Material identification optimization method and system based on RFID radio frequency

Abstract

The invention discloses a material identification optimization method and system based on RFID radio frequency, and relates to the technical field of RFID radio frequency identification. A material identification optimization system based on RFID radio frequency comprises a material identification optimization module and a special signal processing module. According to the invention, through analysis of the radio frequency signal receiving environment data and the material identification dynamic data, the identification strategy can be adaptively optimized under different identification environments and conditions, so that the material identification precision is improved; the working parameters of the material identification equipment can be dynamically adjusted according to an optimization strategy to ensure that the material identification equipment adapts to changes in different environments, and the identification flexibility and efficiency are improved; through a material identification resource scheduling model, identification tasks and equipment resources can be intelligently allocated, and after a material identification omission signal is triggered, a special identification strategy is adopted and equipment is dynamically adjusted so as to ensure that omission in the identification process is compensated in time.

Description

Technical Field

[0001] The present invention relates to the technical field of RFID radio frequency identification, and particularly to an optimization method and system for material identification based on RFID radio frequency. Background Art

[0002] With the increasing refinement requirements for material management in industries such as logistics, warehousing, and manufacturing, RFID radio frequency identification technology has become an important means for material identification and tracking due to its non-contact, automated, and highly real-time characteristics. However, in complex application environments, such as large-scale warehousing, outdoor environments, and dense tag deployments, RFID systems often face problems such as multi-tag conflicts, frequency interference, and inaccurate positioning, which affect the identification efficiency and accuracy.

[0003] To overcome these problems, multi-band scheduling, positioning technology integration, and dynamic scheduling and adaptive technology can be combined to optimize the RFID material identification process in different environments and application scenarios. Summary of the Invention

[0004] The present invention aims to provide an optimization method and system for material identification based on RFID radio frequency to improve the accuracy and precision of RFID radio frequency identification in complex environments.

[0005] An optimization method for material identification based on RFID radio frequency includes the following steps: Obtain radio frequency signal reception environment data and material identification dynamic data based on the current material identification scenario; at least N material identification devices B are included in the current material identification scenario n Perform material identification, where n = 2,..., N; analyze based on the radio frequency signal reception environment data, material identification dynamic data, and material identification environment optimization model to obtain an adaptive material identification optimization strategy L n ; where L n ={J n , U n , V n}, J n represents the shortest material identification interval of the material identification device B n , U n represents the material identification power of the material identification device B n , V n represents the material identification intensity of the material identification device B n ; the material identification environment optimization model optimizes the working environment of the material identification device through environmental data analysis, dynamic prediction, and adaptive strategy adjustment, improves the identification accuracy, and effectively responds to changing identification conditions; According to the adaptive material identification optimization strategy L n for the material identification device B nPerform dynamic adjustment and carry out material identification tasks; when receiving a signal of missing material identification, analyze based on the material identification resource scheduling model to obtain a special material identification strategy and dynamic material identification equipment; the material identification resource scheduling model ensures the efficiency, accuracy, and completeness of the material identification process through signal data analysis, equipment matching, and dynamic strategy adjustment, thereby optimizing the use of material identification equipment resources and improving the identification accuracy; dynamically adjust the dynamic material identification equipment based on the special material identification strategy until a material identification task is completed.

[0006] As a preferred technical solution of the present invention, the material identification environment optimization model includes an environmental data analysis layer, a material identification prediction layer, a dynamic strategy output layer, and a strategy output layer; The environmental data analysis layer is used to perform feature recognition on the radio frequency signal reception environment data to obtain the radio frequency signal reception environment data feature T n ; among them, the radio frequency signal reception environment data feature T n represents the material identification environment feature data corresponding to the current material identification device B n ; The material identification prediction layer is used to perform prediction analysis based on the material identification dynamic data to obtain the current material identification prediction feature; The dynamic strategy output layer is used to perform dynamic strategy output according to the radio frequency signal reception environment data feature T n and the current material identification prediction feature to obtain an adaptive material identification optimization strategy L n ; The strategy output layer is used to output the adaptive material identification optimization strategy L n ;

