Artificial intelligence college experiment box with automatic judgment function

Abstract

The invention belongs to the technical field of experiment boxes, and particularly relates to an artificial intelligence college experiment box with an automatic judgment function. Comprising a hardware layer and a driving layer. The hardware layer comprises a single-chip microcomputer module, a sensor module, a first communication module, a display module and an interaction module. The judgment layer comprises a data recording module, a second communication module and an upper computer; a plurality of evaluation algorithms are built in the data evaluation module, and the cloud center data of the experiment box are evaluated according to a preset evaluation standard; and the judgment result is transmitted to the display screen to be displayed. Teaching experience is concluded and summarized, objective judgment standards and algorithms are formulated, and an upper computer is designed for unified management and respective calculation, so that the system has an intelligent automatic judgment function, and the experiment practical operation effect of students is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of experimental boxes, and in particular, relates to an artificial intelligence university experimental box with an automatic evaluation function. Background Art

[0002] With the rapid development of electronic technology, experimental platform teaching in the form of experimental boxes is an important part of electronic teaching; and single-chip microcomputers in electronic technology are widely used in various intelligent systems and electronic teaching experiments. The practical operation and development of single-chip microcomputers has become a compulsory course for electronic majors in many universities.

[0003] The existing single-chip microcomputer teaching experiment boxes in colleges and universities generally have the following shortcomings:

[0004] Traditional experimental boxes mostly adopt a closed design, which makes it difficult for students to carry out secondary development and add new functional modules or electronic devices according to application requirements, limiting the development of students' hands-on ability and the development of innovative thinking.

[0005] Traditional experiment boxes only provide simple hardware functions and lack intelligent evaluation and data analysis functions. They are unable to timely and effectively evaluate students' experimental results, resulting in low teaching efficiency, making it difficult for students to obtain timely feedback, and making it difficult to meet the needs of modern teaching and scientific research. Summary of the invention

[0006] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides an artificial intelligence university experiment box with automatic evaluation function; it aims to provide a more convenient and intelligent experimental platform for university teaching through technical means such as layered architecture, standard interface, evaluation criteria and intelligent algorithm.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] An artificial intelligence university experiment box with automatic evaluation function includes a hardware layer and a driver layer; the experiment box is mainly constructed by the hardware layer and the driver layer;

[0009] The hardware layer includes a single chip computer module, a sensor module, a first communication module, a display module and an interaction module;

[0010] The single-chip microcomputer module is used to execute program codes, process sensor data, control peripherals to perform specific functions, and exchange data with other modules through communication interfaces; the single-chip microcomputer module includes a single-chip microcomputer and a memory.

[0011] The sensor module is used to collect application signal data of a specific experimental box and transmit the application signal data to the single-chip microcomputer for processing; the sensor module includes a temperature sensor, a light sensor, and an accelerometer;

[0012] The first communication module is used for data transmission in the experimental box; the first communication module adopts UART, I2C or SPI communication interface;

[0013] The display module is used to display experimental data; the display module includes a display screen;

[0014] The interactive module is used for user input and operation control. It detects the user's input signal and transmits it to the microcontroller for processing. The interactive module includes buttons, knobs or touch screens.

[0015] The driver layer includes an underlying driver library, a driver library management module and a memory management module;

[0016] The underlying driver library is used to provide drivers for each module for easy calling; the underlying driver library includes the internal peripheral drivers and external peripheral drivers of the microcontroller; the internal peripheral drivers of the microcontroller include serial port protocols, ADC, DAC and timers; the external peripheral drivers of the microcontroller include sensor measurement programs and communication protocols.

[0017] The driver library management module is used to manage and initialize different underlying driver programs and realize function calls and resource sharing among modules.

[0018] The memory management module is used to manage memory allocation and data storage to maintain stable system operation.

