WO2024022429A1 - Procédé et appareil d'interaction manuelle pour véhicule, et dispositif, véhicule et support de stockage - Google Patents

Procédé et appareil d'interaction manuelle pour véhicule, et dispositif, véhicule et support de stockage Download PDF

Info

Publication number
WO2024022429A1
WO2024022429A1 PCT/CN2023/109507 CN2023109507W WO2024022429A1 WO 2024022429 A1 WO2024022429 A1 WO 2024022429A1 CN 2023109507 W CN2023109507 W CN 2023109507W WO 2024022429 A1 WO2024022429 A1 WO 2024022429A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
user classification
pressure peak
instantaneous pressure
classification
Prior art date
Application number
PCT/CN2023/109507
Other languages
English (en)
Chinese (zh)
Inventor
张礼元
贺金波
刘思宇
潘甸实
孙栋芸
周伟朋
Original Assignee
奇瑞汽车股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 奇瑞汽车股份有限公司 filed Critical 奇瑞汽车股份有限公司
Publication of WO2024022429A1 publication Critical patent/WO2024022429A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/016—Input arrangements with force or tactile feedback as computer generated output to the user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • the present application relates to the field of artificial interaction technology, and in particular to a vehicle artificial interaction method, device, equipment, vehicle and storage medium.
  • Vibration feedback technology is mainly based on the vibration source in the scenario where the terminal runs the application to trigger the terminal to achieve rich vibration effects, allowing users to feel a full range of tactile experience.
  • vibration feedback technology is now very mature.
  • Traditional vibration feedback technology can be applied in human-computer interaction systems.
  • the human-computer interaction system with active feedback of traditional vibration feedback technology has a single feel, making the user experience poor. waiting to be solved.
  • This application provides a manual interaction method, device, equipment, vehicle and storage medium for a vehicle to solve the problems that the current vibration feedback technology of human-computer interaction has a relatively single feedback force and cannot make adaptive changes according to different users.
  • An embodiment of the first aspect of the present application provides a manual interaction method for a vehicle, including the following steps: collecting the instantaneous pressure peak value during user operation; obtaining the actual user classification of the user based on the instantaneous pressure peak value; and based on the actual user classification.
  • User classification determines the target energization mode of the vibration coil, and the interactive force after the user operation is fed back according to the target energization mode.
  • obtaining the actual user classification of the user based on the instantaneous pressure peak includes:
  • the method before inputting the instantaneous pressure peak value to the user classification model, the method further includes: based on the peak pressing force of multiple training users, obtaining the corresponding values of the multiple training users.
  • the training data of the training user includes the peak pressing force of the training user and the actual user classification of the training user; use the multiple training data to train a neural network model to obtain the user classification model.
  • the method before inputting the instantaneous pressure peak into the pre-built user classification model, the method further includes: based on the gender, age range and peak pressing force of multiple training users.
  • determining the target energization mode of the vibration coil according to the actual user classification, and feeding back the interaction force after the user operation according to the target energization mode includes: according to the The actual user classification matches the best use experience of the actual user classification; the target power-on mode is determined according to the best use experience; the vibration coil is energized according to the target power-on mode, so that the vibration coil is powered according to the current The generated magnetic flux attracts the metal vibrator and generates the interactive force.
  • the actual user classification is a 2 Newton category, a 4 Newton category, a 6 Newton category, an 8 Newton category or a 10 Newton category.
  • a second embodiment of the present application provides a manual interaction device for a vehicle, including: a collection module for collecting the instantaneous pressure peak value during user operation; and a classification module for obtaining the user's pressure peak value based on the instantaneous pressure peak input. Actual user classification; and an interaction module, configured to determine the target energization mode of the vibration coil according to the actual user classification, and feedback the interaction force after the user operation according to the target energization mode.
  • the classification module is configured to: input the instantaneous pressure peak value to a user classification model, and obtain the user classification value obtained by the user classification model based on the instantaneous pressure peak value.
  • the actual user classification of the user or, based on the corresponding relationship between the pressure peak range and the actual user classification, and the instantaneous pressure peak value, the actual user classification of the user is obtained.
  • an acquisition module configured to acquire multiple training data corresponding to the multiple training users according to the peak pressing force of the multiple training users, and the training user's
  • the training data includes the peak pressing force of the training user and the actual user score of the training user.
  • Class use the plurality of training data to train a neural network model to obtain the user classification model.
  • the interactive module is specifically configured to energize the vibration coil according to the target energization mode, so that the vibration coil absorbs the metal vibration piece according to the magnetic flux generated by the current, generating The interaction force.
  • a first acquisition module configured to obtain the gender of multiple training users before inputting the instantaneous pressure peak into the pre-built user classification model. , age range and peak pressing force to obtain input data items; the second acquisition module is used to obtain training data and test data according to the input data items; the third acquisition module is used to train using the training data and the test data Neural network model is used to obtain the user classification model.