[0007] As a preferred technical solution of the present invention, the specific steps for performing dynamic strategy output in the dynamic strategy output layer include: Construct a material identification digital twin model based on the current material identification scenario; Construct K material equipment strategy output individuals G k , k = 1, 2,..., K; each material equipment strategy output individual G k contains the simulated material identification optimization strategies corresponding to all material identification devices B n ; combine the K material equipment strategy output individuals G k to obtain a material equipment strategy output iterative population; the fitness corresponding to the material equipment strategy output individual G k is S k ; the fitness S k is the material simulation identification accuracy corresponding to the material equipment strategy output individual G k ; set the maximum number of iterations to M, and m is the current number of iterations, m = 1, 2,..., M; Based on the current material identification prediction features, the material identification digital twin model, and the swarm optimization algorithm, perform simulation calculations. The specific steps are as follows: When the current iteration number is m, screen the relatively optimal solution set X of the population m =[X m1 , X m2 , …, X mE , where E is the total number of relatively optimal population solutions in the relatively optimal solution set of the population, and e = 1, 2, …, E; the corresponding relatively optimal fitness set of the relatively optimal solution set X of the population is P m =[P m , P m1 , …, P m2 mE ; T Use the formula W e = (P m avg - P me ) / (P m max - P m min ) to calculate the dynamic optimization factor; P m avg represents the average value in the relatively optimal fitness set P m , P m max represents the maximum value in the relatively optimal fitness set P m , and P m min represents the minimum value in the relatively optimal fitness set P m ; Based on the dynamic optimization factor, calculate the population iteration prey position update formula R m , R m = W 1 * X m1 + W 2 * X m2 + … + W E * X mE ; Use the population iteration prey position update formula R m to change the population iteration prey position; If P m max - P m min = 0, then the population iteration prey position remains unchanged; When the maximum iteration number is reached, output the individual corresponding to the maximum current fitness as the optimal material equipment strategy output individual; Based on the optimal material equipment strategy output individual, obtain the adaptive material identification optimization strategy L n . ​​

[0008] As a preferred technical solution of the present invention, the specific steps for training the material recognition prediction layer include: The material recognition prediction layer includes a data feature splitting layer, a vector splicing layer, and a prediction layer; The data feature splitting layer is used to split the data features of the material recognition dynamic data to obtain the split features of the material recognition dynamic data; The vector splicing layer is used to perform hierarchical division splicing according to all the split features of the material recognition dynamic data to obtain the split feature vector of the material recognition dynamic data with hierarchical division; The prediction layer is used to perform prediction analysis based on the split feature vector of the material recognition dynamic data to obtain the current material recognition prediction feature; Collect several groups of material recognition prediction training samples; each group of material recognition prediction training samples contains the current material recognition basic data and the corresponding material recognition prediction feature; combine several groups of material recognition prediction training samples to obtain the material recognition prediction training set; Use the material recognition prediction training set for model training to obtain the initial material recognition prediction layer; perform model evaluation on the initial material recognition prediction layer. If the initial material recognition prediction layer passes the model evaluation, then use the initial material recognition prediction layer as the material recognition prediction layer in the material recognition environment optimization model; otherwise, continue to perform model training using the material recognition prediction training set.

[0009] As a preferred technical solution of the present invention, there are a signal data analysis layer, a material equipment matching layer, a special strategy analysis layer, and a special strategy output layer in the material recognition resource scheduling model; The signal data analysis layer is used to obtain the current material trajectory information based on the material recognition omission signal; The material equipment matching layer is used to match the material recognition equipment according to the current material trajectory information to obtain the dynamic material recognition equipment; The special strategy analysis layer is used to perform strategy analysis on the dynamic material recognition equipment based on the current material trajectory information and the material recognition omission signal to obtain the special recognition strategy for material recognition; The special strategy output layer is used to output the special recognition strategy for material recognition.

[0010] As a preferred technical solution of the present invention, the specific steps for training the special strategy analysis layer include: Collect several groups of special strategy output training samples; each group of special strategy output training samples contains the target resource scheduling strategy and the material recognition feature; combine several groups of special strategy output training samples to obtain the special strategy output training set; the material recognition feature includes the material trajectory information feature and the corresponding material recognition equipment strategy feature; Output a training set based on a special strategy for model training to obtain an initial special strategy analysis layer; perform model evaluation on the initial special strategy analysis layer. If the initial special strategy analysis layer passes the model evaluation, use the initial special strategy analysis layer as the special strategy analysis layer in the material identification resource scheduling model; otherwise, continue model training using the special strategy output training set.