[0019] Preferably, it also includes a judging layer, which includes a data recording module, a second communication module and a host computer;

[0020] The data recording module is arranged in the internal circuit of the experimental box and is used to collect the operation signal data of the experimental box; the data recording module includes a current sensor and a voltage sensor;

[0021] The second communication module is used to establish a communication connection between the host computer and multiple experimental boxes, using the Modbus protocol for communication, specifically using the serial port Master ASCII format.

[0022] The host computer is used to receive and pre-process the operation signal data from each experimental box, execute the evaluation algorithm, and display the data;

[0023] The host computer includes a data preprocessing module and a data evaluation module;

[0024] The data preprocessing module is used to preprocess the operation signal data received from the experimental box, and the preprocessing includes data cleaning or data conversion, and classifying and arranging the operation signal data; the classification and arranging of the operation signal data includes:

[0025] Distinguish according to the experiment box ID;

[0026] Record the timestamp of the experimental box running signal data to facilitate timing analysis in subsequent RMSE calculations;

[0027] Classify the experimental box operation signal data and unify the units.

[0028] The data evaluation module has built-in multiple evaluation algorithms to evaluate the operating data of the experimental box according to preset evaluation criteria; and transmits the evaluation results (accuracy score, power consumption score and performance score) to the display screen to display the evaluation results.

[0029] Preferably, the preset evaluation criteria include the functional signal accuracy, power consumption and performance of the system when performing a specific task;

[0030] The evaluation algorithms include an accuracy evaluation algorithm, a power consumption evaluation algorithm and a performance evaluation algorithm, and correspond one-to-one to preset evaluation criteria.

[0031] Specifically, the preset judging criteria are defined as follows:

[0032] Accuracy: How closely the output signal of a system matches the expected signal when performing a specific task.

[0033] Power consumption: The dynamic power consumption of a system when performing a specific task.

[0034] Performance: A comprehensive score of the time a system takes to perform a specific task and the number of tasks it processes per unit time.

[0035] Preferably, the output signal and the expected signal are the same type of signal in the same experimental box, including:

[0036] Digital signal: A digital signal output by an ADC (analog-to-digital converter).

[0037] Analog signal: high and low level signals output through GPIO (general purpose input and output port).

[0038] Communication signal: data packet sent through communication interfaces such as UART, I2C, SPI, etc.

[0039] Preferably, the implementation steps of the accuracy evaluation algorithm are: for each type of signal, the root mean square error (RMSE) is used to evaluate the matching degree between the output signal and the expected signal; the RMSE formula is as follows:

[0040]

[0041] Where N is the number of data points, Y i and S i are the expected signal and output signal at the i-th time point respectively;

[0042] Scoring is based on the RMSE value; the smaller the error, the higher the score.

[0043] Preferably, the implementation steps of the power consumption evaluation algorithm are: when the single chip microcomputer runs a specific task, use a sensor to measure its current I and voltage U in real time, and calculate the dynamic power consumption P0; the calculation formula of the dynamic power consumption is:

[0044] P0=UI;

[0045] Scoring is based on dynamic power consumption, with lower power consumption giving higher scores.

[0046] Preferably, the implementation steps of the performance evaluation algorithm are:

[0047] S1) Calculate the time required for the experimental box to perform a specific task: Use the microcontroller's timer or system clock to obtain an accurate timestamp. The calculation formula is as follows:

[0048] S = St-S0; where S is the execution time, St is the task end time, and S0 is the task start time;

[0049] S2) Calculate the efficiency of the experimental box in completing the number of tasks in a certain period of time: track and count the number of tasks through the log records in the microcontroller, and use the microcontroller's timer or system clock to obtain an accurate timestamp; the calculation formula is as follows:

[0050] P = N / t; where P is efficiency, N is the number of tasks to be processed, and t is the time taken to complete the number of tasks;

[0051] S3) Performance score: Due to the different hardware and software design architectures of the experimental box, the number of tasks that can be processed in parallel is also different; therefore, according to the performance requirements of the experimental box, different weights are assigned to execution time and efficiency to calculate a more realistic performance score; the calculation formula is as follows:

[0052] EH=1 / w1S+w2P;

[0053] Wherein, EH is the performance score; w1 is the weight coefficient of execution time; S is the execution time; w2 is the weight coefficient of efficiency; P is efficiency; and w1+w2=1.

