A verification warehousing method, system, device and medium based on commodity information

Abstract

The present invention relates to a verification and warehousing method, system, device and medium based on commodity information. The method includes the following steps: collecting multi-dimensional data of the commodities already warehoused in the warehouse and extracting multi-dimensional feature vectors of the commodity multi-dimensional data; constructing a feature spectrogram for each dimension based on the multi-dimensional feature vectors of all commodities, and obtaining a fused feature vector of the commodity after fusing the multi-dimensional feature vector of each commodity with the feature spectrogram of each dimension; constructing a commodity standard feature library based on the fused feature vectors of each commodity; after collecting the multi-dimensional data of the commodity to be warehoused and extracting the fused feature vector of the commodity to be warehoused through the above steps, inputting it into the constructed feature enhancement model for feature enhancement to obtain the enhanced fused feature of the commodity to be warehoused; calculating the wrong warehousing probability of the current commodity to be warehoused based on the enhanced fused feature of the commodity to be warehoused and the commodity standard feature library, and rejecting the warehousing when the wrong warehousing probability of the commodity to be warehoused exceeds a preset threshold.

Description

Technical Field

[0001] The present invention relates to a method, system, device and medium for verifying and warehousing based on commodity information, belonging to the technical field of warehousing management. Background Art

[0002] With the continuous expansion of the scale of B2C and C2C e-commerce, the warehousing center needs to complete the warehousing verification of a large number of commodities within an extremely short cycle. Once "similar but not the same commodity" is wrongly warehoused, subsequent picking, shipping and after-sales links will all incur chain losses, manifested as:

[0003] The costs of consumer returns and exchanges, merchant reverse logistics and customer service increase significantly; the commodity SKUs, batches or purchase order numbers in the system are wrongly bound, resulting in distorted subsequent demand forecasting and replenishment decisions; in case of a quality accident, the true supply batch cannot be accurately traced, bringing regulatory and compliance risks.

[0004] Most warehouses use order barcodes or product QR codes for matching verification. This approach relies on single-character information and cannot effectively distinguish commodities with similar packaging or coding errors; when the supply chain simultaneously circulates parallel coding systems generated by multiple suppliers, the problems of misreading and duplicate codes are particularly prominent. Summary of the Invention

[0005] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a method, system, device and medium for verifying and warehousing based on commodity information.

[0006] The technical solution of the present invention is as follows:

[0007] On the one hand, the present invention provides a method for verifying and warehousing based on commodity information, including the following steps:

[0008] Collect multi-dimensional data of the commodities already warehoused in the warehouse, and extract the multi-dimensional feature vectors of the commodity multi-dimensional data;

[0009] Based on the multi-dimensional feature vectors of all commodities, construct a feature spectrum diagram for each dimension, and after fusing the multi-dimensional feature vector of each commodity with the feature spectrum diagram of each dimension, obtain the fused feature vector of the commodity;

[0010] Construct a commodity standard feature library based on the fused feature vector of each commodity;

[0011] After collecting the multi-dimensional data of the commodity to be warehoused and extracting the fused feature vector of the commodity to be warehoused through the above steps, input it into the constructed feature enhancement model for feature enhancement to obtain the enhanced fused feature of the commodity to be warehoused;

[0012] Calculate the incorrect warehousing probability of the current incoming goods based on the enhanced fusion features of the goods to be warehoused and the goods standard feature library. When the incorrect warehousing probability of the incoming goods exceeds the preset threshold, it is determined that the current incoming goods do not belong to this warehouse and the warehousing is rejected.

[0013] Preferably, the multi-dimensional data of the goods includes image data, information data, and historical warehousing time data;

[0014] The information data includes the purchase order number of the goods, SKU, and the batch number of the goods;

[0015] Extract the features of the image data through the convolutional neural network with the EfficientNet network structure to obtain the image feature vector of the goods;

[0016] Extract the features of the information data through the Transformer network to obtain the information feature vector of the goods;

[0017] Extract the warehousing cycle features corresponding to the historical warehousing time data based on the long short-term memory network to obtain the warehousing cycle feature vector of the goods;

[0018] Construct the multi-dimensional feature vector of the goods based on the image feature vector, information feature vector, and warehousing cycle feature vector of the goods.

[0019] Preferably, the specific steps for constructing the feature spectrogram of each dimension based on the multi-dimensional feature vectors of all goods are as follows:

[0020] For the feature vectors of each dimension, use the feature vectors of each good in this dimension as nodes, connect the two nodes with an edge, and set the correlation between the two nodes in the current dimension feature space as the edge weight, and finally obtain the feature spectrogram of the current dimension.

[0021] Preferably, construct the adjacency matrix for the feature spectrogram of each dimension, as shown in the following formula:

[0022] ;

[0023] Where: represents the adjacency matrix of the th dimension feature spectrogram; represents the th node and the th node in the adjacency matrix of the th dimension feature spectrogram; represents the feature vector of the th good in the th dimension; represents the feature vector of the th good in the th dimension; Indicates the variance of the eigenvector of the th dimension;

[0024] Construct the Laplacian matrix of each dimension feature spectrogram based on the adjacency matrix of each dimension feature spectrogram.