[0011] As a preferred technical solution of the present invention, the swarm optimization algorithm is the pelican optimization algorithm.

[0012] A material identification optimization system based on RFID radio frequency includes: A material identification optimization module, including a data acquisition unit and a strategy analysis unit; the data acquisition unit is used to obtain radio frequency signal reception environment data and material identification dynamic data based on the current material identification scenario; there are at least N material identification devices B in the current material identification scenario n for material identification, n = 2,..., N; the strategy analysis unit is used to analyze based on the radio frequency signal reception environment data, material identification dynamic data, and the material identification environment optimization model to obtain an adaptive material identification optimization strategy L n ; where L n ={J n , U n , V n}, J n represents the shortest material identification interval of the material identification device B n , U n represents the material identification power of the material identification device B n , V n represents the material identification intensity of the material identification device B n ; the material identification environment optimization model optimizes the working environment of the material identification device through environmental data analysis, dynamic prediction, and adaptive strategy adjustment, improves the identification accuracy, and effectively responds to changing identification conditions; A special signal processing module, including a material identification unit and a special strategy analysis unit; the material identification unit is used to dynamically adjust the material identification device B n according to the adaptive material identification optimization strategy L n and perform the material identification task; when receiving a material identification omission signal, analyze based on the material identification resource scheduling model to obtain a material identification special identification strategy and dynamic material identification devices; the special strategy analysis unit is used to deploy the material identification resource scheduling model. The material identification resource scheduling model ensures the efficiency, accuracy, and non-omission of the material identification process through signal data analysis, device matching, and dynamic strategy adjustment, thereby optimizing the use of material identification device resources and improving the identification accuracy; dynamically adjust the dynamic material identification devices based on the material identification special identification strategy until a material identification task is completed.

[0013] The present invention has the following advantages: 1. By analyzing the radio frequency signal reception environment data and the dynamic data of material identification, the present invention can adaptively optimize the identification strategy under different identification environments and conditions, thereby improving the accuracy of material identification; the material identification device can dynamically adjust its working parameters according to the optimized strategy to ensure adaptation to changes under different environments and improve the flexibility and efficiency of identification; through the material identification resource scheduling model, the identification tasks and device resources can be intelligently allocated, reducing the consumption of invalid resources and improving the efficiency and accuracy of the overall identification process. After the omission signal of material identification is triggered, special identification strategies and dynamic adjustment of the device are adopted to ensure that the omissions in the identification process are compensated in a timely manner.