[0054] Beneficial effects of the present invention:

[0055] 1. Ensure the modularity and scalability of the system through a layered service architecture, simplify the MCU development process, and facilitate students to add new functional modules or electronic devices according to application requirements; improve teaching efficiency.

[0056] 2. By summarizing and generalizing teaching experience, and formulating objective judgment standards and algorithms, and then designing a host computer for unified management and separate calculations, it can have an intelligent automatic evaluation function, which can effectively reduce the burden on teachers, provide students with more timely feedback, and improve students' experimental practice results. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0058] Figure 1 This is a structural framework diagram of an artificial intelligence university experiment box with automatic evaluation function of the present invention;

[0059] Figure 2 This is a flow chart of an artificial intelligence university experiment box with automatic evaluation function of the present invention;

[0060] Figure 3 The present invention is a flow chart of a performance evaluation algorithm in an artificial intelligence university experiment box with automatic evaluation function. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] See also Figure 1-Figure 3 As shown in the figure, an artificial intelligence university experiment box with automatic evaluation function includes a hardware layer and a driver layer; the experiment box is mainly built by the hardware layer and the driver layer, providing an experimental operation box for university teaching, and has multiple built-in single-chip standard experiment libraries, covering a variety of experimental courses, including basic hardware experiments, network protocol experiments and comprehensive experiments. Specifically, it includes basic hardware experiments such as general digital I / O interface, clock / interrupt, ADC experiment, temperature measurement, etc.; network protocol experiments such as UART, TI-ZStack, software architecture, and addressing routing; and comprehensive experiments such as smart home, distributed sensor acquisition, and automatic control.

[0063] Using a layered service architecture, the experimental box system is divided into a hardware layer, a driver layer, and a judgment layer. The layers communicate and exchange data through standard interfaces to ensure the modularity and scalability of the system.

[0064] The hardware layer includes a single chip computer module, a sensor module, a first communication module, a display module and an interaction module;

[0065] The MCU module is used to execute program code, process sensor data, control peripherals to perform specific functions, and exchange data with other modules through communication interfaces; the MCU module includes a MCU, memory, and ADC converter.

[0066] The sensor module is used to collect application signal data of a specific experimental box and transmit the application signal data to the single-chip microcomputer for processing; the sensor module includes a temperature sensor, a light sensor, and an accelerometer;

[0067] The first communication module is used for data transmission in the experimental box; the first communication module adopts UART, I2C or SPI communication interface;

[0068] The display module is used to display experimental data and evaluation results; the display module includes a display screen;

[0069] The interactive module is used for user input and operation control. It detects the user's input signal and transmits it to the microcontroller for processing. The interactive module includes buttons, knobs or touch screens.

[0070] The driver layer includes an underlying driver library, a driver library management module and a memory management module;

[0071] The underlying driver library is used to provide drivers for each module for easy calling; the underlying driver library includes the internal peripheral drivers and external peripheral drivers of the microcontroller; the internal peripheral drivers of the microcontroller include serial port protocols, ADC, DAC and timers; the external peripheral drivers of the microcontroller include sensor measurement programs and communication protocols.

[0072] The driver library management module is used to manage and initialize different underlying driver programs and realize function calls and resource sharing among modules.

[0073] The memory management module is used to manage memory allocation and data storage to maintain stable system operation.

