Simulation teaching device

Abstract

An embodiment of the present application provides a simulation teaching device, which includes a 5G simulation platform and a 5G smart car. The 5G simulation platform includes a 5G simulation practice module and a 5G vehicle networking scenario simulation module. The 5G simulation practice module is used to provide simulation practice teaching of 5G knowledge. The 5G vehicle networking scenario simulation module is communicatively connected to the 5G smart car to simulate the 5G vehicle networking scenario and control the operation of the 5G smart car to provide simulation practice teaching of 5G vehicle networking knowledge, which can realize low-cost engineering practice teaching of multi-disciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology.

Description

Technical Field

[0001] The present application relates to the technical field of teaching equipment, and in particular to a simulation teaching device. Background Art

[0002] 5G (the 5th Generation), artificial intelligence, and the Internet of Things are emerging industries. To adapt to the development of society, various universities have also opened courses on 5G, artificial intelligence, and the Internet of Things. However, since schools focus on theoretical teaching, it is difficult to meet the professional needs of society in terms of engineering practice.

[0003] In order to enhance the competitiveness of colleges and universities, relevant departments require college students to have the ability of engineering practice, but colleges and universities do not have the environment of 5G laboratories. With the continuous updating and iteration of communication technology, communication equipment is also constantly replaced. If colleges and universities deploy a set of communication equipment for engineering practice teaching, the cost is too expensive. Therefore, how to realize the engineering practice teaching of multi-disciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology under the condition that the equipment cost allows has become an urgent problem to be solved in the industry. Summary of the invention

[0004] The embodiment of the present application provides a simulation teaching device to solve the defect in the prior art that it is impossible to realize engineering practice teaching of multi-disciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology when the equipment cost permits, and to realize low-cost engineering practice teaching of multi-disciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology.

[0005] In a first aspect, an embodiment of the present application provides a simulation teaching device, comprising:

[0006] 5G simulation platform and 5G smart car;

[0007] The 5G simulation platform includes a 5G simulation practice module and a 5G vehicle networking scenario simulation module;

[0008] The 5G simulation practice module is used to provide simulation practice teaching of 5G knowledge;

[0009] The 5G Internet of Vehicles scenario simulation module is communicatively connected to the 5G smart car, and is used to simulate the 5G Internet of Vehicles scenario and control the operation of the 5G smart car to provide simulation practical teaching of 5G Internet of Vehicles knowledge.

[0010] Optionally, according to a simulation teaching device of an embodiment of the present application, the 5G simulation practice module includes:

[0011] Engineering practice unit, which is used to conduct simulation practice teaching of the operation process in 5G engineering practice based on 5G engineering practice examples;

[0012] Theory practice unit, used for simulation practice teaching of 5G theoretical knowledge based on 5G theory practice examples;

[0013] Among them, the simulation practice teaching corresponding to the engineering practice unit and the theoretical practice unit is realized through human-computer interaction.

[0014] Optionally, according to the simulation teaching device of one embodiment of the present application, the engineering practice unit includes:

[0015] The experimental background subunit is used to provide the cell planning, cell parameters, neighboring cell relations and neighboring cell information corresponding to the base station commissioning process as the background of engineering practice;

[0016] The station survey planning configuration subunit is used to realize the simulation practice teaching of the configuration process corresponding to the station survey planning stage;

[0017] The network deployment configuration subunit is used to implement simulation practice teaching of the configuration process corresponding to the network deployment stage;

[0018] The commissioning subunit is activated to verify whether the configurations in the site survey planning subunit and the network deployment subunit are correct. If the configurations are incorrect, the user is prompted to return to reconfigure the site survey planning and network deployment.

[0019] The business verification configuration subunit is used to implement the simulation practice teaching of the configuration process corresponding to the business verification stage.

[0020] Optionally, according to a simulation teaching device of an embodiment of the present application, the theory practice unit includes:

[0021] 5G interface protocol stack subunit, used to realize simulation practice teaching of 5G interface protocol stack knowledge;

[0022] 5G physical layer process subunit, used to realize simulation practice teaching of 5G physical layer process knowledge;

[0023] 5G network architecture subunit, used to realize simulation practice teaching of 5G network architecture knowledge;

[0024] The 5G signaling process sub-unit is used to realize the simulation practice teaching of 5G signaling process knowledge.

[0025] Optionally, according to a simulation teaching device of an embodiment of the present application, the 5G Internet of Vehicles scenario simulation module includes:

[0026] Data acquisition module, used to receive images collected by the 5G smart car;

[0027] The vehicle networking algorithm implementation module is used to determine the target image based on the image recognition model and the positioning algorithm, and control the operation of the 5G smart car;

[0028] The image recognition model is obtained after training based on image sample data.

[0029] Optionally, according to a simulation teaching device of an embodiment of the present application, in the process of training an image recognition model based on image sample data, the minimum value of the loss function is determined based on a small batch gradient descent method.

