Method and device for detecting movement trend of RFID commodities

Abstract

The present application relates to a method and device for detecting the movement trend of RFID goods. By presetting a time period, RFID tag metadata of an RFID tag within the time period is collected; the time period is divided into a plurality of time slices according to a preset division rule, and the average RSSI value of the RFID tag within each time slice is calculated in sequence; an N-order eigenvalue algorithm matrix is constructed, and the average RSSI values of all time slices are written into the N-order eigenvalue algorithm matrix for timed calculation; the commodity feature matrix values of different time periods within the time period are obtained in sequence, and relative eigenvalue is calculated based on the commodity feature matrix values. The relative eigenvalue is compared with a preset eigenvalue, and the movement trend of the RFID goods is detected according to the comparison result. It can effectively monitor the movement trend of the tag through one RFID tag, expand the business scale, and improve the risk of commodity safety monitoring.

Description

Technical Field

[0001] The present disclosure relates to the technical field of commercial Internet of Things, and particularly to a method and device for detecting the movement trend of RFID products. Background Art

[0002] With the reduction of the price of RFID tags, the applications based on RFID technology are increasing. In many project applications, the applications of RFID can be basically divided into the following categories:

[0003] 1) Judging whether an item exists by whether the tag bound to the item can be read;

[0004] 2) Recording the number of times of an item within a certain time interval by whether the item can be read;

[0005] 3) Conducting some high-level applications by reading the characteristics of RFID tags.

[0006] Using the above application methods, the detection in the form of door channels using RFID technology is common, and a reminder action is performed when the tag is read. In practice, it is found that due to the reflection and refraction of the tag, the reminder range is unstable; therefore, in actual application scenarios, a larger application range needs to be delimited for use, which results in limited use in many application scenarios of door channels; at the same time, it may also bring property safety problems to the shopping mall.

[0007] In addition, in some application scenarios, it is necessary to set multiple monitoring points on the path where the item passes to detect how the item passes through the monitoring points successively, and the number of tags is large. Summary of the Invention

[0008] To solve the above problems, the present application proposes a method and device for detecting the movement trend of RFID products.

[0009] On the one hand, a method for detecting the movement trend of RFID products according to the present application includes the following steps:

[0010] S100. Presetting a time period, and collecting RFID tag metadata of an RFID tag within the time period;

[0011] S200. Dividing the time period into several time slices according to a preset division rule, and successively calculating the average RSSI value of the RFID tag within each time slice;

[0012] S300. Constructing an N-order eigenvalue algorithm matrix, writing the average RSSI values of all time slices into the N-order eigenvalue algorithm matrix, and performing timing calculation;

[0013] S400. Obtain the commodity feature matrix values for different time periods within the time cycle in sequence, calculate the relative feature values based on the commodity feature matrix values, compare the relative feature values with the preset feature values, and detect the RFID commodity movement trend according to the comparison result.

[0014] As an optional implementation solution of the present application, preferably, in step S200, after calculating the RSSI average value of the RFID tags within each time slice, it is also necessary to perform noise reduction processing on the RFID tag metadata, including:

[0015] S201. Screen out the sporadic data exceeding the preset signal strength from the RFID tag metadata;

[0016] S202. Perform peak flattening and noise reduction processing on the sporadic data according to the calculated RSSI average value of the RFID tags within each time slice;

[0017] S203. Obtain the RSSI average value after peak flattening and noise reduction processing, record and save it as the RFID tag noise reduction data.

[0018] As an optional implementation solution of the present application, preferably, in step S200, the step of dividing the time cycle into N time slices according to the preset division rule and calculating the RSSI average value of the RFID tags within each time slice in sequence includes:

[0019] S210. Divide the time cycle into N time slices;

[0020] S220. Arrange the N time slices in sequence in the order from the back to the front, collect and save the RSSI signal value sets of each time slice;

[0021] S230. Calculate the RSSI average value of the RFID tags within each time slice respectively according to the RSSI signal value sets.

[0022] As an optional implementation solution of the present application, preferably, in step S300, the step of constructing the N - order eigenvalue algorithm matrix and writing the RSSI average values of all time slices into the N - order eigenvalue algorithm matrix for timing calculation includes:

[0023] S301. Set the matrix construction conditions, and construct an N - order eigenvalue algorithm matrix matching the number of time slices according to the matrix construction conditions;

[0024] S302. Write the obtained RSSI average value of each time slice into the N - order eigenvalue algorithm matrix in sequence to obtain the eigenvalue timing algorithm matrix;

[0025] S303. Timely obtain the matrix eigenvalues at different time points according to the eigenvalue timing algorithm matrix.

