Unmanned warehouse management method and system with real-time checking function

Abstract

The invention relates to the technical field of warehouse management, in particular to an unmanned warehouse management method and system with a real-time inventory function, and the method comprises the steps: building a signal strength-probability statistical model through return signal data generated in a historical inventory process, and carrying out the stability verification of each RFID tag return signal in a current inventory period, and under the condition that the stability is confirmed, carrying out preliminary positioning based on the time difference of arrival and determining the probability of the storage unit. And finally, the preliminary positioning is verified in combination with the probability of the storage unit and the checking information of the last checking period, so that the situation that whether the position of the RFID tag is changed really cannot be confirmed due to the fact that verification cannot be carried out when the positioning jumps is avoided. According to the invention, low-cost and high-reliability material positioning can be realized by using an existing RFID system, so that real-time and accurate checking is realized, and an information basis is provided for management of unmanned warehouses.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and particularly to an unmanned warehousing management method and system with a real-time inventory-taking function. Background Art

[0002] Unmanned warehousing management is a management mode that uses modern technological means such as automated equipment, robotics, Internet of Things (IoT), artificial intelligence (AI), and big data analysis to achieve a series of operations such as storage, handling, picking, and packaging of goods in a warehouse. This mode aims to reduce the dependence on manual operations and improve the efficiency and accuracy of warehousing management.

[0003] Real-time inventory-taking is the core of unmanned warehousing management. Based on the data of real-time inventory-taking, a series of operations such as storage, handling, picking, and packaging can be guided. The existing inventory-taking technologies are mainly based on RFID tags. However, the positioning accuracy of RFID-based positioning technology is usually poor and is easily interfered. Especially for the close-range position change of RFID tags, jumps are likely to occur in the positioning information. Therefore, accurate real-time inventory-taking of inventory cannot be achieved only through RFID positioning technology. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an unmanned warehousing management method and system with a real-time inventory-taking function to solve the above technical problems.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: The unmanned warehousing management method with a real-time inventory-taking function of the present invention includes the steps of: Obtaining the historical inventory return signal data of multiple storage units on the shelves in the warehouse, and obtaining the intensity of the return signals returned by the RFID tags multiple times and the arrival times of the return signals returned multiple times during the current inventory-taking period. Among them, the historical inventory return signal data includes the historical signal intensities of multiple historical return signals returned by the RFID tags to the RFID tags during multiple historical inventory-taking time periods, and the return signals returned multiple times are generated based on the radio signals transmitted by the RIFD base stations multiple times; Constructing a signal intensity-probability statistical model between multiple storage units and the RFID base station based on the historical inventory return signal data, where the signal intensity-probability statistical model represents the corresponding relationship between different signal intensities of the return signals and the probabilities of belonging storage units; Calculating the signal stable state and average signal intensity of the RFID tag based on the intensity of the return signals returned multiple times; Determine the probability that the RFID tag belongs to one or more storage units based on the average signal strength of the RFID tag in a stable state and the signal strength - probability statistical model; and, perform positioning based on the arrival times of the return signals returned multiple times by the RFID tag in a stable state to obtain a preliminary positioning. Perform positioning verification by combining the probability, the preliminary positioning, and the inventory information of the previous inventory cycle to obtain the positioning result of the RFID tag; and, perform warehouse management based on the positioning result of the RFID tag.

[0006] In an embodiment of the present application, it further includes: Extract the identification information of the RFID tag in an unstable signal state, and extract the positioning result of the identification information from the inventory cycle of the previous positioning result containing the identification information. Call a pre - set camera to capture an image containing the positioning result, and send the image containing the positioning result to a target object, where the target object is a remote management personnel or a server containing a visual recognition model.

[0007] In an embodiment of the present application, constructing a signal strength - probability statistical model between multiple storage units and an RFID base station based on the historical inventory return signal data includes: Obtain the reference signal strength of multiple storage units , where the reference signal strength is obtained based on experiments, is the storage unit serial number; Calculate the standard deviation and the average value of the historical signal strengths of the multiple return signals returned to the RFID tag within each historical inventory time period in the historical inventory return signal data, represents the time period serial number; Retain the data in the historical inventory return signal data that meets the target conditions to obtain target data, where the target conditions include: the standard deviation of the historical signal strengths of the multiple return signals is less than a preset standard deviation threshold, and the deviation rate of the average value of the standard deviations of the historical signal strengths of the multiple return signals and the corresponding reference signal strength is less than a preset deviation rate threshold, where, ; ; Calculate the average intensity and the intensity standard deviation of the historical return signals corresponding to each storage unit in the target data, and based on the average intensity and the intensity standard deviation Construct a probability density distribution function based on the Gaussian distribution and a signal strength reference range that conforms to three standard deviations. Among them, there are multiple RFID base stations, and the number of probability density distribution functions and signal strength reference ranges of each storage unit is the same as the number of RFID base stations; Construct a signal strength - probability statistical model based on the probability density distribution functions and signal strength reference ranges of multiple storage units.