[0030] Optionally, according to the simulation teaching device of one embodiment of the present application, the determining of the target image based on the image recognition model and the positioning algorithm includes:

[0031] Determining a preliminary target image based on the image recognition model;

[0032] Build a map based on the simultaneous positioning and mapping SLAM algorithm to determine the distance between the target corresponding to the preliminary target image and the 5G smart car;

[0033] Based on the distance between the target and the 5G smart car, a final target image is determined from the preliminary target images.

[0034] Optionally, according to the simulation teaching device of an embodiment of the present application, the determining of the final target image from the preliminary target images based on the distance between the target and the 5G smart car includes:

[0035] Based on the comparison result between the distance between the target and the 5G smart car and a preset threshold, a final target image is determined from the preliminary target images;

[0036] The preset threshold is determined based on the distance range within which the camera of the 5G smart car can capture clear images.

[0037] Optionally, according to a simulation teaching device of an embodiment of the present application, the 5G smart car runs based on a loaded motion control program and control instructions of a 5G simulation platform.

[0038] Optionally, according to the simulation teaching device of an embodiment of the present application, the configuration process corresponding to the site survey planning stage includes a configuration process of a radio frequency unit;

[0039] The configuration process corresponding to the network deployment stage includes the configuration process of the operation and maintenance center OMC equipment, core network equipment and indoor baseband processing unit BBU equipment;

[0040] The configuration process corresponding to the service verification phase includes the configuration process of test parameters and terminal equipment.

[0041] The simulation teaching device provided in the embodiment of the present application provides simulation practice teaching of 5G knowledge through the 5G simulation practice module. The 5G vehicle networking scenario simulation module connected to the 5G smart car simulates the 5G vehicle networking scenario and controls the operation of the 5G smart car to provide simulation practice teaching of 5G vehicle networking knowledge. It can realize low-cost engineering practice teaching of multi-disciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a structural schematic diagram of a simulation teaching device provided in an embodiment of the present application;

[0044] Figure 2 It is a schematic diagram of the overall structure of a simulation teaching device provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the architecture of a 5G simulation platform of a simulation teaching device provided in an embodiment of the present application;

[0046] Figure 4 It is a schematic diagram of an interactive interface of a station survey planning configuration process of a simulation teaching device provided in an embodiment of the present application;

[0047] Figure 5 It is a schematic diagram of an interactive interface of a network deployment configuration process of a simulation teaching device provided in an embodiment of the present application;

[0048] Figure 6 It is a schematic diagram of an interactive interface for the commissioning and debugging process of a simulation teaching device provided in an embodiment of the present application;

[0049] Figure 7 It is a schematic diagram of an interactive interface of a business verification configuration process of a simulation teaching device provided in an embodiment of the present application;

[0050] Figure 8 It is a schematic diagram of an interactive interface of a 5G interface protocol stack configuration process of a simulation teaching device provided in an embodiment of the present application;

[0051] Fig. 9 It is a schematic diagram of an interactive interface of a 5G physical layer process configuration process of a simulation teaching device provided in an embodiment of the present application;

[0052] Fig.10 It is a schematic diagram of an interactive interface of a 5G networking architecture configuration process of a simulation teaching device provided in an embodiment of the present application;

[0053] Fig.11 It is a schematic diagram of an interactive interface of a 5G signaling flow configuration process of a simulation teaching device provided in an embodiment of the present application;

[0054] Fig.12 It is a schematic diagram of the interaction framework between a 5G simulation platform and a 5G smart car of a simulation teaching device provided in an embodiment of the present application;

[0055] Fig.13 It is a schematic diagram of a neural network structure of a simulation teaching device provided in an embodiment of the present application;

[0056] Fig.14 It is a schematic diagram of a target image determination process of a simulation teaching device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0058] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] The embodiment of the present application provides a simulation teaching device to solve the defect in the prior art that it is impossible to realize engineering practice teaching of multidisciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology when the equipment cost permits.

[0061] Figure 1 This is a schematic diagram of the structure of the simulation teaching device provided in the embodiment of the present application. Figure 1 As shown, the device includes: a 5G simulation platform 110 and a 5G smart car 120;

[0062] The 5G simulation platform includes a 5G simulation practice module 1101 and a 5G Internet of Vehicles scenario simulation module 1102;

[0063] The 5G simulation practice module 1101 is used to provide simulation practice teaching of 5G knowledge;

[0064] The 5G Internet of Vehicles scenario simulation module 1102 is communicatively connected to the 5G smart car 120 for simulating the 5G Internet of Vehicles scenario and controlling the operation of the 5G smart car to provide simulation practical teaching of 5G Internet of Vehicles knowledge.

[0065] Specifically, the development of the simulation teaching device provided in the embodiment of the present application is divided into three stages. The first stage is the refinement of 5G knowledge, which uses animation, interactive scenes and other methods to present 5G knowledge and form a basic simulation teaching platform. The second stage is to simulate the 5G Internet of Vehicles scenario, build 5G base stations, 5G car models and Internet of Things communication modules, design communication circuit boards, and develop application scenarios for 5G Internet of Vehicles. The third stage is to apply image recognition in artificial intelligence to 5G cars to realize functions such as remote driving, automatic obstacle avoidance, and vehicle-road collaboration of 5G cars.