[0026] As an optional implementation of the present application, preferably, in step S400, the method of sequentially obtaining the commodity feature matrix values in different time periods within the time period, calculating the relative eigenvalues based on the commodity feature matrix values, comparing the relative eigenvalues with the preset eigenvalues, and detecting the RFID commodity movement trend according to the comparison result includes:

[0027] S401. Sequentially divide the time period into different time periods;

[0028] S402. Based on the eigenvalue timing algorithm matrix, calculate the matrix eigenvalues at the first and last time points of each time period respectively and perform difference calculation to obtain the commodity feature matrix value of each time period;

[0029] S403. Substitute the commodity feature matrix value of each time period into the first-order matrix, calculate to obtain the relative eigenvalue, and use the relative eigenvalue as the moving distance of the RFID tag.

[0030] As an optional implementation of the present application, preferably, in step S400, the method of sequentially obtaining the commodity feature matrix values in different time periods within the time period, calculating the relative eigenvalues based on the commodity feature matrix values, comparing the relative eigenvalues with the preset eigenvalues, and detecting the RFID commodity movement trend according to the comparison result further includes:

[0031] S404. Preset the RFID tag feature range value;

[0032] S405. Compare the relative eigenvalue with the preset eigenvalue range to determine whether the relative eigenvalue is within the RFID tag feature range value;

[0033] S406. Obtain the judgment result, and judge whether to send an alarm signal according to the judgment result.

[0034] On the other hand, the present application proposes a device for implementing the method for detecting the RFID commodity movement trend described above, including an RFID tag metadata acquisition unit, a time slice RSSI average value calculation module, a timing calculation module, and a movement trend monitoring module, where:

[0035] RFID tag metadata acquisition unit: used to preset a time period and acquire the RFID tag metadata of an RFID tag within the time period;

[0036] Time slice RSSI average value calculation module: used to divide the time period into several time slices according to a preset division rule, and calculate the RSSI average value of the RFID tag in each time slice in sequence;

[0037] Timing calculation module: used to construct an N-order eigenvalue algorithm matrix, write the RSSI average values of all time slices into the N-order eigenvalue algorithm matrix, and perform timing calculations;

[0038] Movement trend monitoring module: used to obtain the commodity feature matrix values of different time periods in the time period in sequence, calculate the relative eigenvalue based on the commodity feature matrix values, compare the relative eigenvalue with a preset eigenvalue, and detect the movement trend of the RFID commodity according to the comparison result.

[0039] As an optional implementation scheme of the present application, preferably, it further includes a noise reduction processing module: used to perform noise reduction processing on the RFID tag metadata, and the noise reduction processing module includes:

[0040] Screening module: used to screen out sporadic data exceeding the preset signal strength from the RFID tag metadata;

[0041] Peak flattening noise reduction processing module: used to perform peak flattening noise reduction processing on the sporadic data according to the calculated RSSI average value of the RFID tag in each time slice;

[0042] Storage module: used to obtain the RSSI average value after peak flattening noise reduction processing, record and save it as RFID tag noise reduction data.

[0043] As an optional implementation scheme of the present application, preferably, the timing calculation module includes:

[0044] Matrix construction module: used to set matrix construction conditions, and construct an N-order eigenvalue algorithm matrix matching the number of time slices according to the matrix construction conditions;

[0045] Data writing module: used to write the obtained RSSI average value of each time slice into the N-order eigenvalue algorithm matrix in sequence to obtain an eigenvalue timing algorithm matrix;

[0046] Eigenvalue timing calculation module: used to obtain the matrix eigenvalues at different time points regularly according to the eigenvalue timing algorithm matrix.

[0047] As an optional implementation scheme of the present application, preferably, the movement trend monitoring module includes:

[0048] Time period division module: used to divide the time period into different time periods in sequence;

[0049] Difference calculation module: configured to calculate the matrix eigenvalues of the first and last time points of each time period based on the eigenvalue timing algorithm matrix, and perform difference calculation to obtain the commodity feature matrix values of each time period;

[0050] Relative eigenvalue calculation module: configured to substitute the commodity feature matrix values of each time period into a first-order matrix, calculate the relative eigenvalues, and use the relative eigenvalues as the moving distance of the RFID tag;

[0051] Threshold setting module: configured to preset the RFID tag feature range value;

[0052] Threshold comparison module: configured to compare the relative eigenvalues with the preset eigenvalue range to determine whether the relative eigenvalues are within the RFID tag feature range value;

[0053] Alarm module: configured to obtain the judgment result and determine whether to issue an alarm signal according to the judgment result.