[0014] 2. Through the comprehensive analysis of the radio frequency signal reception environment data and the dynamic data of material identification, the present invention generates an adaptive material identification optimization strategy, which can dynamically adjust the working parameters of the identification device according to the changes in the actual environment and the identification requirements, improve the identification accuracy and cope with complex environmental conditions; the material identification environment optimization model can perform feature analysis on the radio frequency signal reception environment data in real time, identify and respond to signal changes in the environment, and ensure that the device maintains high-efficiency identification ability under changing environments. The optimized adaptive strategy can reduce the identification interval, adjust the identification power and intensity, and thus improve the working efficiency and identification accuracy of the material identification device, especially showing superiority in complex and dynamic identification scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic structural diagram of a material identification optimization system based on RFID radio frequency adopted in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0017] Embodiment 1, a material identification optimization method based on RFID radio frequency, includes the following steps: Obtain radio frequency signal reception environment data and dynamic data of material identification based on the current material identification scenario; at least N material identification devices B are included in the current material identification scenario n Perform material identification, n = 2,..., N; the material identification scenario may include actual scenarios such as logistics warehousing management, production line material management, airport luggage identification, etc.; the material identification device B n is an RFID radio frequency identification device; Based on the analysis of radio frequency signal reception environment data, material identification dynamic data, and material identification environment optimization model, an adaptive material identification optimization strategy L is obtained. n ; where L n ={J n , U n , V n}}, J n represents the shortest material identification interval of the material identification device B n , U n represents the material identification power of the material identification device B n , V n represents the material identification intensity of the material identification device B n ; The material identification environment optimization model optimizes the working environment of the material identification device through environmental data analysis, dynamic prediction, and adaptive strategy adjustment, improves the identification accuracy, and effectively responds to changing identification conditions; The material identification environment optimization model includes an environmental data analysis layer, a material identification prediction layer, a dynamic strategy output layer, and a strategy output layer; The environmental data analysis layer is used to perform feature recognition on the radio frequency signal reception environment data to obtain the radio frequency signal reception environment data feature T n ; where the radio frequency signal reception environment data feature T n represents the material identification environment feature data corresponding to the current material identification device B n ; The material identification prediction layer is used to perform prediction analysis based on the material identification dynamic data to obtain the current material identification prediction feature; The dynamic strategy output layer is used to perform dynamic strategy output according to the radio frequency signal reception environment data feature T n and the current material identification prediction feature to obtain the adaptive material identification optimization strategy L n ; The strategy output layer is used to output the adaptive material identification optimization strategy L n ; By comprehensively analyzing the radio frequency signal reception environment data and the dynamic data of material identification, an adaptive material identification optimization strategy is generated. This strategy can dynamically adjust the working parameters of the identification device (such as identification interval, power, identification intensity) according to the changes in the actual environment and identification requirements, improve the identification accuracy, and cope with complex environmental conditions. The material identification environment optimization model can perform feature analysis on the radio frequency signal reception environment data in real time, identify and respond to signal changes in the environment, such as interference and occlusion, to ensure that the device maintains high-efficiency identification ability in a changing environment. Through the dynamic data analysis of the material identification prediction layer, potential problems in the identification task, such as signal loss or interference between devices, can be predicted in advance, and the strategy is adjusted according to the prediction results through the dynamic strategy output layer to ensure the efficiency and stability of the identification process. The optimized adaptive strategy can reduce the identification interval, adjust the identification power and intensity, thereby improving the working efficiency and identification accuracy of the material identification device, especially showing superiority in complex and dynamic identification scenarios. The specific steps for dynamic strategy output in the dynamic strategy output layer include: Construct a digital twin model of material identification based on the current material identification scenario; Construct K individual material device strategy outputs G k , k = 1, 2,..., K; each individual material device strategy output G k contains the simulated material identification optimization strategies corresponding to all material identification devices B n ; Combine the K individual material device strategy outputs G k to obtain an iterative population of material device strategy outputs; the fitness corresponding to the individual material device strategy output G k is S k ; the fitness S k is the simulated material identification accuracy corresponding to the individual material device strategy output G k ; Set the maximum number of iterations to M, and m is the current number of iterations, m = 1, 2,..., M; Based on the current material identification prediction features, the digital twin model of material identification, and the swarm optimization algorithm, perform simulation calculations. The specific steps are: The swarm optimization algorithm is the pelican optimization algorithm; When the current number of iterations is m, screen the relatively optimal solution set X m =[X m1 , X m2 , …, X mE , E is the total number of relatively optimal population solutions in the relatively optimal solution set of the population, e = 1, 2,..., E; the relatively optimal fitness set corresponding to the relatively optimal solution set X m is P m =[P m1 , P m2 , …, PmE T ; Using the formula W e = (P m avg - P me ) / (P m max - P m min ) to calculate the dynamic optimization factor; P m avg represents the average value in the set of better fitness P m , P m max represents the maximum value in the set of better fitness P m , P m min represents the minimum value in the set of better fitness P m ; Based on the dynamic optimization factor, calculate the population iteration prey position update formula R m , R m = W 1 * X m1 + W 2 * X m2 + … + W E * X mE ; Use the population iteration prey position update formula R m to change the population iteration prey position; If P m max - P m min = 0, then the population iteration prey position remains unchanged; When the maximum number of iterations is reached, output the individual corresponding to the maximum current fitness as the optimal material equipment strategy output individual; Based on the optimal material equipment strategy output individual, obtain the adaptive material identification optimization strategy L n ; ​By constructing a digital twin model for material identification, the physical and dynamic characteristics of the material identification scenario are digitized, providing a more accurate simulation environment. This model can simulate the material identification process and adjust strategies under different conditions, thereby optimizing the accuracy and efficiency of material identification. By constructing multiple individual output strategies for material equipment and using swarm optimization algorithms for iterative calculations, the best strategy can be automatically adjusted and selected. The dynamic optimization factor can intelligently adjust the optimization process to ensure adaptation to different changes in the material identification environment and ensure operation in the optimal state at all times. In each iteration process, screening the relatively optimal solution set, calculating the dynamic optimization factor, and updating the population to iterate the prey position can precisely optimize the working strategy of the material identification equipment. This fine-grained optimization mechanism can better cope with variable environmental factors and ensure the efficient completion of the identification task. Through the iteration