[0025] Preferably, construct a dynamic spectrogram convolution fusion network to fuse the Laplacian matrix of each dimension feature spectrogram with the multi-dimensional feature vector of each commodity, as shown in the following formula:

[0026] ;

[0027] Where: Indicates the fused feature vector of the current commodity; Indicates the activation function; Indicates the dimension set; Indicates the th dimension's trainable weight matrix; Indicates the th dimension feature spectrogram's Laplacian matrix; Indicates the th dimension's spectrogram dynamic filter; Indicates the transpose operation; Indicates the current commodity's eigenvector in the th dimension.

[0028] Preferably, the construction steps of the enhanced fusion feature of the commodity to be warehoused are as follows:

[0029] Collect the weight, volume, and density of the commodity to be warehoused, and construct it into a physical feature vector of the commodity to be warehoused;

[0030] Embed the physical feature vector of the commodity to be warehoused into its fusion feature vector to obtain a preliminary enhanced feature vector;

[0031] Construct a feature enhancement model based on the attention mechanism, and perform secondary enhancement on the preliminary enhanced feature vector through the feature enhancement model to obtain the enhanced fusion feature of the commodity to be warehoused, as shown in the following formula:

[0032] ;

[0033] ;

[0034] Where: Indicates the enhanced fusion feature of the commodity to be warehoused; Indicates the query vector of the preliminary enhanced feature vector; Indicates the key vector of the preliminary enhanced feature vector; Indicates the value vector of the preliminary enhanced feature vector; Represents the dimension of the preliminary enhanced feature vector; Represents the physical interaction matrix; Represents the weight coefficient; Represents the interaction weight matrix of the preliminary enhanced feature vector; Represents the bias term of the physical interaction matrix; Represents the interaction weight matrix of the physical feature vector of the goods to be warehoused; Represents the query vector of the physical feature vector of the goods to be warehoused; Represents the key vector of the physical feature vector of the goods to be warehoused; Represents the Hadamard product.

[0035] Preferably, the calculation formula for the wrong warehousing probability of the goods to be warehoused is:

[0036] ;

[0037] Where: Represents the wrong warehousing probability of the goods to be warehoused; Represents the number of samples in the commodity standard feature library; Represents the th sample in the commodity standard feature library; Represents the similarity normalization coefficient of the th sample in the commodity standard feature library; Represents the decay width of the th sample in the commodity standard feature library; Represents the global multiplier; Represents the balance coefficient of the

[0038] On the other hand, the present invention also provides a verification warehousing system based on commodity information, including a data acquisition module, a feature fusion module, a standard feature library construction module, a feature enhancement module, and a wrong warehousing probability calculation module;

[0039] The data acquisition module is used to collect multi-dimensional data of the goods already warehoused in the warehouse and extract the multi-dimensional feature vectors of the multi-dimensional data of the goods;

[0040] The feature fusion module is used to construct a feature spectrogram for each dimension based on the multi-dimensional feature vectors of all goods, and fuse the multi-dimensional feature vectors of each good with the feature spectrogram of each dimension to obtain the fused feature vector of the good;

[0041] The standard feature library construction module is used to construct a commodity standard feature library based on the fused feature vectors of each good;

[0042] The feature enhancement module is used to collect multi-dimensional data of the goods to be warehoused, extract the fused feature vector of the goods to be warehoused through the feature fusion module, and then input it into the constructed feature enhancement model for feature enhancement to obtain the enhanced fused feature of the goods to be warehoused.

[0043] The mis-warehousing probability calculation module is used to calculate the mis-warehousing probability of the current goods to be warehoused based on the enhanced fused feature of the goods to be warehoused and the standard feature library of goods. When the mis-warehousing probability of the goods to be warehoused exceeds the preset threshold, it is determined that the current goods to be warehoused do not belong to this warehouse and the warehousing is rejected.

[0044] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in the present invention is implemented.

[0045] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the present invention is implemented.

[0046] The present invention has the following beneficial effects:

[0047] 1. The present invention significantly improves the discrimination accuracy through multi-modal fusion and physical quantity enhancement, which is particularly effective for the scenario of "goods with extremely similar appearances but different specifications".

[0048] 2. The present invention extracts multi-dimensional features from data such as commodity images and texts, generates a global spectrogram for each feature dimension, and fuses the features of a single commodity with the spectrograms of each dimension to obtain a unified high-dimensional fused vector, eliminating the information fragmentation between modalities, significantly enhancing the recognition accuracy of fine-grained differences (such as packaging material texture or batch code micro-differences). Since the fused representation captures the global feature distribution, when a single modality is occluded, reflected, or missing, the system can still maintain a stable determination based on other dimensions.

