RFID tag optimization system based on artificial intelligence

Abstract

The invention, which relates to the field of RFID tag optimization, discloses an artificial intelligence-based RFID tag optimization system comprising a data acquisition module, a data analysis module, a comprehensive analysis module and a real-time feedback module. The data acquisition module comprises a system data acquisition unit and an environment data acquisition unit; multi-dimensional data acquisition is carried out through the data acquisition module, so that the limitation of a traditional acquisition mode is effectively overcome; the data analysis module comprises a system data analysis unit and an environment data analysis unit and is used for analyzing the data transmitted by the data acquisition module; a signal quality coefficient value, an identification efficiency coefficient value, a fault-tolerant capability coefficient value, an electromagnetic interference coefficient value, a transmission environment safety coefficient value and a microenvironment safety coefficient value are obtained by performing deep analysis on the acquired data through the RFID tag analysis module, and the performance advantages and improvements of the RFID tag are clearly presented.

Description

Technical Field

[0001] The present invention relates to the technical field of RFID tag optimization, and more specifically, to an RFID tag optimization system based on artificial intelligence. Background Art

[0002] With the continuous development of science and technology, the application of artificial intelligence technology in the field of logistics management is becoming more and more extensive. As a key element in logistics management, the accuracy and stability of RFID tags are crucial to improving logistics efficiency and management quality.

[0003] The existing AI-based RFID tag optimization system mainly includes: data acquisition module, intelligent analysis module, cloud processing module and user interaction module. Among them, the data acquisition module is responsible for real-time collection of RFID tag information and uploading the data to the cloud through a high-speed wireless network; the intelligent analysis module uses advanced artificial intelligence algorithms and pattern recognition technology to conduct in-depth analysis and processing of the received data to achieve accurate identification and classification of items; the cloud processing module automatically pushes relevant information to the terminal device of the logistics management personnel based on the results of the intelligent analysis to ensure efficient logistics management; the user interaction module provides managers and operators with a simple and intuitive operation experience.

[0004] However, in the existing RFID tag optimization system, too much emphasis is placed on the reading function of tag information, and the collected data is one-sided, which makes the subsequent analysis results inaccurate, resulting in limited application in complex logistics scenarios and affecting the efficiency and quality of logistics management.

[0005] Therefore, there is an urgent need for an artificial intelligence-based RFID tag optimization system to solve the problems of insufficient comprehensive data collection and insufficient accuracy of data analysis and processing in the existing system, so as to further improve the precise identification capability and service quality of logistics management. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an RFID tag optimization system based on artificial intelligence, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0007] To achieve the above object, the present invention provides the following technical solution: an artificial intelligence-based RFID tag optimization system, comprising:

[0008] Data batch division module: used to determine the data to be collected as target data, divide the target data into different batches according to equal time division, and mark them as 1, 2, ..., n in sequence;

[0009] Data acquisition module: including a system data acquisition unit and an environmental data acquisition unit, which are used to acquire target data in real time and transmit the acquired target data to the data analysis module; the system data acquisition unit is used to acquire signal data, recognition data and fault-tolerant data; the environmental data acquisition unit is used to acquire electromagnetic data, transmit environmental data and microenvironment data;

[0010] Data analysis module: including a system data analysis unit and an environment data analysis unit, used to analyze the data transmitted by the data acquisition module and transmit the analysis results to the comprehensive analysis module; the system data analysis unit includes a signal data analysis node, an identification data analysis node and a fault-tolerant data analysis node; the environment data analysis unit includes an electromagnetic data analysis node, a transmission environment data analysis node and a microenvironment data analysis node;

[0011] Comprehensive analysis module: including an RFID data comprehensive analysis unit, used to comprehensively analyze the data transmitted by the data analysis module and transmit the analysis results to the real-time feedback module;

[0012] Real-time feedback module: used to establish a preset value of the RFID tag optimization demand index, judge the RFID tag optimization demand index value according to the preset value of the RFID tag optimization demand index, and send a corresponding signal according to the judgment result.