  • the interaction module includes: a matching unit, configured to match the best usage experience of the actual user classification according to the actual user classification; and a determination unit, configured to match the best usage experience according to the actual user classification The best usage experience determines the target power-up method.
  • the actual user classification is a 2 Newton category, a 4 Newton category, a 6 Newton category, an 8 Newton category or a 10 Newton category.
  • a third embodiment of the present application provides a vibration feedback device equipped with a manual interaction device for a vehicle as described in the above embodiment.
  • a fourth embodiment of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor.
  • the processor executes the program to implement the following: The manual interaction method for vehicles described in the above embodiments.
  • a fifth embodiment of the present application provides a computer-readable storage medium that stores a computer program that implements the above manual interaction method for a vehicle when executed by a processor.
  • Embodiments of the present application can collect the instantaneous pressure peak value during user operation; input the instantaneous pressure peak value into a pre-built user classification model to obtain the user's actual user classification; determine the target energization mode of the vibration coil according to the actual user classification, and The target power-on method feedbacks the interaction force after the user's operation.
  • This application can obtain user classification by utilizing instantaneous pressure peaks combined with deep learning, so that the human-computer interaction system can adapt to users with different needs, thereby giving different feedback forces and greatly improving the experience of various users. This solves the problem that the feedback force of current human-computer interaction vibration feedback technology is relatively single and cannot be adaptively changed according to different users.
  • Figure 1 is a flow chart of a manual interaction method for vehicles provided according to an embodiment of the present application
  • Figure 2 is a schematic diagram of input and output of a neural network according to an embodiment of the present application.
  • Figure 3 is a schematic diagram of a user classification model training process according to an embodiment of the present application.
  • Figure 4 is a schematic execution logic diagram of a manual interaction method for a vehicle according to an embodiment of the present application
  • Figure 5 is an example diagram of a manual interaction device for a vehicle according to an embodiment of the present application.
  • Figure 6 is a schematic structural diagram of a vehicle provided by an embodiment of the application.
  • Vehicle manual interaction device-10 collection module-100, classification module-200, interaction module-300; memory-601, processor-602, communication interface-603.
  • this application provides a manual interaction method for vehicles.
  • the instantaneous pressure peak value during user operation is collected; the instantaneous pressure peak value is input into a pre-built user classification model, Obtain the actual user classification of the user; determine the target energization mode of the vibration coil according to the actual user classification, and feedback the interaction force after the user's operation according to the target energization mode.
  • This application can obtain user classification by using instantaneous pressure peaks combined with deep learning, so that the human-computer interaction system can adapt to users with different needs, thereby giving different feedback forces and greatly improving the experience of various users.
  • FIG. 1 is a flow chart of a manual interaction method for a vehicle provided by an embodiment of the present application.
  • the vehicle's manual interaction method includes the following steps:
  • step S101 the instantaneous pressure peak value during user operation is collected.
  • Embodiments of the present application can enable the vehicle system to accurately collect instantaneous pressure peak data in real time through pressure sensors and other equipment when the user operates, such as when the user clicks on an application on the vehicle display screen, thereby providing a subsequent model for user classification. Reliable data source.
  • step S102 the instantaneous pressure peak value is input into the pre-constructed user classification model to obtain the actual user classification of the user.
  • embodiments of the present application can input the above-mentioned instantaneous pressure peak data into the user classification model, so that the user classification model classifies the user based on the instantaneous pressure peak value to obtain the user's actual user classification. And obtain the actual user classification of the user output by the user classification model, thereby achieving accurate classification of users, and at the same time providing data guarantee for determining the target energization method of the vibration coil.
  • the user classification model may also obtain the user's identity information based on the instantaneous pressure peak.
  • the identity information includes the user's gender and/or age range and other information.
  • the instantaneous pressure peak into the pre-built user classification model before inputting the instantaneous pressure peak into the pre-built user classification model, it also includes: obtaining input data items based on the gender, age range and peak pressing force of multiple training users. ; Obtain training data and test data according to the input data items; use the training data and test data to train the neural network model to obtain the user classification model.
  • the technician determines the actual user classification of the training user based on the training user's peak pressing force, and combines the training user's peak pressing force and the training user's actual user classification into one data item.
  • the data item may also include the gender and age range of the training data.
  • For each other training user perform the same process as above to obtain the data items corresponding to each other training user, so that multiple data items corresponding to the multiple training users can be obtained. Use all data items as training data, or use part of the data items as training data and the remaining data items as test data.