[0008] In an embodiment of the present application, constructing a signal strength - probability statistical model based on the probability density distribution functions and signal strength reference ranges of multiple storage units includes: Construct a signal strength data axis, and map the signal strength reference ranges of multiple storage units to the signal strength data axis; Divide the signal strength data axis into multiple signal strength value intervals. For the signal strength reference ranges of one or more storage units included in any signal strength value interval, perform integration based on the probability density distribution functions of one or more storage units to obtain an initial probability , where is the serial number of the signal strength value interval; Based on the initial probabilities of one or more storage units in each signal strength value interval Calculate the probabilities of one or more storage units , where is the number of storage units covered by the signal strength value interval; Based on the probabilities of the storage units corresponding to multiple signal strength value intervals Construct a signal strength - probability statistical model.

[0009] In an embodiment of the present application, calculating the signal stability state and average signal strength of an RFID tag based on the strength of the returned signals returned multiple times includes: Calculate the standard deviation of the strengths of the returned signals returned multiple times; When the standard deviation of the strengths of the returned signals returned multiple times is less than a preset standard deviation threshold, determine that the signal state is stable; otherwise, determine that the signal state is unstable; When the signal state is stable, calculate the average value of the strengths of the returned signals returned multiple times.

[0010] In an embodiment of the present application, determining the probability that an RFID tag belongs to one or more storage units based on the average signal strength of the RFID tag in a stable state and the signal strength - probability statistical model includes: Determine the signal strength value intervals in the signal strength - probability statistical model to which the multiple average signal strengths of the RFID tags in the stable state belong, and obtain the probabilities of one or more storage units within the signal strength value intervals. Sum the probabilities of the same storage unit, and normalize the sum of the probabilities of multiple storage units to obtain the probabilities that the RFID tags belong to one or more storage units.

[0011] In an embodiment of the present application, positioning is performed based on the arrival times of the return signals returned multiple times by the RFID tags in the stable state to obtain a preliminary positioning, including: Taking the arrival time of the reference RFID base station as the reference time, calculate the time difference between the arrival times of other RFID base stations and the reference time. Construct a distance difference equation based on the coordinates of multiple RFID base stations and the time difference, where the distance difference equation represents the correspondence between the difference between the reference distance and the tag - station distance and the time difference. The reference distance is the distance between the reference RFID base station and the RFID tag, and the tag - station distance is the distance between other RFID base stations and the RFID tag. Substitute multiple time differences into the distance difference equation, and fit the distance difference equation by combining the least - squares method to obtain the preliminary positioning of the RFID tag.

[0012] In an embodiment of the present application, positioning verification is performed by combining the probabilities, the preliminary positioning, and the inventory information of the previous inventory cycle to obtain the positioning result of the RFID tag, including: Obtain the pre - constructed three - dimensional model of the shelf, where the three - dimensional model of the shelf includes the coordinate ranges of multiple storage units. Based on the three - dimensional model of the shelf and the preliminary positioning, determine the storage unit to which the RFID tag belongs in the current inventory cycle. Compare the storage unit to which the RFID tag belongs in the current inventory cycle with the storage unit to which it belonged in the previous inventory cycle, and when the storage unit to which the RFID tag belongs in the current inventory cycle is the same as the storage unit to which it belonged in the previous inventory cycle, use the storage unit corresponding to the preliminary positioning as the storage unit to which it belongs in the current inventory cycle. When the storage unit to which the RFID tag belongs in the current inventory cycle is inconsistent with the storage unit to which it belonged in the previous inventory cycle, determine the probability of the storage unit to which it belongs in the current inventory cycle. When the probability of the storage unit to which it belongs in the current inventory cycle is greater than a preset probability threshold, use the storage unit corresponding to the preliminary positioning as the storage unit to which it belongs in the current inventory cycle; when the probability of the storage unit to which it belongs in the current inventory cycle is less than or equal to the preset probability threshold, mark the preliminary positioning as uncertain, and use the storage unit to which the RFID tag belonged in the previous inventory cycle as the storage unit to which it belongs in the current inventory cycle.

[0013] In an embodiment of the present application, warehouse management is performed based on the positioning result of the RFID tag, including: Construct inventory information for the current inventory cycle based on all RFID tags, compare the inventory information for the current inventory cycle and the inventory information for the previous inventory cycle to obtain difference information; and perform management of material receipt, material issue, and material location change based on the difference information.

[0014] The present application also provides an unmanned warehouse management system with a real-time inventory function, including: An acquisition module, configured to acquire historical inventory return signal data of multiple storage units on the shelves in the warehouse, and acquire the intensity of the return signals returned by the RFID tag multiple times and the arrival time of the return signals returned multiple times in the current inventory cycle. Among them, the historical inventory return signal data includes the historical signal intensities of multiple historical return signals returned by the RFID tag to the RFID tag during multiple historical inventory time periods, and the return signals returned multiple times are generated based on radio signals transmitted by the RIFD base station multiple times; A model construction module, configured to construct a signal intensity - probability statistical model between multiple storage units and the RFID base station based on the historical inventory return signal data, where the signal intensity - probability statistical model represents the corresponding relationship between different signal intensities of the return signal and the probability of the belonging storage unit; A feature extraction module, configured to calculate the signal stability state and average signal intensity of the RFID tag based on the intensity of the return signals returned multiple times; A preliminary positioning module, configured to determine the probability that the RFID tag belongs to one or more storage units based on the average signal intensity of the RFID tag in a stable state and the signal intensity - probability statistical model; and perform positioning based on the arrival time of the return signals returned multiple times by the RFID tag in a stable state to obtain a preliminary positioning; A positioning verification module is used to combine the probability that the RFID tag belongs to one or more storage units and the preliminary positioning to correct the positioning and obtain the positioning result of the RFID tag; and, perform warehouse management based on the positioning result of the RFID tag.