[0013] Preferably, the signal data includes the maximum signal attenuation rate Sa, the phase shift angle Pa and the stability error frequency Sf; the identification data includes the multi-tag identification rate Mr, the identification delay time Lt and the conflict resolution time Ct; the fault-tolerant data includes the penetration attenuation rate Pr, the data integrity ratio Dr and the thermal stress threshold Ts.

[0014] Preferably, the electromagnetic data include electrostatic potential volt Ev, spatial electromagnetic field change rate Ec and radio frequency noise density Nd; the transmission environment data include multipath effect attenuation rate Md and polarization mismatch loss rate Pm; the microenvironment data include air humidity vertical change rate Ac, the number of metal obstacles Mn and dust concentration Ed.

[0015] Preferably, the signal data analysis node is used to establish a signal data calculation model, import the signal data transmitted by the data acquisition module into the signal data calculation model, and obtain a signal quality coefficient. The signal data calculation model is specifically expressed as:

[0016]

[0017] in, Represents the signal quality coefficient value calculated for the i-th time, Sa i represents the maximum signal attenuation rate of the ith acquisition, Pa irepresents the phase offset angle of the i-th acquisition, Sf i represents the stability error frequency of the ith acquisition.

[0018] Preferably, the identification data analysis node is used to establish an identification data calculation model, import the identification data transmitted by the data acquisition module into the identification data calculation model, and obtain the identification efficiency coefficient. The identification data calculation model is specifically expressed as:

[0019]

[0020] Among them, e i Represents the recognition efficiency coefficient value of the i-th calculation, Mr i represents the multi-label recognition rate of the i-th acquisition, Lt i Indicates the recognition delay time of the i-th acquisition, Ct i Indicates the conflict resolution time of the i-th collection.

[0021] Preferably, the fault-tolerant data analysis node is used to establish a fault-tolerant data calculation model, and import the fault-tolerant data transmitted by the data acquisition module into the fault-tolerant data calculation model to obtain a fault-tolerant capability coefficient. The fault-tolerant data calculation model is specifically expressed as:

[0022]

[0023] Among them, α i represents the fault tolerance coefficient value calculated for the i-th time, Pr i represents the penetration attenuation rate collected for the i-th time, Dr i represents the data integrity ratio of the ith acquisition, Ts i represents the thermal stress threshold of the ith acquisition.

[0024] Preferably, the electromagnetic data analysis node is used to establish an electromagnetic data calculation model, and import the electromagnetic data transmitted by the data acquisition module into the electromagnetic data calculation model to obtain the electromagnetic interference coefficient. The electromagnetic data calculation model is specifically expressed as:

[0025]

[0026] Among them, β i Indicates the electromagnetic interference coefficient value calculated for the i-th time, Ev i represents the electrostatic potential voltage collected for the i-th time, Ec i Nd represents the rate of change of the spatial electromagnetic field collected for the i-th time. i represents the RF noise density of the i-th acquisition.

[0027] Preferably, the transmission environment data analysis node is used to establish a transmission environment data calculation model, import the transmission environment data transmitted by the data acquisition module into the transmission environment data calculation model, and obtain the transmission environment safety factor. The transmission environment data calculation model is specifically expressed as:

[0028]

[0029] Among them, η i Md represents the transmission environment safety factor value calculated for the i-th time. i Pm represents the multipath effect attenuation rate of the ith acquisition. i represents the polarization mismatch loss rate acquired at the i-th time.

[0030] Preferably, the microenvironment data analysis node is used to establish a microenvironment data calculation model, import the microenvironment data transmitted by the data acquisition module into the microenvironment data calculation model, and obtain the microenvironment safety factor. The microenvironment data calculation model is specifically expressed as:

[0031]

[0032] Among them, μ i represents the microenvironmental safety factor value calculated for the i-th time, Ac i Indicates the vertical change rate of air humidity collected for the i-th time, Mn i represents the number of metal obstacles collected for the i-th time, Ed i Indicates the dust concentration collected for the i-th time.

