Detailed Description
The technical scheme of the invention is further elaborated below by referring to the drawings in the specification and the specific embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the scope of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
In the following description, reference is made to the expression "some embodiments" which describe a subset of all possible embodiments, but it should be understood that "some embodiments" may be the same subset or a different subset of all possible embodiments and may be combined with each other without conflict.
Referring to fig. 1, an application environment diagram of a learning efficiency detection method based on millimeter wave radar in an embodiment is shown. The learning efficiency detection method based on the millimeter wave radar is applied to the electronic equipment 10, and the electronic equipment 10 comprises a millimeter wave radar sensor 12 and a processor 13. The millimeter wave radar sensor 12 is configured to send electromagnetic wave signals to the target space region, and since there are a plurality of targets such as human body and other objects in the target space region, the plurality of targets reflect the electromagnetic wave signals, the millimeter wave radar sensor 12 can receive echo signals reflected by the plurality of targets, and the processor 13 detects learning efficiency of a user in front of the electronic device based on the echo signals detected by the millimeter wave radar sensor 12.
The millimeter wave radar sensor 12 is a radar system that detects a target using electromagnetic waves in the millimeter wave band, and the wavelength range of the millimeter wave is between 1mm and 10mm, between microwaves and terahertz waves. The millimeter wave radar sensor obtains information of the target by transmitting millimeter wave signals and receiving signals reflected by the target, wherein the information of the target comprises but is not limited to body movement data of the target, respiratory data in vital signs of the target and heart rate data.
Where there are multiple processors 13, the multiple processors 13 may be integrated on a single chip or may be separately provided on each chip. Where electronic device 10 is a device that mounts millimeter wave radar sensors, for example, may include a computing device (e.g., desktop computer, laptop computer, tablet computer, handheld computer, smart speaker, server, etc.), a terminal device (e.g., cell phone, etc.), a wearable device (e.g., a pair of smart glasses or smart watches), various infrared imaging devices, a smart desk lamp, or the like.
FIG. 2 is a schematic diagram of an electronic device according to an embodiment; the electronic device 10 is an intelligent desk lamp, and a millimeter wave radar sensor 12 is arranged in the intelligent desk lamp. The intelligent desk lamp can be placed in the front area of a user, and can also detect the learning efficiency of the user on the premise of providing an illumination function for the user, so that the learning efficiency of the user can be unconsciously monitored on the basis of not increasing the wearing equipment. When the intelligent desk lamp is in an on state, namely, under the condition of providing a lighting function, the millimeter wave radar sensor 12 sends electromagnetic wave signals to a target space region corresponding to the installation position of the intelligent desk lamp, and according to echo signals reflected by a human body, body movement data, respiratory data and heart rate data of the human body can be obtained, and the learning efficiency of a user is automatically detected based on the obtained data.
As shown in fig. 3, an application environment diagram of a learning efficiency detection method based on millimeter wave radar in another embodiment is shown. The electronic device 10 may also be communicatively connected to the terminal device 20, and the terminal device 20 may be sent in the event that the electronic device 10 is to detect the concentration of the user. For example, when a child performs writing operation, the intelligent desk lamp is turned on to use, the intelligent desk lamp automatically detects the concentration degree of the child in the writing operation process, and the concentration degree is formed into a report according to the detected concentration data and is sent to the terminal equipment 20 of the parent, so that the parent can know the learning condition of the child in real time without staring at the child at any time.
Referring to fig. 4, a flowchart of a learning efficiency detection method based on millimeter wave radar according to an embodiment of the present application is shown. The learning efficiency detection method based on the millimeter wave radar is applied to the electronic equipment, and comprises the following steps of:
S11, acquiring target echo data with target duration, which are detected to a target space region through a millimeter wave radar sensor.
In the present embodiment, the millimeter wave radar sensor is controlled to transmit an electromagnetic wave signal to a target space region and to receive an echo signal reflected by the target space region. The target space region indicates a region to which a signal of the millimeter wave radar sensor can be emitted, and is related to the installation position and the parameters of the millimeter wave radar sensor itself because of the installation position of the millimeter wave radar sensor in the electronic device. When the electronic equipment is in an on state, the millimeter wave radar sensor is controlled to send electromagnetic wave signals.
