.

[0059] Referring to Figure 3 , if some actions made by the first vehicle occupant, the second vehicle occupant and / or out-of-vehicle detection objects such as pedestrians and adjacent vehicles in the first time period T1 (which can be actions deliberately made for expression or natural actions) reflect the usage requirements for the vehicle's automotive functional components, then in the first context information obtained by executing steps S1 - S3, user functional requirement information will be included. The user functional requirement information indicates that there is a high possibility that the vehicle occupants need to use some automotive functional components of the vehicle to run their functions, so as to meet the usage requirements for the automotive functional components revealed by the actions of the vehicle occupants, or to meet the usage requirements for the automotive functional components for the purpose of ensuring traffic safety, convenient use or good user experience, etc. in the driving environment formed by out-of-vehicle detection objects such as pedestrians and adjacent vehicles that have made specific actions. In such a case, the vehicle occupants only need to make some actions in the second time period T2 after the first time period T1 to indicate their confirmation of the previous usage requirements, which will enable step S2 to detect the second action information, and then step S3 to obtain the second context information. Such second context information will contain requirement confirmation information, and this requirement confirmation information can play a role in confirming the user functional requirement information contained in the first context information. Therefore, the control module can generate a control instruction according to the user functional requirement information contained in the first context information, and trigger the corresponding automotive functional components to work or adjust the working parameters of the automotive functional components through the control instruction to meet the usage requirements for the automotive functional components indicated by the user functional requirement information.

[0060] For example, take such a usage scenario: In the first time period T1, the first person in the vehicle uttered the voice "The window needs to be lowered a bit", and the second person in the vehicle uttered the voice "Don't lower it too much". These two voices will be detected as the first action information when step S1 is executed, and when step S3 is executed, the first action information will be processed into the first context information in text format. The first context information contains the user function requirement information with the content "The window needs to be lowered slightly". In this case, in the second time period T2, the first person in the vehicle or the second person in the vehicle only needs to utter the voice with the content "Lower" (without saying "Please help me lower the window", etc.). Then this voice will be detected as the second action information when step S2 is executed, and when step S3 is executed, the second action information will be processed into the second context information in text format. The second context information can be used as the requirement confirmation information to confirm the user function requirement information with the content "The window needs to be lowered slightly". The control module can generate a control instruction to control the lowering of the window, a vehicle function component, based on this, so as to control the window to lower. And during the process of the window lowering, still in the second time period T2, the first person in the vehicle or the second person in the vehicle only needs to utter the voice with the content "Stop" (without saying "Please stop lowering the window", etc.). Then this voice will be detected as the second action information when step S2 is executed, and when step S3 is executed, the second action information will be processed into the second context information in text format. The second context information can be used as the requirement confirmation information to confirm the user function requirement information with the content "The window needs to be lowered slightly". The control module can generate a control instruction to control the suspension of the lowering of the window, a vehicle function component, based on this, so as to control the window to suspend lowering.

[0061] For example, take such a usage scenario: In the first time period T1, the pedestrian, an external detection object of the vehicle, made the action of opening an umbrella. This action will be detected as the first action information when step S1 is executed, and when step S3 is executed, the first action information will be processed into the first context information in text format. The first context information contains the user function requirement information with the content "The window needs to be closed". In this case, in the second time period T2, the first person in the vehicle or the second person in the vehicle only needs to utter the voice with the content "Close" (without saying "Please help me close the window", etc.). Then this voice will be detected as the second action information when step S2 is executed, and when step S3 is executed, the second action information will be processed into the second context information in text format. The second context information can be used as the requirement confirmation information to confirm the user function requirement information with the content "The window needs to be closed". The control module can generate a control instruction to control the closing of the window, a vehicle function component, based on this, so as to control the window to close.