[0033] Preferably, the RFID data comprehensive analysis unit is used to establish an RFID data comprehensive calculation model, which is used to import the signal quality coefficient value, recognition efficiency coefficient value, fault tolerance coefficient value, electromagnetic interference coefficient value, transmission environment safety coefficient value and microenvironment safety coefficient value transmitted by the RFID data analysis unit into the RFID data comprehensive calculation model to obtain the RFID tag optimization demand index; the RFID data comprehensive calculation model is specifically expressed as:

[0034]

[0035] Where S represents the calculated RFID tag optimization demand index value, represents the signal quality coefficient value calculated for the i-th time, e i Represents the recognition efficiency coefficient value of the i-th calculation, α i represents the fault tolerance coefficient value calculated for the i-th time, β i represents the electromagnetic interference coefficient value calculated for the i-th time, η i represents the transmission environment safety factor value calculated for the i-th time, μ irepresents the microenvironment safety factor value calculated for the i-th time; i represents starting from the i-th number, and n represents ending at the n-th number; λ represents other influencing factors that affect the RFID tag optimization demand index value. Since this factor has a small impact, this embodiment does not make a specific limitation.

[0036] Technical effects and advantages of the present invention:

[0037] 1. The present invention divides RFID tag data into different collection batches according to different data features and application scenarios through the data batch division module, which greatly improves the pertinence and efficiency of data processing; through the data acquisition module, multi-angle collection includes signal data, identification data, fault-tolerant data, electromagnetic data, transmission environment data and microenvironment data. Through multi-dimensional data collection, the limitations of traditional collection methods are effectively overcome, providing a richer and more comprehensive source of information for subsequent precise analysis;

[0038] 2. The present invention uses the RFID tag analysis module to deeply analyze the collected data to obtain the signal quality coefficient value, recognition efficiency coefficient value, fault tolerance coefficient value, electromagnetic interference coefficient value, transmission environment safety coefficient value and micro-environment safety coefficient value, clearly showing the performance advantages and improvements of the RFID tag;

[0039] 3. The present invention uses a comprehensive analysis module to comprehensively evaluate and deeply integrate the output results of the data analysis module, thereby further enhancing the reliability and accuracy of the data analysis results; uses a real-time feedback module to continuously track the working status of the RFID tag, and promptly issues an early warning signal when an abnormal situation occurs, so that logistics management personnel and relevant decision-makers can grasp the operating status and logistics management efficiency of the RFID tag system in real time, optimize the RFID tags in a timely manner, and provide strong support for achieving efficient and intelligent logistics management and scientific decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] As attached Figure 1An artificial intelligence-based RFID tag optimization system is shown, comprising a data batch division module, a data acquisition module, a data analysis module, a comprehensive analysis module, and a real-time feedback module.

[0043] The data batch division module is used to determine the data to be collected as target data, divide the target data into different batches in an equal time division manner, and mark them as 1, 2, ..., n in sequence;

[0044] What needs to be specifically explained in this embodiment is that the method of dividing by equal time is to divide according to the characteristics of each target data through the background information management system, and according to the real-time requirements of each target data, collect it once at an equal time interval and divide it into different collection times.

[0045] The data acquisition module includes a system data acquisition unit and an environmental data acquisition unit, which are used to acquire target data in real time and transmit the acquired target data to the data analysis module; the system data acquisition unit is used to acquire signal data, recognition data and fault-tolerant data; the environmental data acquisition unit is used to acquire electromagnetic data, transmission environment data and microenvironment data.

[0046] In this embodiment, it is specifically necessary to explain that: the signal data includes the maximum signal attenuation rate Sa, the phase offset angle Pa and the stability error frequency Sf; the identification data includes the multi-tag identification rate Mr, the identification delay time Lt and the conflict resolution time Ct; the fault tolerance data includes the penetration attenuation rate Pr, the data integrity ratio Dr and the thermal stress threshold Ts; the electromagnetic data includes the electrostatic potential volt Ev, the spatial electromagnetic field change rate Ec and the radio frequency noise density Nd; the transmission environment data includes the multipath effect attenuation rate Md and the polarization mismatch loss rate Pm; the microenvironment data includes the vertical change rate of air humidity Ac, the number of metal obstacles Mn and the dust concentration Ed.

[0047] The maximum signal attenuation rate reflects the degree of energy loss of the signal during transmission, which directly affects the reading distance and reliability of the RFID system. A high attenuation rate may cause the signal to weaken rapidly within a short distance, affecting the recognition of the tag. The acquisition method is: use a signal generator to generate an RFID signal of a certain intensity, and transmit it through a series of materials with known attenuation characteristics. On the other side of the material, use a highly sensitive signal receiver to capture the attenuated signal, and record the initial intensity of the signal and the intensity after passing through different materials. By comparing these intensity values, the attenuation of the signal in different materials is calculated, thereby obtaining the maximum signal attenuation rate.

[0048] The phase offset angle affects the synchronization and accuracy of the signal. The acquisition method is as follows: place the RFID tag and reader in an interference-free environment and ensure that the relative position between them is fixed, then send an RFID signal with a known phase, and use a phase-sensitive receiver to capture and measure the phase of the signal. By comparing the phase difference between the sent and received signals, the phase offset angle is calculated.

[0049] The stability error frequency indicates the frequency of change in signal stability over a period of time. A high error frequency may lead to unstable reading and affect system performance. The acquisition method is: continuously monitor the RFID signal over a period of time, use high-precision data acquisition equipment, record the values ​​of these parameters once, and then analyze the fluctuations of these data to calculate the stability error frequency.

[0050] The multi-tag recognition rate reflects the system's ability to simultaneously recognize multiple tags, which is particularly important for dense tag environments. The collection method is: use a reader to continuously read tags in the area, and record the number of tags successfully recognized during each reading process, calculate the ratio of the number of successfully recognized tags to the total number of tags, and obtain the multi-tag recognition rate.

[0051] The identification delay time refers to the time required from the tag entering the reader's identification range to successfully reading the data, which affects the system response speed. The collection method is: using a high-precision timer to measure the time interval from the tag triggering reading to the complete reception of data to obtain the identification delay time.

[0052] The conflict resolution time refers to the time required for the system to resolve conflicts and correctly identify tags when multiple tags respond simultaneously. It can evaluate system efficiency. The collection method is: simulate a high-density tag environment and trigger multiple tags to respond to the reader's read request at the same time, use a special conflict detection and resolution mechanism to ensure that all tags can be correctly identified, and record the time interval from the detection of the conflict to the successful identification of all tags to obtain the conflict resolution time.

[0053] The penetration attenuation rate indicates the degree of attenuation of the signal when penetrating different materials, which affects the recognition rate of the tag in a complex environment. The collection method is: place the RFID tag under a cover of different materials and measure the change in signal strength, select materials with different attenuation characteristics, and place the RFID tag under each material, use a reader to send a signal from above, and measure the signal strength received after penetrating the material, and calculate the penetration attenuation rate of each material by comparing the signal strength values ​​under different materials.

[0054] The data integrity ratio reflects the ability of data to maintain integrity during data transmission, which is crucial to the quality of data transmission. The data integrity ratio is collected by adding a certain error detection mechanism at the sending end. During the data transmission process, the receiving end will verify whether the received data is complete and correct. The data integrity ratio is obtained by recording and counting the ratio of the number of data packets that successfully pass the error detection during the data transmission process to the total number of data packets.

[0055] The thermal stress threshold refers to the temperature range in which the RFID tag can still work normally under extreme temperature conditions. Exceeding this threshold may cause the tag performance to degrade or be damaged. The collection method is: place the tag in a temperature-controllable environment and gradually increase the ambient temperature. During the heating process, we will continuously monitor the performance indicators of the tag and record the temperature point at which the tag begins to degrade in performance to obtain the thermal stress threshold of the tag.

[0056] The electrostatic potential volts can damage the electronic components of the RFID tag, especially in a dry environment where static electricity is more likely to be generated. High electrostatic potential may cause damage to the tag chip or data loss, affecting the normal operation of the system. The collection method is: evenly arrange multiple electrostatic voltmeter probes in the space where the RFID system is located to ensure that the static electricity conditions in different locations can be covered. Each probe is connected to the central data acquisition device through a data cable to continuously monitor the electrostatic potential in the environment and transmit the data to the central device in real time. The central device summarizes and analyzes the data of each probe to obtain the electrostatic potential volt value.