[0074] Furthermore, it also includes a judging layer, which includes a data recording module, a second communication module and a host computer;

[0075] The data recording module is arranged in the internal circuit of the experimental box and is used to collect the operation signal data of the experimental box; the data recording module includes a current sensor and a voltage sensor;

[0076] The second communication module is used to establish a communication connection between the host computer and multiple experimental boxes, using the Modbus protocol for communication, specifically using the serial port Master ASCII format;

[0077] The host computer is used to receive and pre-process the operation signal data from each experimental box, execute the evaluation algorithm, and display the data;

[0078] The host computer includes a data preprocessing module and a data evaluation module;

[0079] The data preprocessing module is used to preprocess the received operation signal data of the experimental box, and the preprocessing includes data cleaning or data conversion, and classifying and arranging the operation signal data; the operation signal data classification and arrangement includes:

[0080] Distinguish according to the experiment box ID;

[0081] Record the timestamp of the experimental box running signal data to facilitate timing analysis in subsequent RMSE calculations;

[0082] Classify the experimental box operation signal data and unify the units.

[0083] The data evaluation module has built-in multiple evaluation algorithms to evaluate the operating data of the experimental box according to preset evaluation criteria; and transmits the evaluation results (accuracy score, power consumption score and performance score) to the display screen to display the evaluation results.

[0084] Further, the preset evaluation criteria include functional signal accuracy, power consumption and performance of the system when performing a specific task;

[0085] The evaluation algorithms include an accuracy evaluation algorithm, a power consumption evaluation algorithm and a performance evaluation algorithm, and correspond one-to-one to preset evaluation criteria.

[0086] Specifically, the preset judging criteria are defined as follows:

[0087] Accuracy: How closely the output signal of a system matches the expected signal when performing a specific task.

[0088] Power consumption: The dynamic power consumption of a system when performing a specific task.

[0089] Performance: A comprehensive score of the time a system takes to perform a specific task and the number of tasks it processes per unit time.

[0090] Furthermore, the output signal and the expected signal are the same type of signal in the same experimental box, including:

[0091] Digital signal: A digital signal output by an ADC (analog-to-digital converter).

[0092] Analog signal: high and low level signals output through GPIO (general purpose input and output port).

[0093] Communication signal: data packet sent through communication interfaces such as UART, I2C, SPI, etc.

[0094] Here is an example:

[0095] ADC experiment:

[0096] Expected signal: The digital value that the input analog voltage should theoretically be converted to.

[0097] Output signal: The digital value actually converted by ADC.

[0098] Temperature measurement experiment:

[0099] Expected signal: Temperature value measured by a standard thermometer.

[0100] Output signal: The temperature value measured by the temperature sensor through the microcontroller.

[0101] UART Experiment:

[0102] Expected signal: A packet of data expected to be sent or received.

[0103] Output signal: the data packet actually sent or received through the UART interface.

[0104] Furthermore, the implementation steps of the accuracy evaluation algorithm are as follows: for each type of signal, the root mean square error (RMSE) is used to evaluate the matching degree between the output signal and the expected signal; the RMSE formula is as follows:

[0105]

[0106] Where N is the number of data points, Y i and S i are the expected signal and output signal at the i-th time point respectively;

[0107] Scoring is based on the RMSE value; the smaller the error, the higher the score.

[0108] Furthermore, the implementation steps of the power consumption evaluation algorithm are as follows: when the single chip microcomputer runs a specific task, the current I and voltage U are measured in real time using a sensor, and the dynamic power consumption P0 is calculated; the calculation formula of the dynamic power consumption is:

[0109] P0=UI;

[0110] Scoring is based on dynamic power consumption, with lower power consumption giving higher scores.

[0111] Furthermore, the implementation steps of the performance evaluation algorithm are:

[0112] S1) Calculate the time required for the experimental box to perform a specific task: Use the microcontroller's timer or system clock to obtain an accurate timestamp. The calculation formula is as follows:

[0113] S = St-S0; where S is the execution time, St is the task end time, and S0 is the task start time;

[0114] S2) Calculate the efficiency of the experimental box in completing the number of tasks in a certain period of time: track and count the number of tasks through the log records in the microcontroller, and use the microcontroller's timer or system clock to obtain an accurate timestamp; the calculation formula is as follows:

[0115] P = N / t; where P is efficiency, N is the number of tasks to be processed, and t is the time taken to complete the number of tasks;

[0116] S3) Performance score: Due to the different hardware and software design architectures of the experimental box, the number of tasks that can be processed in parallel is also different; therefore, according to the performance requirements of the experimental box, different weights are assigned to execution time and efficiency to calculate a more realistic performance score; the calculation formula is as follows:

[0117] EH=1 / w1S+w2P;

[0118] Where EH is the performance score; w1 is the weight coefficient of execution time; S is the execution time; w2 is the weight coefficient of efficiency; and P is efficiency.