[0062] For example, take such a usage scenario: In the first time period T1, an external detection object, i.e., a vehicle beside, makes an action of turning on the daytime running lights. This action will be detected as the first action information when step S1 is executed, and the first action information will be processed into the first context information in text format when step S3 is executed. The first context information contains the user function requirement information with the content of "need to turn on the daytime running lights". In this case, in the second time period T2, the first vehicle occupant or the second vehicle occupant only needs to say the voice with the content of "turn on the lights" (without saying content such as "please help me turn on the daytime running lights", etc.). Then this voice will be detected as the second action information when step S2 is executed, and the second action information will be processed into the second context information in text format when step S3 is executed. The second context information can be used as the requirement confirmation information to confirm the user function requirement information with the content of "need to turn on the daytime running lights". The control module can generate a control instruction to control the opening of the daytime running lights, a vehicle function component, based on this, so as to control the daytime running lights to turn on.

[0063] As can be seen from the above usage scenario, by executing steps S1 - S3, the first context information containing the user function requirement information can be identified according to the first action information made by the vehicle occupants and / or external detection objects in the first time period. In the second time period after the first time period, the second context information containing the requirement confirmation information can be identified according to the second action information made by the vehicle occupants. Thus, the control instruction can be generated based on the first context information and the second context information. Since the first context information already contains rich user function requirement information after the information accumulation in the first time period, the vehicle occupants only need to make a simple action in the second time period to generate the second action information and generate the second context information to jointly generate the control instruction with the first context information, so as to meet the subjective usage requirements of the vehicle occupants for the vehicle function components or meet the objective usage requirements of the driving environment for the vehicle function components. Since the control instruction is jointly obtained according to the second context information and the first context information, as long as the vehicle function components corresponding to the first context information are different, it is also possible to use the same second action information to control the use of different vehicle function components, thereby reducing the quantity limitation of the vehicle function components that can be operated and adjusted, and reducing the complexity of the actions to be made for the second action information, achieving the effect of improving the convenience of controlling the vehicle function components and enhancing the user experience.

[0064] In this embodiment, when executing step S1, that is, the step of obtaining the first action information detected in the first time period, the following steps can be specifically executed:

[0065] S101. Continuously detect the actions of the first vehicle occupant or the external detection object to obtain continuous action information;

[0066] S102. Determine the first time period;

[0067] S103. Intercept the continuous action information according to the first time period to obtain the first action information.

[0068] By executing steps S101 - S103, the in-vehicle action detection module and / or the out-of-vehicle action detection module can be called first to continuously detect the actions of the first on-vehicle personnel and / or the out-of-vehicle detection object to obtain the continuous action information, then determine the first time period T1, and intercept the part of the continuous action information within the first time period T1, that is, obtain the first action information.

[0069] In this embodiment, when the control module executes step S102, that is, the step of determining the first time period, the following steps can be specifically executed:

[0070] S10201. Determine the duration of the third time period;

[0071] S10202. Use the start point of the second time period as the end point of the third time period;

[0072] S10203. Determine the start point of the third time period according to the duration and the end point of the third time period;

[0073] S10204. Use at least part of the third time period as the first time period.

[0074] By executing steps S10201 - S10204, a third time period T3 can be determined before the second time period T2, where the duration of the third time period T3 is long enough (for example, 1h), so that part or all of the time periods within the third time period T3 can be selected as the first time period T1.

[0075] In this embodiment, the principle of step S10204 is as Figure 4 shown. Referring to Figure 4 , within the third time period T3, the control module executes step S101, so as to call the in-vehicle action detection module and / or the out-of-vehicle action detection module to continuously detect the actions of the first on-vehicle personnel and / or the out-of-vehicle detection object to obtain the continuous action information; the control module can equally divide the third time period T3 into multiple unit time periods, and there will be a part of the continuous action information within each unit time period. For any unit time period, the control module can perform semantic recognition on part of the continuous action information within this unit time period to obtain the semantic segment corresponding to this unit time period, so as to obtain multiple semantic segments; by performing semantic clustering on each semantic segment, the semantic segments with the same semantics can be clustered into the same class, and the unit time periods corresponding to the semantic segments clustered into the same class are combined into a corresponding first time period.

[0076] For example, Figure 4 In, the 10 non - completely continuous unit time periods corresponding to the slanted - shaded part in the third time period T3 have the same semantics for the semantic fragments they respectively correspond to and are grouped into the same class (a corresponding usage scenario is: the same detection object, such as the first person, makes actions within these 10 unit time periods, expressing the same usage requirements). Therefore, these 10 unit time periods form a first time period T1, and the continuous action information within these 10 unit time periods also forms a corresponding first action information.