The target duration may be a preset time duration, and after the electronic device is in an on state, each preset target duration is used for executing the learning efficiency detection method based on the millimeter wave radar provided by the embodiment of the application to calculate the primary learning efficiency. For example, the target time period may be 15 minutes, half an hour, 1 hour, etc. The target echo data is echo data detected within a target duration. By analyzing the target echo data, the learning efficiency of the user can be detected.
S12, determining input data to be detected based on the target echo data.
In this embodiment, since the target echo data is data detected by the millimeter wave radar, the target echo data has noise and background data, and the noise and the background data need to be processed, so that interference of subsequent detection is reduced. And converting the processed echo data to obtain a discrete echo signal, and taking the obtained discrete echo signal as input data to be detected.
S13, inputting input data to be detected into a pre-trained learning efficiency detection model, outputting first characteristic data indicating that a user is in a departure state and second characteristic data indicating that the user is in different concentration degrees through a learning characteristic extraction network by the learning efficiency detection model, detecting learning efficiency based on the first characteristic data and the second characteristic data through a learning efficiency calculation network, and outputting a learning efficiency score corresponding to the input data to be detected.
In this embodiment, the learning efficiency detection model includes a learning feature extraction network and a learning efficiency calculation network, the learning feature extraction network being connected to the learning efficiency calculation network, output data of the learning feature extraction network being input data of the learning efficiency calculation network. The learning efficiency detection model is obtained based on training of a training sample set, and in the training process, the learning efficiency detection model can learn the features in various training samples, so that after training is completed, a learning feature extraction network can directly extract first feature data of a user in a leaving state and second feature data of the user in a learning state from input data to be detected, wherein the first feature data can represent leaving time of the leaving state, and the second feature data can represent time periods corresponding to different concentration degrees in the learning state. Where concentration levels include low, medium, high, and the like. And taking the first characteristic data and the second characteristic data as inputs of a learning efficiency calculation network, and outputting corresponding learning efficiency scores. For example, the input data to be detected is obtained based on target echo data with 15 minutes duration, and then the leaving duration of 3 minutes, the duration corresponding to the middle concentration degree of 5 minutes, the duration corresponding to the lower concentration degree of 1 minute, and the duration corresponding to the higher concentration degree of 6 minutes are obtained after the extraction of the learning feature extraction network. And then taking the time length of leaving as 3 minutes, the time length corresponding to the middle concentration as 5 minutes, the time length corresponding to the lower concentration as 1 minute, and the time length corresponding to the higher concentration as 6 minutes as the input data of the learning efficiency calculation network, and directly outputting the corresponding learning efficiency score.
Therefore, the learning efficiency detection model not only can output the concentration degree condition of the learning state in the target duration, but also can directly output the learning efficiency score based on the trained learning efficiency detection model, so that the learning condition of students can be intuitively known.
In the above embodiment, the target echo data is obtained, the input data to be detected is formed based on the target echo data, the first characteristic data representing the departure state and the second characteristic data representing the different concentration degrees in the input data to be detected are extracted through the pre-trained learning efficiency detection model, and the learning efficiency scores corresponding to the input data to be detected can also be output through the pre-trained learning efficiency detection model; compared with the empirical formula in the prior art, the learning efficiency detection model trained by the training method can learn the characteristics in the sample data set, so that the learning characteristics in the input data can be accurately detected, and the learning efficiency score can be directly output based on the detected learning characteristics, so that the concentration degree condition of the learning state in the target duration can be output through the pre-trained learning efficiency detection model, the learning efficiency score can be directly output based on the trained learning efficiency detection model, the learning condition of students can be intuitively known, and the learning efficiency detection accuracy is improved.
In some embodiments, the determining input data to be detected based on the target echo data includes:
Preprocessing the target echo data to obtain the input data to be detected, wherein the preprocessing comprises at least one of the following steps: static clutter cancellation, mixer-based processing operations, analog-to-digital converter-based sampling operations, fast time fourier transform-based transform operations.
