A method, device and system for reading embedded RFID tags

Abstract

The present invention discloses a method, device and system for reading embedded RFID tags. The method comprises: sending a first request to each RFID tag within a detection range; generating a second request containing a random number identifier to be verified, sending the second request to each RFID tag within the detection range, determining the RFID tag to be identified based on the analysis of the response to the second request within a preset response time period, identifying it, and sending a third request with a mute request to the RFID tag that has been identified; updating the random number identifier to be verified, repeating the sending process of the second request and the third request, until all RFID tags within the detection range are identified. The present invention predicts the number of RFID tags, combines the binary characteristics of RFID tags and XOR operations, accurately judges the data of non-adjacent collision bits, reduces the number of invalid time slots, speeds up the query process of identifying tags, and improves reading efficiency and accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of embedded RFID tags, and in particular relates to a method, device and system for reading embedded RFID tags. Background Art

[0002] As a key technology of the Internet of Things, RFID identification technology is constantly developing and widely used in the manufacturing industry. According to the actual production background, process, and flow of the application object, RFID technology will present different use effects, achieve real-time monitoring, quality traceability, automated production and other goals, and better assist production. For example, CN116432672A discloses a reading device and a label of a multi-channel sensor signal acquisition coding passive RFID dedicated tag, including a main control system and an RFID reader-writer device, the RFID reader-writer device is provided with an MCU microprocessor and an RFID base station chip, the RFID reader-writer device is connected with an external interface and a reading device antenna, the reading device antenna is connected to the RFID base station chip signal, the main control system is connected to the RFID base station chip signal, the multi-channel sensor signal acquisition coding passive RFID dedicated tag transmits the signal to the RFID base station chip through the RFID wireless carrier, and the external interface transmits the data. It adopts a non-contact passive design method, which greatly reduces the mutual interference between subsystems, and solves the technical problems of poor isolation effect and easy mutual interference between subsystems in the product caused by the use of wired connection to transmit data.

[0003] However, in actual applications, the on-site environment for power cable production is complex. Tags are bound to irregularly placed power cables. The reader needs to read information between many densely placed tags, so it is often interfered by other tag information, which reduces the overall performance of the tag and ultimately leads to missed reading of some tags.

[0004] Therefore, how to provide a reading method that can avoid tag omission is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a method and device for reading embedded RFID tags, which accurately judges the data of two non-adjacent collision bits by predicting the number of power cable RFID tags to be read and combining the binary characteristics of RFID tags and XOR operation, reduces the number of invalid time slots, speeds up the query process of system identification tags, and improves reading efficiency and accuracy. The present invention adopts the following technical solutions.

[0006] A method for reading an embedded RFID tag, the method being applied to a terminal device, the method comprising the following steps:

[0007] Step 1: Send a first request to each RFID tag within the detection range, wherein the first request includes an estimated number of RFID tags within the detection range;

[0008] Step 2: Generate a second request containing a random number identifier to be verified, send the second request to each RFID tag within the detection range, determine the RFID tag to be identified based on the analysis of the response to the second request within a preset response time period, identify it, and send a third request for a mute request to the RFID tag that has been identified;

[0009] Step 3: Update the random number identifier to be verified, and repeat the above second request and third request sending process until all RFID tags within the detection range are identified.

[0010] Furthermore, the random number to be verified is identified as any integer within the estimated number range.

[0011] Furthermore, before sending the first request to each RFID tag within the detection range, the following steps are also included:

[0012] Sending a wake-up request to an RFID tag within a detection range, wherein the wake-up request includes a prefix;

[0013] Based on the analysis of the wake-up request acknowledgement responses within the preset wake-up time period, an estimated number of RFID tags within the detection range is given.

[0014] Furthermore, determining the estimated number of RFID tags within the detection range specifically includes the following steps:

[0015] Based on the analysis of the wake-up request response, successful response and conflict response within the preset wake-up time period, the estimated number of RFID tags to be identified is given.

[0016] Furthermore, in the above step 102, the estimated number of RFID tags within the detection range is given, and the calculation formula is as follows:

[0017] Num p =S+aC

[0018] Among them, Num p is the estimated number of RFID tags within the detection range, S is the number of RFID tags that respond, a is the preset weighting coefficient, a∈[2,3]; C is the number of RFID tags that respond in conflict.

[0019] Further, based on the analysis of the second request response within the preset response time period, specifically including:

[0020] The number of second request acknowledgement responses received within a preset acknowledgement time period and the RFID tags making the second request acknowledgement responses are determined.

[0021] Further, until all RFID tags within the detection range are identified, specifically including:

[0022] The number of RFID tags that have been identified is compared with the estimated number. If the number of RFID tags that have been identified is less than the estimated number, and the value of the random number identifier to be verified is less than or equal to the estimated number, the identification of the RFID tags to be identified within the detection range has not been completed. Otherwise, the identification of all RFID tags within the detection range has been completed.

[0023] Furthermore, in the above step 2, when no second request response is received within a preset response time period, the corresponding random number identifier to be verified is determined as an invalid identifier, and the value of the random number identifier to be verified is self-incremented to update the current random number identifier to be verified.

[0024] A method for reading an embedded RFID tag, the method being applied to an RFID tag, the method comprising the following steps:

[0025] Step 1: receiving a first request sent by a terminal device, wherein the first request includes an estimated number of RFID tags within a detection range;

[0026] Step 2: Generate a random number identifier corresponding to itself according to the estimated quantity, wherein the random number identifier is any integer within the range of the estimated quantity;

[0027] Step 3: receiving a second request sent by the terminal device, wherein the second request includes a random number identifier to be verified;

[0028] Step 4: Based on the comparison between the random number identifier to be verified and the random number identifier, a second request response is made to the terminal device;

[0029] Step 5: Based on the identification of the terminal device, receive the third request sent by the terminal device and enter the mute state.