  • the technician can determine the peak value of the training user
  • the peak pressing force range to which the pressing force belongs is used as the actual user classification type of the training user according to the actual user classification corresponding to the peak pressing force range.
  • the peak pressing force range of the training user's peak pressing force is less than or equal to 3 Newtons
  • the actual user classification corresponding to the peak pressing force range less than or equal to 3 Newtons is the 2 Newtons category. Determine the actual user classification of the training user. Is 2 newton category.
  • the peak pressing force range of the training user's peak pressing force is greater than 3 Newtons and less than or equal to 5 Newtons.
  • the actual user classification corresponding to the peak pressing force range greater than 3 Newtons and less than or equal to 5 Newtons is the 4 Newtons category. , determine that the actual user classification of the training user is the 4 Newton category.
  • the peak pressing force range of the training user's peak pressing force is greater than 5 Newtons and less than or equal to 7 Newtons.
  • the actual user classification corresponding to the peak pressing force range greater than 5 Newtons and less than or equal to 7 Newtons is the 6 Newton category. , determine that the actual user classification of the training user is the 6 Newton category.
  • the peak pressing force range of the training user's peak pressing force is greater than 7 Newtons and less than or equal to 9 Newtons.
  • the actual user classification corresponding to the peak pressing force range greater than 7 Newtons and less than or equal to 9 Newtons is the 8 Newtons category. , determine that the actual user classification of the training user is the 8 Newton category.
  • the peak pressing force range of the training user's peak pressing force is greater than 9 Newtons.
  • the actual user classification corresponding to the peak pressing force range greater than 9 Newtons is the 10 Newtons category. It is determined that the actual user classification of the training user is 10 Newtons. category.
  • the user classification model before using the collected instantaneous pressure peaks to predict the classification of actual users according to the user classification model, the user classification model also needs to be trained.
  • the embodiments of this application can use TensorFlow to write a neural network model, and the input data is set to gender, age range, peak pressing force, etc., and the Adam (Adaptive moment) algorithm can be used, and the learning rate can be set Set the specified learning rate to train the model, as shown in Figure 2.
  • TensorFlow to write a neural network model
  • the input data is set to gender, age range, peak pressing force, etc.
  • the Adam (Adaptive moment) algorithm can be used
  • the learning rate can be set Set the specified learning rate to train the model, as shown in Figure 2.
  • the specified learning rate can be a value such as 0.001 or 0.002.
  • the embodiment of the present application still needs to perform data collection operations to classify the collected or peak values in the data set according to pressure.
  • data with a peak pressing force range of less than 3 Newtons are classified into the 2 Newton category, and data with a peak pressing force range of 3 Newtons to 5 Newtons are classified into the 4 Newton category.
  • Data with a peak pressure range between 5 Newton and 7 Newton are classified into the 6 Newton category, data with a peak pressure range between 7 Newton and 9 Newton are classified into the 8 Newton category, and data with a peak pressure range greater than 9 Newton are classified into the 10 Newton category.
  • embodiments of the present application can allocate all data items according to a specified proportion, where most of the data items are used as training data for training the user classification model, and a small part of the data items are used as test data for testing the user classification model. data. After using the training data to train the user classification model, use the test data to test the user classification model to obtain the test accuracy.
  • embodiments of the present application can use all data items as training data, use the training data to train the model, and if the number of times the model is trained reaches a specified number of times, the model at this time is used as the trained user classification model.
  • embodiments of the present application can allocate all data items in a ratio of 9:1, with 90% of the data items used as training data for training, and 10% of the data items used as test data for test training, and stopping when the accuracy rate is greater than 90%. Training, locking hyperparameters, and exporting the model, so that the above user classification model combined with data such as gender, age range, and peak pressing force can effectively avoid model overfitting, improve the generalization performance of the model, and improve the accuracy and real-time prediction of the model. sex.
  • embodiments of the present application can allocate all data items in a ratio of 9.5:0.5, where 95% of the data items are used as training data for training, and 5% of the data items are used as test data for test training.
  • 95% of the data items are used as training data for training
  • 5% of the data items are used as test data for test training.
  • Stop training lock the hyperparameters, and export the model.
  • the actual user classification is a 2 Newton category, a 4 Newton category, a 6 Newton category, an 8 Newton category or a 10 Newton category.
  • the activation function in the embodiment of the present application can be softmax.
  • those skilled in the art can also use functions such as Tanh as the activation function according to the actual situation, which is not specifically limited here.
  • embodiments of this application can use TensorFlow to build a neural network with 5 to 25 layers of neurons, and the output is five categories of softmax, with labels of 2 Newtons, 4 Newtons, 6 Newtons, 8 Newtons, and 10 Newtons. Therefore, the above users
  • the actual users of the classification model also have five categories: 2 Newtons, 4 Newtons, 6 Newtons, 8 Newtons and 10 Newtons, as shown in Figure 3. To divide the categories of output data, there are This effectively improves the efficiency of model prediction classification and subsequent determination of the target energization mode of the vibration coil.