and dynamic adjustment of the swarm optimization algorithm, invalid calculations and resource waste can be avoided, and in-depth optimization is only carried out on the strategies most likely to improve the identification accuracy, thereby saving computing resources and accelerating the material identification process. The specific steps for training the material identification prediction layer include: The material identification prediction layer includes a data feature splitting layer, a vector concatenation layer, and a prediction layer; the material identification prediction layer can be established through a CNN model. The data feature splitting layer is used to split the data features of the material identification dynamic data to obtain the split features of the material identification dynamic data. The vector concatenation layer is used to perform hierarchical division and concatenation based on all the split features of the material identification dynamic data to obtain the split feature vector of the material identification dynamic data with hierarchical division. The prediction layer is used to perform prediction analysis based on the split feature vector of the material identification dynamic data to obtain the current material identification prediction features. Collect several groups of material identification prediction training samples; each group of material identification prediction training samples contains the current material identification basic data and the corresponding material identification prediction features; combine several groups of material identification prediction training samples to obtain the material identification prediction training set. Use the material identification prediction training set for model training to obtain the initial material identification prediction layer; perform model evaluation on the initial material identification prediction layer. If the initial material identification prediction layer passes the model evaluation, then use the initial material identification prediction layer as the material identification prediction layer in the material identification environment optimization model; otherwise, continue to use the material identification prediction training set for model training. Through hierarchical processing such as data feature splitting and vector splicing, the material identification prediction layer can analyze and process dynamic data more meticulously, extract key features and perform efficient prediction. This structured prediction process improves the accuracy and stability of identification, especially when dealing with complex and multi-dimensional data; the data feature splitting layer can deeply mine the potential information in the dynamic data of material identification and effectively split it, which enables the prediction layer to utilize richer and more diverse feature data and improve the prediction accuracy of material identification; through the vector splicing layer to hierarchically divide and splice different split features, the feature information of the dynamic data of material identification is fully fused. This hierarchical feature representation enables the model to capture the complex relationships and dependencies between data, thereby improving the reliability of the prediction results; According to the adaptive material identification optimization strategy L n For the material identification device B n Perform dynamic adjustment and carry out the material identification task; when receiving the material identification omission signal, analyze it based on the material identification resource scheduling model to obtain the special identification strategy for material identification and the dynamic material identification device; The receiving scenarios or triggering conditions of the material identification omission signal may include the following situations: in a complex environment, the material label may cause signal attenuation or complete loss due to obstacles, metal materials, electronic interference, etc., resulting in the device being unable to correctly identify the material; the identification interval setting of the material identification device is too long, which may cause fast-flowing materials to not be identified in time when passing through the identification device, resulting in an omission signal; the frequency or communication protocol of the material identification device does not match the label, resulting in the device being unable to identify the labels of some materials, resulting in an omission signal; The material identification resource scheduling model ensures the efficiency, accuracy and omission-free of the material identification process through signal data analysis, device matching and dynamic strategy adjustment, thereby optimizing the use of material identification device resources and improving the identification accuracy; based on the special identification strategy for material identification, dynamically adjust the dynamic material identification device until a material identification task is completed; The signal data analysis layer, material device matching layer, special strategy analysis layer and special strategy output layer of the material identification resource scheduling model; The signal data analysis layer is used to obtain the current material trajectory information based on the material identification omission signal; The material device matching layer is used to match the material identification device according to the current material trajectory information to obtain the dynamic material identification device; The special strategy analysis layer is used to perform strategy analysis on the dynamic material identification device based on the current material trajectory information and the material identification omission signal to obtain the special identification strategy for material identification; the special strategy analysis layer is established based on the BP neural network model; The special strategy output layer is used to output the special identification strategy for material identification; The specific steps for training the special strategy analysis layer include: Collect several groups of special strategy output training samples; each group of special strategy output training samples includes a target resource scheduling strategy and a material identification feature; combine several groups of special strategy output training samples to obtain a special strategy output training set; the material identification feature includes a material trajectory information feature and a corresponding material identification device strategy feature; Perform model training based on the special strategy output training set to obtain an initial special strategy analysis layer; perform model evaluation on the initial special strategy analysis layer. If the initial special strategy analysis layer passes the model evaluation, use the initial special strategy analysis layer as the special strategy analysis layer in the material identification resource scheduling model; otherwise, continue model training using the special strategy output training set; Through signal data analysis, device matching, and dynamic strategy adjustment, the material identification resource scheduling model can effectively handle missing signals and environmental changes, and optimize the material identification process. This ensures that the material identification device can efficiently and accurately perform tasks in a changing environment, reducing misidentifications and omissions, and improving the overall work efficiency; through real-time analysis of material trajectory information and material identification missing signals, it is possible to dynamically adjust the configuration and working strategy of the material identification device according to actual needs, ensuring the continuous progress of the task and not being limited by the device performance. This real-time dynamic optimization not only improves the reliability of task execution but also reduces resource waste; the material device matching layer performs precise matching based on the real-time obtained material trajectory information, ensuring that the dynamic material identification device can work at the best position and in the most suitable environment. Effective device matching reduces omissions in material identification and ensures identification accuracy and speed; the special strategy analysis layer can formulate personalized identification strategies based on the current material trajectory information and material identification missing signals through in-depth analysis. This strategy is based on historical data training and dynamic adjustment of the current state, and can flexibly respond to different identification environments and task requirements, improving the quality of task completion; In actual usage scenarios, such as in a large warehouse, materials need to be accurately and efficiently identified and classified to ensure the accuracy of inventory management, material scheduling, and goods sorting. Characteristics such as the type, size, and storage location of each material need to be predicted and identified in a timely manner. Real-time dynamic data of the materials are obtained through RFID tags to predict the status of the materials, and the working parameters of the identification device are automatically adjusted according to the identification data of the materials to ensure identification accuracy and reduce omissions.