[0057] The spatial electromagnetic field change rate will affect the received signal strength of the RFID tag at different positions. When the change rate is large, the performance of the tag at different positions may vary greatly, affecting the stability and reliability of the system. The collection method is: in the space where the RFID system operates, select multiple representative measurement points. These points should include positions close to the RFID device, corners far away from the device, and the middle area. Place an electromagnetic field probe at each measurement point. All probes start measuring the electromagnetic field strength at the same time. The electromagnetic field strength data of each measurement point is transmitted to the data analysis software. By calculating the difference in electromagnetic field strength between different points, the spatial electromagnetic field change rate is obtained.

[0058] The environmental RF noise density can measure the RF noise level in the environment and is used to evaluate the working ability of the RFID system in a complex electromagnetic environment. The collection method is: select a typical RFID working frequency band and use a spectrum analyzer to measure the environmental noise in the frequency band. By performing multiple measurements at different times and places, the noise power is recorded and the noise density within the unit bandwidth is calculated.

[0059] The multipath effect attenuation rate indicates the degree of signal attenuation caused by multipath propagation in a complex environment, which affects signal stability and reading rate. The acquisition method is as follows: select a location with a complex reflection path and ensure that there are multiple reflection paths between the RFID reader and the tag. Use a signal analyzer to record changes in signal strength and simulate different reflection paths by adjusting the positions of the reader and the tag. By analyzing the changes in signal strength, we calculate the attenuation of the signal after passing through multiple paths and obtain the multipath effect attenuation rate.

[0060] The polarization mismatch loss rate can evaluate the degree of signal loss when the antenna polarization direction does not match, and is a key parameter for measuring the signal transmission efficiency of the RFID system. The collection method is: set a fixed RFID reader and ensure that its polarization direction is known, change the polarization angle of the RFID tag, measure the change in signal strength, compare the signal strength at different polarization angles, calculate the degree of signal attenuation caused by polarization mismatch, and thus obtain the polarization mismatch loss rate.

[0061] The vertical change rate of air humidity can evaluate the speed at which the ambient humidity changes with altitude, and is a key indicator for evaluating the working performance of the RFID system in environments at different altitudes. The collection method is: select an area with a large vertical height change, and install humidity sensors at different altitudes, record the air humidity at each altitude, and monitor the changes over time. By analyzing the humidity changes, the change in humidity per unit time is calculated, thereby obtaining the vertical change rate of air humidity.

[0062] The number of metal obstacles refers to the number of metal objects in the environment. Metal has a significant interference effect on RFID signals. The collection method is: using a laser ranging device to measure and record the number of metal obstacles in the area.

[0063] The dust concentration indicates the concentration of dust particles in the air. Dust particles may adhere to the surface of RFID tags or readers, affecting the transmission and reception quality of signals. The data is collected by using an optical particle counter to detect and calculate the number and size of dust particles in the air. An optical particle counter is set up in the area where the RFID system is deployed, and the device is turned on for continuous monitoring to record the dust concentration data in the air.

[0064] The data analysis module includes a system data analysis unit and an environmental data analysis unit, which are used to analyze the data transmitted by the data acquisition module and transmit the analysis results to the comprehensive analysis module; the system data analysis unit includes a signal data analysis node, an identification data analysis node and a fault-tolerant data analysis node; the environmental data analysis unit includes an electromagnetic data analysis node, a transmission environment data analysis node and a microenvironment data analysis node.

[0065] In this embodiment, it is specifically required to be explained that: the signal data analysis node is used to establish a signal data calculation model, and the signal data transmitted by the data acquisition module is imported into the signal data calculation model to obtain a signal quality coefficient. The signal data calculation model is specifically expressed as:

[0066]

[0067] in, Represents the signal quality coefficient value calculated for the i-th time, Sa i represents the maximum signal attenuation rate of the ith acquisition, Pa i represents the phase offset angle of the i-th acquisition, Sf i represents the stability error frequency of the ith acquisition.