[0077] Figure 4 In, in addition to the first time period T1 represented by the slanted - shaded part, there may be other first time periods, that is, there may be other first action information.

[0078] In this embodiment, when performing step S2, that is, the step of obtaining the second action information detected in the second time period, the following steps can be specifically performed:

[0079] S201. During the second time period, perform action detection on the second vehicle personnel to obtain the second action information.

[0080] In step S201, the second vehicle personnel is any vehicle personnel including the first vehicle personnel, so that any vehicle personnel can make a confirmation action, thereby generating the second action information to trigger the generation of a control instruction.

[0081] In this embodiment, when the control module performs step S4, that is, the step of obtaining the control instruction according to the first context information and the second context information, the following steps can be specifically performed:

[0082] S401. Run the artificial intelligence model;

[0083] S402. Input the first context information into the artificial intelligence model for processing, and determine the user function requirement information according to the output result of the artificial intelligence model;

[0084] S403. Obtain the requirement intensity of the user function requirement information;

[0085] S404. Obtain the target vehicle function component pointed to by the user function requirement information;

[0086] S405. Input the second context information into the artificial intelligence model for processing, and determine the requirement confirmation information according to the output result of the artificial intelligence model;

[0087] S406. When the requirement intensity is greater than the intensity threshold, in response to the requirement confirmation information, generate a control instruction according to the requirement intensity and the target vehicle function component.

[0088] In step S401, the running artificial intelligence model can be a lightweight distilled model locally deployed in the control module of the vehicle. Specifically, it can be a large language model with good semantic understanding, reasoning, and association capabilities. In step S402, the artificial intelligence model can identify the user function requirement information contained therein from the first context information with its semantic understanding, reasoning, and association capabilities.

[0089] In step S403, for a user function requirement information output by the artificial intelligence model (such as a specific user function requirement information 1), the corresponding requirement intensity can be determined through the following steps:

[0090] S40301. Obtain the own first context information, the near-synonym first context information, and the anti-synonym first context information of this user function requirement information (user function requirement information 1); wherein, the own first context information is the first context information obtained by the artificial intelligence model processing to obtain this user function requirement information (user function requirement information 1), the near-synonym first context information is the first context information with a similar semantics to the own first context information, and the anti-synonym first context information is the first context information with a semantics opposite to the own first context information;

[0091] S40302. Obtain the first duration, the second duration, and the third duration; the first duration is the duration of the first time period corresponding to the own first context information, the second duration is the duration of the first time period corresponding to the near-synonym first context information, and the third duration is the duration of the first time period corresponding to the anti-synonym first context information;

[0092] S40303. Positively determine the requirement intensity according to the sum of the first duration, the second duration, and the third duration.

[0093] The principle of steps S40301 - S40303 is as Figure 5 shown. The following is an example of a usage scenario for illustration: Refer to Figure 5During the unit time period indicated by the diagonal shading in the third time period T3, the first occupant in the vehicle uttered a voice message with the content "It's a bit stuffy. How about opening the window?" These voice messages were detected as the first context information of the occupant himself / herself and the user function requirement information 1 was recognized. That is, the content of the user function requirement information 1 is "open the window". Correspondingly, the unit time periods indicated by the diagonal shading form one of the first time periods, and its duration is the first duration. During the unit time period indicated by the horizontal shading in the third time period T3, the second occupant (A) uttered a voice message "I also feel it's a bit stuffy". These voice messages were detected as the first context information with similar meaning, and the duration formed by the unit time periods indicated by the horizontal shading is the second duration. During the unit time period indicated by the vertical shading in the third time period T3, the second occupant (B) uttered a voice message "I don't feel stuffy". These voice messages were detected as the first context information with opposite meaning, and the duration formed by the unit time periods indicated by the vertical shading is the third duration. Therefore, the sum of the first duration, the second duration, and the third duration is the duration of the action related to the user function requirement information 1 of "opening the window". The greater it is, the higher the degree of attention (whether in favor or against) of the vehicle occupants to the user function requirement information 1 of "opening the window". If this user function requirement information 1 is finally confirmed in the second time period T2, it means that the demand intensity represented by this user function requirement information 1 is higher, thus determining a higher demand intensity.