[0015] The beneficial effects of the present invention are as follows: The unmanned warehouse management method and system with a real-time inventory function of the present invention constructs a signal strength - probability statistical model through the return signal data generated during the historical inventory process. In the current inventory cycle, by performing stability verification on the return signals of each RFID tag, and when it is confirmed to be stable, perform preliminary positioning based on the time difference of arrival and determine the probability of belonging to the storage unit. Finally, combine the probability of the storage unit and the inventory information of the previous inventory cycle to verify the preliminary positioning, avoiding the situation where when the positioning jumps, it cannot be verified, and thus it cannot be confirmed whether the RFID tag has truly changed its position. This application can utilize the existing RFID system to achieve low-cost and high-reliability material positioning, thereby achieving real-time and accurate inventory information, providing an information basis for the management of unmanned warehouses. Brief Description of the Drawings

[0016] The present invention will be further described below in conjunction with the drawings and embodiments: Figure 1 It is an application scenario diagram of the digital intelligent file management method based on machine vision shown in an embodiment of the present application; Figure 2 It is a flowchart of the digital intelligent file management method based on machine vision shown in an embodiment of the present application; Figure 3 It is a schematic diagram of the rough inspection process in an embodiment of the present application; Figure 4 It is a structural diagram of the unmanned warehouse management system with a real-time inventory function shown in an embodiment of the present application. Detailed Embodiments

[0017] The following specific examples illustrate the embodiments of the present invention. Those skilled in the art can easily understand the other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0018] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention schematically. Therefore, only the layers related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size ratio of the layers in actual implementation. The type, quantity, and can be arbitrarily changed in actual implementation, and the layer layout type may also be more complex.

[0019] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details.

[0020] Figure 1 It is an application scenario diagram of an unmanned warehouse management method with real-time inventory-taking function shown in an embodiment of the present application. As Figure 1 shown, the present application includes at least three ceiling-mounted RFID base stations (readers) for reading the information of all RFID tags within the coverage range. The RFID tags in the present application are ultra-high frequency (UHF) passive RFID tags. The RFID base station can provide energy for the RFID tags by transmitting radio waves, and then the RFID tags return the pre-written identity information to the RFID base station.

[0021] In the present application, a warehouse shelf with a metal frame is adopted, which then interferes with the RFID echo signal and easily causes label positioning jumps during the asset inventory process. Therefore, the following method is adopted for reliable positioning.

[0022] Figure 2 It is a flowchart of an unmanned warehouse management method with real-time inventory-taking function shown in an embodiment of the present application. As Figure 2 shown: The unmanned warehouse management method with real-time inventory-taking function in this embodiment may include steps S210 to S250: S210, obtaining the historical inventory return signal data of multiple storage units on the warehouse shelf, and obtaining the intensity of the return signals returned by the RFID tags multiple times and the arrival time of the return signals returned multiple times during the current inventory cycle. Among them, the historical inventory return signal data includes the historical signal intensities of multiple historical return signals returned by the RFID tags to the RFID tags during multiple historical inventory time periods, and the return signals returned multiple times are generated based on the radio signals transmitted by the RIFD base stations multiple times; In the present application, each time an automatic inventory is performed, it takes a period of time for radio frequency signal transmission and echo signal analysis, etc. This period of time is the inventory cycle.

[0023] During each inventory, the RFID base station emits radio frequency signals 10 - 20 times, with an interval of 50 ms each time; in addition, in order to suppress the multipath effect in this application, a coding and modulation scheme with strong multipath resistance is adopted, such as direct sequence spread spectrum (DSSS) or frequency hopping spread spectrum (FHSS). The returned signal and the radio frequency signal are corresponding based on the time stamp. The following table is the RFID data schematic table in this embodiment, which contains various interference and unstable situations. In the actual inventory process, if the warehouse is static, the signal quality will be better.

[0024] Table 1. RFID Data Table

[0025] S220, construct a signal strength - probability statistical model between multiple storage units and the RFID base station based on the historical inventory returned signal data, wherein the signal strength - probability statistical model characterizes the corresponding relationship between different signal strengths of the returned signal and the probability of belonging to the storage unit; Under stable conditions, the RFID returned signal is related to the distance. The distance between the storage unit in the container and the RFID base station is fixed. Therefore, under stable signal conditions, the intensity RSSI of the echo signal should be within a stable range. Therefore, based on the above logic, this application constructs a signal strength - probability statistical model based on historical data, including: S221, obtain the reference signal strength of multiple storage units , wherein the reference signal strength is obtained based on experiments, is the storage unit serial number; Reference signal strength Obtained through experimental tests, using the reference signal strength can numerically screen the historical echo data to avoid the situation where when the RFID tag is blocked, the echo data shows a stable state, but the value is quite different from the values at other times, which may lead to an overly large reference range obtained in subsequent analysis.

[0026] S222, calculate the standard deviation of the historical signal strength of multiple returned signals returned to the RFID tag within each historical inventory time period in the historical inventory returned signal data and the average value , represents the time period serial number; Standard deviation used to reflect signal stability, and the calculation formula for the standard deviation is:

[0027] In the formula, represents the number of returned signals, represents the The intensity of a return signal.