[0054] Technical effects of the present invention:

[0055] In this application, by presetting a time period, RFID tag metadata of an RFID tag within the time period is collected; the time period is divided into several time slices according to a preset division rule, and the RSSI average value of the RFID tag within each time slice is calculated in sequence; an N-order eigenvalue algorithm matrix is constructed, and the RSSI average values of all time slices are written into the N-order eigenvalue algorithm matrix for timing calculation; the commodity feature matrix values of different time periods within the time period are obtained in sequence, and relative eigenvalues are calculated based on the commodity feature matrix values, and the relative eigenvalues are compared with preset eigenvalues, and the movement trend of the RFID commodity is detected according to the comparison result. It can realize the movement trend of the commodity carrying the RFID tag only through one RFID tag, effectively eliminate the false reminder caused by the too strong label signal due to reflection and refraction, and can effectively monitor the movement trend of the tag within 50CM around the access control, expand the business scale. After using this technology, the application scenarios that can be promoted by the RFID door channel are greatly increased, and it has a broad market prospect. At the same time, it improves the risk of commodity security monitoring.

[0056] According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present disclosure will become clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings included in the specification and constituting a part of the specification show the exemplary embodiments, features and aspects of the present disclosure together with the specification, and are used to explain the principles of the present disclosure.

[0058] Figure 1It shows a schematic diagram of the implementation process of the method for detecting the movement trend of RFID products according to the present invention. Detailed implementation manners

[0059] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0060] The special term "exemplary" here means "serving as an example, embodiment, or illustration". Any embodiment described as "exemplary" here does not have to be construed as superior to or better than other embodiments.

[0061] In addition, for a better description of the present disclosure, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present disclosure can also be implemented without some specific details. In some instances, methods, means, elements, and circuits well-known to those skilled in the art are not described in detail so as to highlight the gist of the present disclosure.

[0062] This solution establishes a comprehensive evaluation using three indicators: the number of readings per unit time, the amplitude, and the signal strength. All three of these indicators need to be correlated with the time when the tag enters the access control area. Therefore, in the software system, according to the external requirements of the product, when a person walks normally into the access control recognition range and then leaves, it is taken as an analysis time period, and the time is split into several small time slices for analysis. The following is an explanation of the three indicators of the number of readings, the amplitude, and the signal strength:

[0063] 1) Explanation of the number of readings: In PG506L, a four-channel RFID reader / writer is used. The numbers of each channel of the reader / writer are 0, 1, 2, and 3. For a standard access control, antennas 0 and 2 are enabled. When the tag is activated, it continuously sends out the EPC data signal carried by the tag itself. In the software, the tag signal can be obtained in real time from the reader / writer through the network cable or USB port, and the signal is recorded in the memory for analysis. The number of readings is the number of times a certain EPC data is read from a certain channel number within a certain time slice.

[0064] 2) Explanation of the amplitude: When the tag is read, the signal strength of the tag is carried in the tag data. Within a certain time slice, the average value of the signal strength values is taken, and the difference between the signal strength values of two time slices is used as the amplitude for statistical calculation.

[0065] 3) Signal strength: When the tag is read by the reader / writer, the signal carries an RSSI value. The maximum value of this value is 0, and the minimum value is -120, which directly represents the signal strength of the tag received by the reader / writer.

[0066] In this embodiment, the following test conditions are set:

[0067] Suppose a label enters the coverage range of the reader antenna from far to near. The RSSI phenomenon at the reader output will increase from small to large.

[0068] (1) The basic test conditions are as follows:

[0069] Device installation mode: two antennas are opposed, the antenna height from the ground is 1.2 meters, and the access control width (the distance between the two is 1.8 meters);

[0070] Antenna wiring mode: Use channels 0 and 2, and the reader power is turned on for inventory at 20, 20.