[0018] Embodiment 2, a material identification optimization system based on RFID radio frequency, as shown in Figure 1 shown, includes: The material identification optimization module includes a data acquisition unit and a strategy analysis unit; the data acquisition unit is used to obtain radio frequency signal reception environment data and material identification dynamic data based on the current material identification scenario; at least N material identification devices B are included in the current material identification scenario n Perform material identification, n = 2, …, N; the strategy analysis unit is used to analyze based on the radio frequency signal reception environment data, material identification dynamic data, and material identification environment optimization model to obtain an adaptive material identification optimization strategy L n ; where L n ={J n , U n , V n}, J n represents the shortest material identification interval of the material identification device B n , U n represents the material identification power of the material identification device B n , V n represents the material identification intensity of the material identification device B n ; the material identification environment optimization model optimizes the working environment of the material identification device through environmental data analysis, dynamic prediction, and adaptive strategy adjustment, improves the identification accuracy, and effectively responds to changing identification conditions; The special signal processing module includes a material identification unit and a special strategy analysis unit; the material identification unit is used to dynamically adjust the material identification device B n according to the adaptive material identification optimization strategy L n and perform the material identification task; when receiving a material identification omission signal, analyze based on the material identification resource scheduling model to obtain a special material identification strategy and dynamic material identification devices; the special strategy analysis unit is used to deploy the material identification resource scheduling model, and the material identification resource scheduling model ensures the efficiency, accuracy, and no omission of the material identification process through signal data analysis, device matching, and dynamic strategy adjustment, thereby optimizing the use of material identification device resources and improving the identification accuracy; dynamically adjust the dynamic material identification devices based on the special material identification strategy until a material identification task is completed.