[0030] Furthermore, before receiving the first request sent by the terminal device, the method further includes the following steps:

[0031] Receiving a wake-up request sent by a terminal device, wherein the wake-up request includes a prefix;

[0032] Determine the reservation identifier corresponding to itself within the preset wake-up value range according to the prefix, and generate a wake-up request response containing the reservation identifier;

[0033] Send the wake-up request acknowledgement response to the terminal device.

[0034] Furthermore, determining a reservation identifier corresponding to itself within a preset wake-up value range according to the prefix, and generating a wake-up request response containing the reservation identifier, specifically includes: receiving a wake-up request from a terminal device, the wake-up request including a prefix; calculating a value range according to the prefix, and randomly selecting a number within the value range as the reservation identifier, and sending it to the terminal device to implement the wake-up request response.

[0035] Further, according to the comparison between the random number identifier to be verified and the random number identifier, a second request response is made to the terminal device, specifically including:

[0036] Obtain the stored random number identifier, and compare the random number identifier with the random number identifier to be verified in the second request. If the two are the same, send a second request response to the terminal device; if the two are not the same, do not make a response.

[0037] A reading device for an embedded RFID tag, specifically comprising:

[0038] A request sending unit sends a first request to each RFID tag within the detection range, wherein the first request includes an estimated number of RFID tags within the detection range;

[0039] Generate a second request containing a random number identifier to be verified, and send the second request to each RFID tag within the detection range;

[0040] Sending a third request for a mute request to the identified RFID tag;

[0041] Update the random number identifier to be verified, and repeat the second request and the third request sending process until all RFID tags within the detection range are identified;

[0042] The identification unit determines the RFID tag to be identified based on the analysis of the second request response within a preset response time period, and performs identification.

[0043] A reading device for an embedded RFID tag, specifically comprising:

[0044] A request receiving unit, receiving a first request sent by a terminal device, wherein the first request includes an estimated number of RFID tags within a detection range;

[0045] Receiving a second request sent by the terminal device, wherein the second request includes a random number identifier to be verified;

[0046] According to the identification of the terminal device, receiving a third request sent by the terminal device and entering a mute state;

[0047] The response unit generates a random number identifier corresponding to itself according to the estimated number, wherein the random number identifier is any integer within the range of the estimated number;

[0048] Based on the comparison between the random number identifier to be verified and the random number identifier, a second request response is made to the terminal device.

[0049] An embedded RFID tag reading system includes at least one terminal device and a plurality of RFID tags;

[0050] When any terminal device performs reading, the above-mentioned reading method is executed;

[0051] When any RFID tag is read, the above-mentioned reading method is executed.

[0052] An embedded RFID tag reading system, the system comprising one or more terminal devices, a plurality of RFID tags and an application server;

[0053] The terminal device comprises a first memory and a first processor, the first memory stores a first computer program, and when the first computer program is executed by the first processor, the method in the terminal device is implemented;

[0054] The RFID tag adopts a resonator-based round-shaped tag structure, including a second memory and a second processor. The second memory stores a second computer program. When the second computer program is executed by the second processor, the method in the RFID tag is implemented.

[0055] The present invention provides an embedded RFID tag reading method, device and system, which have at least the following beneficial effects: the reading method of the present invention can accurately predict the number of RFID tags to be identified, and when an RFID tag reading conflict occurs, determine the combination of conflicting tag transmission information, effectively reduce the number of reading interactions, and reduce system overhead; in the identification process, the tag information can be quickly read, breaking through the bottleneck of low recognition efficiency of traditional anti-collision algorithms. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the composition structure of the reading and writing device;

[0057] Figure 2 It is a schematic diagram of the structure of an RFID tag;

[0058] Figure 3 A flowchart of a reading method on the terminal device side;

[0059] Figure 4It is a flowchart of a reading method on the RFID tag side;

[0060] Figure 5 Data flow diagram of the reading method of the embedded RFID tag.

[0061] Reference numerals:

[0062] 1. RFID tag; 2. Terminal device; 3. Reading range of the terminal device. DETAILED DESCRIPTION

[0063] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. 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.

[0064] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0065] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0066] RFID wireless radio frequency identification technology is a non-contact automatic identification technology that can be applied to various complex and harsh environments. The embedded RFID tag reading and writing device consists of an RFID tag, multiple terminal devices (reading and writing devices) and an application server (not shown). Figure 1 After receiving the radio frequency signal sent by the terminal device, the RFID tag uses the antenna and rectifier circuit to obtain energy, drive the RFID tag to complete the preset signal collection, data storage and communication handshake with the terminal device, and then upload the RFID tag's identity ID and collected data to the terminal device.

[0067] The RFID tag of the present invention adopts a resonator-based circular tag structure, such as Figure 2The overall size of the label structure is 60mm×36mm 2 , consisting of 2 groups of L-shaped resonators and 2 I-shaped resonators patched on a rectangular substrate, 2 I-shaped resonators are arranged in parallel in the middle of the round-shaped label structure, 2 groups of L-shaped resonators are arranged diagonally symmetrically, one group of L-shaped resonators is located on the left side of the I-shaped resonator and extends to the lower left, and the other group of L-shaped resonators is located on the right side of the I-shaped resonator and extends to the upper right; each group of L-shaped resonators consists of 8 L-shaped resonators arranged from left to right. The rectangular substrate is made of polyvinyl chloride, with a relative dielectric constant ε r is 3.3, thickness is 0.1mm, and loss tangent tanδ is 0.077. Figure 2 Where L represents the width of a group of L-shaped resonators in the paper-shaped tag structure, which is 30 mm; H represents the length of the paper-shaped tag structure, which is 36 mm; W represents the width of the resonator, which is 1 mm; S represents the gap between the resonators, which is 1 mm; L1-L8 represent the lengths of different resonators, respectively, satisfying the calculation formula L i+1 =55-5i, i∈[0,7]. The length of each resonator can be determined by the above calculation formula: L1=55mm, L2=50mm, L3=45mm, L4=40mm, L5=35mm, L6=30mm, L7=25mm, L8=20mm, and the length difference and spacing between each resonator are the same. The horizontally polarized wave is used to illuminate the round-shaped tag structure. The overall peak value of the two groups of L-type resonators and the two I-type resonators increases, with the maximum increase of about 5dBsm, which is conducive to the long-distance recognition of RFID tags.