[0071] The label uses a standard clothing label of 1.2cm X 7.9cm;

[0072] (2) Label movement mode:

[0073] It passes between 1.2 meters from the ground and 0.9 meters from the middle of the access control;

[0074] The following data are the original data collected from the reader:

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081] The above are the metadata collected by the reader. However, the intensity signal of the RFID tag is affected by the following factors:

[0082] The human body affects the coverage range of the reader antenna, resulting in an expanded range, activating tags outside the original coverage range, and being received by the reader, resulting in reading tags at a farther distance;

[0083] After the label is activated by the reader, part of the energy is absorbed by the human body, resulting in a weak signal;

[0084] The speeds of the walking people are different, resulting in a smaller number of tags collected per unit time.

[0085] Next, the technical implementation will be described in detail.

[0086] Embodiment 1

[0087] As shown Figure 1 below, a method for detecting the movement trend of RFID goods is publicly proposed, including the following steps:

[0088] S100. Preset a time period, and collect RFID tag metadata of an RFID tag within the time period;

[0089] In the historical data record of the above table, it is the metadata collected by the reader. In this embodiment, it is only the signal value output by a clothing product with an RFID tag through the reader. This technology uses an RFID tag to obtain the signal RSSI value within the time range of the reading and writing scenario, and then further calculates the eigenvalue. By judging the eigenvalue difference, it is determined whether the tag signal, frequency, and intensity increase significantly. If so, it is considered that the tag moves outward within the access control range.

[0090] S200. Divide the time period into several time slices according to a preset division rule, and calculate the average RSSI value of the RFID tag in each time slice in turn;

[0091] S300. Construct an N-order eigenvalue algorithm matrix, write the average RSSI values of all time slices into the N-order eigenvalue algorithm matrix, and perform timing calculations;

[0092] S400. Obtain the commodity feature matrix values of different time periods within the time period in turn, calculate the relative eigenvalue based on the commodity feature matrix values, compare the relative eigenvalue with a preset eigenvalue, and detect the movement trend of the RFID commodity according to the comparison result.

[0093] As an optional implementation scheme of the present application, preferably, in step S200, after calculating the average RSSI value of the RFID tag in each time slice, it is also necessary to perform noise reduction processing on the RFID tag metadata, including:

[0094] S201. Screen out sporadic data exceeding the preset signal intensity from the RFID tag metadata;

[0095] S202. Perform flat peak noise reduction processing on the sporadic data according to the average RSSI value of the RFID tag calculated in each time slice;

[0096] S203. Obtain the average RSSI value after flat peak noise reduction processing, record and save it as RFID tag noise reduction data.

[0097] When a certain tag is reflected by a metal surface, it will emit several very strong signals continuously, but only within one second. Through the eigenvalue algorithm, the signals will be evenly distributed into the numerical average within this time slice. Then, combined with the acquisition data of no other time slices, the algorithm can be used to determine that it is an interference signal.

[0098] This technology mainly continuously collects the historical signals of the current signal. Among the collected signal values, occasionally signals with large intensities will be found. Therefore, it is necessary to filter out the occasional data exceeding the preset signal intensity for noise filtering. The overly strong occasional data is leveled by the average data of a certain time slice, and then the historical records of the tag are substituted into the matrix for eigenvalue calculation according to the average value of the time slice. The preset signal intensity is user-defined.

[0099] After obtaining the RFID tag noise reduction data, advanced matrix eigenvalue calculation is performed.

[0100] As an optional implementation scheme of this application, preferably, in step S200, dividing the time period into N time slices according to the preset division rule and sequentially calculating the RSSI average value of the RFID tag in each time slice includes:

[0101] S210: Divide the time period into N time slices;

[0102] S220: Arrange the N time slices in order from the back to the front, collect and save the RSSI signal value set of each time slice;

[0103] S230: Calculate the RSSI average value of the RFID tag in each time slice according to the RSSI signal value set.

[0104] In this embodiment, the maximum range of the access control power is set to 12 meters longitudinally, and the normal walking speed of a person is 0.8 meters per second as the boundary for data model modeling. The signals within 20 seconds after the tag starts to be read are used as the statistical range.

[0105] The time slice after a tag collects data through the access control is split into 9 time slices as follows:

[0106] (1) The set within 115 - 20 seconds, the long-distance signal set;

[0107] (2) The set within 10 - 15 seconds, the relatively long-distance signal set;

[0108] (3) The set within 5 - 10 seconds, the medium-distance signal set;

[0109] (4) The set within 2 - 5 seconds, the relatively short-distance signal set;

[0110] (5)Collection within 1 - 2 seconds, short - range signal collection;

[0111] (6)Collection within 500 milliseconds - 1 second, critical signal collection;

[0112] (7)Collection within 0 - 500 milliseconds, current signal collection;

[0113] (8)Collection within 2 - 10 seconds, signals outside access control requirements collection;

[0114] (9)Collection within 1 - 5 seconds, signals in the key analysis interval for access control collection.