[0019] It should be understood that for those of ordinary skill in the art, improvements or transformations can be made according to the above description, and all such improvements and transformations should fall within the protection scope of the appended claims of the present invention. The parts not described in detail in this specification belong to the prior art well-known to those of ordinary skill in the art.

Claims

1. A material identification optimization method based on RFID radio frequency, characterized in that: The following steps are involved: Acquire radio frequency signal receiving environment data and material identification dynamic data based on the current material identification scenario; The current material recognition scene contains at least N material recognition devices B n Perform material identification, n=2,…,N; Based on the analysis of RF signal receiving environment data, material identification dynamic data and material identification environment optimization model, the adaptive material identification optimization strategy L is obtained. n Among them, L n ={J n , U n , V n }, J n Indicates material identification equipment B n The shortest material recognition interval, U n Indicates material identification equipment B n Material identification power, V n Indicates material identification equipment B n The material recognition strength; the material recognition environment optimization model optimizes the working environment of the material recognition equipment through environmental data analysis, dynamic prediction and adaptive strategy adjustment, improves the recognition accuracy and effectively responds to changing recognition conditions; Optimize strategy based on adaptive material recognition L n Material identification equipment B n Make dynamic adjustments and perform material identification tasks; when a material identification omission signal is received, analyze it based on the material identification resource scheduling model to obtain a special material identification strategy and dynamic material identification equipment; the material identification resource scheduling model ensures that the material identification process is efficient, accurate and without omissions through signal data analysis, equipment matching and dynamic strategy adjustment, thereby optimizing the use of material identification equipment resources and improving identification accuracy; dynamically adjust the dynamic material identification equipment based on the special material identification strategy until a material identification task is completed.

2. The RFID-based material identification optimization method according to claim 1 is characterized in that: The material identification environment optimization model includes an environmental data analysis layer, a material identification prediction layer, a dynamic strategy output layer, and a strategy output layer; The environmental data analysis layer is used to identify the characteristics of the radio frequency signal receiving environment data and obtain the characteristics T of the radio frequency signal receiving environment data. n ; Among them, the radio frequency signal receiving environment data characteristic T n Indicates the current material identification device B n Corresponding material identification environment characteristic data; The material identification prediction layer is used to perform prediction analysis based on material identification dynamic data to obtain the current material identification prediction features; The dynamic strategy output layer is used to receive environmental data characteristics based on the RF signal. n The dynamic strategy output is carried out with the current material identification prediction characteristics to obtain the adaptive material identification optimization strategy L n ; The strategy output layer is used to output the adaptive material identification optimization strategy L n .

3. The RFID-based material identification optimization method according to claim 2 is characterized in that: The specific steps of performing dynamic policy output in the dynamic policy output layer include: Build a material identification digital twin model based on the current material identification scenario; Construct K material equipment strategies to output individual G k , k=1, 2, ..., K; each material equipment strategy outputs individual G k All material identification equipment B n The corresponding simulated material identification optimization strategy; output K material equipment strategies to individual G k Combination, get the material and equipment strategy output iterative population; material and equipment strategy output individual G k The corresponding fitness is S k ; Fitness is S k Output individual G for material equipment strategy k The corresponding material simulation recognition accuracy; set the maximum number of iterations to M, where m is the current number of iterations, m=1, 2, ..., M; Based on the current material recognition prediction features, material recognition digital twin model and swarm optimization algorithm, simulation calculation is performed. The specific steps are as follows: When the current number of iterations is m, select the optimal solution set X of the population m =[X m1 , X m2 , …, X mE ], E is the total number of better solutions in the population better solution set, e=1, 2, ..., E; the population better solution set X m The corresponding better fitness set is P m =[P m1 , P m2 ,…,P mE ] T ; Using the formula W e =(P m avg -P me ) / (P m max -P m min ) calculates the dynamic optimization factor; P m avg Represents the better fitness set P m The average value, P m max Represents the better fitness set P m The maximum value in P m min Represents the better fitness set P m The minimum value in ; Calculate the update formula R of the prey position of the population iteration based on the dynamic optimization factor m , R m =W1*X m1 +W2*X m2 +…+W E *X mE ; Use population iteration to update the prey position formula R m Changing the population iteration prey location; If P m max -P m min =0, the population iteration prey position remains unchanged; When the maximum number of iterations is reached, the material and equipment strategy output individual corresponding to the current maximum fitness is output, which is the optimal material and equipment strategy output individual; based on the optimal material and equipment strategy output individual, the adaptive material identification optimization strategy L is obtained. n .