[0119] In order to better illustrate the technical solution of the university experiment box with an artificial intelligence and automatic evaluation function of the present invention, the following specific examples are used for illustration:

[0120] Temperature measurement experiment:

[0121] Objective of the experiment course: To measure the application temperature through the temperature sensor, and finally transmit the data to the microcontroller for processing and display.

[0122] Experiment box system architecture:

[0123] 1. Hardware layer design:

[0124] The microcontroller module consists of a microcontroller (such as STM32), a memory and an ADC converter.

[0125] Communication connection: The microcontroller is connected to the ADC converter through the I2C or SPI interface, and the microcontroller is connected to the display screen through the GPIO interface.

[0126] Sensor module composition: temperature sensor (such as DS18B20).

[0127] Connection: The temperature sensor is connected to the ADC converter through the I2C or SPI interface. The data is converted into digital signals by the ADC converter and then transmitted to the microcontroller for processing.

[0128] The first communication module consists of: UART, I2C or SPI communication interface.

[0129] Connection: used for data transmission between the microcontroller and the sensor and display screen.

[0130] Display module composition: display screen (such as LCD or OLED).

[0131] Connection: The display screen is connected to the microcontroller through the GPIO interface; it displays the experimental data and evaluation results.

[0132] Interaction module composition: buttons, knobs or touch screen.

[0133] Connection: The interactive module is connected to the microcontroller through the GPIO interface for user input and control.

[0134] Driver layer design:

[0135] The underlying driver library consists of: internal peripheral drivers and external peripheral drivers of the microcontroller.

[0136] Internal peripheral drivers: including serial port protocols, ADC and timers.

[0137] External peripheral driver: including sensor measurement program and communication protocol.

[0138] Implementation: The driver encapsulates the details of hardware operations and provides a unified interface for upper-level applications to call.

[0139] Functions of the driver library management module: responsible for loading and initializing the driver, managing the driver's life cycle, and coordinating resource usage among modules.

[0140] Function of the memory management module: responsible for dynamically allocating and releasing memory, preventing memory leaks, and ensuring the stability of the system during long-term operation.

[0141] (Temperature measurement) The working process of the experimental box is as follows:

[0142] 1. Initialization:

[0143] Hardware: When the system starts, the microcontroller, temperature sensor, display screen and interactive module are initialized.

[0144] Driver: Load and initialize each driver program in the underlying driver library.

[0145] 2. Sensor data collection:

[0146] Hardware: The temperature sensor collects the temperature data of the application target and transmits it to the microcontroller through the I2C or SPI interface.

[0147] Driver: Call external peripheral drivers, such as sensor drivers, to read temperature data.

[0148] 3. Data processing:

[0149] Hardware: After receiving the temperature data, it is converted and then transmitted to the microcontroller for data processing and calculation.

[0150] Driver: Call internal peripheral drivers, such as timing programs and calculation programs, to perform data processing.

[0151] 4. Data shows:

[0152] Hardware: The processed temperature data is displayed on the display screen through the display module.

[0153] Driver: Call the display driver to update the display content.

[0154] 5. User Interaction:

[0155] Hardware: Users input instructions through the interactive module to control the operation of the system.

[0156] Driver: Call the interactive module driver to process user input signals.