[0068] In this embodiment, it is specifically required to be explained that: the recognition data analysis node is used to establish a recognition data calculation model, import the recognition data transmitted by the data acquisition module into the recognition data calculation model, and obtain the recognition efficiency coefficient. The recognition data calculation model is specifically expressed as:

[0069]

[0070] Among them, e i Represents the recognition efficiency coefficient value of the i-th calculation, Mr i represents the multi-label recognition rate of the i-th acquisition, Lt i Indicates the recognition delay time of the i-th acquisition, Ct i Indicates the conflict resolution time of the i-th collection.

[0071] In this embodiment, it is specifically required to be explained that: the fault-tolerant data analysis node is used to establish a fault-tolerant data calculation model, and the fault-tolerant data transmitted by the data acquisition module is imported into the fault-tolerant data calculation model to obtain a fault-tolerant capability coefficient. The fault-tolerant data calculation model is specifically expressed as:

[0072]

[0073] Among them, α i represents the fault tolerance coefficient value calculated for the i-th time, Pr i represents the penetration attenuation rate collected for the i-th time, Dr i represents the data integrity ratio of the ith acquisition, Ts i represents the thermal stress threshold of the ith acquisition.

[0074] In this embodiment, it is specifically required to be explained that: the electromagnetic data analysis node is used to establish an electromagnetic data calculation model, and the electromagnetic data transmitted by the data acquisition module is imported into the electromagnetic data calculation model to obtain the electromagnetic interference coefficient. The electromagnetic data calculation model is specifically expressed as:

[0075]

[0076] Among them, β i Indicates the electromagnetic interference coefficient value calculated for the i-th time, Ev i represents the electrostatic potential voltage collected for the i-th time, Ec i Nd represents the rate of change of the spatial electromagnetic field collected for the i-th time. i represents the RF noise density of the i-th acquisition.

[0077] In this embodiment, it is specifically required to be explained that: the transmission environment data analysis node is used to establish a transmission environment data calculation model, import the transmission environment data transmitted by the data acquisition module into the transmission environment data calculation model, and obtain the transmission environment safety factor. The transmission environment data calculation model is specifically expressed as:

[0078]

[0079] Among them, η i Md represents the transmission environment safety factor value calculated for the i-th time. i Pm represents the multipath effect attenuation rate of the ith acquisition. i represents the polarization mismatch loss rate acquired for the i-th time.

[0080] In this embodiment, it is specifically required to be explained that: the microenvironment data analysis node is used to establish a microenvironment data calculation model, import the microenvironment data transmitted by the data acquisition module into the microenvironment data calculation model, and obtain the microenvironment safety factor. The microenvironment data calculation model is specifically expressed as:

[0081]

[0082] Among them, μ i represents the microenvironmental safety factor value calculated for the i-th time, Ac i Indicates the vertical change rate of air humidity collected for the i-th time, Mn i represents the number of metal obstacles collected for the i-th time, Ed i Indicates the dust concentration collected for the i-th time.

[0083] The comprehensive analysis module includes an RFID data comprehensive analysis unit, which is used to perform comprehensive analysis on the data transmitted by the data analysis module and transmit the analysis results to the real-time feedback module.

[0084] In this embodiment, it is specifically required to be explained that: the RFID data comprehensive analysis unit is used to establish an RFID data comprehensive calculation model, which is used to import the signal quality coefficient value, recognition efficiency coefficient value, fault tolerance coefficient value, electromagnetic interference coefficient value, transmission environment safety coefficient value and microenvironment safety coefficient value transmitted by the RFID data analysis unit into the RFID data comprehensive calculation model to obtain the RFID tag optimization demand index; the RFID data comprehensive calculation model is specifically expressed as:

[0085]

[0086] Where S represents the calculated RFID tag optimization demand index value, represents the signal quality coefficient value calculated for the i-th time, e i Represents the recognition efficiency coefficient value of the i-th calculation, α i represents the fault tolerance coefficient value calculated for the i-th time, β i represents the electromagnetic interference coefficient value calculated for the i-th time, η i represents the transmission environment safety factor value calculated for the i-th time, μ i represents the microenvironment safety factor value calculated for the i-th time; i represents starting from the i-th number, and n represents ending at the n-th number; λ represents other influencing factors that affect the RFID tag optimization demand index value. Since this factor has a small impact, this embodiment does not make a specific limitation.