[0066] Figure 2 The overall structure diagram of a simulation teaching device provided in the embodiment of the present application is as follows: Figure 2 As shown, the simulation teaching device provided in the embodiment of the present application includes, in addition to the 5G simulation platform 110 and the 5G smart car 120, a 5G simulation base station, a simulation RSU (Road Side Unit) and a mobile terminal, which are used to simulate the actual communication architecture so that students can have a more intuitive understanding of the principles of the 5G Internet of Vehicles communication scenario. The 5G simulation platform 110 can be deployed in the cloud and provide an open API (Application Program Interface) interface. The 5G smart car 120 can be controlled through the API interface to realize the application scenarios of the 5G Internet of Vehicles, such as vehicle-road collaboration, automatic driving, and automatic obstacle avoidance. Of course, the 5G simulation platform 110 can also be deployed on a terminal device, and the embodiment of the present application does not specifically limit this.

[0067] The 5G simulation platform 110 can simulate the functions of the core network and provide simulation practice of 5G theoretical knowledge. The construction of this platform is to extract 5G theoretical knowledge to form a practical operation course. The design of the underlying circuit board also imitates real wireless devices, and the wireless devices are responsible for the realization of the air interface function of wireless communication. The 5G smart car 120 is developed using the mature Raspberry Pi ROS development board. Functions such as obstacle avoidance between vehicles are all implemented by issuing instructions from the 5G simulation platform 110. The mobile terminal (actually a SIM card) can simulate the operation of the vehicle, use a 3D printer to print 5G simulation base stations and simulation RSUs, and use the Internet of Things technology to interconnect devices.

[0068] Students can do engineering practice based on this simulation teaching device. For example, based on the simulation practice teaching examples of 5G knowledge provided by the 5G simulation practice module 1101, they can master 5G engineering practice and theoretical knowledge in the process of practice. Based on the simulation practice examples of 5G vehicle networking knowledge provided by the 5G vehicle networking scenario simulation module 1102, they can master the Internet of Things and artificial intelligence related technologies in the process of practice, providing support for colleges and universities to cultivate comprehensive multidisciplinary talents.

[0069] The simulation teaching device provided in the embodiment of the present application provides simulation practice teaching of 5G knowledge through the 5G simulation practice module. The 5G vehicle networking scenario simulation module connected to the 5G smart car simulates the 5G vehicle networking scenario and controls the operation of the 5G smart car to provide simulation practice teaching of 5G vehicle networking knowledge. It can realize low-cost engineering practice teaching of multi-disciplinary knowledge such as 5G communication knowledge, artificial intelligence technology, and Internet of Things technology.

[0070] Based on the above embodiment, the 5G simulation practice module includes:

[0071] Engineering practice unit, which is used to conduct simulation practice teaching of the operation process in 5G engineering practice based on 5G engineering practice examples;

[0072] Theory practice unit, used for simulation practice teaching of 5G theoretical knowledge based on 5G theory practice examples;

[0073] Among them, the simulation practice teaching corresponding to the engineering practice unit and the theoretical practice unit is realized through human-computer interaction.

[0074] Specifically, all practical steps in 5G engineering practice are designed based on 5G engineering experience, and simulation practice teaching of 5G theoretical knowledge is carried out through theoretical practice units based on 5G theoretical practice examples; 5G theoretical practice is designed based on 5G theoretical knowledge points, and simulation practice teaching of 5G theoretical knowledge is carried out through theoretical practice units based on 5G theoretical practice examples. Students perform practical operations based on the above two practice units to master 5G theoretical knowledge and 5G engineering operation steps. The above practical operation processes are all carried out through human-computer interaction, and the whole process will be guided by animated characters to achieve user-friendly operation.

[0075] Figure 3 A schematic diagram of the architecture of a 5G simulation platform of a simulation teaching device provided in an embodiment of the present application, such as Figure 3 As shown, the 5G simulation platform architecture is divided into a data source layer, a data collection layer, a data warehouse, a data analysis layer, and an application layer, and their functions are as follows:

[0076] Data source: Collect the data that the platform needs to analyze. This data may be obtained from various industries. In addition, there are also teaching experiment data and log data generated by the platform.

[0077] Data collection layer: collects real-time data and offline data through Flume, Kafka, and Sqoop plug-ins in big data technology and transmits them to the data warehouse.

[0078] Data warehouse: clean and store the data transmitted from the data collection layer.

[0079] Data analysis layer: Spark and Flink big data components are used to process data, and the Tensorflow framework is used to process artificial intelligence algorithm models. The algorithm engine supports all data models and supports upper-level applications after data analysis.

[0080] Application layer: used to display platform functions, which mainly consist of engineering simulation practice and theoretical simulation practice.

[0081] The simulation teaching device provided in the embodiment of the present application performs simulation practice teaching of the operation process in 5G engineering practice based on 5G engineering practice examples through the engineering practice unit, and performs simulation practice teaching of 5G theoretical knowledge based on 5G theoretical practice examples through the theoretical practice unit. The simulation practice teaching corresponding to the engineering practice unit and the theoretical practice unit are both realized through human-computer interaction. Students do not need to go to the equipment site to observe and practice to achieve the purpose of mastering 5G technology, which not only achieves the purpose of practical teaching but also reduces teaching costs.