[0094] In this embodiment, when performing steps S40301 - S40303, it is also possible not to detect the first context information with similar meaning, but only to detect the first context information of the occupant himself / herself and the first context information with opposite meaning, so as to calculate the sum of the first duration and the third duration, and determine the demand intensity positively correlated with the sum of the first duration and the third duration.

[0095] In step S404, the target vehicle functional component is the vehicle functional component pointed to by the user function requirement information, and the user function requirement information represents the vehicle functional component to be controlled. For example, in the embodiment of steps S40301 - S40303, the target vehicle functional component is the window.

[0096] In step S405, the second context information is input into the artificial intelligence model for processing. The artificial intelligence model can, with its semantic understanding, reasoning, and associative abilities, identify the requirement confirmation information contained in the second context information.

[0097] In response to the requirement confirmation information identified in step S405, step S406 is executed to set an intensity threshold, and the requirement intensity detected in step S403 is compared with the intensity threshold. If the requirement intensity is greater than the intensity threshold, it can be determined that the requirement intensity of the user function requirement information 1 is relatively large, and thus a control instruction is generated based on the requirement intensity and the target vehicle functional component. Among them, the target vehicle functional component determines the vehicle functional component to be controlled by the control instruction, and the requirement intensity determines the amplitude of the functional action to be performed by the vehicle functional component controlled by the control instruction. For example, when the content of the user function requirement information 1 is "open the window", the greater the requirement intensity of the user function requirement information 1, the greater the opening degree of the window controlled by the generated control instruction.

[0098] In this embodiment, by executing steps S401 - S406, the semantic understanding, reasoning, and association capabilities of the artificial intelligence model can be utilized to identify the user function requirement information and the requirement confirmation information. This allows for a greater degree of freedom when the detection object makes the first action information and the second action information, thereby enhancing the application flexibility of the vehicle functional component control method, reducing the action requirements for the vehicle occupants, and improving the user experience. Moreover, the artificial intelligence model can be deployed locally in the vehicle, thus protecting privacy and security.

[0099] The vehicle functional component control method in this embodiment can be implemented by writing a computer program. The computer program is written into a computer device or a storage medium. When the computer program is read and run, the vehicle functional component control method in this embodiment is executed, thereby achieving the same technical effects as the vehicle functional component control method in the embodiment.

[0100] It should be noted that, unless otherwise specified, when a feature is referred to as "fixed" or "connected" to another feature, it can be directly fixed or connected to the other feature, or indirectly fixed or connected to the other feature. In addition, the up, down, left, right, etc. descriptions used in this disclosure are only relative to the mutual positional relationship of the components of this disclosure in the drawings. The singular forms "a", "an", and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. In addition, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by those skilled in the technical field of this disclosure. The terms used in the description of this embodiment are only for describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this embodiment includes any combination of one or more of the related listed items.

[0101] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various elements, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, without departing from the scope of this disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element. The use of any and all examples or exemplary language ("for example", "such as", etc.) provided in this embodiment is only intended to better illustrate the embodiments of the present invention and will not impose a limitation on the scope of the present invention unless otherwise required.

[0102] It should be recognized that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The methods can be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes the computer to operate in a specific and predefined manner - in accordance with the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. In addition, for this purpose, the program is capable of running on a programmed application-specific integrated circuit.

[0103] Furthermore, the operations of the processes described in this embodiment can be performed in any suitable order, unless this embodiment otherwise indicates or is otherwise detected to be clearly inconsistent with the context. The processes described in this embodiment (or variations and / or combinations thereof) can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) commonly executed on one or more processors, by hardware, or a combination thereof. A computer program includes a plurality of instructions executable by one or more processors.

[0104] Further, the method can be implemented in any type of computing platform operatively connected to a suitable one, including but not limited to personal computers, minicomputers, mainframes, workstations, network or distributed computing environments, separate or integrated computer platforms, or communicating with charged particle tools or other imaging devices, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into the computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it can be read by a programmable computer and can be used to configure and operate the computer to perform the processes described herein when the storage medium or device is read by the computer. In addition, the machine-readable code, or portions thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the above steps in combination with a microprocessor or other data processor, the invention of this embodiment includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques of the present invention, the present invention also includes the computer itself.