[0068] In another embodiment, the structural parameters of the paper-shaped label structure are maintained, and the substrate is a high-frequency material mixed press board with a relative dielectric constant ε r is 3.3, the thickness is 0.15mm, and the loss tangent tanδ is 0.077.

[0069] Different terminal equipment models and parameters correspond to different detection ranges. The determination of the detection range can be expressed by the following relationship:

[0070]

[0071] Where D represents the detection range of the terminal device, G T Indicates the signal gain of the transmitting antenna in the terminal device, G D represents the signal gain of the receiving antenna of the terminal device, λ represents the signal wavelength, and P T represents the transmission power of the transmitting antenna in the terminal device, σ represents the scattering cross section of the round-shaped tag structure, P min Indicates the sensitivity of the terminal device.

[0072] It can be seen that the recognition distance of the terminal device is proportional to the σ value of the paper-shaped tag structure. Therefore, when other conditions remain unchanged, when the paper-shaped tag structure has a higher σ value, the detection range of the terminal device will be improved accordingly.

[0073] In another embodiment, by shortening the gap S between multiple L-shaped tags, the radar cross section can be increased to a certain extent, thereby obtaining a farther tag recognition distance.

[0074] The present invention provides a method for reading an embedded RFID tag. Since the information of RFID tags implanted on different types of power cables occupies different data lengths, the information format of the RFID tag is unified for the convenience of data parsing. The information of the RFID tag includes two parts: a header and valid data, wherein the header is 128B (bits) and the valid data is (N-1)×128B (bits), and N is the initial value of the prefix, for example, N=8; if there is remaining space in the last block 128B, zero padding is automatically performed to meet the RFID tag information storage requirements. When performing data parsing, the first 128B is first received to obtain information such as the acquisition time and the valid data length, and then the valid data content is continued to be received according to the valid data length, and finally the indefinite length data content is completely parsed to obtain the corresponding key information. The total number of tags within the detection range is estimated by the prediction algorithm, and then all tags are grouped using random number identifiers. If multiple tags select the same random number identifier, it means that there is a conflict response, and the tags with the conflict response are identified and processed.

[0075] The tag reading method of the present invention is as follows Figures 3 to 5 As shown, the specific process is as follows:

[0076] Step S1, sending a first request to each RFID tag within the detection range, wherein the first request includes an estimated number of RFID tags within the detection range;

[0077] The RFID tag receives a first request sent by the terminal device; and generates a random number identifier corresponding to itself according to the estimated number, wherein the random number identifier is any integer within the range of the estimated number.

[0078] The RFID tag receives a wake-up request sent by the terminal device, wherein the wake-up request includes a prefix; determines a reservation identifier corresponding to itself within a preset wake-up value range according to the prefix, and generates a wake-up request response including the reservation identifier; and sends the wake-up request response to the terminal device;

[0079] In the above steps, the terminal device broadcasts the estimated quantity (first request) to the RFID tags within the detection range by broadcasting.

[0080] For application scenarios with higher real-time requirements, in a first embodiment, the estimated number of RFID tags within the detection range can be determined from the terminal device and the RFID tag end respectively. Specifically, taking the terminal device as an example, the estimated number of RFID tags within the detection range is determined including:

[0081] Sending a wake-up request to an RFID tag within a detection range, wherein the wake-up request includes a prefix;

[0082] Based on the analysis of the wake-up request acknowledgement responses within the preset wake-up time period, an estimated number of RFID tags within the detection range is given.

[0083] Taking RFID tags as an example, the estimated number of RFID tags within the detection range is determined including:

[0084] Receiving a wake-up request sent by a terminal device, wherein the wake-up request includes a prefix;

[0085] Determine the reservation identifier corresponding to itself within the preset wake-up value range according to the prefix, and generate a wake-up request response containing the reservation identifier;

[0086] Send the wake-up request acknowledgement response to the terminal device.

[0087] The present invention can also provide an estimated number of RFID tags within the detection range from an overall perspective, specifically comprising the following steps:

[0088] Step 101: The terminal device broadcasts a wake-up request to all RFID tags within the detection range, and the wake-up request carries a prefix symbol P;

[0089] The value of the prefix can be set according to different application scenarios. In this embodiment, the initial value of the prefix P is 8.

[0090] Step 102: After receiving the prefix in the wake-up request, each RFID tag randomly selects a number within a preset wake-up value range as a reservation identifier, and generates a wake-up request response containing the reservation identifier;

[0091] Send a wake-up request response to the terminal device, carrying the reservation identifier in the wake-up request response; the wake-up value range can be preset according to different application scenarios. For example, in this embodiment, the wake-up value range is 1 to 2 P ;

[0092] In the above step 102, the reservation identifier is selected and generated by the random number generator built into the RFID tag. After a short delay, the RFID tag sends the selected reservation identifier to the terminal device in the wake-up request response. The length of the reservation identifier can be one byte (8 bits).

[0093] Step 103: The terminal device receives the wake-up request response sent by the RFID tag within the preset wake-up time period, thereby calculating the number of successful responses S and the number of conflicting responses C;

[0094] If the number of conflicting responses is equal to the total number of wake-ups, that is, C = 2 P , then the number of RFID tags within the detection range is greater than 2 P , it is necessary to perform a self-increment operation on the prefix symbol P, and return to step 101 to execute again;

[0095] If the number of conflicting responses is less than 1 / 3 of the total number of wake-ups, that is, C < 2 P / 3, the estimated number of RFID tags to be identified is determined based on the number of successful responses and the number of conflicting responses;

[0096] Since there is path loss during the propagation of the signal, the longer the propagation path, the greater the path loss. In the process of reading the RFID tag in the power cable, the terminal device sends a read signal to the RFID tag, the RFID tag receives and responds to the signal, and carries the data in the response signal to the terminal device.