[0115] Then, within each time slice, the average RSSI value of this tag is recorded as a collection a, and then the absolute values of the average RSSI values corresponding to 9 time slices are filled into a third - order matrix. By calculating the eigenvalues of this matrix at regular intervals, and using the eigenvalue difference to judge whether the tag signal, number of times, and intensity have increased significantly. If the increase is significant, it is considered that the tag has moved outwards within the access control range.

[0116] As an optional implementation of this application, preferably, in step S300, the construction of the N - order eigenvalue algorithm matrix and writing the average RSSI values of all time slices into the N - order eigenvalue algorithm matrix for regular calculation includes:

[0117] S301. Set matrix construction conditions, and according to the matrix construction conditions, construct an N - order eigenvalue algorithm matrix that matches the number of time slices;

[0118] S302. Write the average RSSI value obtained within each time slice into the N - order eigenvalue algorithm matrix in sequence to obtain an eigenvalue timing algorithm matrix;

[0119] S303. According to the eigenvalue timing algorithm matrix, obtain the matrix eigenvalues at different time points regularly.

[0120] For the matrix construction conditions, the value of N is determined according to the order and the number of time slices defined by the user. For example, in this embodiment, there are average RSSI values corresponding to 9 time slices, and a third - order matrix is used to construct the eigenvalue algorithm matrix.

[0121] Specifically, the third - order matrix eigenvalue algorithm at a certain moment:

[0122]

[0123] The matrix eigenvalues at different time points can be obtained regularly according to the above - mentioned third - order eigenvalue timing algorithm matrix.

[0124] As an alternative implementation of the present application, preferably, in step S400, obtaining the commodity feature matrix values for different time periods within the time period in sequence, calculating the relative feature values based on the commodity feature matrix values, and comparing the relative feature values with the preset feature values to detect the RFID commodity movement trend according to the comparison results includes:

[0125] S401. Divide the time period into different time periods in sequence;

[0126] S402. Based on the eigenvalue timing algorithm matrix, calculate the matrix eigenvalue at the first and last time points of each time period respectively and perform difference calculation to obtain the commodity feature matrix value of each time period;

[0127] S403. Substitute the commodity feature matrix value of each time period into the first-order matrix, calculate the relative feature value, and use the relative feature value as the RFID tag movement distance.

[0128] After splitting the time slice after a tag collects data through the access control into time slices, obtaining the average value and constructing the eigenvalue timing algorithm matrix, the difference between several different time periods before and after the current time period of the RFID tag can be used as such, and this is used as the commodity feature matrix value of the RFID tag in each time period. Calculate the relative feature value through the commodity feature matrix value, and use the relative feature value as the RFID tag movement distance.

[0129] The specific calculation steps are as follows:

[0130] 1. Calculate the difference in eigenvalue between two time slices: M = M t -M t-1 , where the commodity feature matrix value M represents the feature quantity value of the commodity detected at the current moment;

[0131] Suppose

[0132]

[0133] 2. Then:

[0134]

[0135]

[0136]

[0137] 3.

[0138]

[0139]

[0140] 4. Calculate the eigenvalue of the difference between two time slices to obtain the relative eigenvalue, and use this eigenvalue to judge the moving distance of the tag.

[0141] Then record the eigenvalue matrix values of the last three times, substitute them into a first-order matrix, and convert the eigenvalue W as the relative parameter of the tag distance:

[0142]

[0143] As an alternative implementation of the present application, preferably, in step S400, obtaining the commodity eigenvalue matrix values of different time periods within the time period in sequence, calculating the relative eigenvalue based on the commodity eigenvalue matrix values, comparing the relative eigenvalue with a preset eigenvalue, and detecting the RFID commodity movement trend according to the comparison result further includes:

[0144] S404. Preset the RFID tag feature range value;

[0145] S405. Compare the relative eigenvalue with the preset eigenvalue range to judge whether the relative eigenvalue is within the RFID tag feature range value;

[0146] S406. Obtain the judgment result, and judge whether to send an alarm signal according to the judgment result.

[0147] In this embodiment, a threshold is set, and an RFID tag feature range value is set. Taking 1.5 as the calculation standard, which is close to the installation door width of the actual access control, the calculated value is used as the relative distance. If the eigenvalue exceeds 2.2, it is considered a long-distance tag and is not included in the alarm logic. If it is less than 2.2, it is considered a short-distance tag, and the multi-channel features of the tag need to be analyzed to judge whether to alarm.