[0082] Based on the above embodiment, the engineering practice unit includes:

[0083] The experimental background subunit is used to provide the cell planning, cell parameters, neighboring cell relations and neighboring cell information corresponding to the base station commissioning process as the background of engineering practice;

[0084] The station survey planning configuration subunit is used to realize the simulation practice teaching of the configuration process corresponding to the station survey planning stage;

[0085] The network deployment configuration subunit is used to implement simulation practice teaching of the configuration process corresponding to the network deployment stage;

[0086] The commissioning subunit is activated to verify whether the configurations in the site survey planning subunit and the network deployment subunit are correct. If the configurations are incorrect, the user is prompted to return to reconfigure the site survey planning and network deployment.

[0087] The business verification configuration subunit is used to implement the simulation practice teaching of the configuration process corresponding to the business verification stage.

[0088] Specifically, engineering practice design includes several major work modules: experimental background, site survey and planning, network deployment, commissioning and testing, and business verification.

[0089] In the experimental background, the cell planning, cell parameters, neighboring cell relations, neighboring cell information and other information involved in the base station commissioning and testing process will be presented in the form of a table. Based on this large background, students will carry out subsequent site survey planning and configuration and network deployment configuration processes.

[0090] In the site survey planning, students need to design the antenna height, downtilt angle, equipment selection, and fiber optic module connection of the three RF units. Figure 4 A schematic diagram of an interactive interface for a simulation teaching device for a site survey planning configuration process provided in an embodiment of the present application is shown in FIG. Figure 4 As shown in the figure, when students enter the configuration interface corresponding to the survey station planning, there will be an animated character to guide them, so as to reduce the difficulty of operation for students and enable them to better understand and master the entire configuration process. There will be an animated character to guide them in the interactive interface corresponding to engineering practice and theoretical practice. In the subsequent introduction, this design will not be repeated.

[0091] After the site survey and planning is completed, network deployment begins. Figure 5 A schematic diagram of an interactive interface for a network deployment configuration process of a simulation teaching device provided in an embodiment of the present application, such as Figure 5 As shown in the figure, in network deployment, students need to configure the parameters of OMC (Operation and Maintenance Center), core network equipment, and BBU (Building Baseband Unit). OMC needs to set the IP (Internet Protocol) address and routing relationship, and the core network equipment also needs to configure the IP and routing relationship to OMC and business servers. The BBU part needs to select equipment, plan boards, install GPS (Global Positioning System), plan cell networks, plan transmission, and upgrade versions. The parameter settings for network deployment are simulated based on the existing network equipment. Each parameter will have an impact on the entire network. If the configuration is wrong, the entire network will not be connected.

[0092] After the network configuration is completed, enter the commissioning test. Figure 6 A schematic diagram of an interactive interface for the commissioning and debugging process of a simulation teaching device provided in an embodiment of the present application, such as Figure 6 As shown in the figure, commissioning is to verify whether the parameter settings and routing relationships in the site survey planning and network deployment are configured correctly. If the configuration is wrong, it will be highlighted in red to prompt the operator, and the operator will return to reconfigure the site survey planning and network deployment based on the error prompt.

[0093] Business verification is to determine whether the terminal can communicate with the network after the network is connected. Figure 7 A schematic diagram of an interactive interface for a business verification configuration process of a simulation teaching device provided in an embodiment of the present application, such as Figure 7 As shown in the figure, students need to complete the configuration of test parameters and terminal equipment according to the prompts of the animated character. After the configuration is completed, the terminal can test the network performance by downloading FTP (File Transfer Protocol) data packets. At this point, the entire experimental process is simulated and completed. During the entire experimental process, students have an in-depth understanding of the advanced technology of 5G, and they do not need to go to the equipment site to observe and practice to achieve the purpose of mastering 5G technology.

[0094] The simulation teaching device provided in the embodiment of the present application provides the cell planning, cell parameters, neighboring cell relations and neighboring cell information corresponding to the base station commissioning and debugging process through the experimental background subunit as the background of engineering practice. The survey station planning configuration subunit and the network deployment configuration subunit respectively realize the simulation practice teaching of the configuration process corresponding to the survey station planning stage and the network deployment stage. The commissioning and debugging subunit verifies whether the configuration in the survey station planning subunit and the network deployment subunit is correct. If the configuration is wrong, it prompts to return to reconfigure the survey station planning and network deployment. The business verification configuration subunit realizes the simulation practice teaching of the configuration process corresponding to the business verification stage. Students do not need to go to the equipment site to observe and practice to achieve the purpose of mastering all the operation processes in the 5G engineering practice process, which not only ensures the practical teaching effect but also reduces the teaching cost.