[0028] S223, retain the data in the historical inventory return signal data that meets the target conditions to obtain target data; The target conditions include: (1) the standard deviation of the historical signal intensities of multiple return signals is less than a preset standard deviation threshold; (2) the average value of the standard deviations of the historical signal intensities of multiple return signals and the deviation rate from the corresponding reference signal intensity is less than a preset deviation rate threshold, where ; When target condition (1) is met, it indicates that the return signal intensity of the RFID tags in this historical inventory cycle is relatively stable. When target condition (2) is also met, it indicates that the value of the return signal intensity of the RFID tags in this historical inventory cycle is also close to the reference value. Therefore, it can be used as the target data for subsequent analysis.

[0029] S224, calculate the average intensity and intensity standard deviation of the historical return signals corresponding to each storage unit in the target data, and construct a probability density distribution function based on the Gaussian distribution and a signal intensity reference range that conforms to three standard deviations, where there are multiple RFID base stations, and the number of probability density distribution functions and signal intensity reference ranges for each storage unit is the same as the number of RFID base stations; Step S223 calculates the average value and standard deviation of the return signal intensities within an inventory cycle. In this step, the average value and standard deviation of the intensities of all return signals corresponding to a single RFID tag are calculated. Then, a probability density distribution function and a signal intensity reference range that conforms to three standard deviations are constructed. The mathematical expression of the probability density function is:

[0030] In the formula, represents the probability density, represents the value of the return signal intensity.

[0031] In addition, in order to make the total probability of the probability density function within the three standard deviation range equal to 1, it is also necessary to perform a normalization process on it.

[0032] The three standard deviation range is the signal intensity reference range of the return signals of the RFID tags in the storage unit under normal circumstances, and the mathematical representation is .

[0033] S225. Construct a signal strength data axis and map the signal strength reference ranges of multiple storage units to the signal strength data axis; Figure 3 This is a schematic diagram of the strength data axis in an embodiment of the present application. As Figure 3 shown, after obtaining the probability density distribution function and the signal strength reference range, map the signal strength reference range and the storage unit serial number to a two-dimensional coordinate system. The horizontal axis of the two-dimensional coordinate system is the strength data axis, and the vertical axis is the serial number axis.

[0034] In addition, since there are multiple RFID base stations in the present application and their corresponding reference signal strength reference ranges are different, only the signal strength data axis corresponding to one of the RFID base stations is shown in the present application. For the signal strength data axes of other RFID base stations, please refer to Figure 3 for understanding.

[0035] S226. Divide the signal strength data axis into multiple signal strength value intervals. For the signal strength reference range of one or more storage units included in any signal strength value interval, perform integration based on the probability density distribution function of the one or more storage units to obtain an initial probability , where is the serial number of the signal strength value interval; As Figure 3 shown, there are overlapping parts among the multiple signal strength reference ranges in the two-dimensional coordinate system. The probability that the return signal strength of the RFID tag in the storage unit falls into the overlapping part can be obtained by integrating the probability density function. However, since there may actually be multiple reference ranges overlapping each other, it is difficult to define the overlapping sections. Therefore, in the present application, the signal strength data axis is directly divided to obtain multiple signal strength intervals, and then the probability density function is integrated for the signal strength reference range in each signal strength interval to obtain the probabilities of multiple signal strength intervals.

[0036] S227. Calculate the probability of one or more storage units based on the initial probability of one or more storage units in each signal strength value interval, , where is the number of storage units covered by the signal strength value interval; Finally, for the initial probability Reallocate so that the total probability of each signal strength value range is 100%. The probability of the storage unit within each signal strength value range can be obtained. This probability reflects the probability that when the strength of the returned signal received by the RFID base station falls within one of the ranges, it belongs to the corresponding one or more storage units.

[0037] S228. Based on the probabilities of the storage units corresponding to multiple signal strength value ranges Construct a signal strength - probability statistical model.

[0038] S230. Calculate the signal stability state and average signal strength of the RFID tag based on the strength of the returned signals returned multiple times; after constructing the signal strength - probability statistical model and before needing to combine the signal strength - probability statistical model, stability judgment and average signal strength calculation are required, specifically including: S231. Calculate the standard deviation of the strength of the returned signals returned multiple times; the calculation formula of the standard deviation is referred to the previous text and will not be elaborated here.

[0039] S232. When the standard deviation of the strength of the returned signals returned multiple times is less than the preset standard deviation threshold, determine that the signal state is stable; otherwise, determine that the signal state is unstable. S233. When the signal state is stable, calculate the average value of the strength of the returned signals returned multiple times.

[0040] Evaluate the signal stability by calculating the volatility (standard deviation) of the signal strength. The more stable the signal strength (such as ), it indicates that the environmental interference is small and the path is single. If the signal fluctuates violently (such as ), there may be multipath effects, metal interference or dynamic environment impacts.

[0041] When the signal is stable, extract the representative value (average value) of the signal strength for use in subsequent analysis processes.

[0042] In addition, in this application, for RFID tags in an unstable signal state, this application remotely performs manual / AI inventory by collecting image information at the corresponding location, including: (1) Extract the identification information of the RFID tag in an unstable signal state, and extract the positioning result of the identification information from the inventory cycle of the previous positioning result containing the identification information. (2) Call a pre - set camera to take an image containing the positioning result and send the image containing the positioning result to the target object, where the target object is a remote manager or a server containing a visual recognition model.