  • step S103 the target energization mode of the vibration coil is determined according to the actual user classification, and the interactive force after user operation is fed back according to the target energization mode.
  • the embodiment of the present application can determine the target energization mode of the vibration coil according to the actual user classification, and then feed back the interaction force after the user's operation, so that the human-computer interaction system can adapt to users with different needs and provide Produce different feedback forces to enhance and improve the user experience of all types of users.
  • determining the target power-on mode of the vibration coil according to the actual user classification includes: matching the best use experience of the actual user classification according to the actual user classification; determining the target power-on mode according to the best use experience .
  • the first correspondence may be configured in advance, and the first correspondence is used to save the correspondence between the actual user classification and the target power-on mode, or the first correspondence is used to save the identity information, the actual user classification and the target power-on mode.
  • the corresponding target power-on mode is obtained from the first correspondence relationship based on the actual user classification.
  • obtain the corresponding target power-on mode from the first correspondence relationship based on the actual user classification and the identity information.
  • Embodiments of the present application integrate the softmax multivariate classifier of deep learning into the traditional vibration feedback system, thereby matching the best user experience according to the actual user classification, and then determining the target power-on mode.
  • the terminal device can allow the girl to get the best result when she performs the pressing operation.
  • the user experience can be determined by reducing the current intensity and other indicators to determine the target power-on method, thereby matching the user's gender and pressing force to the most appropriate power-on method, greatly improving the user's experience and willingness to use.
  • feedback of the interaction force after user operation according to the target energization method includes: energizing the vibration coil according to the target energization method, so that the vibration coil absorbs the metal vibration piece according to the magnetic flux generated by the current, generating interaction force.
  • different target energization modes correspond to different current intensities.
  • a current can be input to the vibration coil based on the current intensity corresponding to the target energization mode, so that the vibration coil can absorb according to the magnetic flux generated by the current.
  • Metal vibrator produces interactive force.
  • the trained model is transplanted into the vibration feedback device to perform vibration feedback testing. Specifically, after prediction and judgment based on data such as peak pressure through the above user classification model, the actual classification of the user is obtained, and then the vibration coil is energized according to the user classification. The coil generates magnetic flux based on the current to absorb the metal vibration piece, thereby generating an interactive force. This allows the user to feel the feedback force, as shown in Figure 4. This allows the human-computer interaction system to give different feedback forces according to different users, meeting the needs of different users and making the function more humane and A sense of technology.
  • the instantaneous pressure peak value during user operation is collected; the instantaneous pressure peak value is input into the pre-constructed user classification model to obtain the user's actual user classification; the vibration coil is determined according to the actual user classification The target power-on method, and feedback the interaction force after the user's operation according to the target power-on method.
  • This application can obtain user classification by utilizing instantaneous pressure peaks combined with deep learning, so that the human-computer interaction system can adapt to users with different needs without increasing hardware costs.
  • the algorithm occupies very few resources, thereby giving different feedback forces and greatly improving improve the user experience of all types of users.
  • embodiments of the present application also provide another manual interaction method for vehicles.
  • a second correspondence relationship is configured in advance, and the second correspondence relationship is used to save the correspondence relationship between the peak pressing force range and the actual user classification.
  • the second correspondence relationship as shown in Table 1 below can be configured in advance.
  • the target peak pressing force range to which the instantaneous pressure peak value belongs is determined from each peak pressing force range included in the second correspondence relationship. Based on the target peak pressing force range, obtain the corresponding actual user classification from the second correspondence relationship. Based on the actual user classification, the corresponding target power-on mode is obtained from the above-mentioned first correspondence relationship. Based on the current intensity corresponding to the target energization mode, the current is input to the vibration coil, so that the vibration coil generates vibration according to the current. The magnetic flux attracts the metal vibrator and generates interactive force.
  • Figure 5 is a block diagram of a manual interaction device for a vehicle according to an embodiment of the present application.
  • the manual interaction device 10 of the vehicle includes: a collection module 100 , a classification module 200 and an interaction module 300 .
  • the collection module 100 is used to collect the instantaneous pressure peak value during user operation.
  • the classification module 200 is used to obtain the actual user classification of the user based on the instantaneous pressure peak value.
  • the interaction module 300 is used to determine the target energization mode of the vibration coil according to the actual user classification, and feedback the interaction force after the user's operation according to the target energization mode.
  • the classification module 200 is specifically configured to input the instantaneous pressure peak value to a user classification model, and obtain the user's profile obtained by the user classification model based on the instantaneous pressure peak value. Actual user classification; or,
  • the actual user classification of the user is obtained.
  • the manual interaction device 10 of the vehicle in the embodiment of the present application further includes: an acquisition module, used for:
  • the plurality of training data are used to train a neural network model to obtain the user classification model.
  • the interaction module 300 is specifically configured to energize the vibration coil according to the target energization mode, so that the vibration coil absorbs the metal vibration piece according to the magnetic flux generated by the current, and generates an interactive force.
  • the vehicle manual interaction device 10 of the embodiment of the present application further includes: a first acquisition module, a second acquisition module, and a first acquisition module.
  • the first acquisition module is used to obtain input data items based on the gender, age range and peak pressing force of multiple training users before inputting the instantaneous pressure peak value into the pre-built user classification model.
  • the second acquisition module is used to obtain training data and test data according to the input data items.
  • the third acquisition module is used to train the neural network model using training data and test data to obtain a user classification model.
  • the interaction module 300 includes: a matching unit and a determining unit.
  • the matching unit is used to match the best usage experience of actual user classification according to actual user classification.
  • the determination unit is used to determine the target power-on method based on the best usage experience.
  • the actual user classification is a 2 Newton category, a 4 Newton category, a 6 Newton category, an 8 Newton category or a 10 Newton category.
  • the instantaneous pressure peak value during user operation is collected; the instantaneous pressure peak value is input into the pre-constructed user classification model to obtain the user's actual user classification; the vibration coil is determined according to the actual user classification The target power-on method, and feedback the interaction force after the user's operation according to the target power-on method.
  • This application can obtain user classification by utilizing instantaneous pressure peaks combined with deep learning, so that the human-computer interaction system can adapt to users with different needs, thereby giving different feedback forces and greatly improving the experience of various users. This solves the problems of current human-computer interaction vibration feedback technology, which has a single feedback force and cannot adapt to user needs.
  • This embodiment also provides a vibration feedback device, which is equipped with the manual interaction device of the vehicle as described in the above embodiment.
  • FIG. 6 is a schematic structural diagram of a vehicle provided by an embodiment of the present application.
  • the vehicle can include:
  • vehicles also include:
  • Communication interface 603 is used for communication between the memory 601 and the processor 602.
  • Memory 601 is used to store computer programs that can run on the processor 602.
  • Memory 601 may include high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.
  • the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component
  • EISA Extended Industry Standard Architecture
  • the bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one thick line is used in Figure 6, but it does not mean that there is only one bus or one type of bus.
  • the memory 601, the processor 602 and the communication interface 603 are integrated on one chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through the internal interface.
  • the processor 602 may be a central processing unit (Central Processing Unit, referred to as CPU), or a specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), or one or more processors configured to implement the embodiments of the present application. integrated circuit.
  • CPU Central Processing Unit
  • ASIC Application Specific Integrated Circuit
  • This embodiment also provides a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the above manual interaction method for a vehicle is implemented.
  • references to the terms “one embodiment,” “some embodiments,” “an example,” “specific examples,” or “some examples” or the like means that specific features are described in connection with the embodiment or example. , structures, materials or features are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the specific features, structures, materials or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, those skilled in the art may combine and combine different embodiments or examples and features of different embodiments or examples described in this specification unless they are inconsistent with each other.
  • first and second are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Therefore, features defined as “first” and “second” may explicitly or implicitly include at least one of these features. In the description of this application, “N” means at least two, such as two, three, etc., unless otherwise clearly and specifically limited.
  • a "computer-readable medium” may be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
  • Non-exhaustive list of computer readable media include the following: electrical connections with one or N wires (electronic device), portable computer disk cartridge (magnetic device), random access memory (RAM), Read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM).
  • the computer-readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned and subsequently edited, interpreted, or otherwise suitable as necessary. Processing is performed to obtain the program electronically and then stored in computer memory.
  • N steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: discrete logic circuits having logic gate circuits for implementing logical functions on data signals , application-specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.
  • PGA programmable gate arrays
  • FPGA field programmable gate arrays
  • the program can be stored in a computer-readable storage medium.
  • the program can be stored in a computer-readable storage medium.
  • each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. middle.
  • the above integrated modules can be implemented in the form of hardware or software function modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
  • the storage media mentioned above can be read-only memory, magnetic disks or optical disks, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