[0095] Based on the above embodiment, the theory-practice unit includes:

[0096] 5G interface protocol stack subunit, used to realize simulation practice teaching of 5G interface protocol stack knowledge;

[0097] Specifically, in order to establish a theoretical practice unit, the embodiment of the present application designs the knowledge in the book into an experimental method to facilitate students' operation and understanding. First, the entire knowledge system of 5G is constructed, and then it is broken down into modules according to the knowledge system, and a design is made for each knowledge module.

[0098] Among them, the 5G interface protocol stack is a subunit that combines the protocol layer content of the protocol stack with the business flow, so that students can understand the interfaces between network elements, how the interface protocols are composed, which protocol stacks the network elements use to communicate, and how their business data flows through the protocol layers through the practical design of this part. The embodiment of this application adopts two dimensions to design the knowledge module of the protocol stack. One dimension is from the perspective of the network element. Each network element has its own protocol stack, and different protocol stacks communicate in a protocol-peer manner. What students need to master is the hierarchical relationship of the protocol stack. The other dimension is to think from the perspective of data flow, without considering the relationship between network elements, but only considering how the data is finally communicated through the protocol. The combination of the two dimensions can enable students to have an in-depth understanding of the entire protocol stack.

[0099] Figure 8 A schematic diagram of an interactive interface of a 5G interface protocol stack configuration process of a simulation teaching device provided in an embodiment of the present application, such as Figure 8 As shown, students can select different service types and corresponding interfaces corresponding to 5G through the service type selection control in the interactive interface, and then configure the protocol stack content in the lower part of the interface. After the configuration is completed, you can verify whether the configuration result is correct by clicking the corresponding control (not shown in the figure). Of course, commonly used operation buttons such as submit and cancel can also be set in the above-mentioned interactive interface to facilitate student operation, and the embodiments of the present application do not make specific limitations on this. Based on this, students can continue to familiarize themselves with and master the relevant knowledge of the interface protocol stack corresponding to each 5G service type in the process of practical operation. Of course, corresponding buttons such as submit, cancel, and verify can also be set in the interactive interface of the subsequent sub-unit, which will not be repeated in the subsequent embodiments.

[0100] 5G physical layer process subunit, used to realize simulation practice teaching of 5G physical layer process knowledge;

[0101] Specifically, a process-based design scheme is adopted for the abstract 5G physical layer process. The knowledge points of the 5G physical layer process are gradually decomposed in the process. Students will be prompted and guided by animated characters during the operation. After completing the operation, they will basically have mastered the 5G physical layer process.

[0102] Fig. 9 A schematic diagram of an interactive interface for a 5G physical layer configuration process of a simulation teaching device provided in an embodiment of the present application, such as Fig. 9 As shown, students need to configure the channel mapping relationship according to the prompts of the animated character and verify whether it is correct, and master the physical layer process of 5G during practical exercises.

[0103] 5G network architecture subunit, used to realize simulation practice teaching of 5G network architecture knowledge;

[0104] Specifically, for the complex 5G networking architecture, the 5G networking architecture subunit must implement open and flexible configuration solutions to realize various application scenarios of independent networking and non-independent networking. In different application scenarios, students are required to build the networking architecture of the core network, the networking architecture of the access network, and the networking architecture of the protocol module. Through the 5G networking architecture subunit, students can understand how 5G is networked, have a clear understanding of 5G independent networking and non-independent networking, and understand how different network elements work.

[0105] Fig.10 A schematic diagram of an interactive interface for a 5G networking architecture configuration process of a simulation teaching device provided in an embodiment of the present application, such as Fig.10 As shown in the figure, students can choose network element interfaces to import according to different scenarios of independent networking and non-independent networking, and conduct networking exercises. The error window at the bottom of the interface will report errors in real time so that corrections can be made. Based on this, students can gradually master how 5G is networked during practical exercises, have a clear understanding of 5G independent networking and non-independent networking, and master how different network elements work.

[0106] The 5G signaling process sub-unit is used to realize the simulation practice teaching of 5G signaling process knowledge.

[0107] Specifically, the 5G signaling process involves the signaling process of independent networking and non-independent networking. The process is very complicated and difficult to master, but the signaling process is the key to communication troubleshooting. If you only learn theoretical knowledge, it is difficult to have an in-depth understanding of the overall process. The embodiment of the present application combines the signaling process with the business process to create an application scenario. During the operation, students can master the messages of the signaling process between different network elements and the key content of the protocol stack, and prepare for troubleshooting in engineering practice.

[0108] Fig.11 A schematic diagram of an interactive interface for a 5G signaling flow configuration process of a simulation teaching device provided in an embodiment of the present application, such as Fig.11 As shown, students need to configure the signaling process of each communication step in independent networking and non-independent networking, including the corresponding signaling messages and interaction directions. The communication steps include system message acquisition, RRC (Radio Resource Control) connection, authentication process, access layer encryption, RRC reconfiguration, PDU (Protocol Data Unit) session establishment and measurement switching process. By configuring the signaling process of each communication step, students can master the key contents of the message and protocol stack of the signaling process between different network elements.