4. The RFID-based material identification optimization method according to claim 3 is characterized in that: The specific steps for training the material recognition prediction layer include: The material identification prediction layer includes a data feature splitting layer, a vector splicing layer, and a prediction layer; The data feature splitting layer is used to split the material identification dynamic data into data features to obtain the material identification dynamic data splitting features; The vector concatenation layer is used to perform hierarchical division and concatenation according to all material identification dynamic data splitting features, and obtain a material identification dynamic data splitting feature vector with hierarchical division; The prediction layer is used to perform prediction analysis based on the dynamic data splitting feature vector of material identification to obtain the current material identification prediction features; Collecting several groups of material recognition prediction training samples; each group of material recognition prediction training samples contains current material recognition basic data and corresponding material recognition prediction features; combining several groups of material recognition prediction training samples to obtain a material recognition prediction training set; The material identification prediction training set is used for model training to obtain an initial material identification prediction layer; the initial material identification prediction layer is evaluated, and if the initial material identification prediction layer passes the model evaluation, the initial material identification prediction layer is used as the material identification prediction layer in the material identification environment optimization model; otherwise, the material identification prediction training set is used to continue model training.

5. The RFID-based material identification optimization method according to claim 4 is characterized in that: Material identification resource scheduling model signal data analysis layer, material equipment matching layer, special strategy analysis layer and special strategy output layer; The signal data analysis layer is used to obtain the current material trajectory information based on the missing signal of material identification; The material equipment matching layer is used to match the material identification equipment according to the current material trajectory information to obtain the dynamic material identification equipment; The special strategy analysis layer is used to perform strategy analysis on the dynamic material identification device based on the current material trajectory information and the material identification missing signal to obtain the special identification strategy for material identification; The special strategy output layer is used to output special identification strategies for material identification.

6. The RFID-based material identification optimization method according to claim 5 is characterized in that: The specific steps for training a special strategy analysis layer include: Collect several groups of special strategy output training samples; each group of special strategy output training samples contains target resource scheduling strategy and material identification features; combine several groups of special strategy output training samples to obtain a special strategy output training set; the material identification features contain material trajectory information features and corresponding material identification equipment strategy features; Model training is performed based on the special strategy output training set to obtain an initial special strategy analysis layer; a model evaluation is performed on the initial special strategy analysis layer. If the initial special strategy analysis layer passes the model evaluation, the initial special strategy analysis layer is used as the special strategy analysis layer in the material identification resource scheduling model; otherwise, the model training is continued using the special strategy output training set.

7. The RFID-based material identification optimization method according to claim 6 is characterized in that: The swarm optimization algorithm is the Pelican optimization algorithm.

8. A material identification optimization system based on RFID radio frequency, characterized in that: The system applies a material identification optimization method based on RFID radio frequency as described in any one of claims 1 to 7, including: The material identification optimization module includes a data acquisition unit and a strategy analysis unit; the data acquisition unit is used to acquire radio frequency signal receiving environment data and material identification dynamic data based on the current material identification scene; the current material identification scene contains at least N material identification devices B n Perform material identification, n=2, ..., N; the strategy analysis unit is used to analyze based on the radio frequency signal receiving environment data, material identification dynamic data and material identification environment optimization model to obtain the adaptive material identification optimization strategy L n Among them, L n ={J n , U n , V n }, J n Indicates material identification equipment B n The shortest material recognition interval, U n Indicates material identification equipment B n Material identification power, V n Indicates material identification equipment B n The material recognition strength; the material recognition environment optimization model optimizes the working environment of the material recognition equipment through environmental data analysis, dynamic prediction and adaptive strategy adjustment, improves the recognition accuracy and effectively responds to changing recognition conditions; Special signal processing module, including material identification unit and special strategy analysis unit; material identification unit is used to optimize strategy L according to adaptive material identification n Material identification equipment B n Make dynamic adjustments and perform material identification tasks; when a material identification omission signal is received, analyze it based on the material identification resource scheduling model to obtain a special material identification strategy and dynamic material identification equipment; the special strategy analysis unit is used to deploy the material identification resource scheduling model, and the material identification resource scheduling model ensures that the material identification process is efficient, accurate and without omissions through signal data analysis, equipment matching and dynamic strategy adjustment, thereby optimizing the use of material identification equipment resources and improving identification accuracy; dynamically adjust the dynamic material identification equipment based on the special material identification strategy until a material identification task is completed.

Images