La présente invention concerne un procédé et un appareil d'interaction manuelle pour un véhicule, ainsi qu'un dispositif, un véhicule et un support de stockage. Le procédé consiste à : collecter une valeur de pic de pression instantanée lorsqu'un utilisateur effectue une opération ; obtenir la catégorie d'utilisateur réelle de l'utilisateur sur la base de la valeur de pic de pression instantanée ; et déterminer un mode de mise sous tension cible d'une bobine de vibration selon la catégorie d'utilisateur réelle, et selon le mode de mise sous tension cible, effectuer une rétraction par une force d'interaction après que l'utilisateur a effectué l'opération. Dans la présente invention, une catégorie d'utilisateur peut être acquise au moyen d'une valeur de pic de pression instantanée en combinaison avec un apprentissage profond, de sorte qu'un système d'interaction homme-machine s'adapte à des utilisateurs ayant différentes exigences, et différentes forces de rétroaction d'interaction sont ainsi données, ce qui permet d'améliorer considérablement l'expérience d'utilisation de divers utilisateurs.
PCT/CN2023/109507 2022-07-29 2023-07-27 Procédé et appareil d'interaction manuelle pour véhicule, et dispositif, véhicule et support de stockage WO2024022429A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210911994.7 2022-07-29
CN202210911994.7A CN115291722A (zh) 2022-07-29 2022-07-29 车辆的人工交互方法、装置、设备、车辆及存储介质

