CN114580455A - RFID label moving direction judging method and system based on artificial intelligence - Google Patents
RFID label moving direction judging method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN114580455A CN114580455A CN202210189095.0A CN202210189095A CN114580455A CN 114580455 A CN114580455 A CN 114580455A CN 202210189095 A CN202210189095 A CN 202210189095A CN 114580455 A CN114580455 A CN 114580455A
- Authority
- CN
- China
- Prior art keywords
- rfid
- rfid tag
- moving direction
- artificial intelligence
- decision model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000000611 regression analysis Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
- G06K7/10019—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers.
- G06K7/10079—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the spatial domain, e.g. temporary shields for blindfolding the interrogator in specific directions
- G06K7/10089—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the spatial domain, e.g. temporary shields for blindfolding the interrogator in specific directions the interrogation device using at least one directional antenna or directional interrogation field to resolve the collision
- G06K7/10099—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the spatial domain, e.g. temporary shields for blindfolding the interrogator in specific directions the interrogation device using at least one directional antenna or directional interrogation field to resolve the collision the directional field being used for pinpointing the location of the record carrier, e.g. for finding or locating an RFID tag amongst a plurality of RFID tags, each RFID tag being associated with an object, e.g. for physically locating the RFID tagged object in a warehouse
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
Abstract
The invention discloses an artificial intelligence-based RFID label moving direction judging method and system, wherein the method comprises the following steps: setting a plurality of RFID antennas and moving directions, moving a plurality of RFID tags according to each moving direction, reading data reported by each RFID tag every time, and acquiring a training data set; performing machine learning according to the training data set to obtain a decision model; and reading the data of the RFID tag to be decided, and judging the moving direction of the RFID tag to be decided by using the decision model. The invention realizes the judgment of the moving direction of the RFID label with lower cost.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a system for judging a moving direction when an RFID (radio frequency identification) tag moves.
Background
At present, in modern factories, if automatic and unmanned internal logistics need to be realized, after the digitalized registration of materials is completed, the circulation of the materials in the factory or warehouse needs to be tracked urgently. At present, the main scheme of asset digitization is to use a bar code label or an electronic label, and complete the operations of material warehousing or production line state updating and the like through a card reader, and all the operations need manual intervention to ensure the accuracy and can not meet the requirements of judging the asset moving direction and the like.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based RFID tag moving direction judging method and system, which can realize the RFID tag moving direction judgment at lower cost.
The technical scheme for realizing the purpose is as follows:
an artificial intelligence-based RFID tag moving direction judging method comprises the following steps:
setting a plurality of RFID antennas and moving directions, moving a plurality of RFID tags according to each moving direction, reading data reported by each RFID tag every time, and acquiring a training data set;
performing machine learning according to the training data set to obtain a decision model;
and reading the data of the RFID tag to be decided, and judging the moving direction of the RFID tag to be decided by using the decision model.
Preferably, the data reported by each RFID tag at a time includes: the time difference of reading the card between every two adjacent RFID antennae and the characteristic value of each RFID label signal.
Preferably, in the decision model,
if the output judgment value only has two directions, performing regression analysis and output by using a binary classification function;
and if the output judgment value is more than two, performing regression analysis and outputting by using a multi-classification function.
Preferably, the decision model checks the accuracy of the output; the decision model supports external newly-added input judgment.
An artificial intelligence-based RFID tag moving direction determination system, comprising: a group of RFID antennae, a plurality of RFID labels and a card reader connected with each RFID antenna,
the card reader includes:
the card reading module is used for reading data reported by the RFID label and acquiring a training data set and data of the RFID label to be decided;
performing machine learning according to the training data set to obtain a training module of a decision model;
and the decision module is loaded with a decision model and used for judging the moving direction of the RFID label to be decided according to the data of the RFID label to be decided.
Preferably, the number of RFID antennas is 4.
Preferably, the data in the training dataset refer to: and setting a plurality of moving directions, moving a plurality of RFID tags according to each moving direction, and reading the data reported by each RFID tag every time.