[0097] In order to enable the terminal equipment to detect the RFID tag RF1-RF embedded in the power cable N The reading takes into account both efficiency and accuracy. In the above step 103, the terminal device analyzes and counts the received wake-up request response, determines the number of successful responses S and the number of conflicting responses C. In the above step 103, the estimated number is calculated by the following formula:

[0098] Num p =S+aC

[0099] Among them, Num p is the estimated number of RFID tags within the detection range, S is the number of RFID tags that respond, C is the number of RFID tags that respond in conflict, a is the preset weighting coefficient, a∈[2,3], and the preferred value of a is 2.4.

[0100] In order to ensure a good interaction effect between the terminal device and the RFID tag, before sending a wake-up request to the RFID tag within the detection range, the RFID tags within the detection range are filtered through a pre-set filtering model so that they meet the predetermined conditions. Specifically, the filtering model is as follows:

[0101]

[0102] Among them, M1 represents the RFID tag RF embedded in the power cable i The maximum value of the signal power returned to the terminal device; M2 indicates the maximum value of the signal power returned to the terminal device when the terminal device is identifying the RFID tag RF i The minimum distance between them; st means that the condition is met; D i Indicates that the terminal device is identifying with the RFID tag RF i The distance between ij Indicates RFID tag RF i With RF j The vertical distance between ij Indicates RFID tag RF i With RF j The horizontal distance between i Indicates the RFID tag on the power cable i The power of the returned signal transmitted to the location of the terminal device; PW limit It indicates the minimum threshold for transmitting the signal returned from the RFID tag embedded in the power cable to the location of the terminal device. i represents the i-th tag of the RFID tag, RF j represents the jth tag of the RFID tag.

[0103] In the above filtering model, the RFID tag RF i The power PW_return of the returned signal delivered to the location of the terminal device i It should be as large as possible to ensure that the power of the return signal when it reaches the terminal device can meet the minimum requirement for the terminal device to effectively identify the signal. The location where the terminal device outputs the signal is close to the tag RF i The distance D i The output power PW of the terminal equipment is also defined in the filtering model. OUT , RFID tags on power cables i Received signal power PW_recv sent by the terminal device i , RFID tags on power cables i Signal power returned to the terminal device PW_back i .

[0104] For application scenarios that require higher accuracy of data analysis, in a second embodiment, an estimated number of RFID tags within the detection range is given, which specifically includes the following steps:

[0105] Step 101', obtain historical statistical information of the terminal device broadcasting wake-up signals of different frame lengths to all RFID tags within the detection range and the RFID tags responding, and calculate the idle number E of the number of RFID tags n in the time period under different wake-up signal frame lengths J. t , the number of successful responses S t 、Number of conflicting responses C t , estimate the number of remaining labels Left t , and generate the corresponding prediction model training data set Train_N = {Left t |(E t ,S t ,C t )}, the calculation formula is as follows:

[0106] E t =nP1;S t =nP2;C t =NP3;Left t =nS t ;

[0107] P3=1-P2-P1

[0108] Where P1 is the idle ratio of RFID tags, P2 is the successful response ratio of RFID tags, and P3 is the conflict response ratio of RFID tags.

[0109] In the above steps, the value of the wake-up signal frame length J and the number of RFID tags n can be preset to correspond to each other, and the specific correspondence varies according to different scenarios. For example, in a certain embodiment: frame length J = 4, number of tags n∈[1,4]; frame length J = 8, number of tags n∈[5,10]; frame length J = 16, number of tags n∈[11,22]; frame length J = 32, number of tags n∈[23,44]; frame length J = 64, number of tags n∈[45,88]; frame length J = 128, number of tags n is greater than or equal to 89;

[0110] Step 102', input the prediction model training data set Train_N corresponding to different wake-up signal frame lengths J into the prediction model for training, and obtain the trained prediction model Model_N of the corresponding wake-up signal frame length J after realizing the indicator constraint. t ;

[0111] In the above steps, the establishment of the prediction model includes the following steps:

[0112] Step 1021', initialize the prediction model structure, and configure initial parameters and constraints;

[0113] Initialize the prediction model structure. The prediction model includes 3 input neurons, 5 hidden neurons and 1 output neuron. The 3 input neurons represent the number of idle time periods E, the number of successful responses S and the number of conflicting responses C respectively. The output neuron represents the number of predicted remaining labels Left.

[0114] Configure prediction factors t , by configuring the initial step size to set the query area, predict the element d t The calculation formula is as follows:

[0115]

[0116] Among them, D max , D min Respectively represent the maximum and minimum values ​​of the step length; f t , They represent the individual matching degree after t rotations, the average matching degree of the individual group, the maximum matching degree, and the minimum matching degree respectively; the matching degree calculation formula is as follows:

[0117]

[0118]

[0119] Where N represents the number of training samples; E_sample i 、S_sample i 、C_sample i Respectively represent the output value of the i-th training sample of the idle quantity E in the time period; E_sample' i 、S_sample' i 、C_sample' i They represent the true values ​​of the i-th training sample of the idle number E, successful response number S, and conflict response number C of the time period respectively;

[0120] Constraints include accuracy threshold and rotation maximum value;

[0121] Initialize the model individual group, use piecewise linear chaotic mapping to create the initial model individual group, assign a random vector to each model individual, and calculate the matching degree of the initial position;

[0122] Step 1022': Use the known position information to calculate the individual matching degree after t rotations Average match with the population Update the individual's location and adjust the threshold and weight of the prediction model to calculate the matching degree of the current location information and update the prediction model;

[0123]

[0124] Among them, d t Represents the forecast element; Indicates the predicted direction. After t rotations, if the matching degree of the left trend is greater than that of the right trend, sign() takes 1, and the individual moves in the left direction; if the matching degree of the right trend is greater than that of the left trend, the individual moves in the right direction; represents the guiding strategy, s t represents the learning factor, represents the best individual in the population, δ represents a random value that satisfies the (0,1) random distribution, It means that in the b-time rotation process, the best individual and the general individual in the individual group are compared to determine the guidance strategy for the general individual;

[0125] Step 1023', determine whether the preset constraints are met. If the matching degree meets the accuracy threshold or the number of rotations reaches the maximum value, the initial weights and thresholds obtained from the training of the prediction model are input into the prediction model again for secondary training, and finally the prediction model Model_N is output. t .

[0126] In another embodiment, when the prediction model iteration is completed and the matching function value satisfies the preset accuracy threshold of 0.03 and the rotation maximum value of 10000, the initial weights and thresholds obtained from the training of the prediction model are input into the prediction model again for secondary training.

[0127] Step 103', the terminal device starts the identification operation, and determines the number of idle time periods E, the number of completed reads S, and the number of conflicts C corresponding to the current wake-up signal frame length N; determines whether the number of idle time periods E, the number of completed reads S, and the number of conflicts C are all 0. If they are all zero, the reading operation is terminated; if they are not all zero, the number of idle time periods E, the number of completed reads S, and the number of conflicts C are input into the trained prediction model Model_N t , output the estimated number of remaining tags Left, and determine the estimated number of RFID tags to be identified.

[0128] Step S2, generating a second request containing a random number identifier to be verified, sending the second request to each RFID tag within the detection range, determining the RFID tag to be identified based on the analysis of the response to the second request within a preset response time period, identifying the RFID tag, and sending a third request for a mute request to the RFID tag that has been identified;

[0129] The RFID tag receives a second request sent by the terminal device, wherein the second request includes a random number identifier to be verified; based on a comparison between the random number identifier to be verified and the random number identifier, a second request response is made to the terminal device; based on the identification status of the terminal device, a third request sent by the terminal device is received and a mute state is entered.

[0130] Determine whether the identification of the RFID tags to be identified within the detection range is completed according to the number of identified tags and the random number identification to be verified;

[0131] If it is completed, the identification process ends; if it is not completed, step S3 is executed;

[0132] In the above steps, the number of identified tags is compared with the estimated number. If the number of identified tags is less than the estimated number, and the random number identifier to be verified is less than or equal to the estimated number, the identification of the RFID tags to be identified within the detection range has not been completed.

[0133] If the random number identifier to be verified is less than or equal to the estimated number, the terminal device broadcasts the random number identifier to be verified to the RFID tags within the detection range, and the RFID tags determine whether their own random number identifier is the same as the random number identifier to be verified; if they are the same, the RFID tag with the random number identifier with the same value as the random number identifier to be verified broadcasts a response to the terminal device;

[0134] In the above steps, after receiving the broadcast message sent by the terminal device, the RFID tag obtains the random number identifier to be verified carried in the broadcast message, and determines whether its own random number identifier is the same as the random number identifier to be verified. If they are the same, the RFID tag selects the random number identifier sent by the current terminal device, thereby determining the RFID tag that responds to the terminal device;

[0135] Step S3: update the random number identifier to be verified, and repeat the above second request and third request sending process until all RFID tags within the detection range are identified.

[0136] The terminal device determines whether a broadcast response from the RFID tag is received within a preset time period; if no broadcast response is received, a self-addition operation is performed on the random number identifier to be verified, and the process returns to and continues with step S2; if a broadcast response is received, step S4 is continued;

[0137] In the above steps, if no broadcast response is received, it indicates that in the operation of randomly generating a random number identifier, no RFID tag has generated a random number identifier with the same value as the random number identifier to be verified, then the current random number identifier to be verified is an empty random number identifier, and after performing a self-addition operation, the random number identifier to be verified is updated;

[0138] Step S4, the terminal device determines whether the number of received broadcast response responses is greater than or equal to 2. If so, a tag conflict occurs, the tag in conflict is identified, and a mute instruction is sent to the identified tag, the number of identified tags is updated, and a self-add operation is performed on the random number identifier to be verified;

[0139] If not, there is no conflict, identify the RFID tag that broadcasts the response, and send a mute instruction to it after the identification is completed, perform self-addition operations on the random number identifier to be verified and the random number identifier to be verified respectively, and return to and execute step 2.

[0140] In one implementation, identifying conflicting tags specifically includes the following steps:

[0141] Step 401, the terminal device sends a first instruction and checks whether a first instruction response is received. If not, the current period is idle and step 402 is executed; if received, step 403 is executed; the first instruction response includes identification information of each valid RFID tag itself;

[0142] In the above steps, the terminal device sends a first instruction, such as a notification or wake-up instruction, by broadcasting. All valid RFID tags in the power cable within its reading range respond to the notification or wake-up of the terminal device, and respond with feedback, returning the first instruction response. If the first instruction response (response feedback) is not received, it means that there is no valid RFID tag within the reading range. The identification information of the RFID tag itself is a globally unique identification code composed of 0 and 1. The specific implementation method of the above notification or wake-up instruction is to execute the function Inform (Preceder, CF), where Preceder is a prefix, indicating that the corresponding RFID tag is in a valid state. CF is a conflict indication identifier, CF∈(0,1), "1" indicates a conflict occurs, that is, at least two RFID tags transmit signals to the terminal device at the same time, "0" indicates that no conflict occurs, the specific position of the conflict bit is determined according to CF, and the grouping information is returned to the terminal device according to the attribute value CV.

[0143] The terminal device receives the response data of the conflicting RFID tag until the third conflicting bit is received. Then the terminal device sends a command to the tag to indicate the specific location of the conflicting bit, with "1" representing the conflicting bit and "0" representing the non-conflicting bit. If the terminal device sends 1010, it means that the first and third bits are conflicting bits, and the group number information is returned to the terminal device according to the attribute value rule. If the group number does not conflict, then the combination of the two conflicting bits can be accurately inferred. If the group number conflicts, then the combination of the four conflicting bits can be directly inferred.

[0144] Step 402: The terminal device checks whether the current cache is empty. If the cache is empty, there is no prefix of the RFID tag to be queried, and the reading process ends. If the cache is not empty, there is a prefix of the RFID tag to be queried, and the process jumps to step 406.