[0043] S240. Determine the probability that the RFID tag belongs to one or more storage units based on the average signal strength of the RFID tag in the stable state and the signal strength - probability statistical model; and, perform positioning based on the arrival time of the returned signals returned multiple times by the RFID tag in the stable state to obtain a preliminary positioning. When determining the probability, it is only necessary to determine the signal strength value range in the signal strength - probability statistical model to which the average signal strength of the RFID tag in the stable state belongs, and then obtain the probability of one or more storage units within the signal strength value range. For example: Interval A includes the probabilities of two storage units, 70% and 30% respectively. If the average signal strength of the RFID tag in the stable state falls into Interval A, then the probabilities corresponding to the two storage units are 70% and 30% respectively.

[0044] However, due to the existence of multiple RFID base stations, there are also multiple average signal strengths for the same RFID tag. For example, there are three RFID base stations. According to the above process, the probabilities of falling into the storage units obtained are as follows: Table 2. Storage Unit Attribution Probability Table

[0045] Sum the multiple probabilities of the same storage unit, and normalize the sum of the probabilities of multiple storage units to obtain the probability that the RFID tag belongs to one or more storage units.

[0046] For example: The total probability of storage unit 1 is 170%, the total probability of storage unit 2 is 100%, and the total probability of storage unit 3 is 30%. After normalization, the probability of storage unit 1 is 57%, the probability of storage unit 2 is 33%, and the probability of storage unit 3 is 10%.

[0047] The above process can be regarded as a positioning process based on statistics and big data. In this application, positioning is also performed on each RFID tag based on the Time Difference of Arrival (TDOA) method, specifically including: S241. Taking the arrival time of the reference RFID base station as the reference time, calculate the time difference between the arrival times of other RFID base stations and the reference time. For example, in this application, there are three RFID base stations, namely BS - 001, BS - 002, and BS - 003; taking BS - 001 as the reference RFID base station. Therefore, it is necessary to calculate the arrival time of each time the return signal is received by BS - 002 and BS - 003 and the arrival time of each time the return signal is received by BS - 001 The difference, that is and ; S242. Construct a distance difference equation based on the coordinates of multiple RFID base stations and the time difference. Among them, the distance difference equation represents the corresponding relationship between the difference between the reference distance and the tag-station distance and the arrival time difference. The reference distance is the distance between the reference RFID base station and the RFID tag, and the tag-station distance is the distance between other RFID base stations and the RFID tag; Time difference and The corresponding distance difference is and , is the electromagnetic wave velocity; the corresponding distance difference equation is:

[0048] In the formula, is the coordinate of the RFID tag, is the positioning coordinate of the reference RFID base station BS-001, is the coordinate of the base station BS-002, is the coordinate of the base station BS-003.

[0049] S243. Substitute multiple time differences into the distance difference equation, and combine the least squares method to fit the distance difference equation to obtain the preliminary positioning of the RFID tag.

[0050] Finally, substitute the multiple time differences calculated based on the multiple return signals obtained in the current inventory cycle and the coordinates of the three known RFID base stations into the above equation, and combine the least squares method for fitting to obtain the preliminary positioning. The process of performing the least squares method fitting includes: Construct an objective function. The objective in this embodiment is to minimize the sum of the squared residuals of all equations, that is:

[0051] In the formula, represents the total number of equations (determined by the number of base station pairs). For example, there are two pairs in the above equation set, ; ik represents the base station i in the kth base station pair, and jk represents the base station j in the kth base station pair; Then, select the initial estimate , and the target position can be roughly estimated by a geometric method (such as the intersection of hyperbolas).

[0052] At the initial estimate perform a first-order Taylor expansion to obtain the residual function :

[0053] Among them,

[0054] Substitute the residual to obtain a system of linear equations:

[0055] In the formula, is the Jacobian matrix, ; Update the estimated value by solving the system of linear equations, ; Repeat the above process until the residual converges to less than the threshold, and the preliminary positioning can be obtained.

[0056] S250, perform positioning verification by combining the probability, the preliminary positioning, and the inventory information of the previous inventory cycle to obtain the positioning result of the RFID tag; and perform warehouse management based on the positioning result of the RFID tag.

[0057] After obtaining the preliminary positioning calculated by the time difference of arrival method and the probability positioning obtained by the data statistics method. The positioning verification can be carried out, specifically including: S251, obtain the pre-constructed three-dimensional model of the shelf, where the three-dimensional model of the shelf includes the coordinate ranges of multiple storage units; The three-dimensional model of the shelf is pre-constructed. The coordinate positions of the shelf corner points are collected by uwb tags at the shelf corner positions, and then the modeling can be completed by combining the geometric information of the shelf. The storage units can be deduced according to the corresponding sizes and the relative position information with the shelf corner positions.

