An intelligent positioning system and positioning method for warehousing logistics

Abstract

The present invention relates to the field of deep learning technology, and discloses an intelligent positioning system and positioning method for warehousing logistics, comprising the following steps: collecting cargo information through a wireless communication network, the cargo information including attribute information of the cargo and information of the transport unit where the cargo is located; obtaining first-order two-dimensional structural data including first-order data matrix and first-order relationship matrix based on historically collected cargo information; inputting the first-order two-dimensional structural data into an intelligent positioning model, and outputting a result representing the ID of the transport unit where the cargo is located; updating the cargo information through the ID of the transport unit where the cargo is located output by the intelligent positioning model; the present invention predicts missing cargo location information through a deep learning model, can flexibly respond to emergencies of electronic tags, and only predicts the essential information, namely, cargo location information.

Description

Technical Field

[0001] The present invention relates to the field of deep learning technology, and more specifically, to an intelligent positioning system and positioning method for warehousing logistics. Background Art

[0002] The transit transportation management of logistics goods needs to achieve the goal of maximizing transportation failure as much as possible, which requires relying on the positioning of cargo logistics. Although the use of electronic tags combined with cargo pallets can be used as a means of cargo positioning, the actual logistics environment is extremely dynamic. Some cargo electronic tags may be blocked or damaged, resulting in communication interruption. The lack of information will make it impossible to achieve the optimal transportation allocation goal. Summary of the Invention

[0003] The present invention provides an intelligent positioning system and positioning method for warehousing logistics, which solves the technical problem in related technologies that communication interruption caused by shielding or damage of some goods' electronic tags and missing information will lead to the inability to achieve the optimal goal of transportation allocation.

[0004] The present invention provides an intelligent positioning system and positioning method for warehousing logistics, comprising the following steps:

[0005] Step 100: collecting cargo information via a wireless communication network, the cargo information including cargo attribute information and information about the transport unit where the cargo is located;

[0006] Cargo information is stored through the electronic tags on the warehouse logistics pallets carrying the goods, and then transmitted and collected through the wireless communication network;

[0007] Step 200: Based on the historically collected cargo information, first two-dimensional structural data is obtained, including a first data matrix and a first relationship matrix. Each cell of the first data matrix represents the first one-dimensional structural data of a cargo. The element in the i-th row and j-th column of the first relationship matrix represents the association between the cargo represented by the i-th cell and the j-th cell of the first data matrix. If an association exists, the value of the element in the first relationship matrix is 1, otherwise it is 0.

[0008] The relationship between goods means that the goods have the same attributes and are located in the same transport unit;

[0009] The one-dimensional structure data No. 1 includes n data items sorted by time, and the t-th data item represents the cargo information collected at the t-th moment;

[0010] Step 300: Input the first two-dimensional structure data into the intelligent positioning model. The intelligent positioning model includes a first intermediate layer, a second intermediate layer, and a first output layer. The first intermediate layer inputs the first one-dimensional structure data and outputs first intermediate representation data to the second intermediate layer. The second intermediate layer also inputs the first relationship matrix. The second intermediate layer outputs second intermediate representation data to the first output layer. The first output layer outputs a result indicating the ID of the transport unit where the goods are located.

[0011] Step 400: Update cargo information using the ID of the transport unit where the cargo is located output by the intelligent positioning model.

[0012] Furthermore, the updating method is to replace the transport unit where the goods are located in the goods information with the ID of the transport unit where the goods are located output by the intelligent positioning model.

[0013] Furthermore, the calculation formula of the first intermediate layer is as follows:

[0014] h t =tanh(W hh h t-1 +W xh x t +b h )

[0015] where h t represents the t-th first intermediate representation data output by the first intermediate layer, h t-1 Indicates the t-1th first intermediate representation data, x t Represents the tth data item of the one-dimensional structure data, W hh and W xh are the first and second weight parameters, b h is the first bias parameter, and tanh is the hyperbolic tangent function.

[0016] Furthermore, the calculation formula of the second intermediate layer is as follows:

[0017]

[0018] where k v The second intermediate representation data of the vth unit of the data matrix No. 1, M (v) is the set of cells associated with the vth cell of the data matrix No. 1, The nth first intermediate representation data output when the first unit of the first data matrix is input as the structure data into the first intermediate layer, c v is a normalization constant, σ is the sigmoid function, W k Represents the third weight parameter.

[0019] Furthermore, the calculation formula of the first output layer is as follows:

[0020] y v =σ(W y k v +b y )

[0021] where y v Represents the first output vector, whose cth component value represents the probability value of the ID of the cth transport unit, and the ID of the transport unit with the largest probability value is selected as the ID of the transport unit where the goods represented by the vth unit are located, k v The second intermediate representation data of the vth unit of the data matrix No. 1, W y is the out weight parameter, b y is the out bias parameter, and σ represents the sigmoid function.

[0022] Furthermore, an intelligent positioning system and positioning method for warehousing logistics further includes the following steps:

[0023] Step 500 , the information of the transport unit where the cargo is located includes: the transport capacity of the transport unit, the used capacity of the transport unit, the speed of the transport unit, the location of the transport unit, the weather in the area where the transport unit is located, and the remaining fuel of the transport unit;

[0024] The updated cargo information is sorted to obtain second one-dimensional structure data; the second one-dimensional structure data includes n data items sorted by time, and the t-th data item represents the second two-dimensional structure data generated by the cargo information collected at the t-th moment;

[0025] The second two-dimensional structure data includes a second data matrix and a second relationship matrix. A unit of the second data matrix represents the cargo information of a cargo. The element in the i-th row and j-th column of the second relationship matrix represents the association between the cargoes represented by the i-th unit and the j-th unit of the second data matrix. If an association exists, the value of the element in the second relationship matrix is 1, otherwise it is 0.

[0026] Step 600, input the second one-dimensional structure data into the transportation strategy model, the transportation strategy model includes a third intermediate layer, a fourth intermediate layer and a second output layer, wherein the third intermediate layer inputs the second two-dimensional structure data, outputs the third intermediate representation data to the fourth intermediate layer, the fourth intermediate layer outputs the fourth intermediate representation data to the second output layer, and the second output layer outputs a structure representing the transportation strategy of the goods at the next moment, the transportation strategy includes the transportation unit to which each cargo needs to be moved when it arrives at the cargo transfer station next time.

[0027] Furthermore, the calculation formula of the third intermediate layer is as follows:

[0028]

[0029] where Q i The third intermediate representation data of the i-th unit of the second relationship matrix, W Q Represents the state weight parameter, in i and in j Respectively represent the cargo information of the cargo represented by the i-th unit and the j-th unit of the second data matrix, T i represents the set of vertices directly connected to the i-th vertex, M represents T i The total number of vertices in R i，j =tanh(δ*in i T *in j +1), tanh represents the hyperbolic tangent function, and δ represents an adjustable parameter; the default value of δ is 25.

[0030] Furthermore, the calculation formula of the fourth intermediate layer is as follows:

[0031] u (t) =σ(W u X (t) +W u H (t-1) +b u )

[0032] r (t) =σ(W r X (t) +W r H (t-1) +b r )

[0033] C (t) =tanh(W c X (t) +W c r (t) ⊙H (t-1) +b c )

[0034] H (t) =(1-u (t) )⊙C (t) +u (t) ⊙H (t-1)

[0035]

[0036] Among them, W u 、W r 、W c represents the fourth, fifth, and sixth weight parameters, b u 、b r 、b crepresents the fourth, fifth, and sixth bias parameters, ⊙ represents the dot product, u (t) 、r (t) and C (t) Represent the first, second, and third intermediate states respectively, where X (t) represents the t-th input of the fourth intermediate layer, The third intermediate representation data of the i-th unit of the second relationship matrix output when the t-th data item is input into the third intermediate layer, H 9t) and H (t-1) Respectively represent the t-th and t-1-th fourth intermediate representation data, n≥t≥1, n represents the number of data items of the second one-dimensional structure data, when t=1, H (t-1) =X (t) , tanh is the hyperbolic tangent function, and σ represents the sigmoid function.

[0037] Furthermore, the calculation formula of the second output layer is as follows:

[0038] G=σ(W G H (n) +b G )

[0039] Where G represents the second output vector, a component value of the second output vector represents the probability value of a transportation strategy, the transportation strategy belongs to the transportation strategy set, and the transportation strategy set contains all transportation strategies that can be executed, H (n) Indicates the nth fourth intermediate representation data, W G is the second output weight parameter, b G is the second output bias parameter, and σ represents the sigmoid function.

[0040] The present invention provides a computer storage medium for storing computer-readable instructions, which can execute the aforementioned intelligent positioning system and positioning method for warehousing logistics when the computer-readable instructions are read.

[0041] The beneficial effects of the present invention are:

[0042] The present invention uses a deep learning model to predict missing cargo location information, which can flexibly respond to unexpected situations of electronic tags. It only predicts the essential information of cargo location. Subsequently, the transportation strategy model can generate the cargo into two-dimensional structure data, and supplement the original characteristics of the cargo by filling in the data. The information transmission of the two-dimensional structure data supports the generation of the transportation strategy for the cargo.

[0043] In addition, the present invention adds weather information of the transport unit, and can adapt to emergencies such as temporary route interruption, vehicle failure, weather changes, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of an intelligent positioning system and positioning method for warehousing logistics of the present invention. DETAILED DESCRIPTION

[0045] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. Furthermore, features described in some examples may be combined in other examples.

[0046] At least one embodiment of the present invention discloses an intelligent positioning system and positioning method for warehousing logistics, such as Figure 1 As shown, the following steps are included:

[0047] Step 100: collecting cargo information via a wireless communication network, the cargo information including cargo attribute information and information about the transport unit where the cargo is located;

[0048] Cargo information is stored through the electronic tags on the warehouse logistics pallets carrying the goods, and then transmitted and collected through the wireless communication network;

[0049] Step 200: Based on the historically collected cargo information, first two-dimensional structural data is obtained, including a first data matrix and a first relationship matrix. Each cell of the first data matrix represents the first one-dimensional structural data of a cargo. The element in the i-th row and j-th column of the first relationship matrix represents the association between the cargo represented by the i-th cell and the j-th cell of the first data matrix. If an association exists, the value of the element in the first relationship matrix is 1, otherwise it is 0.

[0050] The relationship between goods means that the goods have the same attributes and are located in the same transport unit;

[0051] The one-dimensional structure data No. 1 includes n data items sorted by time, and the t-th data item represents the cargo information collected at the t-th moment;

[0052] Step 300: Input the first two-dimensional structure data into the intelligent positioning model. The intelligent positioning model includes a first intermediate layer, a second intermediate layer, and a first output layer. The first intermediate layer inputs the first one-dimensional structure data and outputs first intermediate representation data to the second intermediate layer. The second intermediate layer also inputs the first relationship matrix. The second intermediate layer outputs second intermediate representation data to the first output layer. The first output layer outputs a result indicating the ID of the transport unit where the goods are located.

[0053] Step 400: Update cargo information using the ID of the transport unit where the cargo is located output by the intelligent positioning model;

[0054] The specific updating method is to replace the transport unit where the goods are located in the cargo information with the ID of the transport unit where the goods are located output by the intelligent positioning model.

[0055] In one embodiment of the present invention, the calculation formula of the first intermediate layer is as follows:

[0056] h t =tanh(W hh h t-1 +W xh x t +b h )

[0057] where h t represents the t-th first intermediate representation data output by the first intermediate layer, h t-1 Indicates the t-1th first intermediate representation data, x t Represents the tth data item of the one-dimensional structure data, W hh and W xh are the first and second weight parameters, b h is the first bias parameter, and tanh is the hyperbolic tangent function.

[0058] In one embodiment of the present invention, the calculation formula of the second intermediate layer is as follows:

[0059]

[0060] where k v The second intermediate representation data of the vth unit of the data matrix No. 1, M (v) is the set of cells associated with the vth cell of the data matrix No. 1, The nth first intermediate representation data output when the first unit of the first data matrix is input as the structure data into the first intermediate layer, c v is a normalization constant (such as node degree), σ is the sigmoid function, W k Represents the third weight parameter.

[0061] In one embodiment of the present invention, the calculation formula of the first output layer is as follows:

[0062] y v =σ(W y k v +b y )

[0063] where y vRepresents the first output vector, whose cth component value represents the probability value of the ID of the cth transport unit, and the ID of the transport unit with the largest probability value is selected as the ID of the transport unit where the goods represented by the vth unit are located, k v The second intermediate representation data of the vth unit of the data matrix No. 1, W y is the out weight parameter, b y is the out bias parameter, and σ represents the sigmoid function.

[0064] In one embodiment of the present invention, an intelligent positioning system and positioning method for warehousing logistics further include the following steps:

[0065] Step 500 , the information of the transport unit where the cargo is located includes: the transport capacity of the transport unit, the used capacity of the transport unit, the speed of the transport unit, the location of the transport unit, the weather in the area where the transport unit is located, and the remaining fuel of the transport unit;

[0066] The updated cargo information is sorted to obtain second one-dimensional structure data; the second one-dimensional structure data includes n data items sorted by time, and the t-th data item represents the second two-dimensional structure data generated by the cargo information collected at the t-th moment;

[0067] The second two-dimensional structure data includes a second data matrix and a second relationship matrix. A unit of the second data matrix represents the cargo information of a cargo. The element in the i-th row and j-th column of the second relationship matrix represents the association between the cargoes represented by the i-th unit and the j-th unit of the second data matrix. If an association exists, the value of the element in the second relationship matrix is 1, otherwise it is 0.

[0068] Step 600, input the second one-dimensional structure data into the transportation strategy model, the transportation strategy model includes a third intermediate layer, a fourth intermediate layer and a second output layer, wherein the third intermediate layer inputs the second two-dimensional structure data, outputs the third intermediate representation data to the fourth intermediate layer, the fourth intermediate layer outputs the fourth intermediate representation data to the second output layer, and the second output layer outputs a structure representing the transportation strategy of the goods at the next moment, the transportation strategy includes the transportation unit to which each cargo needs to be moved when it arrives at the cargo transfer station next time (if the transportation unit to be moved to is the transportation unit where it is currently located, there is no need to move the cargo).

[0069] In one embodiment of the present invention, the calculation formula of the third intermediate layer is as follows:

[0070]

[0071] where Q i The third intermediate representation data of the i-th unit of the second relationship matrix, W QRepresents the state weight parameter, in i and in j Respectively represent the cargo information of the cargo represented by the i-th unit and the j-th unit of the second data matrix, T i represents the set of vertices directly connected to the i-th vertex, M represents T i The total number of vertices in R i,j =tanh(δ*in i T *in j +1), tanh represents the hyperbolic tangent function, and δ represents an adjustable parameter; the default value of δ is 25.

[0072] In one embodiment of the present invention, the calculation formula of the fourth intermediate layer is as follows:

[0073] u (t) =σ(W u X (t) +W u H (t-1) +b u )

[0074] r (t) =σ(W r X (t) +W r H (t-1) +b r )

[0075] C (t) =tanh(W c X (t) +W c r (t) ⊙H (t-1) +b c )

[0076] H (t) =(1-u (t) )⊙C (t) +u (t) ⊙H (t-1)

[0077]

[0078] Among them, W u 、W r 、W c represents the fourth, fifth, and sixth weight parameters, b u 、b r 、b c represents the fourth, fifth, and sixth bias parameters, ⊙ represents the dot product, u (t) 、r (t) and C (t)Represent the first, second, and third intermediate states respectively, where X (t) represents the t-th input of the fourth intermediate layer, The third intermediate representation data of the i-th unit of the second relationship matrix output when the t-th data item is input into the third intermediate layer, H (t) and H (t-1) Respectively represent the t-th and t-1-th fourth intermediate representation data, n≥t≥1, n represents the number of data items of the second one-dimensional structure data, when t=1, H (t-1) =X (t) , tanh is the hyperbolic tangent function, and σ represents the sigmoid function.

[0079] In one embodiment of the present invention, the calculation formula of the second output layer is as follows:

[0080] G=σ(W G H (n) +b G )

[0081] Where G represents the second output vector, a component value of the second output vector represents the probability value of a transportation strategy, the transportation strategy belongs to the transportation strategy set, and the transportation strategy set contains all transportation strategies that can be executed, H (n) Indicates the nth fourth intermediate representation data, W G is the second output weight parameter, b G is the second output bias parameter, and σ represents the sigmoid function.

[0082] In at least one embodiment of the present invention, a computer storage medium is provided for storing computer-readable instructions, which, when read, can execute the aforementioned intelligent positioning system and positioning method for warehousing logistics.

[0083] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make more forms of equivalent embodiments based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. An intelligent positioning method for warehousing logistics, characterized in that: The following steps are involved: Step 100: collecting cargo information via a wireless communication network, the cargo information including cargo attribute information and information about the transport unit where the cargo is located; Cargo information is stored through the electronic tags on the warehouse logistics pallets carrying the goods, and then transmitted and collected through the wireless communication network; Step 200: Obtain first-order two-dimensional structural data based on historically collected cargo information. The first-order two-dimensional structural data includes a first-order data matrix and a first-order relationship matrix. Each cell of the first-order data matrix represents the first-order one-dimensional structural data of a cargo. The element in the i-th row and j-th column of the first-order relationship matrix represents the association between the cargo represented by the i-th cell and the j-th cell of the first-order data matrix. If an association exists, the value of the element in the first-order relationship matrix is 1, otherwise it is 0. The relationship between goods means that the goods have the same attributes and are located in the same transport unit; The one-dimensional structure data No. 1 includes n data items sorted by time, and the t-th data item represents the cargo information collected at the t-th moment; Step 300: Input the first two-dimensional structure data into the intelligent positioning model. The intelligent positioning model includes a first intermediate layer, a second intermediate layer, and a first output layer. The first intermediate layer inputs the first one-dimensional structure data and outputs first intermediate representation data to the second intermediate layer. The second intermediate layer also inputs the first relationship matrix. The second intermediate layer outputs second intermediate representation data to the first output layer. The first output layer outputs a result indicating the ID of the transport unit where the goods are located. Step 400: Update cargo information using the ID of the transport unit where the cargo is located output by the intelligent positioning model.

2. The intelligent positioning method for warehousing logistics according to claim 1, characterized in that: The updating method is to replace the transport unit where the goods are located in the goods information with the ID of the transport unit where the goods are located output by the intelligent positioning model.

3. The intelligent positioning method for warehousing logistics according to claim 1, characterized in that: The calculation formula for the first intermediate layer is as follows: ； in Represents the t-th first intermediate representation data output by the first intermediate layer, represents the t-1th first intermediate representation data, Represents the tth data item of the one-dimensional structure data. and are the first and second weight parameters, is the first bias parameter, and tanh is the hyperbolic tangent function.

4. The intelligent positioning method for warehousing logistics according to claim 3, characterized in that: The calculation formula for the second intermediate layer is as follows: ； in The second intermediate representation data of the vth unit of the data matrix No. 1, is the set of cells associated with the vth cell of the data matrix No. 1, The nth first intermediate representation data output when the one-dimensional structure data of the vth unit of the data matrix is input into the first intermediate layer, is a normalizing constant, is the sigmoid function, Represents the third weight parameter.

5. The intelligent positioning method for warehousing logistics according to claim 4, characterized in that: The calculation formula of the first output layer is as follows: ； in Represents the first output vector, whose cth component value represents the probability value of the ID of the cth transport unit, and the ID of the transport unit with the largest probability value is selected as the ID of the transport unit where the goods represented by the vth unit are located. The second intermediate representation data of the vth unit of the data matrix No. 1, is the out weight parameter, is the out bias parameter, Represents the sigmoid function.

6. The intelligent positioning method for warehousing logistics according to claim 1, characterized in that: The following steps are also included: Step 500 , the information of the transport unit where the cargo is located includes: the transport capacity of the transport unit, the used capacity of the transport unit, the speed of the transport unit, the location of the transport unit, the weather in the area where the transport unit is located, and the remaining fuel of the transport unit; The updated cargo information is sorted to obtain second one-dimensional structure data; the second one-dimensional structure data includes n data items sorted by time, and the t-th data item represents the second two-dimensional structure data generated by the cargo information collected at the t-th moment; The second two-dimensional structure data includes a second data matrix and a second relationship matrix. A unit of the second data matrix represents the cargo information of a cargo. The element in the i-th row and j-th column of the second relationship matrix represents the association between the cargoes represented by the i-th unit and the j-th unit of the second data matrix. If an association exists, the value of the element in the second relationship matrix is 1, otherwise it is 0. Step 600, input the second one-dimensional structure data into the transportation strategy model, the transportation strategy model includes a third intermediate layer, a fourth intermediate layer and a second output layer, wherein the third intermediate layer inputs the second two-dimensional structure data, outputs the third intermediate representation data to the fourth intermediate layer, the fourth intermediate layer outputs the fourth intermediate representation data to the second output layer, and the second output layer outputs a structure representing the transportation strategy of the goods at the next moment, the transportation strategy includes the transportation unit to which each cargo needs to be moved when it arrives at the cargo transfer station next time.

7. The intelligent positioning method for warehousing logistics according to claim 6, characterized in that: The calculation formula for the third intermediate layer is as follows: ； in The third intermediate representation data representing the i-th unit of the second relationship matrix, represents the state weight parameter, and Respectively represent the cargo information of the cargo represented by the i-th unit and the j-th unit of the second data matrix, represents the set of vertices directly connected to the i-th vertex, express The total number of vertices in , , tanh represents the hyperbolic tangent function, Indicates adjustable parameters; The default value is 25.

8. The intelligent positioning method for warehousing logistics according to claim 7, characterized in that: The calculation formula for the fourth intermediate layer is as follows: ； ； ； ； ； in, 、 、 represents the fourth, fifth, and sixth weight parameters, 、 、 Indicates the fourth, fifth, and sixth bias parameters, represents the dot product, 、 and Represent the first, second, and third intermediate states respectively, where represents the t-th input of the fourth intermediate layer, The third intermediate representation data of the i-th unit of the second relationship matrix output when the t-th data item is input into the third intermediate layer, and Respectively represent the t-th and t-1-th fourth intermediate representation data, n≥t≥1, n represents the number of data items of the second one-dimensional structure data, when t=1 , tanh is the hyperbolic tangent function, Represents the sigmoid function.

9. The intelligent positioning method for warehousing logistics according to claim 8, characterized in that: The calculation formula of the second output layer is as follows: ； Where G represents the second output vector, and a component value of the second output vector represents the probability value of a transportation strategy. The transportation strategy belongs to the transportation strategy set, which contains all transportation strategies that can be executed. Indicates the nth fourth intermediate representation data, is the second output weight parameter, is the second output bias parameter, Represents the sigmoid function.

10. A computer storage medium, characterized in that It is used to store computer-readable instructions, and when the computer-readable instructions are read, it can execute an intelligent positioning method for warehousing logistics as described in any one of claims 1-9.

Images