The target echo data is first subjected to preprocessing operations to obtain input data to be detected, wherein the preprocessing operations include, but are not limited to, static clutter cancellation, mixer-based processing operations, analog-to-digital converter-based sampling operations, fast time fourier transform-based transformation operations, and the like. The method comprises the steps of performing static clutter elimination on input data to be detected, performing static clutter elimination processing, reducing the influence of clutter signals generated by large static objects in a room on target echo signals, mixing a transmitting signal with the echo signals based on the processing operation of a mixer to obtain a signal with new frequency, wherein the signal is an intermediate frequency signal, the frequencies and phases of the echo signals and the transmitting signal are different, therefore, data such as distance, speed and angle can be extracted and analyzed from the superimposed intermediate frequency signal, the sampling operation of an analog-digital converter is used for sampling the processed echo signals, and fourier transformation processing is performed on the sampled signals to obtain a discrete echo signal x (m, n) containing distance dimension and slow time dimension information, wherein m represents a slow time dimension, m represents a pulse echo, and n represents a distance dimension and n represents a distance unit.
In the embodiment, through preprocessing the target echo data, clutter interference signals can be eliminated, sampling operation and conversion operation are simultaneously performed, so that a discrete echo signal comprising various information is obtained, more characteristic information can be conveniently extracted later, and the accuracy of learning efficiency detection is improved.
In some embodiments, as shown in fig. 5, fig. 5 is a flowchart of training a learning efficiency detection model in a learning efficiency detection method based on millimeter wave radar in an embodiment, where the method further includes:
S51, acquiring a training sample set.
In this embodiment, each training sample in the training sample set includes leaving sample data in a leaving state, learning sample data in a learning state, a learning efficiency score tag corresponding to the training sample, and a concentration degree tag corresponding to the learning sample data. In an alternative implementation manner, a plurality of electronic devices may be connected to a server, the server may collect data of the plurality of electronic devices, and then collect a training sample set based on the data of the plurality of electronic devices, so that the training sample set may include learning state data of a plurality of student users, and the training sample set is diversified, so that in a subsequent training process, richer feature data can be provided. Wherein the concentration level label includes low, medium, high, and the like. More degree levels may also be set as desired.
S52, constructing an initial learning efficiency detection model, wherein the initial learning efficiency detection model comprises a learning characteristic extraction network and a learning efficiency calculation network.
In this embodiment, the learning feature extraction network may be a deep neural network, and the learning feature extraction network includes an input layer, a hidden layer, a full connection layer, and an output layer. Wherein the input layer is for receiving input data, which is input into the network, for example, a discrete echo signal or the like. The hidden layer may be a plurality of hidden layers, each layer being composed of a plurality of neurons. These layers learn the high-level features of the data through nonlinear activation functions (e.g., reLU). Full tie layer: at the last few layers of the network, there are typically fully connected layers that map learned features onto the final class. The output layer is typically a softmax layer that converts the output of the network into a probability distribution that represents the probability that the input data belongs to each category. The learning efficiency calculation network may also be a deep neural network.
S53, sample input data are obtained based on the training sample set, the sample input data are input into a learning efficiency detection model in iterative training to carry out iterative training, the concentration degree corresponding to the learning sample data is output through the learning feature extraction network in the iterative training, and learning sample duration and sample leaving duration corresponding to different concentration degrees are output.
In an optional implementation manner, the concentration level label corresponding to the learning sample data is a concentration level label output by the trained concentration level classification network model. In the training process, learning sample data in the sample input data is input into a trained concentration classification network model, and concentration degree labels corresponding to the learning sample data are output.
In this embodiment, in the training process, since the trained concentration classification network model is a model trained in advance based on the concentration training data set, the concentration degree can be accurately output. When the learning efficiency detection model is trained, the trained concentration degree classification network model is equivalent to a teacher model, and sample input data is input into the trained concentration degree classification network model and the learning feature extraction network, so that concentration degree labels corresponding to the sample input data can be obtained through the trained concentration degree classification network model, in the training process, the learning feature extraction network is equivalent to a student model, the concentration degree labels output by the teacher model are taken as training targets, the learning feature extraction network in the learning efficiency detection model is trained, convergence of the learning efficiency detection model can be accelerated, and training time is shortened.
In an alternative implementation, a trained concentration classification network model is obtained;
The acquiring the trained concentration classification network model comprises the following steps:
Acquiring an concentration training data set, wherein each training data in the concentration training data set comprises heart rate sample data and concentration degree labels corresponding to the heart rate sample data;
constructing an initial concentration degree classification network model;
And training the concentration degree classification network model based on the concentration degree training data set to obtain a trained concentration degree classification network model.