[0058] S252, determine the storage unit to which the RFID tag belongs in the current inventory cycle based on the three-dimensional model of the shelf and the preliminary positioning; The serial number of the storage unit to which it belongs can be directly obtained by comparing the preliminary positioning with the shelf corner positions. The target of the positioning in this application is the serial number of the storage unit to which it belongs. However, due to the unreliability of RFID positioning, the inventory information of the previous inventory cycle and the results of probability statistics are introduced in this application for verification, specifically as follows: S253, compare the storage unit to which the RFID tag belongs in the current inventory cycle with the storage unit to which it belonged in the previous inventory cycle, and when the storage unit to which the RFID tag belongs in the current inventory cycle is the same as the storage unit to which it belonged in the previous inventory cycle, use the storage unit corresponding to the preliminary positioning as the storage unit to which it belongs in the current inventory cycle; If, for the current RFID tag, the positioning information is the same as the positioning information in the inventory information of the previous inventory cycle, it can be directly inferred that the item corresponding to the RFID tag has not been shipped out and its position has not changed, etc. Since the positions of items rarely change during the warehousing process, this situation is in line with management habits. At this time, statistical probability is not introduced.

[0059] S254. When the storage unit to which the RFID tag belongs in the current inventory cycle is inconsistent with the storage unit to which it belonged in the previous inventory cycle, determine the probability of the storage unit to which it belongs in the current inventory cycle. When the probability of the storage unit to which it belongs in the current inventory cycle is greater than the preset probability threshold, use the storage unit corresponding to the preliminary positioning as the storage unit to which it belongs in the current inventory cycle; when the probability of the storage unit to which it belongs in the current inventory cycle is less than or equal to the preset probability threshold, mark the preliminary positioning as uncertain, and use the storage unit to which the RFID tag belonged in the previous inventory cycle as the storage unit to which it belongs in the current inventory cycle.

[0060] If, for the current RFID tag, the positioning information is inconsistent with the positioning information in the inventory information of the previous inventory cycle, it is possible that the position of the item corresponding to the current RFID tag has changed. To rule out position jumps caused by poor accuracy of the RFID positioning technology, this application uses the statistical probability extracted above for verification. That is, if the preliminary positioning of the RFID tag jumps from storage unit A to storage unit B, and at the same time, the probability that the signal strength belongs to the RFID tag is greater than 50%, then it can be verified that the position of the item corresponding to the current RFID tag has indeed changed. On the contrary, if the probability that the signal strength belongs to the RFID tag is small, then verification cannot be performed at this time. In this case, the inventory result of the previous inventory cycle is adopted, and further verification in the next inventory cycle is awaited.

[0061] Through the above process, the situation of incorrect change of item position information caused by poor RFID positioning accuracy can be effectively avoided. It has strong reliability for position update.

[0062] After completing the automatic inventory of the inventory in the current inventory cycle, the position information and status information of all materials (whether it can be read to determine whether it has been shipped out) can be obtained. Then, based on all RFID tags, the inventory information of the current inventory cycle is constructed, and the inventory information of the current inventory cycle is compared with the inventory information of the previous inventory cycle to obtain the difference information; and based on the difference information, management of material receipt, material shipment, and material position change is carried out.

[0063] The unmanned warehouse management method with real-time inventory taking function of the present invention constructs a signal strength - probability statistical model through the return signal data generated during the historical inventory process. In the current inventory cycle, by performing stability verification on the return signals of each RFID tag, and when it is confirmed to be stable, preliminary positioning based on the time difference of arrival and the probability of belonging to a storage unit is determined. Finally, the preliminary positioning is verified by combining the probability of the storage unit and the inventory information of the previous inventory cycle, avoiding the situation where when the positioning jumps, it cannot be verified, and thus it cannot be confirmed whether the RFID tag has really changed its position. This application can utilize the existing RFID system to achieve low-cost and high-reliability material positioning, thereby realizing real-time and accurate inventory information, providing an information basis for the management of unmanned warehouses.

[0064] This application also provides an unmanned warehouse management system with real-time inventory taking function, including: An acquisition module, configured to acquire the historical inventory return signal data of multiple storage units on the shelves in the warehouse, and acquire the strength of the return signals returned by the RFID tag multiple times and the arrival time of the return signals returned multiple times during the current inventory cycle. Among them, the historical inventory return signal data includes the historical signal strength of multiple historical return signals returned by the RFID tag to the RFID tag during multiple historical inventory time periods, and the return signals returned multiple times are generated based on the radio signals transmitted by the RIFD base station multiple times; A model construction module, configured to construct a signal strength - probability statistical model between multiple storage units and the RFID base station based on the historical inventory return signal data. Among them, the signal strength - probability statistical model represents the corresponding relationship between different signal strengths of the return signal and the probability of belonging to a storage unit; A feature extraction module, configured to calculate the signal stability state and the average signal strength of the RFID tag based on the strength of the return signals returned multiple times; A preliminary positioning module, configured to determine the probability that the RFID tag belongs to one or more storage units based on the average signal strength of the RFID tag in a stable state and the signal strength - probability statistical model; and perform positioning based on the arrival time of the return signals returned multiple times by the RFID tag in a stable state to obtain a preliminary positioning; A positioning verification module, configured to perform positioning correction by combining the probability that the RFID tag belongs to one or more storage units and the preliminary positioning to obtain the positioning result of the RFID tag; and perform warehouse management based on the positioning result of the RFID tag.