[0157] 6. Data evaluation:

[0158] Hardware: The data collection module transmits the operating data of the experimental box to the host computer through the Modbus communication protocol, and then undergoes preprocessing and data classification by the data preprocessing module;

[0159] The operating data of the experimental box is judged through the data judgment module;

[0160] The evaluation results (accuracy score, power consumption score and performance score) are displayed on the display screen through the display module.

[0161] Driver: Call the evaluation algorithm in the data evaluation module to generate the evaluation results. The evaluation algorithm is as follows:

[0162] Accuracy: Compares the temperature sensor measurement to the reading of a standard thermometer, calculates the error using the RMSE algorithm, and outputs an accuracy score.

[0163] Power consumption: Use current sensors and voltage sensors to collect power consumption data of the experiment box during operation and output power consumption scores.

[0164] Performance: Measure the time required for the test box to complete one temperature measurement; measure the time taken by the test box to complete multiple temperature measurements at multiple points and calculate its efficiency, and output a performance score based on the assigned weights.

[0165] In summary, the artificial intelligence university experiment box with automatic evaluation function proposed in this invention aims to provide a powerful, easy-to-use experimental platform with automatic evaluation capabilities for university teaching. The scheme adopts a layered architecture design, which divides the system into a hardware layer, a driver layer, and an evaluation layer, and realizes unified management and evaluation of multiple experiment boxes through a host computer.

[0166] The present invention adopts a layered service architecture to ensure the modularity and scalability of the system, and facilitates users to add new functional modules according to their needs. On the other hand, the present invention provides a stronger hardware platform and intelligent automatic evaluation function. By summarizing and summarizing teaching experience, and formulating objective judgment standards and algorithms, and then designing a unified management of the host computer, respectively calculating, so that it has an automatic evaluation function; it can effectively reduce the burden on teachers, and provide students with more timely feedback, and improve the practical effect of students' experiments. It provides a more powerful experimental platform for college teaching, which has important application value.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0169] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0171] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

[0172] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0173] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. An artificial intelligence university experiment box with automatic evaluation function, characterized by: It includes a hardware layer and a driver layer; the hardware layer includes a single chip microcomputer module, a sensor module, a first communication module, a display module and an interaction module; The MCU module is used to execute program codes, process sensor data, control peripherals to perform specific functions, and exchange data with other modules through communication interfaces; the MCU module includes a MCU and a memory; The sensor module is used to collect the application signal data of the experimental box and transmit the application signal data to the single-chip microcomputer for processing; the sensor module includes a temperature sensor, a light sensor, and an accelerometer; The first communication module is used for data transmission in the experimental box; the first communication module adopts UART, I2C or SPI communication interface; The display module is used to display experimental data and evaluation results; the display module includes a display screen; The interactive module is used for user input and operation control. It detects the user's input signal and transmits it to the microcontroller for processing. The interactive module includes buttons, knobs or touch screens. The driver layer includes an underlying driver library, a driver library management module and a memory management module; The underlying driver library is used to store the drivers of each module; The driver includes an internal peripheral driver and an external peripheral driver of the single-chip microcomputer; The internal peripheral drivers of the MCU include serial port protocol, ADC, DAC and timer; the external peripheral drivers of the MCU include sensor measurement program and communication protocol; The driver library management module is used to manage and initialize different underlying drivers, and realize function calls and resource sharing among modules; The memory management module is used to manage memory allocation and data storage.

2. The university experiment box with artificial intelligence and automatic evaluation function according to claim 1, characterized in that: It also includes a judging layer, which includes a data recording module, a second communication module and a host computer; The data recording module is arranged in the internal circuit of the experimental box and is used to collect the operation signal data of the experimental box; the data recording module includes a current sensor and a voltage sensor; The second communication module is used to establish a communication connection between the host computer and multiple experimental boxes; The host computer is used to receive and pre-process the operation signal data from each experimental box, execute the evaluation algorithm, and display the data; The host computer includes a data preprocessing module and a data evaluation module; The data preprocessing module is used to preprocess the received operation signal data and classify and organize the operation signal data; The data evaluation module has multiple built-in evaluation algorithms, which evaluate the operating data of the experimental box according to the preset evaluation criteria; and transmits the evaluation results to the display screen to display the evaluation results.