[0109] The simulation teaching device provided in the embodiment of the present application realizes the simulation practical teaching of 5G interface protocol stack knowledge, 5G physical layer process knowledge, 5G networking architecture knowledge and 5G signaling process knowledge respectively through the 5G interface protocol stack subunit, the 5G physical layer process subunit, the 5G networking architecture subunit and the 5G signaling process subunit. Students do not need to go to the equipment site to observe and practice to achieve the purpose of mastering 5G theoretical knowledge, which not only ensures the theoretical teaching effect but also reduces the teaching cost.

[0110] Based on the above embodiment, the 5G Internet of Vehicles scenario simulation module includes:

[0111] Data acquisition module, used to receive images collected by the 5G smart car;

[0112] The vehicle networking algorithm implementation module is used to determine the target image based on the image recognition model and the positioning algorithm, and control the operation of the 5G smart car;

[0113] The image recognition model is obtained after training based on image sample data.

[0114] Specifically, the 5G smart car used in the application scenario of 5G Internet of Vehicles adopts the mainstream robot communication framework - ROS (Robot Operating System) framework, which is an open source meta-operating system for robots and provides operating system application services, including hardware abstraction, underlying device control, implementation of common functions, inter-process messaging, and package management. It also provides the tools and library functions needed to obtain, compile, write and run code across computers.

[0115] The underlying driver board of the 5G smart car includes a CPU, memory, video interface, communication interface, and voice interface, which not only provides computing and storage units but also provides various scalable interfaces. On this basis, the embodiment of this application develops an automatic obstacle avoidance algorithm and transplants it to the driver board to control the smart car to automatically avoid obstacles as a teaching example. Students can learn the algorithm in this example or write their own corresponding algorithm, so as to master the relevant knowledge of the Internet of Things and artificial intelligence in the process of practice.

[0116] Fig.12 A schematic diagram of the interactive framework of a 5G simulation platform and a 5G smart car of a simulation teaching device provided in an embodiment of the present application, such as Fig.12As shown, the 5G vehicle networking scenario simulation module includes a data acquisition module for receiving images collected by the 5G smart car. The 5G smart car uses a high-definition binocular camera to collect image data, and transmits the image data to the data acquisition module through the communication module. The data acquisition module uses a GPU to perform pixel processing on the image and saves the pixel data of each image into the database.

[0117] The 5G Internet of Vehicles scenario simulation module also includes an Internet of Vehicles algorithm implementation module, which is used to determine the target image based on the image recognition model and positioning algorithm, and control the operation of the 5G smart car. The teaching example provided in the embodiment of this application uses deep learning algorithm + radar scanning to implement the Internet of Vehicles application scenario, providing technical support for image tracking and intelligent obstacle avoidance of 5G Internet of Vehicles. For the selection of models, the example uses Fig.13 The neural network structure shown in the figure inputs different images into the neural network structure, and learns the similarity function between the two images through the deep network. The principle of the model is to use the neural network to extract the image description operator, obtain the feature vector, and then use the feature vectors of the two images to judge the similarity. It is just that the convolutional network is used to extract features, and the feature vector is used to construct the loss function and perform network training. The above-mentioned neural network structure is used to output 1000 features for each picture for target picture comparison. Of course, the number of features can be freely selected according to the actual situation, and the embodiment of the present application does not make specific restrictions on this.

[0118] As for the relevant parameter settings of the network, they are shown in Table 1 below:

[0119] name illustrate Input image size 224*224 Preprocessing Subtract the mean Convolution Kernel 3*3，1*1 padding 1for3*3 Max-pooling 2*2 s-2 Activation Function ReLU

[0120] It is worth noting that the above parameter settings are only examples, and students can choose other settings during practice, and the embodiments of the present application do not specifically limit this.

[0121] The simulation teaching device provided in the embodiment of the present application receives images collected by the 5G smart car through the data acquisition module. The Internet of Vehicles algorithm implementation module determines the target image based on the image recognition model and the positioning algorithm, and controls the operation of the 5G smart car. It can realize the simulation teaching of the 5G Internet of Vehicles application scenarios, which not only ensures the practical teaching effect but also reduces the teaching cost.

[0122] Based on the above embodiment, in the process of training an image recognition model based on image sample data, the minimum value of the loss function is determined based on a mini-batch gradient descent method.

[0123] Specifically, given a photo A of a target, if another photo P of the same target is given, the distance between the model's output vectors f(A) and f(P) should be relatively small. If another photo N of another target is given, the distance between the model's output vectors f(A) and f(N) will be relatively large. So d(A,P) <d(A,N)。

[0124] Based on this goal, we get the loss function, where a is the target photo, p is a different photo of the same target, and n is a non-target photo. By traversing all triples (a, p, n), we can find the minimum value of the loss function according to the following formula:

[0125]

[0126] in the formula and are the output vectors corresponding to the i-th target photo a, different photos of the same target p, and non-target photo n, respectively. i is the photo number, and α is a hyperparameter that can avoid the model outputting all zero vectors.