In this embodiment, the concentration training data set may be derived from collected heart rate data of a plurality of users. In order to enrich the concentration training data set, heart rate sample data under different concentration degrees can be acquired, so that in the training process, the concentration classification network model can learn heart rate sample characteristics under different concentration degrees. Input data are acquired from the concentration training data set, the input data are input into the concentration classification network model, and loss values in each iteration process are calculated until the concentration classification network model converges, so that a trained concentration classification network model is obtained.
And S54, the learning efficiency calculation network in the iterative training calculates the current learning efficiency score in the current iteration based on the learning sample time length and the leaving sample time length corresponding to different concentration degrees.
S55, calculating a current loss value in the current iteration based on a loss function in the iteration process, wherein the current loss value comprises a concentration degree loss value between a concentration degree corresponding to learning sample data output by the learning feature extraction network in the current iteration and a concentration degree label corresponding to the learning sample data, and a score loss value between a current learning efficiency score and a learning efficiency score label.
In some alternative implementations, the calculating the current loss value in the current iteration based on the loss function in the iterative process includes:
calculating the concentration degree loss value based on a first loss function;
calculating the score loss value based on a second loss function; wherein the loss function is:
Wherein,As a function of the loss,As a function of the first loss,As a function of the second loss,、Respectively, weight coefficients. Wherein the first loss function may be the same or different from the second loss function, e.g., the first loss function is a mean square error loss function, the second loss function is a cross entropy loss function, etc.
S56, judging whether the current iteration meets an iteration termination condition or not based on the current loss value; if the current iteration meets the iteration termination condition, taking the learning efficiency detection model after stopping the iteration as a pre-trained learning efficiency detection model; and if the current iteration does not meet the iteration termination condition, continuing to process based on the training sample set to obtain sample input data, and performing iterative training on the learning efficiency detection model.
In the above embodiment, based on each training sample in the training sample set, and the learning efficiency score label corresponding to each training sample and the concentration degree label corresponding to the learning sample data, training and learning are performed on the learning efficiency detection model, so that the learning efficiency detection model uses the concentration degree label corresponding to each training sample as a training target, and thus the concentration degree level corresponding to the learning sample data is output, the learning efficiency detection model can accurately calculate the learning efficiency score subsequently, and in the training process, the learning efficiency detection model uses the learning efficiency score label corresponding to each training sample as a training target, thereby outputting an accurate learning efficiency score, and improving the accuracy of learning efficiency detection.
In some embodiments, the method further comprises at least one of:
sending the learning efficiency score corresponding to the target duration to a terminal device in communication with the electronic device;
Displaying state identifiers in each time period in the target time period by taking the time sequence as a sequence, wherein the state identifiers comprise leaving state identifiers and identifiers of different concentration degrees in a learning state;
And displaying the duty ratio of different concentration degrees in the learning state in the target duration and the duration corresponding to the different concentration degrees.
In this embodiment, since the learning feature extraction network is capable of extracting the first feature data and the second feature data within the target duration, and the input data to be detected is data in which time is a sequence, each feature data corresponds to each time period. Therefore, the extracted state identifiers in each time period can be displayed in the time sequence, so that the user can intuitively observe the learning condition of the user in the target time period, for example, the target time period is 15 minutes, and the states from the beginning to the 3 rd minute to the leaving state, from the 3 rd minute to the 8 th minute to the medium concentration state, from the 8 th minute to the 9 th minute to the low concentration state and from the 9 th minute to the 15 th minute to the high concentration state are displayed in the time sequence. Through time sequence state display, parents can know the progress of learning state. Fig. 6 is a schematic diagram of the duty ratios of different attentiveness degrees in an embodiment, and the duty ratios of different attentiveness states and the durations corresponding to the different attentiveness states are displayed through the schematic diagram, so that a user can more intuitively understand the situation of each learning state, for example, in fig. 6, the data of deep attentiveness, medium attentiveness and shallow attentiveness are displayed through a ring chart, and the durations of various attentiveness states are displayed, so that a parent can intuitively understand the learning situation in a certain time period.
In the above embodiment, the time sequence is used as a sequence, and the state identifiers in each time period are displayed, and/or the duty ratio of different concentration degrees and the time periods corresponding to the different concentration degrees in the learning state in the target time period are displayed, so that parents can intuitively know the learning condition of students in a certain time period.