[0148] The implementation of the alarm signal is realized according to the circuit or other alternative methods.

[0149] Here, 20 seconds will be used as an example:

[0150] Suppose the EPC number 00B07A147C593490180000FE starts to enter the venue. When it enters the venue and is recognized by the reader, at the 2nd second, calculate the average RSSI as follows:

[0151]

[0152]

[0153] Substitute into the formula: Let

[0154]

[0155] After entering the venue, the tag continues to move towards the access control for 8 seconds. At the 10th second in total, calculate the average RSSI as follows:

[0156]

[0157] Substitute into the formula: Let

[0158]

[0159] After entering the venue, the tag continues to move towards the access control for 5 seconds. At the 15th second in total, calculate the average RSSI as follows:

[0160]

[0161]

[0162] Substitute into the formula: Let

[0163]

[0164] And it moves 20 seconds towards the outside of the access control. After aggregating all the collected signals, the following information is generated:

[0165]

[0166] Substitute into the formula: Let

[0167]

[0168] Therefore, preset X = M(10) - M(2);

[0169] Y = M(15) - M(10);

[0170] Z = M(20) - M(15);

[0171] Then through:

[0172]

[0173] Calculate the relative distance of the tag to the access control.

[0174] Through the above implementation, the movement trend of the commodity carrying the RFID tag can be realized only through one RFID tag, which can effectively eliminate the false reminder caused by the overly strong tag signal due to reflection and refraction, and can effectively monitor the movement trend of the tag within 50CM around the access control, expand the business scale. After using this technology, the applicable scenarios that can be promoted by the RFID door channel are greatly increased, with a broad market prospect. At the same time, it improves the risk of commodity safety monitoring.

[0175] It should be noted that although the above eigenvalue calculation is introduced by taking 9 time slices as an example, those skilled in the art can understand that the present disclosure should not be limited thereto. In fact, the user can flexibly set the number of time slices according to the actual application scenario, as long as the technical functions of the present application can be realized according to the above technical methods.

[0176] Embodiment 2

[0177] Based on the implementation principle of Embodiment 1, this embodiment proposes a method and device for detecting the movement trend of RFID commodities to implement the processes of the control methods in Embodiment 1 above.

[0178] On the other hand, the present application proposes a device for implementing the method for detecting the movement trend of RFID commodities described above, including an RFID tag metadata acquisition unit, a time slice RSSI average value calculation module, a timing calculation module, and a movement trend monitoring module, where:

[0179] RFID tag metadata acquisition unit: used to preset a time period and acquire RFID tag metadata of an RFID tag within the time period;

[0180] Time slice RSSI average value calculation module: used to divide the time period into several time slices according to a preset division rule, and sequentially calculate the RSSI average value of the RFID tag within each time slice;

[0181] Timing calculation module: used to construct an N - order eigenvalue algorithm matrix, write the RSSI average values of all time slices into the N - order eigenvalue algorithm matrix, and perform timing calculation;

[0182] Movement trend monitoring module: used to sequentially obtain the commodity feature matrix values of different time periods within the time period, calculate the relative eigenvalue based on the commodity feature matrix values, compare the relative eigenvalue with a preset eigenvalue, and detect the movement trend of the RFID commodity according to the comparison result.

[0183] In this embodiment, for the specific functions and technical implementation processes of the RFID tag metadata acquisition unit, the time slice RSSI average value calculation module, the timing calculation module, and the movement trend monitoring module, please refer to Embodiment 1. At the same time, the information interaction method between each module is not limited to wired or wireless methods, or other communication protocols.

[0184] As an optional implementation scheme of the present application, preferably, it further includes a noise reduction processing module: used to perform noise reduction processing on the RFID tag metadata, and the noise reduction processing module includes:

[0185] Screening module: used to screen out sporadic data exceeding a preset signal strength from the RFID tag metadata;

[0186] Flat peak noise reduction processing module: used to perform flat peak noise reduction processing on the sporadic data according to the calculated average RSSI value of RFID tags in each time slice;

[0187] Storage module: used to obtain the average RSSI value after flat peak noise reduction processing, record and save it as RFID tag noise reduction data.