The invention has the beneficial effects that: according to the invention, a large amount of expensive hardware investment is not needed, software upgrading is only needed for the RFID card reader, and the moving direction of the RFID label can be supported and judged by adding the training module and the decision module to the software of the card reader, so that the cost is low and the accuracy is high. Compared with the existing method for judging the moving direction of the assets, the method is easy to interfere, can often generate misjudgment, and cannot reach the practical and commercial degree.
Drawings
FIG. 1 is a flow chart of an artificial intelligence based RFID tag movement direction determination method of the present invention;
FIG. 2 is a specific flow of the RFID tag moving direction determination in the present invention;
fig. 3 is a schematic diagram of a 2X2 antenna layout (overhead) according to the present invention;
fig. 4 is a schematic structural diagram of a 1X4 antenna layout in the present invention;
fig. 5 is a schematic structural diagram of a 2X2 antenna layout (side-mounted) in the present invention.
Detailed Description
The invention will be further explained with reference to the drawings.
Referring to fig. 1-2, the method for determining the moving direction of the RFID tag based on artificial intelligence according to the present invention includes the following steps:
setting a plurality of RFID antennas and moving directions, moving a plurality of RFID tags according to each moving direction, reading data reported by each RFID tag every time, and acquiring a training data set. In particular, the amount of the solvent to be used,
1) and setting the card reader into a training mode, fixing the position of the RFID antenna, and determining the RFID label for training.
2) In the training mode, the direction of movement of the label is set to "direction 1".
3) And moving the tag, and finishing the reading and recording of the RFID tag data.
4) And 3) repeating until the binding of the label data of a plurality of groups and the set direction is completed.
5) In the training mode, the direction of movement of the label is set to "direction 2".
6) And moving the tag, and finishing the reading and recording of the RFID tag data.
7) And 5) repeating until the binding of the label data of a plurality of groups and the set direction is completed.
The data reported by each RFID label at a time comprises the following data: the time difference of reading the card between every two adjacent RFID antennae and the characteristic value of each RFID label signal. The method comprises the following specific steps:
where T is the time difference between the readings of the RFID antennas, and if the polling interval between the antennas is 0.1 second, T1 is 0, T2 is 0.1, T3 is 0.2, and T4 is 0.3, which can be calculated from the time stamp recorded by the reading of the card. RSSI, MS _ CSR, NB _ RSSI, WB _ RSSI _ OTHER, PHASE are characteristic values of the tag RFID signal. After a plurality of sets (e.g., 500 sets) of the above data are obtained, learning and training are performed based on the set determination value "direction 1".
And secondly, performing machine learning according to the training data set to obtain a decision model.
If the output decision value has only two directions, performing regression analysis and output by using a binary function (such as sigmoid or tanh);
if the output decision value is greater than two, regression analysis and output are performed using a multi-classification function (such as softmax).
Reading the data of the RFID label to be decided, and judging the moving direction of the RFID label to be decided by using the decision model.
As shown in fig. 3 to 5, the artificial intelligence-based RFID tag moving direction determination system of the present invention includes: the RFID system comprises a group of RFID antennae, a plurality of RFID labels and a card reader connected with the RFID antennae. In the figure, ANT1-ANT4 represent 4 RFID antennas.
The card reader includes: the device comprises a card reading module, a training module and a decision-making module.
The card reading module reads data reported by the RFID label to acquire a training data set and data of the RFID label to be decided. And the training module performs machine learning according to the training data set to obtain a decision model. And the decision module loads the decision model and judges the moving direction of the RFID label to be decided according to the data of the RFID label to be decided.
The number of the RFID antennas is more than or equal to 4, preferably 4, and the antennas are preferably circularly polarized antennas; the arrangement mode is random, but the position is relatively fixed when the card is read.