[0145] In the above steps, the terminal device includes a cache for storing the prefix.

[0146] Step 403: the terminal device checks whether a conflict occurs with the RFID tag that responds to the first instruction; if no conflict occurs, the current period is in a readable state, the terminal device directly identifies the RFID tag and sets the RFID tag to a mute state, and returns to step 402 to continue execution; if a conflict occurs, the current period is in a conflict state;

[0147] In Manchester encoding, the first half cycle of the digital 0 is low level, and the second half cycle is high level, and the first half cycle of the digital 1 is high level, and the second half cycle is low level. Therefore, the digital signal composed of 0 and 1 cannot be high or low level for three consecutive half cycles. If it is high or low level for three consecutive half cycles, it can be judged that a conflict has occurred. In the above steps, the terminal device judges the conflict based on the above principle. If there is no conflict, it means that only one RFID tag currently returns the first command response, and the current period is in a readable state.

[0148] Step 404: The terminal device receives the response data of the conflicting RFID tag, and when receiving the third conflicting bit, sends a second instruction to the conflicting RFID tag to indicate the position of the conflicting bit, and the RFID tag returns the attribute value to the terminal device according to the attribute value rule;

[0149] In the above steps, the second instruction is to execute the function Inform(Preceder, CF), which is used to indicate the position of the conflicting bit. For example, the mth bit and the nth bit are conflicting bits, namely Cm and Cn. According to the first-in-first-out rule, the prefix that enters the cache first has the highest priority and will be output from the cache first. The i-th bit and the j-th bit of the identification information of the RFID tag itself are represented by Bi and B j , if B i and B j After the XOR operation, the result is 1, then the attribute value CV is 1; if B i and B j If the result after XOR operation is 0, the attribute value CV is 0. By summarizing the different values ​​of the attribute value CV, the following grouping can be obtained:

[0150] Attribute value CV is 0: (B i ,B j ) is (0,1) or (1,0)

[0151] The attribute value CV is 1: (B i ,B j ) is (0,0) or (1,1)

[0152] In the case of the above grouping, if the terminal device receives a group from an attribute value CV=1, the m-th and n-th bits of the response data of the conflicting RFID tag are conflict bits, namely Cm and Cn, respectively. According to the above grouping, it can be determined that the values ​​of Cm and Cn are mutually different, namely 0 and 1, from which it can be deduced that the combinations of conflict bits are Cm=1, Cn=0 and Cm=0, Cn=1; if Cm and Cn are from the CV=0 group, then Cm and Cn are the same value, from which it can be deduced that the combinations of conflict bits are Cm=0, Cn=0 and Cm=1, Cn=1.

[0153] Step 405: The terminal device receives the attribute value, determines whether the attribute value conflicts, and determines a combination of conflicting bits; the terminal device executes a third instruction to place the prefix at the bottom of the cache;

[0154] In the above steps, if there is no conflict in the attribute value CV, two combinations of conflicting bits are determined. When CV=0, the conflicting bits are (0,0) and (1,1); when CV=1, the conflicting bits are (0,1) and (1,0); if there is a conflict in the attribute value CV, four combinations of conflicting bits are determined, and the conflicting bits are (0,0), (0,1), (1,0), and (1,1); the third instruction is to execute the function Press(Preceder), which is used to place the newly generated prefix at the bottom of the cache.

[0155] Step 406: The terminal device executes the fourth instruction, takes out the prefix of the next round of polling from the top of the cache, returns and continues to execute step 402;

[0156] In the above steps, the fourth instruction is to execute the function Eject(Preceder), which takes out the Preceder from the top of the cache Cache as the prefix of the next round of polling.

[0157] In the above RFID tag identification method, the terminal device only receives the data before the third conflicting bit in the information transmitted by the RFID tag, which effectively reduces the time consumed by bit transmission and improves the identification efficiency of the RFID tag by identifying the conflicting bit.

[0158] In the above steps, the number of identified tags is updated and calculated using the following formula:

[0159]

[0160] Wherein, Num is the updated number of identified tags, Num0 is the number of identified tags before the update, M is the number of extension codes, and the value is one of 16, 32 or 64; m is the number of conflicts; F is the initial signal frame length;

[0161] The corresponding relationship between the initial signal frame length F and the number of RFID tags is as follows: frame length F = 4, the number of tags n∈[1,4]; frame length F = 8, the number of tags n∈[5,10]; frame length F = 16, the number of tags n∈[11,22]; frame length F = 32, the number of tags n∈[23,44]; frame length F = 64, the number of tags n∈[45,88]; frame length F = 128, the number of tags n is greater than or equal to 89.

[0162] The present invention provides a reading device for an embedded RFID tag, specifically comprising:

[0163] A request sending unit sends a first request to each RFID tag within the detection range, wherein the first request includes an estimated number of RFID tags within the detection range;

[0164] Generate a second request containing a random number identifier to be verified, and send the second request to each RFID tag within the detection range;

[0165] Sending a third request for a mute request to the identified RFID tag;

[0166] Update the random number identifier to be verified, and repeat the second request and the third request sending process until all RFID tags within the detection range are identified;

[0167] The identification unit determines the RFID tag to be identified based on the analysis of the second request response within a preset response time period, and performs identification.

[0168] The present invention provides a reading device for an embedded RFID tag, specifically comprising:

[0169] A request receiving unit, receiving a first request sent by a terminal device, wherein the first request includes an estimated number of RFID tags within a detection range;

[0170] Receiving a second request sent by the terminal device, wherein the second request includes a random number identifier to be verified;

[0171] According to the identification of the terminal device, receiving a third request sent by the terminal device and entering a mute state;

[0172] The response unit generates a random number identifier corresponding to itself according to the estimated number, wherein the random number identifier is any integer within the range of the estimated number;

[0173] Based on the comparison between the random number identifier to be verified and the random number identifier, a second request response is made to the terminal device.