[0127] The optimization function uses a mini-batch gradient descent method:

[0128] Here we set batchsize = 10 and the number of samples m = 1000

[0129] The pseudo code form is:

[0130]

[0131] Among them, θ j are the image parameters generated during the calculation process, i represents the image index value, j represents the number of iterations, and h θ (x (k) ) is the predicted value corresponding to the picture, y (k) is the true value corresponding to the image, Refers to the pixel value of the input image.

[0132] By calculating the Euclidean distance between the two vectors output by the model, we can get the similarity between the two input images. If the input images X1 and X2 are the same target, the Euclidean distance between the two one-dimensional vectors output by the model is small; if the input images X1 and X2 are not the same target, the Euclidean distance between the two one-dimensional vectors output by the model is large. The above method can improve the self-learning ability, and the accuracy of image recognition can be greatly improved through continuous iteration.

[0133] This deep network is used to identify and track targets. Given a clear picture, the recognition accuracy can reach 99% after testing.

[0134] The simulation teaching device provided in the embodiment of the present application, in the process of training the image recognition model based on the image sample data, determines the minimum value of the loss function based on the small batch gradient descent method, which can ensure the accuracy of model recognition, thereby ensuring the practical teaching effect and reducing the teaching cost.

[0135] Based on the above embodiment, the method of determining the target image based on the image recognition model and the positioning algorithm includes:

[0136] Determining a preliminary target image based on the image recognition model;

[0137] Build a map based on the simultaneous localization and mapping (SLAM) algorithm to determine the distance between the target corresponding to the preliminary target image and the 5G smart car;

[0138] Based on the distance between the target and the 5G smart car, a final target image is determined from the preliminary target images.

[0139] Specifically, the preliminary target image is determined based on the image recognition model. For the blurred images with incorrect recognition, the Internet of Vehicles algorithm implementation module will label the images according to the radar scanning positioning. Specifically, the SLAM algorithm of laser radar positioning is used to build the map. At the same time, the positioning of the 5G smart car is performed during movement, so that the distance between the target and the smart car can be determined. The distance calculation formula is:

[0140]

[0141] Where T represents transpose, x i and x j are the vectors composed of the i-th observation feature and the j-th observation feature respectively, and S is the sample covariance matrix.

[0142] Based on the distance between the target and the 5G smart car, the final target image can be determined from the preliminary target image, so that image recognition and error correction can be achieved.

[0143] The simulation teaching device provided in the embodiment of the present application determines a preliminary target image based on the image recognition model, builds a map based on the simultaneous localization and mapping SLAM algorithm, determines the distance between the target corresponding to the preliminary target image and the 5G smart car, and determines the final target image from the preliminary target image based on the distance between the target and the 5G smart car. This device can realize image recognition error correction and further ensure the accuracy of model recognition, which not only ensures the practical teaching effect but also reduces the teaching cost.

[0144] Based on the above embodiment, determining the final target image from the preliminary target images based on the distance between the target and the 5G smart car includes:

[0145] Based on the comparison result between the distance between the target and the 5G smart car and a preset threshold, a final target image is determined from the preliminary target images;

[0146] The preset threshold is determined based on the distance range within which the camera of the 5G smart car can capture clear images.

[0147] Specifically, Fig.14 FIG. 1 is a schematic diagram of a target image determination process of a simulation teaching device provided in an embodiment of the present application. Fig.14 As shown, the monocular camera used in the embodiment of the present application can take clear pictures within a range of 7 meters. If it exceeds 7 meters, the picture will be particularly blurry. Therefore, after defining the distance between the car and the target to be greater than 7 meters (i.e., the preset threshold), it is judged that the camera cannot correctly capture a clear picture. Therefore, when the camera captures a picture at a distance beyond 7 meters and recognizes it as a target picture, it will be judged as a non-target picture based on the distance label data, thereby correcting errors in image recognition.

[0148] The simulation teaching device provided in the embodiment of the present application determines the final target image from the preliminary target image based on the comparison result of the distance between the target and the 5G smart car and the preset threshold, and can realize image recognition error correction, further ensure the accuracy of model recognition, which not only ensures the practical teaching effect but also reduces the teaching cost.

[0149] Based on the above embodiments, the 5G smart car runs based on the loaded motion control program and the control instructions of the 5G simulation platform.

[0150] Specifically, the motion control program can adopt the program in the teaching example of the embodiment of this application, or it can be a program developed by the students themselves; the control instructions of the 5G simulation platform can also adopt the program in the teaching example of the embodiment of this application, or it can be implemented by the program developed by the students themselves. Based on this, it can be ensured to the greatest extent that students can flexibly use the teaching content for simulation practice, and then master the artificial intelligence, Internet of Things and 5G communication technologies in the 5G Internet of Vehicles scenario.

[0151] The simulation teaching device provided in the embodiment of the present application, wherein the 5G smart car runs based on the loaded motion control program and the control instructions of the 5G simulation platform, can maximize the guarantee that students can flexibly use the teaching content for simulation practice, and thus master artificial intelligence, Internet of Things and 5G communication technologies in the 5G vehicle networking scenario.