The card reading mode of the card reader is a polling mode, and the card reading period of each antenna is 50-200 ms, preferably 100 ms; 5-10 RFID tags;
the number of the movement directions is not more than 4, preferably 2;
the decision model supports a verification mode, and accuracy can be verified. And in the checking mode, correcting the parameters and the decision model. The selection of the RFID parameters reported under different scenes can be used for training by selecting different parameters under different industrial scenes. And a multi-decision model is supported, and different models are selected under different scenes. The invention supports a preset model and also supports externally added input judgment, such as an ultrasonic motion induction or vibration sensor, and can set weight to calibrate an output result.
During the label moving process, such as in a production manufacturing type enterprise, the determination of the moving direction can be carried out by the method, and reliable data input is provided for automatic logistics. The present invention is not limited to the moving direction of the tag, and may be used for determining whether the tag is located in a certain position interval or not, or for determining whether the tag has a plurality of different positions. Because the data volume of the label data is small, the training scale is small, the invention usually does not need high calculation power, and the learning and decision can be carried out on a plurality of low-end devices.
In summary, the invention can determine the moving direction or position of the RFID tag through machine learning by applying an artificial intelligence method, and has low requirements on hardware configuration and great cost advantage.
The above embodiments are provided only for illustrating the present invention and not for limiting the present invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and therefore all equivalent technical solutions should also fall within the scope of the present invention, and should be defined by the claims.
Claims (7)
1. An artificial intelligence-based RFID tag moving direction judging method is characterized by comprising the following steps:
setting a plurality of RFID antennas and moving directions, moving a plurality of RFID tags according to each moving direction, reading data reported by each RFID tag every time, and acquiring a training data set;
performing machine learning according to the training data set to obtain a decision model;
and reading the data of the RFID tag to be decided, and judging the moving direction of the RFID tag to be decided by using the decision model.
2. The method according to claim 1, wherein the data reported by each RFID tag at a time comprises: the time difference of reading the card between every two adjacent RFID antennae and the characteristic value of each RFID label signal.
3. The artificial intelligence based RFID tag movement direction determination method of claim 1, wherein in the decision model,
if the output judgment value only has two directions, performing regression analysis and output by using a binary classification function;
and if the output judgment value is more than two, performing regression analysis and outputting by using a multi-classification function.
4. The artificial intelligence based RFID tag movement direction determination method of claim 1, wherein the decision model checks the accuracy of the output; the decision model supports external newly-added input judgment.
5. An artificial intelligence-based RFID tag movement direction determination system, comprising: a group of RFID antennae, a plurality of RFID labels and a card reader connected with each RFID antenna,
the card reader includes:
the card reading module is used for reading data reported by the RFID label and acquiring a training data set and data of the RFID label to be decided;
performing machine learning according to the training data set to obtain a training module of a decision model;
and the decision module is loaded with a decision model and used for judging the moving direction of the RFID label to be decided according to the data of the RFID label to be decided.
6. The artificial intelligence based RFID tag movement direction determination system of claim 5, wherein the number of RFID antennas is 4.