[0174] The present invention provides an embedded RFID tag reading system, comprising at least one terminal device and a plurality of RFID tags;

[0175] When any terminal device performs reading, the above-mentioned reading method is executed;

[0176] When any RFID tag is read, the above-mentioned reading method is executed.

[0177] The present invention provides an embedded RFID tag reading device, which includes one or more terminal devices, multiple RFID tags and an application server; the terminal device includes a first memory and a first processor, the first memory stores a first computer program, and when the first computer program is executed by the first processor, the method on the terminal device side is implemented;

[0178] The RFID tag adopts a resonator-based round-shaped tag structure, including a second memory and a second processor. The second memory stores a second computer program. When the second computer program is executed by the second processor, the above-mentioned RFID tag side method is implemented.

[0179] Various implementations of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0180] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0181] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0182] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0183] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. A method for reading an embedded RFID tag, characterized in that: The reading method is executed by a terminal device and includes the following steps: Sending a first request to each RFID tag within the detection range, wherein the first request includes an estimated number of RFID tags within the detection range; Generate a second request containing a random number identifier to be verified, send the second request to each RFID tag within the detection range, determine the RFID tag to be identified based on the analysis of the response to the second request within a preset response time period, identify it, and send a third request for a mute request to the RFID tag that has been identified; Update the random number identifier to be verified, and repeat the second request and the third request sending process until all RFID tags within the detection range are identified; The estimated number of RFID tags within the detection range is given, specifically including the following steps: Step 101', obtaining historical statistical information of the terminal device broadcasting wake-up signals with different frame lengths to all RFID tags within the detection range and the RFID tags providing feedback, and calculating the number of idle RFID tags, the number of successful responses, the number of conflicting responses, and the estimated number of remaining tags in the time period under different wake-up signal frame lengths, and generating a corresponding prediction model training data set; Step 102', respectively inputting prediction model training data sets corresponding to different wake-up signal frame lengths into the prediction model for training, to obtain trained prediction models of corresponding wake-up signal frame lengths; Step 103', the terminal device starts the identification operation, and determines the number of idle time periods, the number of completed reads, and the number of conflicts corresponding to the current wake-up signal frame length; determines whether the number of idle time periods, the number of completed reads, and the number of conflicts are all 0, and if they are all zero, then the reading operation is terminated; if they are not all zero, then the number of idle time periods, the number of completed reads, and the number of conflicts are input into the trained prediction model, the estimated number of remaining tags is output, and the estimated number of RFID tags to be identified is determined; The establishment of the prediction model includes the following steps: Step 1021', initialize the prediction model structure, and configure initial parameters and constraints; Step 1022', using the known location information, calculate the The individual matching degree after the rotation is compared with the average matching degree of the individual group, the individual position is updated, and the threshold and weight of the prediction model are adjusted to calculate the matching degree of the current position information and realize the update of the prediction model; Step 1023', determine whether the preset constraints are met. If the matching degree meets the accuracy threshold or the number of rotations reaches the maximum rotation value, the initial weights and thresholds obtained from the training of the prediction model are input into the prediction model again for secondary training, and finally the prediction model is output.

2. The reading method according to claim 1, characterized in that: The random number to be verified is identified as any integer within the estimated number range.

3. The reading method according to claim 2, characterized in that: Based on the analysis of the second request response within the preset response time period, specifically including: The number of second request acknowledgement responses received within a preset acknowledgement time period and the RFID tags making the second request acknowledgement responses are determined.

4. The reading method according to claim 1, characterized in that: Before sending the first request to each RFID tag within the detection range, the following steps are also included: Sending a wake-up request to an RFID tag within a detection range, wherein the wake-up request includes a prefix; Based on the analysis of the wake-up request acknowledgement responses within the preset wake-up time period, an estimated number of RFID tags within the detection range is given.

5. The reading method according to claim 1, characterized in that: Updates the location of an individual, including: ； in, Represents the forecast element; Indicates the prediction direction. After the rotation, if the matching degree of the left trend is greater than that of the right trend, If it is 1, the individual moves to the left; if the matching degree of the right trend is greater than that of the left trend, the individual moves to the right; Indicates the guiding strategy, represents the learning factor, represents the best individual in the population, represents a random value that satisfies the (0,1) random distribution. Indicated in During the rotation, the best individual and the average individual in the group are compared to determine the guidance strategy for the average individual. , Respectively represent the maximum and minimum values ​​of the step length; , , , Respectively indicate that The individual matching degree after the rotation, the average matching degree of the individual group, the maximum matching degree and the minimum matching degree.

6. A method for reading an embedded RFID tag, characterized in that: The reading method is performed by the RFID tag and includes the following steps: Receiving a first request sent by a terminal device, wherein the first request includes an estimated number of RFID tags within a detection range; Generate a random number identifier corresponding to itself according to the estimated quantity, wherein the random number identifier is any integer within the range of the estimated quantity; Receiving a second request sent by the terminal device, wherein the second request includes a random number identifier to be verified; Performing a second request response to the terminal device based on the comparison between the random number identifier to be verified and the random number identifier; According to the identification of the terminal device, receiving a third request sent by the terminal device and entering a mute state; The estimated number of RFID tags within the detection range is given, specifically including the following steps: Step 101', obtaining historical statistical information of the terminal device broadcasting wake-up signals with different frame lengths to all RFID tags within the detection range and the RFID tags providing feedback, and calculating the number of idle RFID tags, the number of successful responses, the number of conflicting responses, and the estimated number of remaining tags in the time period under different wake-up signal frame lengths, and generating a corresponding prediction model training data set; Step 102', respectively inputting prediction model training data sets corresponding to different wake-up signal frame lengths into the prediction model for training, to obtain trained prediction models of corresponding wake-up signal frame lengths; Step 103', the terminal device starts the identification operation, and determines the number of idle time periods, the number of completed reads, and the number of conflicts corresponding to the current wake-up signal frame length; determines whether the number of idle time periods, the number of completed reads, and the number of conflicts are all 0, and if they are all zero, then the reading operation is terminated; if they are not all zero, then the number of idle time periods, the number of completed reads, and the number of conflicts are input into the trained prediction model, the estimated number of remaining tags is output, and the estimated number of RFID tags to be identified is determined; The establishment of the prediction model includes the following steps: Step 1021', initialize the prediction model structure, and configure initial parameters and constraints; Step 1022', using the known location information, calculate the The individual matching degree after the rotation is compared with the average matching degree of the individual group, the individual position is updated, and the threshold and weight of the prediction model are adjusted to calculate the matching degree of the current position information and realize the update of the prediction model; Step 1023', determine whether the preset constraints are met. If the matching degree meets the accuracy threshold or the number of rotations reaches the maximum rotation value, the initial weights and thresholds obtained from the training of the prediction model are input into the prediction model again for secondary training, and finally the prediction model is output.