[0152] Based on the above embodiment, the configuration process corresponding to the site survey planning stage includes a configuration process of a radio frequency unit;

[0153] The configuration process corresponding to the network deployment stage includes the configuration process of the operation and maintenance center OMC equipment, core network equipment and indoor baseband processing unit BBU equipment;

[0154] The configuration process corresponding to the service verification phase includes the configuration process of test parameters and terminal equipment.

[0155] The configuration processes corresponding to the site survey planning stage, the network deployment stage, and the service verification stage have been described in detail in the aforementioned embodiments and will not be described again here.

[0156] The simulation teaching device provided in the embodiment of the present application, the configuration process corresponding to the site survey and planning stage includes the configuration process of the radio frequency unit, the configuration process corresponding to the network deployment stage includes the configuration process of the operation and maintenance center OMC equipment, core network equipment and indoor baseband processing unit BBU equipment, and the configuration process corresponding to the service verification stage includes the configuration process of test parameters and terminal equipment, which can enable a comprehensive and systematic grasp of the detailed configuration steps in the 5G engineering practice process, which not only ensures the practical teaching effect but also reduces the teaching cost.

[0157] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0158] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-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, server, or network device, etc.) or a processor (processor) 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 (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0159] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A simulation teaching device, characterized in that: include: 5G simulation platform and 5G smart car; The 5G simulation platform includes a 5G simulation practice module and a 5G vehicle networking scenario simulation module; The 5G simulation practice module is used to provide simulation practice teaching of 5G knowledge; The 5G Internet of Vehicles scenario simulation module is communicatively connected to the 5G smart car, and is used to simulate the 5G Internet of Vehicles scenario and control the operation of the 5G smart car to provide simulation practice teaching of 5G Internet of Vehicles knowledge; The 5G Internet of Vehicles scenario simulation module includes an Internet of Vehicles algorithm implementation module, which is used to determine the target image from the image collected by the 5G smart car based on the image recognition model and the positioning algorithm, and control the operation of the 5G smart car; wherein the image recognition model is obtained after training based on the image sample data; in the process of training the image recognition model based on the image sample data, the minimum value of the loss function is determined based on the small batch gradient descent method; The determining of the target image based on the image recognition model and the positioning algorithm includes: Determining a preliminary target image based on the image recognition model; Build a map based on the simultaneous positioning and mapping SLAM algorithm to determine the distance between the target corresponding to the preliminary target image and the 5G smart car; Based on the distance between the target and the 5G smart car, determine the final target image from the preliminary target images; The determining the final target image from the preliminary target images based on the distance between the target and the 5G smart car includes: Based on the comparison result between the distance between the target and the 5G smart car and a preset threshold, a final target image is determined from the preliminary target images; The preset threshold is determined based on the distance range within which the camera of the 5G smart car can capture clear images.

2. The simulation teaching device according to claim 1, characterized in that: The 5G simulation practice module includes: Engineering practice unit, which is used to conduct simulation practice teaching of the operation process in 5G engineering practice based on 5G engineering practice examples; Theory practice unit, used for simulation practice teaching of 5G theoretical knowledge based on 5G theory practice examples; Among them, the simulation practice teaching corresponding to the engineering practice unit and the theoretical practice unit is realized through human-computer interaction.

3. The simulation teaching device according to claim 2, characterized in that: The engineering practice unit includes: The experimental background subunit is used to provide the cell planning, cell parameters, neighboring cell relations and neighboring cell information corresponding to the base station commissioning process as the background of engineering practice; The station survey planning configuration subunit is used to realize the simulation practice teaching of the configuration process corresponding to the station survey planning stage; The network deployment configuration subunit is used to implement simulation practice teaching of the configuration process corresponding to the network deployment stage; The commissioning subunit is activated to verify whether the configurations in the site survey planning subunit and the network deployment subunit are correct. If the configurations are incorrect, the user is prompted to return to reconfigure the site survey planning and network deployment. The business verification configuration subunit is used to implement the simulation practice teaching of the configuration process corresponding to the business verification stage.

4. The simulation teaching device according to claim 2, characterized in that: The theoretical practice units include: 5G interface protocol stack subunit, used to realize simulation practice teaching of 5G interface protocol stack knowledge; 5G physical layer process subunit, used to realize simulation practice teaching of 5G physical layer process knowledge; 5G network architecture subunit, used to realize simulation practice teaching of 5G network architecture knowledge; The 5G signaling process sub-unit is used to realize the simulation practice teaching of 5G signaling process knowledge.

5. The simulation teaching device according to claim 1, characterized in that: The 5G vehicle networking scenario simulation module also includes: The data acquisition module is used to receive images collected by the 5G smart car.

6. The simulation teaching device according to claim 1, characterized in that: The 5G smart car runs based on the loaded motion control program and the control instructions of the 5G simulation platform.

7. The simulation teaching device according to claim 3, characterized in that: The configuration process corresponding to the station survey planning stage includes the configuration process of the radio frequency unit; The configuration process corresponding to the network deployment stage includes the configuration process of the operation and maintenance center OMC equipment, core network equipment and indoor baseband processing unit BBU equipment; The configuration process corresponding to the service verification phase includes the configuration process of test parameters and terminal equipment.

Images