In some embodiments, the method further comprises:
calculating a concentration score based on the second characteristic data; acquiring a historical target time period sent by terminal equipment, acquiring multiple record data in the historical target time period, and displaying the multiple record data;
Wherein the displaying the multiple record data includes at least one of:
Displaying the change trend of each data in the recorded data by a time axis, wherein the recorded data comprises a learning efficiency score and a concentration degree score;
The packet displays the recorded data of each time and the corresponding time period.
In this embodiment, the concentration score may also be calculated based on the second feature data representing the learning state in the target duration, for example, different scores and weights may be assigned to different concentration degrees, so that the concentration score may be calculated. And displaying a time selection control on a user interface of the terminal equipment, and enabling the parents to select a historical target time period to be checked through the time selection control and sending the historical target time period to the electronic equipment. The electronic device obtains the multiple record data in the historical target time period from the memory and displays the multiple record data. In an alternative implementation, for any kind of data, the change trend of the data may be displayed on a time axis, for example, the learning efficiency score of the historical target time period is displayed, so that parents can intuitively observe whether the learning efficiency of the child in the historical target time period is improved or stepped. In an alternative implementation, as shown in fig. 7, fig. 7 is a schematic diagram of grouping display record data in an embodiment, where record data may be recorded each time in a group.
In the above embodiment, the change trend of each data in the recorded data is displayed by a time axis, and/or the recorded data of each time and the corresponding time period are displayed in groups, so that parents can intuitively know the learning condition of students in a certain time period.
In another aspect, the present application provides a computer program product, which includes a computer program, where the computer program when executed by a processor implements the learning efficiency detection method based on millimeter wave radar according to any embodiment of the present application.
In the computer program product, an optional implementation form of a program module architecture of a computer program for implementing steps of the learning efficiency detection method based on the millimeter wave radar may be a learning efficiency detection device based on the millimeter wave radar.
Referring to fig. 8, an embodiment of the present application provides a learning efficiency detection device based on millimeter wave radar, including: an acquisition module 81 for acquiring target echo data having a target duration detected toward a target space region by a millimeter wave radar sensor; a determining module 82, configured to determine input data to be detected based on the target echo data; the detection module 83 is configured to input the input data to be detected into a pre-trained learning efficiency detection model, where the learning efficiency detection model outputs, through a learning feature extraction network, first feature data indicating that a user is in a away state and second feature data indicating that the user is in different concentration degrees, and performs learning efficiency detection through a learning efficiency calculation network based on the first feature data and the second feature data, and outputs a learning efficiency score corresponding to the input data to be detected; the first characteristic data comprise leaving time periods, and the second characteristic data comprise time periods corresponding to different concentration degrees.
Optionally, the determining module 82 is further configured to:
Preprocessing the target echo data to obtain the input data to be detected, wherein the preprocessing comprises at least one of the following steps: static clutter cancellation, mixer-based processing operations, analog-to-digital converter-based sampling operations, fast time fourier transform-based transform operations.
Optionally, the detection module 83 is further configured to:
acquiring a training sample set, wherein each training sample in the training sample set comprises leaving sample data in a leaving state, learning sample data in a learning state, a learning efficiency score label corresponding to the training sample and a concentration degree label corresponding to the learning sample data;
constructing an initial learning efficiency detection model, wherein the initial learning efficiency detection model comprises a learning characteristic extraction network and a learning efficiency calculation network;
Sample input data is obtained based on the training sample set processing, the sample input data is input into a learning efficiency detection model in iterative training for iterative training, the concentration degree corresponding to the learning sample data is output through the learning characteristic extraction network in the iterative training, and learning sample time lengths and sample leaving time lengths corresponding to different concentration degrees are output;
The learning efficiency calculation network in the iterative training calculates the current learning efficiency score in the current iteration based on the learning sample time length and the leaving sample time length corresponding to different concentration degrees;
calculating a current loss value in the current iteration based on a loss function in the iteration process, wherein the current loss value comprises a concentration degree loss value between a concentration degree corresponding to learning sample data output by the learning feature extraction network in the current iteration and a concentration degree label corresponding to the learning sample data, and a score loss value between a current learning efficiency score and a learning efficiency score label;
judging whether the current iteration meets an iteration termination condition or not based on the current loss value; if the current iteration meets the iteration termination condition, taking the learning efficiency detection model after stopping the iteration as a pre-trained learning efficiency detection model; and if the current iteration does not meet the iteration termination condition, continuing to process based on the training sample set to obtain sample input data, and performing iterative training on the learning efficiency detection model.