3. The university experiment box with artificial intelligence and automatic evaluation function according to claim 2 is characterized in that: The second communication module communicates using the Modbus protocol, specifically using the serial port Master ASCII format.

4. The university experiment box with artificial intelligence and automatic evaluation function according to claim 2 is characterized in that: The preprocessing includes data cleaning or data conversion; the classification and sorting of the operation signal data includes: Distinguish according to the experiment box ID; Record the timestamp of the experimental box running signal data to facilitate timing analysis in subsequent RMSE calculations; Classify the operating signal data of the experimental box and unify the units.

5. The university experiment box with artificial intelligence and automatic evaluation function according to claim 2 is characterized in that: The preset evaluation criteria include the functional signal accuracy, power consumption and performance of the system when performing a specific task; The evaluation algorithms include an accuracy evaluation algorithm, a power consumption evaluation algorithm and a performance evaluation algorithm, and correspond one-to-one to preset evaluation criteria.

6. The artificial intelligence university experiment box with automatic evaluation function according to claim 2 is characterized in that: The pre-set judging criteria are defined as follows: Accuracy: How well the system's output matches the expected signal when performing a specific task; Power consumption: The dynamic power consumption of the system when performing a specific task; Performance: A comprehensive score of the time a system takes to perform a specific task and the number of tasks it processes per unit time.

7. The artificial intelligence university experiment box with automatic evaluation function according to claim 6 is characterized in that: The output signal and the expected signal are the same type of signal in the same experimental box, including digital signals, analog signals and communication signals: The digital signal is a digital signal output by an ADC converter; The analog signal is a high and low level signal output through the GPIO port; The communication signal is a data packet sent through a UART, I2C or SPI communication interface.

8. The university experiment box with artificial intelligence and automatic evaluation function according to claim 5 is characterized by: The implementation steps of the accuracy evaluation algorithm are as follows: for each type of signal, the root mean square error is used to evaluate the matching degree between the output signal and the expected signal; the calculation formula of the root mean square error RMSE is as follows: Where N is the number of data points, Y i and S i are the expected signal and output signal at the i-th time point respectively; Scoring is based on the RMSE value; the smaller the error, the higher the score.

9. The artificial intelligence university experiment box with automatic evaluation function according to claim 5 is characterized by: The implementation steps of the power consumption evaluation algorithm are as follows: when the single chip microcomputer runs a specific task, the current I and voltage U are measured in real time by using a sensor, and the dynamic power consumption P0 is calculated; the calculation formula of the dynamic power consumption is: P0=UI; Scoring is based on dynamic power consumption, with lower power consumption giving higher scores.

10. The artificial intelligence university experiment box with automatic evaluation function according to claim 5, characterized in that: The implementation steps of the performance evaluation algorithm are as follows: S1) Calculate the time required for the experimental box to perform a specific task: Use the microcontroller's timer or system clock to obtain an accurate timestamp. The calculation formula is as follows: S=S t -S0; where S is the execution time, S t is the task end time, S0 is the task start time; S2) Calculate the efficiency of the experimental box in completing the number of tasks in a certain period of time: track and count the number of tasks through the log records in the microcontroller, and use the microcontroller's timer or system clock to obtain an accurate timestamp; the calculation formula is as follows: P = N / t; where P is efficiency, N is the number of tasks to be processed, and t is the time taken to complete the number of tasks; S3) Performance score: According to the performance requirements of the experimental box, different weights are assigned to execution time and efficiency to calculate a more realistic performance score; the calculation formula is as follows: EH=1 / w1S+w2P; Wherein, EH is the performance score; w1 is the weight coefficient of execution time; S is the execution time; w2 is the weight coefficient of efficiency; P is efficiency; and w1+w2=1.

Images