[0087] The real-time feedback module is used to establish a preset value of the RFID tag optimization demand index, judge the RFID tag optimization demand index value according to the preset value of the RFID tag optimization demand index, and send a corresponding signal according to the judgment result.

[0088] In this embodiment, it should be specifically noted that: the preset value of the RFID tag optimization demand index is marked as S def , when S>=S def When S is equal to or greater than the preset value of the RFID tag optimization demand index, a normal signal is sent, indicating that the RFID tag is in good condition and does not need to be optimized. def When , it indicates that the preset value of the RFID tag optimization demand index is marked as S def , when S>=S def When , it means that the RFID tag optimization demand index value is less than the RFID tag optimization demand index preset value, then a warning signal is issued to the relevant technical personnel, which indicates that the RFID tag status is poor and needs to be optimized.

[0089] ​The present invention divides the RFID tag data into different collection batches according to different data features and application scenarios through a data batch division module, which greatly improves the pertinence and efficiency of data processing; through the data collection module, signal data, identification data, fault tolerance data, electromagnetic data, transmission environment data and microenvironment data are collected from multiple angles, and through multi-dimensional data collection, the limitations of traditional collection methods are effectively overcome, and a richer and more comprehensive information source is provided for subsequent accurate analysis; through the RFID tag analysis module, the collected data is deeply analyzed to obtain signal quality coefficient values, identification efficiency coefficient values, fault tolerance coefficient values, electromagnetic interference coefficient values, transmission environment safety coefficient values ​​and microenvironment safety coefficient values, and the performance advantages and improvements of the RFID tag are clearly presented; through the comprehensive analysis module, the output results of the data analysis module are comprehensively evaluated and deeply integrated, and the reliability and accuracy of the data analysis results are further enhanced; through the real-time feedback module, the working status of the RFID tag is continuously tracked, and a warning signal is promptly issued when an abnormal situation occurs, so that logistics management personnel and relevant decision-makers can grasp the operation status and logistics management efficiency of the RFID tag system in real time, and optimize the RFID tag in time, so as to provide strong support for realizing efficient and intelligent logistics management and scientific decision-making.

[0090] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0091] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An artificial intelligence-based RFID tag optimization system, characterized in that: include: Data batch division module: used to determine the data to be collected as target data, divide the target data into different batches according to equal time division, and mark them as 1, 2, ..., n in sequence; Data acquisition module: including system data acquisition unit and environment data acquisition unit, used to collect target data in real time and transmit the collected target data to the data analysis module; The system data acquisition unit is used to collect signal data, identification data and fault tolerance data; the environmental data acquisition unit is used to collect electromagnetic data, transmission environment data and micro-environment data; Data analysis module: including a system data analysis unit and an environment data analysis unit, used to analyze the data transmitted by the data acquisition module and transmit the analysis results to the comprehensive analysis module; the system data analysis unit includes a signal data analysis node, an identification data analysis node and a fault-tolerant data analysis node; the environment data analysis unit includes an electromagnetic data analysis node, a transmission environment data analysis node and a microenvironment data analysis node; Comprehensive analysis module: including an RFID data comprehensive analysis unit, used to comprehensively analyze the data transmitted by the data analysis module and transmit the analysis results to the real-time feedback module; Real-time feedback module: used to establish a preset value of the RFID tag optimization demand index, judge the RFID tag optimization demand index value according to the preset value of the RFID tag optimization demand index, and send a corresponding signal according to the judgment result.

2. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The signal data includes the maximum signal attenuation rate Sa, the phase offset angle Pa and the stability error frequency Sf; the identification data includes the multi-tag identification rate Mr, the identification delay time Lt and the conflict resolution time Ct; the fault tolerance data includes the penetration attenuation rate Pr, the data integrity ratio Dr and the thermal stress threshold Ts.

3. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The electromagnetic data include electrostatic potential volts Ev, spatial electromagnetic field change rate Ec and radio frequency noise density Nd; the transmission environment data include multipath effect attenuation rate Md and polarization mismatch loss rate Pm; the microenvironment data include air humidity vertical change rate Ac, the number of metal obstacles Mn and dust concentration Ed.

4. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The signal data analysis node is used to establish a signal data calculation model, import the signal data transmitted by the data acquisition module into the signal data calculation model, and obtain the signal quality coefficient. The signal data calculation model is specifically expressed as: in, Represents the signal quality coefficient value calculated for the i-th time, Sa i represents the maximum signal attenuation rate of the ith acquisition, Pa i represents the phase offset angle of the i-th acquisition, Sf i represents the stability error frequency of the ith acquisition.

5. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The identification data analysis node is used to establish an identification data calculation model, import the identification data transmitted by the data acquisition module into the identification data calculation model, and obtain the identification efficiency coefficient. The identification data calculation model is specifically expressed as: Among them, l i Represents the recognition efficiency coefficient value of the i-th calculation, Mr i represents the multi-label recognition rate of the i-th acquisition, Lt i Indicates the recognition delay time of the i-th acquisition, Ct i Indicates the conflict resolution time of the i-th collection.

6. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The fault-tolerant data analysis node is used to establish a fault-tolerant data calculation model, import the fault-tolerant data transmitted by the data acquisition module into the fault-tolerant data calculation model, and obtain the fault-tolerant capacity coefficient. The fault-tolerant data calculation model is specifically expressed as: Among them, α i represents the fault tolerance coefficient value calculated for the i-th time, Pr i represents the penetration attenuation rate collected for the i-th time, Dr i represents the data integrity ratio of the ith acquisition, Ts i represents the thermal stress threshold of the ith acquisition.

7. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The electromagnetic data analysis node is used to establish an electromagnetic data calculation model, import the electromagnetic data transmitted by the data acquisition module into the electromagnetic data calculation model, and obtain the electromagnetic interference coefficient. The electromagnetic data calculation model is specifically expressed as: Among them, β i Indicates the electromagnetic interference coefficient value calculated for the i-th time, Ev i represents the electrostatic potential voltage collected for the i-th time, Ec i Nd represents the rate of change of the spatial electromagnetic field collected for the i-th time. i represents the RF noise density of the i-th acquisition.

8. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The transmission environment data analysis node is used to establish a transmission environment data calculation model, import the transmission environment data transmitted by the data acquisition module into the transmission environment data calculation model, and obtain the transmission environment safety factor. The transmission environment data calculation model is specifically expressed as: Among them, η i Md represents the transmission environment safety factor value calculated for the i-th time. i Pm represents the multipath effect attenuation rate of the ith acquisition. i represents the polarization mismatch loss rate acquired at the i-th time.

9. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The microenvironment data analysis node is used to establish a microenvironment data calculation model, import the microenvironment data transmitted by the data acquisition module into the microenvironment data calculation model, and obtain the microenvironment safety factor. The microenvironment data calculation model is specifically expressed as: Among them, μ i represents the microenvironmental safety factor value calculated for the i-th time, Ac i Indicates the vertical change rate of air humidity collected for the i-th time, Mn i represents the number of metal obstacles collected for the i-th time, Ed i Indicates the dust concentration collected for the i-th time.

10. The artificial intelligence-based RFID tag optimization system according to claim 1, characterized in that: The RFID data comprehensive analysis unit is used to establish an RFID data comprehensive calculation model, and is used to import the signal quality coefficient value, recognition efficiency coefficient value, fault tolerance coefficient value, electromagnetic interference coefficient value, transmission environment safety coefficient value and micro-environment safety coefficient value transmitted by the RFID data analysis unit into the RFID data comprehensive calculation model to obtain the RFID tag optimization demand index; the RFID data comprehensive calculation model is specifically expressed as: Where S represents the calculated RFID tag optimization demand index value, represents the signal quality coefficient value calculated for the i-th time, e i Represents the recognition efficiency coefficient value of the i-th calculation, α i represents the fault tolerance coefficient value calculated for the i-th time, β i represents the electromagnetic interference coefficient value calculated for the i-th time, η i represents the transmission environment safety factor value calculated for the i-th time, μ i represents the microenvironment safety factor value calculated for the i-th time; i represents starting from the i-th number, and n represents ending at the n-th number; λ represents other influencing factors that affect the RFID tag optimization demand index value.

Images