7. The reading method according to claim 6, characterized in that: Before receiving the first request sent by the terminal device, the method further includes the following steps: Receiving a wake-up request sent by a terminal device, wherein the wake-up request includes a prefix; Determine the reservation identifier corresponding to itself within the preset wake-up value range according to the prefix, and generate a wake-up request response containing the reservation identifier; Send the wake-up request acknowledgement response to the terminal device.

8. A reading device for an embedded RFID tag, characterized in that: Specifically include: A request sending unit sends a first request to each RFID tag within the detection range, wherein the first request includes an estimated number of RFID tags within the detection range; Generate a second request containing a random number identifier to be verified, and send the second request to each RFID tag within the detection range; Sending a third request for a mute request to the identified RFID tag; Update the random number identifier to be verified, and repeat the second request and the third request sending process until all RFID tags within the detection range are identified; an identification unit, based on an analysis of a response to the second request within a preset response time period, determining an RFID tag to be identified and performing identification; The estimated number of RFID tags within the detection range is given, specifically including the following steps: Step 101', obtaining historical statistical information of the terminal device broadcasting wake-up signals with different frame lengths to all RFID tags within the detection range and the RFID tags providing feedback, and calculating the number of idle RFID tags, the number of successful responses, the number of conflicting responses, and the estimated number of remaining tags in the time period under different wake-up signal frame lengths, and generating a corresponding prediction model training data set; Step 102', respectively inputting prediction model training data sets corresponding to different wake-up signal frame lengths into the prediction model for training, to obtain trained prediction models of corresponding wake-up signal frame lengths; Step 103', the terminal device starts the identification operation, and determines the number of idle time periods, the number of completed reads, and the number of conflicts corresponding to the current wake-up signal frame length; determines whether the number of idle time periods, the number of completed reads, and the number of conflicts are all 0, and if they are all zero, then the reading operation is terminated; if they are not all zero, then the number of idle time periods, the number of completed reads, and the number of conflicts are input into the trained prediction model, the estimated number of remaining tags is output, and the estimated number of RFID tags to be identified is determined; The establishment of the prediction model includes the following steps: Step 1021', initialize the prediction model structure, and configure initial parameters and constraints; Step 1022', using the known location information, calculate the The individual matching degree after the rotation is compared with the average matching degree of the individual group, the individual position is updated, and the threshold and weight of the prediction model are adjusted to calculate the matching degree of the current position information and realize the update of the prediction model; Step 1023', determine whether the preset constraints are met. If the matching degree meets the accuracy threshold or the number of rotations reaches the maximum rotation value, the initial weights and thresholds obtained from the training of the prediction model are input into the prediction model again for secondary training, and finally the prediction model is output.

9. A reading device for an embedded RFID tag, characterized in that: Specifically include: A request receiving unit, receiving a first request sent by a terminal device, wherein the first request includes an estimated number of RFID tags within a detection range; Receiving a second request sent by the terminal device, wherein the second request includes a random number identifier to be verified; According to the identification of the terminal device, receiving a third request sent by the terminal device and entering a mute state; The response unit generates a random number identifier corresponding to itself according to the estimated number, wherein the random number identifier is any integer within the range of the estimated number; Performing a second request response to the terminal device based on the comparison between the random number identifier to be verified and the random number identifier; The estimated number of RFID tags within the detection range is given, specifically including the following steps: Step 101', obtaining historical statistical information of the terminal device broadcasting wake-up signals with different frame lengths to all RFID tags within the detection range and the RFID tags providing feedback, and calculating the number of idle RFID tags, the number of successful responses, the number of conflicting responses, and the estimated number of remaining tags in the time period under different wake-up signal frame lengths, and generating a corresponding prediction model training data set; Step 102', respectively inputting prediction model training data sets corresponding to different wake-up signal frame lengths into the prediction model for training, to obtain trained prediction models of corresponding wake-up signal frame lengths; Step 103', the terminal device starts the identification operation, and determines the number of idle time periods, the number of completed reads, and the number of conflicts corresponding to the current wake-up signal frame length; determines whether the number of idle time periods, the number of completed reads, and the number of conflicts are all 0, and if they are all zero, then the reading operation is terminated; if they are not all zero, then the number of idle time periods, the number of completed reads, and the number of conflicts are input into the trained prediction model, the estimated number of remaining tags is output, and the estimated number of RFID tags to be identified is determined; The establishment of the prediction model includes the following steps: Step 1021', initialize the prediction model structure, and configure initial parameters and constraints; Step 1022', using the known location information, calculate the The individual matching degree after the rotation is compared with the average matching degree of the individual group, the individual position is updated, and the threshold and weight of the prediction model are adjusted to calculate the matching degree of the current position information and realize the update of the prediction model; Step 1023', determine whether the preset constraints are met. If the matching degree meets the accuracy threshold or the number of rotations reaches the maximum rotation value, the initial weights and thresholds obtained from the training of the prediction model are input into the prediction model again for secondary training, and finally the prediction model is output.

10. A reading system for an embedded RFID tag, characterized in that: comprising at least one terminal device and a plurality of RFID tags; When any terminal device performs reading, the reading method described in any one of claims 1 to 5 is executed; When any RFID tag is read, the reading method described in claim 6 or 7 is executed.

Images