[0188] As an optional implementation solution of the present application, preferably, the timing calculation module includes:

[0189] Matrix construction module: used to set matrix construction conditions and construct an N-order eigenvalue algorithm matrix matching the number of time slices according to the matrix construction conditions;

[0190] Data writing module: used to write the obtained average RSSI value in each time slice into the N-order eigenvalue algorithm matrix according to the sorting to obtain an eigenvalue timing algorithm matrix;

[0191] Eigenvalue timing calculation module: used to obtain matrix eigenvalues at different time points regularly according to the eigenvalue timing algorithm matrix.

[0192] As an optional implementation solution of the present application, preferably, the motion trend monitoring module includes:

[0193] Time period division module: used to divide the time period into different time periods in sequence;

[0194] Difference calculation module: used to calculate the matrix eigenvalues at the beginning and end of each time period based on the eigenvalue timing algorithm matrix and perform difference calculation to obtain the commodity feature matrix value of each time period;

[0195] Relative eigenvalue calculation module: used to substitute the commodity feature matrix value of each time period into a first-order matrix, calculate to obtain a relative eigenvalue, and use the relative eigenvalue as the moving distance of the RFID tag;

[0196] Threshold setting module: used to preset the RFID tag feature range value;

[0197] Threshold comparison module: used to compare the relative eigenvalue with the preset feature value range to judge whether the relative eigenvalue is within the RFID tag feature range value;

[0198] Alarm module: used to obtain the judgment result and judge whether to send an alarm signal according to the judgment result.

[0199] Obviously, those skilled in the art should understand that to implement all or part of the processes in the methods of the above embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above control methods. Each module or step of the present invention described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the present invention is not limited to any specific combination of hardware and software.

[0200] Those skilled in the art can understand that to implement all or part of the processes in the methods of the above embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above control methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (abbreviation: HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0201] Embodiment 3

[0202] Furthermore, according to another aspect of the present disclosure, a control system is also provided.

[0203] The control system according to the embodiments of the present disclosure includes a processor and a memory for storing instructions executable by the processor. Among them, the processor is configured to implement the method for detecting the movement trend of RFID products described in any one of the above when executing the executable instructions.

[0204] Here, it should be noted that the number of processors can be one or more. At the same time, in the traceability system according to the embodiments of the present disclosure, an input device and an output device can also be included. Among them, the processor, the memory, the input device, and the output device can be connected through a bus or in other ways, which is not specifically limited here.

[0205] A memory, as a computer-readable storage medium for a method of detecting the movement trend of RFID products, can be used to store software programs, computer-executable programs, and various modules, such as the programs or modules corresponding to a method of detecting the movement trend of RFID products according to an embodiment of the present disclosure. The processor executes various functional applications and data processing of the traceability system by running the software programs or modules stored in the memory.

[0206] The input device can be used to receive input numbers or signals. Among them, the signal can be a key signal related to the user settings and function control of the device / terminal / server. The output device can include display devices such as a display screen.

[0207] The embodiments of the present disclosure have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the market, or to enable other ordinary skill in the art in the technical field to understand the embodiments disclosed herein.

Claims

1. A method for detecting the movement trend of RFID goods, characterized in that, It includes the following steps: S100. Set a preset time period, and collect RFID tag metadata of an RFID tag within the time period; S200. Divide the time period into several time slices according to a preset division rule, and calculate the average RSSI value of the RFID tag in each time slice in turn; S201. Screen out sporadic data exceeding the preset signal strength from the RFID tag metadata; S202. Perform peak flattening and noise reduction processing on the sporadic data according to the average RSSI value of the RFID tag in each calculated time slice; S203. Obtain the average RSSI value after peak flattening and noise reduction processing, record and save it as RFID tag noise reduction data; S300. Construct an N-order eigenvalue algorithm matrix, write the average RSSI values of all time slices into the N-order eigenvalue algorithm matrix, and perform timing calculations; S301. Set matrix construction conditions, and construct an N-order eigenvalue algorithm matrix matching the number of time slices according to the matrix construction conditions; S302. Write the average RSSI value obtained in each time slice into the N-order eigenvalue algorithm matrix in sequence to obtain an eigenvalue timing algorithm matrix; S303. Obtain matrix eigenvalues at different time points regularly according to the eigenvalue timing algorithm matrix; S400. Obtain the commodity feature matrix values in different time periods within the time period in sequence, calculate relative eigenvalues based on the commodity feature matrix values, compare the relative eigenvalues with preset eigenvalues, and detect the movement trend of RFID commodities according to the comparison results; Among them, step S400 includes: S401. Divide the time period into different time periods in sequence; S402. Based on the eigenvalue timing algorithm matrix, calculate the matrix eigenvalues at the first and last time points of each time period respectively and perform difference calculations to obtain the commodity feature matrix values of each time period; S403. Substitute the commodity feature matrix values of each time period into a first-order matrix, calculate to obtain relative eigenvalues, and use the relative eigenvalues as the moving distance of the RFID tag.