[0065] The unmanned warehouse management system with real-time inventory taking function of the present invention constructs a signal strength-probability statistical model through the return signal data generated in the historical inventory process. In the current inventory cycle, after the stability verification of the return signals of each RFID tag, when it is confirmed to be stable, the preliminary positioning based on the time difference of arrival and the probability of the belonging storage unit are determined. Finally, the preliminary positioning is verified by combining the probability of the storage unit and the inventory information of the previous inventory cycle, avoiding the situation that when the positioning jumps, it cannot be verified, and thus it cannot be confirmed whether the RFID tag has actually changed its position. This application can utilize the existing RFID system to achieve low-cost and high-reliability material positioning, so as to obtain real-time and accurate inventory information, providing an information basis for the management of unmanned warehouses.

[0066] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements any one of the methods in this embodiment, where the method is the execution logic of this system.

[0067] This embodiment also provides an electronic terminal, including: a processor and a memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0068] For the computer-readable storage medium in this embodiment, those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to the computer program. The foregoing computer program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disk, or optical disc that can store program codes.

[0069] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver, and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store a computer program, the communication interface is used for communication, and the processor and the transceiver are used to run the computer program, so that the electronic terminal executes each step of the above method.

[0070] In this embodiment, the memory may include a random access memory (Random Access Memory, abbreviated as RAM), and may also include a non-volatile memory, such as at least one disk memory.

[0071] The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0072] In the above embodiments, although the present invention has been described in conjunction with specific embodiments of the present invention, many substitutions, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. The embodiments of the present invention are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims.

[0073] The above embodiments are only illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. An unmanned warehousing management method with a real-time inventory taking function, characterized in that Including the steps: Obtain the historical inventory return signal data of multiple storage units on the shelves in the warehouse, and obtain the intensity of the return signals returned by the RFID tag multiple times and the arrival time of the return signals returned multiple times during the current inventory cycle. Among them, the historical inventory return signal data includes the historical signal intensities of multiple historical return signals returned by the RFID tag to the RFID tag during multiple historical inventory time periods, and the return signals returned multiple times are generated based on the radio signals transmitted by the RIFD base station multiple times; Construct a signal intensity - probability statistical model between multiple storage units and the RFID base station based on the historical inventory return signal data. Among them, the signal intensity - probability statistical model characterizes the corresponding relationship between different signal intensities of the return signal and the probability of belonging to the storage unit; Calculate the signal stability state and average signal intensity of the RFID tag based on the intensity of the return signals returned multiple times; Determine the probability that the RFID tag belongs to one or more storage units based on the average signal intensity of the RFID tag in the stable state and the signal intensity - probability statistical model; and, perform positioning based on the arrival time of the return signals returned multiple times by the RFID tag in the stable state to obtain a preliminary positioning; Combine the probability, the preliminary positioning, and the inventory information of the previous inventory cycle to perform positioning verification to obtain the positioning result of the RFID tag; and, perform warehouse management based on the positioning result of the RFID tag.

2. The unmanned warehouse management method with real-time inventory taking function according to claim 1, wherein, It also includes: Extract the identification information of the RFID tag in the signal unstable state, and extract the positioning result of the identification information from the inventory cycle of the previous positioning result including the identification information; Call a pre - set camera to capture an image including the positioning result, and send the image including the positioning result to the target object, where the target object is a remote management personnel or a server including a visual recognition model.

3. The unmanned warehousing management method with real-time inventory checking function according to claim 1, characterized in that, Constructing a signal intensity - probability statistical model between multiple storage units and the RFID base station based on the historical inventory return signal data includes: Obtain the reference signal strength of multiple memory cells , wherein the reference signal strength is obtained based on a test is the memory cell serial number Calculate the standard deviation of the historical signal strengths of the multiple return signals returned to the RFID tag within each historical inventory time period in the historical inventory return signal data and the average value , indicating the time period serial number; Retain the data in the historical inventory return signal data that meets the target conditions to obtain target data, where the target conditions include: the standard deviation of the historical signal strengths of multiple return signals less than a preset standard deviation threshold, and the average value of the standard deviations of the historical signal strengths of multiple return signals and the deviation rate from the corresponding reference signal strength is less than a preset deviation rate threshold, where ; ; Calculate the average intensity of the historical return signals corresponding to each storage unit in the target data and the standard deviation of the intensity , and based on the average intensity and the standard deviation of the intensity Construct a probability density distribution function based on the Gaussian distribution and a signal intensity reference range that conforms to three standard deviations, where there are multiple RFID base stations, and the number of probability density distribution functions and signal intensity reference ranges for each storage unit is the same as the number of RFID base stations; Construct a signal intensity - probability statistical model based on the probability density distribution function of multiple storage units and the signal intensity reference range.

4. The unmanned warehouse management method with real-time inventory taking function according to claim 3, characterized in that, Constructing a signal intensity - probability statistical model based on the probability density distribution function of multiple storage units and the signal intensity reference range includes: Construct a signal intensity data axis, and map the signal intensity reference ranges of multiple storage units to the signal intensity data axis; Divide the signal strength data axis into multiple signal strength value intervals. For the signal strength reference range of one or more storage units included in any signal strength value interval, integrate based on the probability density distribution function of the one or more storage units to obtain an initial probability , where is the serial number of the signal strength value interval; Initial probabilities of one or more memory cells within each signal strength value range Calculate the probabilities of one or more memory cells , , where is the number of memory cells covered by the signal strength value range; Probability based on storage units corresponding to multiple signal strength value ranges Construct a signal strength - probability statistical model.