[0105] A computer program can be applied to input data to perform the functions of this embodiment, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the transformed data represents physical and tangible objects, including a specific visual depiction of the physical and tangible objects generated on the display.

[0106] The above are only the preferred embodiments of the present invention. The present invention is not limited to the above-described embodiments. As long as it achieves the technical effects of the present invention by the same means, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention. Within the scope of protection of the present invention, its technical solutions and / or implementation manners can have various different modifications and variations.

Claims

1. A method for controlling functional components of an automobile, characterized in that: The automobile functional component control method comprises: Acquire first action information detected in a first time period; Acquire second action information detected in a second time period; the second time period is a time period after the first time period; Identify the first action information to obtain first context information, and identify the second action information to obtain second context information; A control instruction is acquired according to the first context information and the second context information.

2. The method for controlling functional components of an automobile according to claim 1, characterized in that: The acquiring of first action information detected in the first time period includes: Continuously performing motion detection on a person on the first vehicle or a detection object outside the vehicle to obtain continuous motion information; determining the first time period; The continuous action information is segmented according to the first time period to obtain the first action information.

3. The method for controlling functional components of an automobile according to claim 2, characterized in that: The acquiring of the second action information detected in the second time period includes: During the second time period, motion detection is performed on a second vehicle occupant to obtain the second motion information; the second vehicle occupant is any vehicle occupant including the first vehicle occupant.

4. The method for controlling functional components of an automobile according to claim 2, characterized in that: The determining the first time period includes: determining the duration of the third time period; Taking the starting point of the second time period as the end point of the third time period; Determining the starting point of the third time period according to the duration and the end point of the third time period; At least a portion of the third time period is used as the first time period.

5. The method for controlling functional components of an automobile according to claim 4, characterized in that: The taking at least a part of the third time period as the first time period comprises: Dividing the third time period into a plurality of unit time periods; For any of the unit time periods, semantic recognition is performed on the portion of the continuous action information corresponding to the unit time period to obtain a semantic segment corresponding to the unit time period; Performing semantic clustering on each of the semantic segments; The unit time periods corresponding to the semantic segments that are clustered into the same category are combined into a corresponding first time period.

6. The method for controlling functional components of an automobile according to any one of claims 1 to 5, characterized in that: The acquiring a control instruction according to the first context information and the second context information includes: Run AI models; Inputting the first context information into the artificial intelligence model for processing, and determining user function requirement information according to an output result of the artificial intelligence model; Obtaining the demand intensity of the user function demand information; Acquire the target automobile functional component pointed to by the user functional requirement information; inputting the second context information into the artificial intelligence model for processing, and determining demand confirmation information according to an output result of the artificial intelligence model; In response to the demand confirmation information, when the demand intensity is greater than an intensity threshold, the control instruction is generated according to the demand intensity and the target automobile functional component.

7. The method for controlling functional components of an automobile according to claim 6, characterized in that: The running of the artificial intelligence model includes: Deploy and run lightweight distillation models locally in the car; The lightweight distillation model is used as the artificial intelligence model.

8. The method for controlling functional components of an automobile according to claim 6, characterized in that: The obtaining of the demand intensity of the user function demand information includes: Acquire the own first context information, synonymous first context information and antonymous first context information of the user function requirement information; wherein the own first context information is the first context information of the user function requirement information obtained by being processed by the artificial intelligence model, the synonymous first context information is the first context information with semantics similar to the own first context information, and the antonymous first context information is the first context information with semantics opposite to the own first context information; Obtain a first duration, a second duration, and a third duration; the first duration is the duration of the first time period corresponding to the first context information itself, the second duration is the duration of the first time period corresponding to the synonymous first context information, and the third duration is the duration of the first time period corresponding to the antonymous first context information; The demand intensity is determined in a positive correlation according to the sum of the first duration, the second duration and the third duration.

9. A computer device, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store at least one program, and the processor is used to load at least one program to execute the automobile functional component control method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to execute the automobile functional component control method described in any one of claims 1 to 8 when executed by the processor.

Images