Publications (1)

Publication Number Publication Date
WO2024022429A1 true WO2024022429A1 (fr) 2024-02-01

Family

ID=83825931

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/109507 WO2024022429A1 (fr) 2022-07-29 2023-07-27 Procédé et appareil d'interaction manuelle pour véhicule, et dispositif, véhicule et support de stockage

Country Status (2)

Country Link
CN (1) CN115291722A (fr)
WO (1) WO2024022429A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115291722A (zh) * 2022-07-29 2022-11-04 奇瑞汽车股份有限公司 车辆的人工交互方法、装置、设备、车辆及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120098750A1 (en) * 2010-10-22 2012-04-26 Southern Methodist University Method for subject classification using a pattern recognition input device
CN106598236A (zh) * 2016-11-29 2017-04-26 上海创功通讯技术有限公司 一种触压反馈方法及装置
US20200126670A1 (en) * 2018-10-23 2020-04-23 International Business Machines Corporation Stress level reduction using haptic feedback
US20220019286A1 (en) * 2019-03-08 2022-01-20 Jiangxi Oumaisi Microelectronics Co., Ltd. Touch feedback device, intelligent terminal and vehicle
CN115291722A (zh) * 2022-07-29 2022-11-04 奇瑞汽车股份有限公司 车辆的人工交互方法、装置、设备、车辆及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120098750A1 (en) * 2010-10-22 2012-04-26 Southern Methodist University Method for subject classification using a pattern recognition input device
CN106598236A (zh) * 2016-11-29 2017-04-26 上海创功通讯技术有限公司 一种触压反馈方法及装置
US20200126670A1 (en) * 2018-10-23 2020-04-23 International Business Machines Corporation Stress level reduction using haptic feedback
US20220019286A1 (en) * 2019-03-08 2022-01-20 Jiangxi Oumaisi Microelectronics Co., Ltd. Touch feedback device, intelligent terminal and vehicle
CN115291722A (zh) * 2022-07-29 2022-11-04 奇瑞汽车股份有限公司 车辆的人工交互方法、装置、设备、车辆及存储介质

Also Published As

Publication number Publication date
CN115291722A (zh) 2022-11-04

Similar Documents

Publication Publication Date Title
CN107291822B (zh) 基于深度学习的问题分类模型训练方法、分类方法及装置
US9773044B2 (en) Multi-dimensional feature merging for supporting evidence in a question and answering system
WO2020135337A1 (fr) Classification de relations sémantiques d'entités
WO2024022429A1 (fr) Procédé et appareil d'interaction manuelle pour véhicule, et dispositif, véhicule et support de stockage
JP2024075662A (ja) アイテムを分類する装置、方法及び媒体
CN108733722A (zh) 一种对话机器人自动生成方法及装置
US20210256326A1 (en) Systems, techniques, and interfaces for obtaining and annotating training instances
CN111859149A (zh) 资讯信息推荐方法、装置、电子设备及存储介质
CN111651571B (zh) 基于人机协同的会话实现方法、装置、设备及存储介质
US20230087292A1 (en) Data annotation method and apparatus, and fine-grained recognition method and apparatus
Zhao et al. Lassl: Label-guided self-training for semi-supervised learning
CN109977209A (zh) 多轮人机交互方法、系统、计算机及介质
CN110363090A (zh) 智能心脏疾病检测方法、装置及计算机可读存储介质
WO2023124215A1 (fr) Procédé et dispositif d'étiquetage de question d'utilisateur
WO2019115236A1 (fr) Lecture indépendante et dépendante à l'aide de réseaux récurrents pour inférence de langage naturel
CN109858212A (zh) 用于数字密码软键盘的身份识别方法、装置和终端
CN110458600A (zh) 画像模型训练方法、装置、计算机设备及存储介质
US20230368028A1 (en) Automated machine learning pre-trained model selector
CN111339745A (zh) 一种随访报告生成方法、设备、电子设备和存储介质
WO2019061851A1 (fr) Procédé et appareil de reconnaissance d'effacement de geste et dispositif électronique
CN109408658A (zh) 表情图片提示方法、装置、计算机设备及存储介质
CN111552802A (zh) 文本分类模型训练方法和装置
Hantke et al. Trustability-based dynamic active learning for crowdsourced labelling of emotional audio data
CN117057855A (zh) 一种数据处理方法及相关装置
CN111382793A (zh) 一种特征提取方法、装置和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23845636

Country of ref document: EP

Kind code of ref document: A1