2. The method for detecting the movement trend of RFID goods according to claim 1, wherein In step S200, the step of dividing the time period into N time slices according to a preset division rule and calculating the average RSSI value of the RFID tag in each time slice in turn includes: S210. Divide the time period into N time slices; S220. Arrange the N time slices in sequence from the last to the first in time, collect and save the RSSI signal value sets of each time slice; S230. Calculate the average RSSI value of the RFID tag in each time slice according to the RSSI signal value set.

3. The method for detecting the movement trend of RFID commodities according to claim 1, wherein In step S400, the step of obtaining the commodity feature matrix values in different time periods within the time period in sequence, calculating relative eigenvalues based on the commodity feature matrix values, comparing the relative eigenvalues with preset eigenvalues, and detecting the movement trend of RFID commodities according to the comparison results further includes: S404. Set a preset RFID tag feature range value; S405. Compare the relative eigenvalue with a preset eigenvalue range to determine whether the relative eigenvalue is within the RFID tag feature range value; S406. Obtain the judgment result, and based on the judgment result, determine whether to send an alarm signal.

4. An apparatus for implementing the method for detecting the movement trend of RFID goods according to any one of claims 1-3, characterized in that, It includes an RFID tag metadata acquisition unit, a time slice RSSI average value calculation module, a timing calculation module, and a movement trend monitoring module, where: RFID tag metadata acquisition unit: For a preset time period, acquire the RFID tag metadata of an RFID tag within the time period; Time slice RSSI average value calculation module: For dividing the time period into several time slices according to a preset division rule, and sequentially calculate the RSSI average value of the RFID tag within each time slice; Timing calculation module: For constructing an N-order eigenvalue algorithm matrix, writing the RSSI average values of all time slices into the N-order eigenvalue algorithm matrix, and performing timing calculations; Movement trend monitoring module: For sequentially obtaining the commodity feature matrix values of different time periods within the time period, calculating and obtaining a relative eigenvalue based on the commodity feature matrix values, comparing the relative eigenvalue with a preset eigenvalue, and detecting the movement trend of the RFID commodity according to the comparison result.

5. The device according to claim 4, characterized in that It further includes a noise reduction processing module: For performing noise reduction processing on the RFID tag metadata, and the noise reduction processing module includes: Screening module: For screening out sporadic data exceeding a preset signal strength from the RFID tag metadata; Flat peak noise reduction processing module: For performing flat peak noise reduction processing on the sporadic data according to the calculated RSSI average value of the RFID tag within each time slice; Storage module: For obtaining the RSSI average value after flat peak noise reduction processing, recording and saving it as RFID tag noise reduction data.

6. The device according to claim 5, characterized in that The timing calculation module includes: Matrix construction module: For setting matrix construction conditions, and constructing an N-order eigenvalue algorithm matrix matching the number of time slices according to the matrix construction conditions; Data writing module: For writing the obtained RSSI average value of each time slice into the N-order eigenvalue algorithm matrix in sequence to obtain an eigenvalue timing algorithm matrix; Eigenvalue timing calculation module: For obtaining the matrix eigenvalues at different time points regularly according to the eigenvalue timing algorithm matrix.

7. The device according to claim 6, characterized in that, The movement trend monitoring module includes: Time period division module: For sequentially dividing the time period into different time periods; Difference calculation module: For sequentially calculating the matrix eigenvalues at the beginning and end of each time period based on the eigenvalue timing algorithm matrix and performing difference calculations to obtain the commodity feature matrix values of each time period; Relative eigenvalue calculation module: For substituting the commodity feature matrix values of each time period into a first-order matrix, calculating and obtaining a relative eigenvalue, and taking the relative eigenvalue as the RFID tag movement distance; Threshold setting module: For presetting the RFID tag feature range value; Threshold comparison module: used to compare the relative eigenvalue with a preset eigenvalue range to determine whether the relative eigenvalue is within the RFID tag feature range value; Alarm module: used to obtain the judgment result and determine whether to issue an alarm signal according to the judgment result.

Images