5. The unmanned warehouse management method with real-time inventory taking function according to claim 1, characterized in that, Calculating the signal stability state and average signal intensity of the RFID tag based on the intensity of the return signals returned multiple times includes: Calculate the standard deviation of the intensities of the return signals returned multiple times; When the standard deviation of the intensities of the return signals returned multiple times is less than a preset standard deviation threshold, determine that the signal state is stable; otherwise, determine that the signal state is unstable; When the signal state is stable, calculate the average value of the intensities of the return signals returned multiple times.

6. The unmanned warehousing management method with a real-time inventory-taking function according to claim 4, characterized in that, Determining the probability that the RFID tag belongs to one or more storage units based on the average signal intensity of the RFID tag in the stable state and the signal intensity - probability statistical model includes: Determine the signal strength value intervals in the signal strength - probability statistical model to which the multiple average signal strengths of the RFID tags in the stable state belong, and obtain the probabilities of one or more storage units within the signal strength value intervals. Sum the probabilities of the same storage unit and normalize the sum of the probabilities of multiple storage units to obtain the probabilities that the RFID tags belong to one or more storage units.

7. The unmanned warehousing management method with real-time inventory taking function according to claim 1, characterized in that, Perform positioning based on the arrival times of the returned signals repeatedly returned by the RFID tags in the stable state to obtain a preliminary positioning, including: Taking the arrival time of the reference RFID base station as the reference time, calculate the time difference between the arrival times of other RFID base stations and the reference time. Construct a distance difference equation based on the coordinates of multiple RFID base stations and the time difference, where the distance difference equation represents the corresponding relationship between the difference between the reference distance and the station - tag distance and the arrival time difference. The reference distance is the distance between the reference RFID base station and the RFID tag, and the station - tag distance is the distance between other RFID base stations and the RFID tag. Substitute multiple time differences into the distance difference equation and fit the distance difference equation using the least - squares method to obtain the preliminary positioning of the RFID tag.

8. The unmanned warehousing management method with real-time inventory counting function according to claim 1, characterized in that, Combine the probabilities, the preliminary positioning, and the inventory information of the previous inventory cycle to perform positioning verification to obtain the positioning result of the RFID tag, including: Obtain the pre - constructed three - dimensional model of the shelf, where the three - dimensional model of the shelf includes the coordinate ranges of multiple storage units. Based on the three - dimensional model of the shelf and the preliminary positioning, determine the storage unit to which the RFID tag belongs in the current inventory cycle. Compare the storage unit to which the RFID tag belongs in the current inventory cycle with the storage unit to which it belonged in the previous inventory cycle. When they are the same, use the storage unit corresponding to the preliminary positioning as the storage unit to which it belongs in the current inventory cycle. When the storage unit to which the RFID tag belongs in the current inventory cycle is different from the storage unit to which it belonged in the previous inventory cycle, determine the probability of the storage unit to which it belongs in the current inventory cycle. When the probability of the storage unit to which it belongs in the current inventory cycle is greater than the preset probability threshold, use the storage unit corresponding to the preliminary positioning as the storage unit to which it belongs in the current inventory cycle. When the probability of the storage unit to which it belongs in the current inventory cycle is less than or equal to the preset probability threshold, mark the preliminary positioning as uncertain and use the storage unit to which the RFID tag belonged in the previous inventory cycle as the storage unit to which it belongs in the current inventory cycle.

9. The unmanned warehouse management method with real-time inventory checking function according to claim 1, characterized in that, Perform warehouse management based on the positioning results of the RFID tags, including: Construct the inventory information of the current inventory cycle based on all RFID tags, compare the inventory information of the current inventory cycle with the inventory information of the previous inventory cycle to obtain the difference information, and perform management of material inbound, material outbound, and material location change based on the difference information.

10. An unmanned warehousing management system with a real-time inventory function, characterized in that, Including: An acquisition module, configured to acquire historical inventory return signal data of multiple storage units on the shelves in a warehouse, and acquire the intensity of the return signals returned by the RFID tags multiple times and the arrival times of the return signals returned multiple times within the current inventory cycle. Wherein, the historical inventory return signal data includes the historical signal intensities of multiple historical return signals returned by the RFID tags to the RFID tags within multiple historical inventory time periods, and the return signals returned multiple times are generated based on the radio signals transmitted by the RIFD base station multiple times; A model construction module, configured to construct a signal intensity - probability statistical model between multiple storage units and the RFID base station based on the historical inventory return signal data. Wherein, the signal intensity - probability statistical model characterizes the corresponding relationship between different signal intensities of the return signals and the probabilities of belonging storage units; A feature extraction module, configured to calculate the signal stability state and the average signal intensity of the RFID tag based on the intensity of the return signals returned multiple times; A preliminary positioning module, configured to determine the probability that the RFID tag belongs to one or more storage units based on the average signal intensity of the RFID tag in a stable state and the signal intensity - probability statistical model; and perform positioning based on the arrival times of the return signals returned multiple times by the RFID tag in a stable state to obtain a preliminary positioning; A positioning verification module, configured to perform positioning correction in combination with the probability that the RFID tag belongs to one or more storage units and the preliminary positioning to obtain the positioning result of the RFID tag; and perform warehouse management based on the positioning result of the RFID tag.

Images