7. The artificial intelligence based RFID tag movement direction determination system of claim 5, wherein the data in the training data set refers to: and setting a plurality of moving directions, moving a plurality of RFID tags according to each moving direction, and reading the data reported by each RFID tag every time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210189095.0A CN114580455A (en) | 2022-02-28 | 2022-02-28 | RFID label moving direction judging method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210189095.0A CN114580455A (en) | 2022-02-28 | 2022-02-28 | RFID label moving direction judging method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114580455A true CN114580455A (en) | 2022-06-03 |
Family
ID=81771369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210189095.0A Pending CN114580455A (en) | 2022-02-28 | 2022-02-28 | RFID label moving direction judging method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114580455A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115238717A (en) * | 2022-08-16 | 2022-10-25 | 中国建筑一局(集团)有限公司 | Regional population trend calculation system and method |
| CN115470806A (en) * | 2022-09-14 | 2022-12-13 | 佳源科技股份有限公司 | Method and system for judging direction of goods entering and exiting warehouse based on single antenna |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081728A (en) * | 2009-11-30 | 2011-06-01 | 西门子公司 | Label activity detecting method and device in radio frequency identification (RFID) system as well as reader |
| CN108871332A (en) * | 2018-04-26 | 2018-11-23 | 广西大学 | A kind of RFID indoor locating system and method based on XGBoost |
| CN111178106A (en) * | 2020-01-03 | 2020-05-19 | 华东理工大学 | Method for judging label displacement direction based on ultrahigh frequency RFID phase and SVM |
-
2022
- 2022-02-28 CN CN202210189095.0A patent/CN114580455A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081728A (en) * | 2009-11-30 | 2011-06-01 | 西门子公司 | Label activity detecting method and device in radio frequency identification (RFID) system as well as reader |
| CN108871332A (en) * | 2018-04-26 | 2018-11-23 | 广西大学 | A kind of RFID indoor locating system and method based on XGBoost |
| CN111178106A (en) * | 2020-01-03 | 2020-05-19 | 华东理工大学 | Method for judging label displacement direction based on ultrahigh frequency RFID phase and SVM |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115238717A (en) * | 2022-08-16 | 2022-10-25 | 中国建筑一局(集团)有限公司 | Regional population trend calculation system and method |
| CN115470806A (en) * | 2022-09-14 | 2022-12-13 | 佳源科技股份有限公司 | Method and system for judging direction of goods entering and exiting warehouse based on single antenna |
| CN115470806B (en) * | 2022-09-14 | 2024-02-02 | 佳源科技股份有限公司 | Method and system for judging article entering and exiting direction based on single antenna |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114580455A (en) | RFID label moving direction judging method and system based on artificial intelligence | |
| Velandia et al. | Towards industrial internet of things: Crankshaft monitoring, traceability and tracking using RFID | |
| Lotlikar et al. | Comparative study of Barcode, QR-code and RFID System | |
| KR101597199B1 (en) | Rfid portal system with rfid tags having various read ranges | |
| CN101957924A (en) | Method for detecting motion in radio frequency identification system and readers | |
| KR100964593B1 (en) | Rfid system and rfid tag | |
| CN109635797B (en) | Steel coil sequence accurate positioning method based on multi-carrier identification technology | |
| Jo et al. | Mobile RFID tag detection influence factors and prediction of tag detectability | |
| US20080061939A1 (en) | Method and apparatus for determining ordering of RFID tagged objects | |
| CN111753937B (en) | RFID (radio frequency identification) label rapid detection method and system based on multi-label | |
| US20130060725A1 (en) | Judgment apparatus, judgment system, and judgment method | |
| CN109472177B (en) | Inventory method capable of reading TID (terminal identification) number of electronic tag | |
| CN105444518A (en) | Food management system and method of refrigerator and refrigerator | |
| CN105354521A (en) | BP neural network-based RFID label distribution optimum configuration method | |
| CN108647756B (en) | Asset management system and method based on RFID (radio frequency identification) tag | |
| CN101685495A (en) | Label identification method and reader and radio frequency identification system | |
| CN103065106B (en) | The recognition methods of RFID tag scan and system | |
| KR20160104246A (en) | Unmanned inventory actual inspection system using arerial vehicle and the method thereof | |
| CN113447729A (en) | Test method of wireless radio frequency system and computer device | |
| CN210573908U (en) | Electronic tag for logistics storage | |
| CN111929636B (en) | Intelligent identification and marking positioning method for metal container | |
| CN109272085B (en) | RFID intelligent tool management system based on cloud data | |
| CN112184119A (en) | Power grid first-aid repair resource warehousing system and method based on RFID and two-dimensional code | |
| CN114254663A (en) | Method, system and medium for preventing misreading of RFID (radio frequency identification) electronic tags on multiple adjacent objects | |
| CN114611639A (en) | Radio frequency communication method and device, radio frequency communication system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |