Commodity logistics sorting management system and method based on artificial intelligence

Abstract

The present invention relates to the technical field of commodity logistics sorting, and in particular to a commodity logistics sorting management system and method based on artificial intelligence. The method comprises: obtaining basic information of commodities, obtaining appearance information of commodities; generating a first commodity sorting prediction characteristic value based on the basic information of commodities and basic information indicators, generating a second commodity sorting prediction characteristic value based on the appearance information of commodities and appearance information indicators, and obtaining a commodity sorting prediction characteristic value based on the first commodity sorting prediction characteristic value and the second commodity sorting prediction characteristic value; obtaining commodity inventory environment information, and determining a commodity sorting target area based on the commodity sorting prediction characteristic value, determining a commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sorting commodities based on the commodity sorting path. The present invention can reduce the error rate of commodity logistics sorting and improve the efficiency of commodity logistics sorting.

Description

Technical Field

[0001] The present invention relates to the technical field of commodity logistics sorting, and in particular to a commodity logistics sorting management system and method based on artificial intelligence. Background Art

[0002] With the rapid development of globalization and e-commerce, the logistics industry is experiencing unprecedented changes and challenges. As a key link in the entire logistics chain, the efficiency and accuracy of logistics sorting directly affect the overall quality of logistics services and customer satisfaction. Traditional logistics sorting methods mainly rely on manual operations, which have problems such as low sorting efficiency, high error rate, and high labor costs. It is difficult to meet the needs of the modern logistics industry for efficient, accurate, and timely services.

[0003] At present, there are many AI-based logistics sorting management systems on the market, such as automated warehouse management systems, intelligent transportation scheduling systems, unmanned delivery technologies, etc. These systems have achieved automation and intelligence in warehouse storage, sorting, transportation and other links by introducing advanced technologies such as robots, machine vision, and intelligent algorithms. However, these systems still have the following problems in practical applications:

[0004] Limited sorting efficiency: Some systems are limited by algorithm accuracy and hardware performance and are unable to quickly and accurately identify and process large quantities of complex and diverse goods.

[0005] Lack of flexibility: The system is often designed for specific scenarios and is difficult to adapt to the needs of logistics centers of different sizes and types.

[0006] Poor scalability: The system architecture is complex, the upgrade and maintenance costs are high, and it is difficult to flexibly adjust according to business changes.

[0007] Therefore, there is an urgent need for a commodity logistics sorting management system and method based on artificial intelligence to solve the above problems. Summary of the invention

[0008] The purpose of the present invention is to provide a commodity logistics sorting management system and method based on artificial intelligence: to solve the technical problems of high error rate and low sorting efficiency in commodity logistics sorting management in existing solutions.

[0009] The purpose of the present invention can be achieved by the following technical solutions:

[0010] On the one hand, a commodity logistics sorting management system based on artificial intelligence, the system includes a commodity basic information acquisition module, a commodity appearance information acquisition module, a commodity sorting prediction feature value calculation module and a commodity sorting path planning module;

[0011] The commodity basic information acquisition module is used to acquire commodity basic information, wherein the commodity basic information includes the volume of commodity packaging, the quality of commodity packaging, the inventory quantity of the commodity and the type of the commodity;

[0012] The product appearance information acquisition module is used to acquire product appearance information, where the product appearance information includes product packaging images;

[0013] The commodity sorting prediction characteristic value calculation module is used to generate a first commodity sorting prediction characteristic value based on commodity basic information and basic information indicators, generate a second commodity sorting prediction characteristic value based on commodity appearance information and appearance information indicators, and obtain a commodity sorting prediction characteristic value based on the first commodity sorting prediction characteristic value and the second commodity sorting prediction characteristic value;

[0014] The commodity sorting path planning module is used to obtain commodity inventory environment information, determine the commodity sorting target area based on the commodity sorting prediction feature value, determine the commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sort the commodities based on the commodity sorting path.

[0015] Furthermore, generating the first commodity sorting prediction feature value based on the commodity basic information and the basic information index specifically includes the following process:

[0016] Based on the basic information indicators, the standard volume and standard mass of the commodity packaging are obtained, and the difference V between the volume of the commodity packaging and the standard volume of the commodity packaging is calculated, and the difference G between the mass of the commodity packaging and the standard mass of the commodity packaging is calculated;

[0017] Based on the basic information indicators, the maximum inventory quantity that the commodity sorting target area can accommodate is obtained, and it is determined whether the inventory quantity of the commodity exceeds the maximum inventory quantity that the commodity sorting target area can accommodate. If so, the sorting safety factor R is 0, otherwise, the sorting safety factor R is 1;

[0018] Based on the basic information indicators, a sorting factor value table corresponding to the commodity type is obtained, and based on the commodity type, a sorting factor value E corresponding to the commodity type is queried, wherein the sorting factor value table corresponding to the commodity type contains a sorting factor value corresponding to each commodity type, and the sorting factor value table corresponding to the commodity type is preset by the system;

[0019] Substitute the difference V, difference G, sorting safety factor R and sorting factor value E into the calculation formula of the first commodity sorting prediction characteristic value to obtain the first commodity sorting prediction characteristic value FLZ. The calculation formula is as follows:

[0020]

[0021] Among them, e is 2.72, γ and α are weights, γ is 0.4, and α is 0.6.

[0022] Furthermore, generating the second commodity sorting prediction feature value based on the commodity appearance information and the appearance information index specifically includes the following process:

[0023] Get the packaging image of the product P = (S, D), where S is the node set representing the product appearance information in the packaging image of the product, and the node set S = {v 1 ,v 2 ...v N}, D is the edge set representing the product appearance information in the product packaging image, edge set D = {e 1 ,e 2 ...e M}, the number of edges is M;

[0024] Substitute the product packaging image P = (S, D) into the embedding matrix Z (1) Perform comparative learning to obtain the representation H = f(X, A) learned by the node, and the node v i The embedding of i , where, through the encoder network f(X,A)∈Y N×M Generate the embedding matrix Z (1) ;

[0025] Retrieve the representation corresponding to the appearance information indicator and compare and analyze it with the node representation H = f(X, A):

[0026] Determine whether the representation of the comparison node has a texture abnormality indicator representation, if not, query the appearance sorting factor value WL corresponding to the texture indicator;

[0027] Determine whether the representation of the comparison node has a shape abnormality indicator representation, if not, query the appearance sorting factor value XZ corresponding to the indicator shape;

[0028] Determine whether the comparison node shows abnormal damage indicators. If not, query the appearance sorting factor value PS corresponding to the damage indicator.

[0029] Based on the appearance sorting factor value WL, the appearance sorting factor value XZ and the appearance sorting factor value PS, the second commodity sorting prediction characteristic value FLS is obtained by substituting the appearance sorting factor value WL, the appearance sorting factor value XZ and the appearance sorting factor value PS into the second commodity sorting prediction characteristic value calculation formula. The calculation formula is as follows:

[0030]

[0031] Among them, k1, k2, and k3 are weight coefficients respectively, and the appearance information index includes the appearance sorting factor value corresponding to the texture index, the appearance sorting factor value corresponding to the index shape, and the appearance sorting factor value corresponding to the damage index.

[0032] Further, obtaining the commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value specifically includes the following process:

[0033] Calculate the sum of the first commodity sorting prediction feature value and the second commodity sorting prediction feature value;

[0034] Obtaining the first commodity sorting target area status information, the second commodity sorting target area information, and the i-th commodity sorting target area status information; wherein the first commodity sorting target area status information includes the first computing power redundancy of the preset sorting task amount, the first computing power failure trigger frequency, and the first sorting transmission distance; the i-th commodity sorting target area status information includes the i-th computing power redundancy of the preset sorting task amount, the i-th computing power failure trigger frequency, and the i-th sorting transmission distance; wherein the computing power redundancy of the preset sorting task amount is the difference between the maximum number of stored commodities in the commodity sorting target area and the number of commodities to be sorted, the computing power failure trigger frequency is the probability that the commodity has not reached the commodity sorting target area, and the sorting transmission distance is the distance of the commodity from the sorting starting point to the commodity sorting target area;

[0035] The sum value, the first computing power redundancy of the preset sorting task volume, the first computing power failure trigger frequency and the first sorting transmission distance are added together to obtain the first sorting prediction characteristic value of the commodity to be selected; until the i-th sorting prediction characteristic value of the commodity to be selected is calculated;

[0036] The largest prediction characteristic value of the commodity to be selected among the first prediction characteristic value of the commodity to be selected to the i-th prediction characteristic value of the commodity to be selected is selected, and the largest prediction characteristic value of the commodity to be selected is used as the commodity sorting prediction characteristic value.

[0037] Furthermore, obtaining commodity inventory environment information, and determining a commodity sorting target area based on the commodity sorting prediction feature value, and determining a commodity sorting path based on the commodity inventory environment information and the commodity sorting target area specifically includes the following processes:

[0038] Obtain commodity inventory environment information, which includes route environment and inventory environment; the route environment is the traffic condition of the preset route for the sorting and handling equipment to travel, and the inventory environment is the space information for storing commodities;

[0039] Determining a commodity sorting target area based on the commodity sorting prediction feature value, wherein each commodity sorting prediction feature value corresponds to a commodity sorting target area;

[0040] The sorting starting point is obtained based on the spatial information of the stored goods, the sorting end point is obtained based on the goods sorting target area, and the goods sorting path is generated based on the sorting starting point, the sorting end point and the route environment.

[0041] Furthermore, generating a commodity sorting path based on the sorting starting point, the sorting end point and the route environment specifically includes the following processes:

[0042] When acquiring the route environment, multiple collection points are preset on the route. First, the conveying equipment whose sorting terminal is more than the preset distance from the collection point is marked as the collection equipment. Within a preset collection time period, the passing speeds of all the collection equipment passing through the collection point are collected, and the arithmetic mean of the collected passing speeds is calculated. The arithmetic mean of the passing speeds is recorded as the passing speed at the collection point, and the passing speed at the collection point is compared with the preset passing speed threshold. If the passing speed at the collection point is less than the preset passing speed threshold, the collection point is marked as an abnormal collection point. If the passing speed at the collection point is greater than or equal to the preset passing speed threshold, the collection point is marked as a normal collection point.

[0043] The number of normal collection points and abnormal collection points on the route is counted, and the proportion of abnormal collection points in the statistical results is analyzed. If the proportion of abnormal collection points is higher than the preset proportion value, a route abnormal signal is generated; if the proportion of abnormal collection points is not higher than the preset proportion value, a route normal signal is generated.

[0044] Furthermore, obtaining the inventory environment includes the following processes:

[0045] S1: obtaining the inventory environment in an initial state by manual preset, and storing the spatial information of multiple locations in the inventory environment respectively;

[0046] S2: When the conveying equipment transports the goods to be sorted to the destination, if the destination is a space in the warehouse for storing goods, the space information of the space for storing goods is updated;

[0047] S3: When the conveying equipment uses the space where the goods are stored as the starting point for transporting the goods, the conveying equipment updates the space information of the space where the goods are stored;

[0048] S4: Use the most recently updated spatial information as the inventory environment.

[0049] Further, the system also includes a warehouse management system;

[0050] The warehouse management system is used to obtain order information of goods.

[0051] On the other hand, a commodity logistics sorting management method based on artificial intelligence includes:

[0052] Obtaining basic information of the product, wherein the basic information of the product includes the volume of the product packaging, the quality of the product packaging, the inventory quantity of the product, and the type of the product;

[0053] Acquire the appearance information of the product, which includes the packaging image of the product;

[0054] Generate a first commodity sorting prediction feature value based on commodity basic information and basic information indicators, generate a second commodity sorting prediction feature value based on commodity appearance information and appearance information indicators, and obtain a commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value;

[0055] The commodity inventory environment information is obtained, and a commodity sorting target area is determined based on the commodity sorting prediction feature value, a commodity sorting path is determined based on the commodity inventory environment information and the commodity sorting target area, and commodities are sorted based on the commodity sorting path.

[0056] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0057] The present invention obtains basic information of commodities and appearance information of commodities; generates a first commodity sorting prediction characteristic value based on the basic information of commodities and basic information indicators, generates a second commodity sorting prediction characteristic value based on the appearance information of commodities and appearance information indicators, and obtains a commodity sorting prediction characteristic value based on the first commodity sorting prediction characteristic value and the second commodity sorting prediction characteristic value; obtains commodity inventory environment information, determines a commodity sorting target area based on the commodity sorting prediction characteristic value, determines a commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sorts commodities based on the commodity sorting path. The present invention can reduce the error rate of commodity logistics sorting and improve sorting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0059] Figure 1 This is a system block diagram of a commodity logistics sorting management system based on artificial intelligence according to an embodiment of the present invention;

[0060] Figure 2 This is a workflow diagram of a commodity logistics sorting management system based on artificial intelligence according to an embodiment of the present invention;

[0061] Figure 3 This is a workflow diagram of a commodity logistics sorting management system based on artificial intelligence according to an embodiment of the present invention;

[0062] Figure 4It is a workflow diagram of a commodity logistics sorting management method based on artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0065] This embodiment provides a commodity logistics sorting management system based on artificial intelligence. Figure 1 is a system block diagram of a commodity logistics sorting management system based on artificial intelligence according to an embodiment of the present invention, such as Figure 1 As shown, the system includes a commodity basic information acquisition module, a commodity appearance information acquisition module, a commodity sorting prediction feature value calculation module and a commodity sorting path planning module;

[0066] The commodity basic information acquisition module is used to acquire commodity basic information, wherein the commodity basic information includes the volume of commodity packaging, the quality of commodity packaging, the inventory quantity of the commodity and the type of the commodity;

[0067] The product appearance information acquisition module is used to acquire product appearance information, where the product appearance information includes product packaging images;

[0068] The commodity sorting prediction characteristic value calculation module is used to generate a first commodity sorting prediction characteristic value based on commodity basic information and basic information indicators, generate a second commodity sorting prediction characteristic value based on commodity appearance information and appearance information indicators, and obtain a commodity sorting prediction characteristic value based on the first commodity sorting prediction characteristic value and the second commodity sorting prediction characteristic value;

[0069] The commodity sorting path planning module is used to obtain commodity inventory environment information, determine the commodity sorting target area based on the commodity sorting prediction feature value, determine the commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sort the commodities based on the commodity sorting path.

[0070] In summary, the present invention obtains basic information of goods and appearance information of goods; generates a first commodity sorting prediction characteristic value based on the basic information of goods and basic information indicators, generates a second commodity sorting prediction characteristic value based on the appearance information of goods and appearance information indicators, and obtains a commodity sorting prediction characteristic value based on the first commodity sorting prediction characteristic value and the second commodity sorting prediction characteristic value; obtains commodity inventory environment information, and determines a commodity sorting target area based on the commodity sorting prediction characteristic value, determines a commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sorts the goods based on the commodity sorting path. The present invention can reduce the error rate of commodity logistics sorting and improve sorting efficiency.

[0071] In some embodiments, Figure 2 is a workflow diagram of a commodity logistics sorting management system based on artificial intelligence in an embodiment of the present invention, such as Figure 2 As shown, generating the first commodity sorting prediction feature value based on the commodity basic information and basic information indicators specifically includes the following steps:

[0072] Step S201: obtaining the standard volume and standard mass of the commodity packaging based on the basic information indicators, and calculating the difference V between the volume of the commodity packaging and the standard volume of the commodity packaging, and calculating the difference G between the mass of the commodity packaging and the standard mass of the commodity packaging;

[0073] Step S202: based on the basic information indicators, the maximum inventory quantity that the commodity sorting target area can accommodate is obtained, and it is determined whether the inventory quantity of the commodity exceeds the maximum inventory quantity that the commodity sorting target area can accommodate. If so, the sorting safety factor R is 0, and if not, the sorting safety factor R is 1;

[0074] Step S203: obtaining a sorting factor value table corresponding to the commodity type based on the basic information index, and querying the sorting factor value E corresponding to the commodity type based on the commodity type;

[0075] The sorting factor value table corresponding to the commodity type contains the sorting factor value corresponding to each commodity type, and the sorting factor value table corresponding to the commodity type is preset by the system;

[0076] Step S204: Substitute the difference V, the difference G, the sorting safety factor R and the sorting factor value E into the first commodity sorting prediction characteristic value calculation formula to obtain the first commodity sorting prediction characteristic value FLZ. The calculation formula is as follows:

[0077]

[0078] Among them, e is 2.72, γ and α are weights, γ is 0.4, and α is 0.6.

[0079] In some embodiments, generating the second commodity sorting prediction feature value based on the commodity appearance information and the appearance information index specifically includes the following process:

[0080] Get the packaging image of the product P = (S, D), where S is the node set representing the product appearance information in the packaging image of the product, and the node set S = {v 1 ,v 2 ...v N}, D is the edge set representing the product appearance information in the product packaging image, edge set D = {e 1 ,e 2 ...e M}, the number of edges is M;

[0081] Substitute the product packaging image P = (S, D) into the embedding matrix Z (1) Perform comparative learning to obtain the representation H = f(X, A) learned by the node, and the node v i The embedding of i , where, through the encoder network f(X,A)∈Y N×M Generate the embedding matrix Z (1) ;

[0082] Retrieve the representation corresponding to the appearance information indicator and compare and analyze it with the node representation H = f(X, A):

[0083] Determine whether the representation of the comparison node has a texture abnormality indicator representation, if not, query the appearance sorting factor value WL corresponding to the texture indicator;

[0084] Determine whether the representation of the comparison node has a shape abnormality indicator representation, if not, query the appearance sorting factor value XZ corresponding to the indicator shape;

[0085] Determine whether the comparison node shows abnormal damage indicators. If not, query the appearance sorting factor value PS corresponding to the damage indicator.

[0086] Based on the appearance sorting factor value WL, the appearance sorting factor value XZ and the appearance sorting factor value PS, the second commodity sorting prediction characteristic value FLS is obtained by substituting the appearance sorting factor value WL, the appearance sorting factor value XZ and the appearance sorting factor value PS into the second commodity sorting prediction characteristic value calculation formula. The calculation formula is as follows:

[0087]

[0088] Among them, k1, k2, and k3 are weight coefficients respectively, and the appearance information index includes the appearance sorting factor value corresponding to the texture index, the appearance sorting factor value corresponding to the index shape, and the appearance sorting factor value corresponding to the damage index.

[0089] In some embodiments, Figure 3 is a workflow diagram of a commodity logistics sorting management system based on artificial intelligence in an embodiment of the present invention, such as Figure 3 As shown, obtaining the commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value specifically includes the following steps:

[0090] Step S301: Calculate the sum of the first commodity sorting prediction feature value and the second commodity sorting prediction feature value;

[0091] Step S302: obtaining the first commodity sorting target area status information, the second commodity sorting target area status information, and so on until the i-th commodity sorting target area status information;

[0092] The first commodity sorting target area status information includes the first computing power redundancy of the preset sorting task volume, the first computing power failure trigger frequency and the first sorting transmission distance; the i-th commodity sorting target area status information includes the i-th computing power redundancy of the preset sorting task volume, the i-th computing power failure trigger frequency and the i-th sorting transmission distance; wherein the computing power redundancy of the preset sorting task volume is the difference between the maximum number of stored commodities in the commodity sorting target area and the number of commodities to be sorted, the computing power failure trigger frequency is the probability that the commodity has not reached the commodity sorting target area, and the sorting transmission distance is the distance of the commodity from the sorting starting point to the commodity sorting target area;

[0093] Step S303: Add the sum value, the first computing power redundancy of the preset sorting task volume, the first computing power failure trigger frequency and the first sorting transmission distance to obtain the first to-be-selected commodity sorting prediction characteristic value; until the i-th to-be-selected commodity sorting prediction characteristic value is calculated;

[0094] Step S304: selecting the largest candidate commodity sorting prediction characteristic value from the first candidate commodity sorting prediction characteristic value to the ith candidate commodity sorting prediction characteristic value, and taking the largest candidate commodity sorting prediction characteristic value as the commodity sorting prediction characteristic value.

[0095] In some embodiments, obtaining commodity inventory environment information, determining a commodity sorting target area based on a commodity sorting prediction feature value, and determining a commodity sorting path based on the commodity inventory environment information and the commodity sorting target area specifically include the following processes:

[0096] Obtain commodity inventory environment information, which includes route environment and inventory environment; the route environment is the traffic condition of the preset route for the sorting and handling equipment to travel, and the inventory environment is the space information for storing commodities;

[0097] Determining a commodity sorting target area based on the commodity sorting prediction feature value, wherein each commodity sorting prediction feature value corresponds to a commodity sorting target area;

[0098] The sorting starting point is obtained based on the spatial information of the stored goods, the sorting end point is obtained based on the goods sorting target area, and the goods sorting path is generated based on the sorting starting point, the sorting end point and the route environment.

[0099] Furthermore, generating a commodity sorting path based on the sorting starting point, the sorting end point and the route environment specifically includes the following processes:

[0100] When acquiring the route environment, multiple collection points are preset on the route. First, the conveying equipment whose sorting terminal is more than the preset distance from the collection point is marked as the collection equipment. Within a preset collection time period, the passing speeds of all the collection equipment passing through the collection point are collected, and the arithmetic mean of the collected passing speeds is calculated. The arithmetic mean of the passing speeds is recorded as the passing speed at the collection point, and the passing speed at the collection point is compared with the preset passing speed threshold. If the passing speed at the collection point is less than the preset passing speed threshold, the collection point is marked as an abnormal collection point. If the passing speed at the collection point is greater than or equal to the preset passing speed threshold, the collection point is marked as a normal collection point.

[0101] The number of normal collection points and abnormal collection points on the route is counted, and the proportion of abnormal collection points in the statistical results is analyzed. If the proportion of abnormal collection points is higher than the preset proportion value, a route abnormal signal is generated; if the proportion of abnormal collection points is not higher than the preset proportion value, a route normal signal is generated.

[0102] Furthermore, obtaining the inventory environment includes the following processes:

[0103] S1: obtaining the inventory environment in an initial state by manual preset, and storing the spatial information of multiple locations in the inventory environment respectively;

[0104] S2: When the conveying equipment transports the goods to be sorted to the destination, if the destination is a space in the warehouse for storing goods, the space information of the space for storing goods is updated;

[0105] S3: When the conveying equipment uses the space where the goods are stored as the starting point for transporting the goods, the conveying equipment updates the space information of the space where the goods are stored;

[0106] S4: Use the most recently updated spatial information as the inventory environment.

[0107] Further, the system also includes a warehouse management system;

[0108] The warehouse management system is used to obtain order information of goods.

[0109] On the other hand, the present invention also provides a commodity logistics sorting management method based on artificial intelligence, which is applicable to the above-mentioned commodity logistics sorting management system based on artificial intelligence. Figure 4 is a workflow diagram of a commodity logistics sorting management method based on artificial intelligence in an embodiment of the present invention, such as Figure 4 As shown, the method comprises the following steps:

[0110] Step S401: Obtaining basic information of the commodity, wherein the basic information of the commodity includes the volume of the commodity packaging, the quality of the commodity packaging, the inventory quantity of the commodity, and the type of the commodity;

[0111] Step S402: Acquire appearance information of the product, where the appearance information of the product includes a packaging image of the product;

[0112] Step S403: generating a first commodity sorting prediction feature value based on commodity basic information and basic information indicators, generating a second commodity sorting prediction feature value based on commodity appearance information and appearance information indicators, and obtaining a commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value;

[0113] Step S404: Acquire commodity inventory environment information, determine a commodity sorting target area based on the commodity sorting prediction feature value, determine a commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sort the commodities based on the commodity sorting path.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0115] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only for some logical functions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A commodity logistics sorting management system based on artificial intelligence, characterized in that: The system includes a commodity basic information acquisition module, a commodity appearance information acquisition module, a commodity sorting prediction feature value calculation module and a commodity sorting path planning module; The commodity basic information acquisition module is used to acquire commodity basic information, wherein the commodity basic information includes the volume of commodity packaging, the quality of commodity packaging, the inventory quantity of the commodity and the type of the commodity; The product appearance information acquisition module is used to acquire product appearance information, where the product appearance information includes product packaging images; The commodity sorting prediction characteristic value calculation module is used to generate a first commodity sorting prediction characteristic value based on commodity basic information and basic information indicators, generate a second commodity sorting prediction characteristic value based on commodity appearance information and appearance information indicators, and obtain a commodity sorting prediction characteristic value based on the first commodity sorting prediction characteristic value and the second commodity sorting prediction characteristic value; The process of obtaining the commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value specifically includes the following steps: Calculate the sum of the first commodity sorting prediction feature value and the second commodity sorting prediction feature value; Obtaining the first commodity sorting target area status information, the second commodity sorting target area status information, and the i-th commodity sorting target area status information; wherein the first commodity sorting target area status information includes the first computing power redundancy of the preset sorting task amount, the first computing power failure triggering frequency, and the first sorting transmission distance; the i-th commodity sorting target area status information includes the i-th computing power redundancy of the preset sorting task amount, the i-th computing power failure triggering frequency, and the i-th sorting transmission distance; wherein the computing power redundancy of the preset sorting task amount is the difference between the maximum number of stored commodities in the commodity sorting target area and the number of commodities to be sorted, the computing power failure triggering frequency is the probability that the commodity has not reached the commodity sorting target area, and the sorting transmission distance is the distance of the commodity from the sorting starting point to the commodity sorting target area; The sum value, the first computing power redundancy of the preset sorting task volume, the first computing power failure trigger frequency and the first sorting transmission distance are added together to obtain the first sorting prediction characteristic value of the commodity to be selected; until the i-th sorting prediction characteristic value of the commodity to be selected is calculated; Select the largest prediction characteristic value of the commodity to be selected from the first prediction characteristic value of the commodity to be selected to the i-th prediction characteristic value of the commodity to be selected, and use the largest prediction characteristic value of the commodity to be selected as the commodity sorting prediction characteristic value; The commodity sorting path planning module is used to obtain commodity inventory environment information, determine the commodity sorting target area based on the commodity sorting prediction feature value, determine the commodity sorting path based on the commodity inventory environment information and the commodity sorting target area, and sort the commodities based on the commodity sorting path.

2. According to the artificial intelligence-based commodity logistics sorting management system of claim 1, it is characterized in that: Generate the first commodity sorting prediction feature value based on the commodity basic information and basic information indicators The process includes: Based on the basic information indicators, the standard volume and standard mass of the commodity packaging are obtained, and the difference V between the volume of the commodity packaging and the standard volume of the commodity packaging is calculated, and the difference G between the mass of the commodity packaging and the standard mass of the commodity packaging is calculated; Based on the basic information indicators, the maximum inventory quantity that the commodity sorting target area can accommodate is obtained, and it is determined whether the inventory quantity of the commodity exceeds the maximum inventory quantity that the commodity sorting target area can accommodate. If so, the sorting safety factor R is 0, otherwise, the sorting safety factor R is 1; Based on the basic information indicators, a sorting factor value table corresponding to the commodity type is obtained, and based on the commodity type, a sorting factor value E corresponding to the commodity type is queried, wherein the sorting factor value table corresponding to the commodity type contains a sorting factor value corresponding to each commodity type, and the sorting factor value table corresponding to the commodity type is preset by the system; Substitute the difference V, difference G, sorting safety factor R and sorting factor value E into the calculation formula of the first commodity sorting prediction characteristic value to obtain the first commodity sorting prediction characteristic value FLZ. The calculation formula is as follows: Among them, e is 2.72, γ and α are weights, γ is 0.4, and α is 0.

6.

3. According to the artificial intelligence-based commodity logistics sorting management system of claim 1, it is characterized in that: Generating the second commodity sorting prediction feature value based on the commodity appearance information and the appearance information index specifically includes the following process: Get the packaging image of the product P = (S, D), where S is the node set representing the product appearance information in the packaging image of the product, and the node set S = {v1, v2...v N }, D is the edge set representing the product appearance information in the product packaging image, edge set D = {e1, e2...e M }, the number of edges is M; Substitute the product packaging image P = (S, D) into the embedding matrix Z (1) Perform comparative learning to obtain the representation H = f(X, A) learned by the node, and the node v i The embedding of i , where, through the encoder network f(X,A)∈Y N×M Generate the embedding matrix Z (1) ; Retrieve the representation corresponding to the appearance information indicator and compare and analyze it with the node representation H = f(X, A): Determine whether the representation of the comparison node has a texture abnormality indicator representation, if not, query the appearance sorting factor value WL corresponding to the texture indicator; Determine whether the representation of the comparison node has a shape abnormality indicator representation, if not, query the appearance sorting factor value XZ corresponding to the indicator shape; Determine whether the comparison node shows abnormal damage indicators. If not, query the appearance sorting factor value PS corresponding to the damage indicator. Based on the appearance sorting factor value WL, the appearance sorting factor value XZ and the appearance sorting factor value PS, the second commodity sorting prediction characteristic value FLS is obtained by substituting the appearance sorting factor value WL, the appearance sorting factor value XZ and the appearance sorting factor value PS into the second commodity sorting prediction characteristic value calculation formula. The calculation formula is as follows: Among them, k1, k2, and k3 are weight coefficients respectively, and the appearance information index includes the appearance sorting factor value corresponding to the texture index, the appearance sorting factor value corresponding to the index shape, and the appearance sorting factor value corresponding to the damage index.

4. According to the artificial intelligence-based commodity logistics sorting management system of claim 1, it is characterized in that: Obtain commodity inventory environment information, and determine the commodity sorting target area based on the commodity sorting prediction feature value, and determine the specific commodity sorting path based on the commodity inventory environment information and the commodity sorting target area. The process includes: Obtain commodity inventory environment information, which includes route environment and inventory environment; the route environment is the traffic condition of the preset route for the sorting and handling equipment to travel, and the inventory environment is the space information for storing commodities; Determining a commodity sorting target area based on the commodity sorting prediction feature value, wherein each commodity sorting prediction feature value corresponds to a commodity sorting target area; The sorting starting point is obtained based on the spatial information of the stored goods, the sorting end point is obtained based on the goods sorting target area, and the goods sorting path is generated based on the sorting starting point, the sorting end point and the route environment.

5. The commodity logistics sorting management system based on artificial intelligence according to claim 4 is characterized in that: Based on the sorting starting point, sorting end point and route environment, the commodity sorting path is generated. The process includes: When acquiring the route environment, multiple collection points are preset on the route. First, the conveying equipment whose sorting terminal is more than the preset distance from the collection point is marked as the collection equipment. Within a preset collection time period, the passing speeds of all the collection equipment passing through the collection point are collected, and the arithmetic mean of the collected passing speeds is calculated. The arithmetic mean of the passing speeds is recorded as the passing speed at the collection point, and the passing speed at the collection point is compared with the preset passing speed threshold. If the passing speed at the collection point is less than the preset passing speed threshold, the collection point is marked as an abnormal collection point. If the passing speed at the collection point is greater than or equal to the preset passing speed threshold, the collection point is marked as a normal collection point. The number of normal collection points and abnormal collection points on the route is counted, and the proportion of abnormal collection points in the statistical results is analyzed. If the proportion of abnormal collection points is higher than the preset proportion value, a route abnormal signal is generated; if the proportion of abnormal collection points is not higher than the preset proportion value, a route normal signal is generated.

6. The commodity logistics sorting management system based on artificial intelligence according to claim 4 is characterized in that: Obtaining the inventory environment includes the following processes: S1: obtaining the inventory environment in an initial state by manual preset, and storing the spatial information of multiple locations in the inventory environment respectively; S2: When the conveying equipment transports the goods to be sorted to the destination, if the destination is a space in the warehouse for storing goods, the space information of the space for storing goods is updated; S3: When the conveying equipment uses the space where the goods are stored as the starting point for transporting the goods, the conveying equipment updates the space information of the space where the goods are stored; S4: Use the most recently updated spatial information as the inventory environment.

7. The commodity logistics sorting management system based on artificial intelligence according to claim 1 is characterized in that: The system also includes a warehouse management system; The warehouse management system is used to obtain order information of goods.

8. A commodity logistics sorting management method based on artificial intelligence, characterized in that: A commodity logistics sorting management system based on artificial intelligence applicable to any one of claims 1 to 7, the method comprising: Obtaining basic information of the product, wherein the basic information of the product includes the volume of the product packaging, the quality of the product packaging, the inventory quantity of the product, and the type of the product; Acquire the appearance information of the product, which includes the packaging image of the product; Generate a first commodity sorting prediction feature value based on commodity basic information and basic information indicators, generate a second commodity sorting prediction feature value based on commodity appearance information and appearance information indicators, and obtain a commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value; The process of obtaining the commodity sorting prediction feature value based on the first commodity sorting prediction feature value and the second commodity sorting prediction feature value specifically includes the following steps: Calculate the sum of the first commodity sorting prediction feature value and the second commodity sorting prediction feature value; Obtaining the first commodity sorting target area status information, the second commodity sorting target area status information, and the i-th commodity sorting target area status information; wherein the first commodity sorting target area status information includes the first computing power redundancy of the preset sorting task amount, the first computing power failure triggering frequency, and the first sorting transmission distance; the i-th commodity sorting target area status information includes the i-th computing power redundancy of the preset sorting task amount, the i-th computing power failure triggering frequency, and the i-th sorting transmission distance; wherein the computing power redundancy of the preset sorting task amount is the difference between the maximum number of stored commodities in the commodity sorting target area and the number of commodities to be sorted, the computing power failure triggering frequency is the probability that the commodity has not reached the commodity sorting target area, and the sorting transmission distance is the distance of the commodity from the sorting starting point to the commodity sorting target area; The sum value, the first computing power redundancy of the preset sorting task volume, the first computing power failure trigger frequency and the first sorting transmission distance are added together to obtain the first sorting prediction characteristic value of the commodity to be selected; until the i-th sorting prediction characteristic value of the commodity to be selected is calculated; Select the largest prediction characteristic value of the commodity to be selected from the first prediction characteristic value of the commodity to be selected to the i-th prediction characteristic value of the commodity to be selected, and use the largest prediction characteristic value of the commodity to be selected as the commodity sorting prediction characteristic value; The commodity inventory environment information is obtained, and a commodity sorting target area is determined based on the commodity sorting prediction feature value, a commodity sorting path is determined based on the commodity inventory environment information and the commodity sorting target area, and commodities are sorted based on the commodity sorting path.

Images