Optionally, the concentration degree label corresponding to the learning sample data is a concentration degree label output by the trained concentration degree classification network model.
Optionally, the detection module 83 is further configured to:
Acquiring a trained concentration degree classification network model;
The acquiring the trained concentration classification network model comprises the following steps:
Acquiring an concentration training data set, wherein each training data in the concentration training data set comprises heart rate sample data and concentration degree labels corresponding to the heart rate sample data;
constructing an initial concentration degree classification network model;
And training the concentration degree classification network model based on the concentration degree training data set to obtain a trained concentration degree classification network model.
Optionally, the detection module 83 is further configured to:
in the iteration process, learning sample data in the sample input data is input into the trained concentration classification network model, and concentration degree labels corresponding to the learning sample data are output.
Optionally, the detection module 83 is further configured to:
calculating the concentration degree loss value based on a first loss function;
calculating the score loss value based on a second loss function; wherein the loss function is:
Wherein,As a function of the loss,As a function of the first loss,As a function of the second loss,、Respectively, weight coefficients.
Optionally, the detection module 83 is further configured to:
sending the learning efficiency score corresponding to the target duration to a terminal device in communication with the electronic device;
Displaying state identifiers in each time period in the target time period by taking the time sequence as a sequence, wherein the state identifiers comprise leaving state identifiers and identifiers of different concentration degrees in a learning state;
And displaying the duty ratio of different concentration degrees in the learning state in the target duration and the duration corresponding to the different concentration degrees.
Optionally, the detection module 83 is further configured to:
calculating a concentration score based on the second characteristic data; acquiring a historical target time period sent by terminal equipment, acquiring multiple record data in the historical target time period, and displaying the multiple record data;
Wherein the displaying the multiple record data includes at least one of:
Displaying the change trend of each data in the recorded data by a time axis, wherein the recorded data comprises a learning efficiency score and a concentration degree score;
The packet displays the recorded data of each time and the corresponding time period.
It will be appreciated by those skilled in the art that the structure of the learning efficiency detection apparatus based on millimeter wave radar in fig. 8 does not constitute a limitation of the learning efficiency detection apparatus based on millimeter wave radar, and the respective modules may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules. In other embodiments, more or fewer modules than illustrated may be included in the millimeter wave radar-based learning efficiency detection apparatus.
Referring to fig. 9, in another aspect of the embodiment of the present application, there is further provided an electronic device 10, including a processor 13 and a memory 14, where the memory 14 stores a computer program, and the computer program when executed by the processor causes the processor 13 to execute the steps of the learning efficiency detection method based on millimeter wave radar provided by any one of the embodiments of the present application. Where electronic device 10 is an infrared imaging enabled device, for example, may include a computing device (e.g., desktop computer, laptop computer, tablet computer, handheld computer, smart speaker, server, etc.), a terminal device (e.g., cell phone, etc.), a wearable device (e.g., a pair of smart glasses or a smart watch), a smart desk lamp, or the like.
Wherein the processor 13 is a control center that uses various interfaces and lines to connect the various parts of the overall computer device, perform various functions of the computer device and process data by running or executing software programs and/or modules stored in the memory 14, and invoking data stored in the memory 14. Optionally, processor 13 may include one or more processing cores; preferably, the processor 13 may integrate an application processor and a modem processor, wherein the application processor primarily handles operating systems, user pages, applications, etc., and the modem processor primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 13.
The memory 14 may be used to store software programs and modules, and the processor 13 executes various functional applications and data processing by executing the software programs and modules stored in the memory 14. The memory 14 may mainly include a storage program area that may store an operating system, application programs required for at least one function (such as a sound playing function, an image playing function, etc.), and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, memory 14 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 14 may also include a memory processor to provide access to the memory 14 by the processor 13.
In another aspect of the embodiments of the present application, there is further provided a storage medium storing a computer program, where the computer program when executed by a processor causes the processor to execute the steps of the learning efficiency detection method based on millimeter wave radar provided in any one of the above embodiments of the present application.
Those skilled in the art will appreciate that implementing all or part of the processes of the methods provided in the above embodiments may be accomplished by computer programs stored on a non-transitory computer readable storage medium, which when executed, may comprise processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. The scope of the invention is to be determined by the appended claims.