[0049] 3. After injecting measured physical features such as weight, volume, and density into the vector, goods with extremely similar appearances but different specifications can be quickly distinguished. In visual recognition difficult scenarios such as low light or reflection, the physical signals provide a second "discrimination path" to ensure that the overall detection rate is not affected by environmental fluctuations.

[0050] 4. The present invention constructs a standard feature library of standard goods. Each time a new SKU is added or removed from the inventory, only the corresponding vector needs to be written or removed from the standard goods standard library to complete the update, without the need for overall model retraining, ensuring long-term maintainability. Description of the Drawings

[0051] Figure 1 It is a flowchart of the method of the present invention. Detailed Embodiments

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] It should be understood that the step numbers used herein are only for convenience of description and do not limit the order of execution of the steps.

[0054] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0055] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0056] The term " / and / " refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0057] Embodiment 1:

[0058] A verification and warehousing method based on commodity information, comprising the following steps:

[0059] Collect multi-dimensional data of the goods already warehoused in the warehouse, and extract the multi-dimensional feature vectors of the goods' multi-dimensional data;

[0060] Based on the multi-dimensional feature vectors of all goods, construct a feature spectrum diagram for each dimension, and after fusing the multi-dimensional feature vectors of each good with the feature spectrum diagram of each dimension, obtain the fused feature vector of the good;

[0061] Construct a commodity standard feature library based on the fused feature vectors of each commodity;

[0062] After collecting the multi-dimensional data of the goods to be warehoused and extracting the fused feature vectors of the goods to be warehoused through the above steps, input them into the constructed feature enhancement model for feature enhancement to obtain the enhanced fused features of the goods to be warehoused;

[0063] Calculate the mis-warehousing probability of the current incoming commodity based on the enhanced fusion features of the incoming commodity and the commodity standard feature library. When the mis-warehousing probability of the incoming commodity exceeds the preset threshold, it is determined that the current incoming commodity does not belong to this warehouse and the warehousing is rejected.

[0064] As a preferred implementation manner of this embodiment, the multi-dimensional data of the commodity includes image data, information data, and historical warehousing time data;

[0065] The information data includes the commodity purchase order number, SKU, and commodity batch;

[0066] Extract the features of the image data through the convolutional neural network of the EfficientNet network structure to obtain the image feature vector of the commodity;

[0067] Extract the features of the information data through the Transformer network to obtain the information feature vector of the commodity;

[0068] Extract the warehousing cycle features corresponding to the historical warehousing time data based on the long short-term memory network to obtain the warehousing cycle feature vector of the commodity;

[0069] Construct the multi-dimensional feature vector of the commodity based on the image feature vector, information feature vector, and warehousing cycle feature vector of the commodity.

[0070] As a preferred implementation manner of this embodiment, the specific steps for constructing the feature spectrogram of each dimension based on the multi-dimensional feature vectors of all commodities are as follows:

[0071] For the feature vectors of each dimension, use the feature vectors of each commodity in this dimension as nodes, connect the two nodes with an edge, and set the correlation between the two nodes in the current dimension feature space as the edge weight, and finally obtain the feature spectrogram of the current dimension.

[0072] As a preferred implementation manner of this embodiment, construct the adjacency matrix for the feature spectrogram of each dimension, as shown in the following formula:

[0073] ;

[0074] Where: Represents the adjacency matrix of the th dimension feature spectrogram; Represents the th node and the th node in the adjacency matrix of the th dimension feature spectrogram are adjacent; Represents the feature vector of the th commodity in the th dimension; Represents the th commodity in the The eigenvector of the -th dimension; The variance of the eigenvector of the

[0075] Construct the Laplacian matrix of each-dimensional feature spectrogram based on the adjacency matrix of each-dimensional feature spectrogram, as shown in the following formula:

[0076] ;

[0077] Where: Represents the degree matrix of the adjacency matrix, and its diagonal elements are the sum of each row of the adjacency matrix.

[0078] As a preferred implementation manner of this embodiment, construct a dynamic spectrogram convolution fusion network to fuse the Laplacian matrix of each-dimensional feature spectrogram with the multi-dimensional feature vector of each commodity, as shown in the following formula:

[0079] ;

[0080] Where: Represents the fused feature vector of the current commodity; Represents the activation function; Represents the dimension set; Represents the -th dimension's trainable weight matrix; Represents the -th dimension feature spectrogram's Laplacian matrix; Represents the -th dimension's spectrogram dynamic filter; Represents the transpose operation; Represents the eigenvector of the current commodity in the -th dimension;

[0081] The construction steps of the spectrogram dynamic filter are as follows:

[0082] Extract the statistical vector corresponding to the Laplacian matrix of each-dimensional feature spectrogram, as shown in the following formula:

[0083] ;

[0084] Where: Represents the statistical vector of the Laplacian matrix of the current-dimensional feature spectrogram; Represents the selected sample set of the Laplacian matrix. In this embodiment, the first 60 samples of the Laplacian matrix are selected as statistical data; Represents the average value of the selected samples; Represents the variance of the selected samples; Represents the total number of nodes; Represents the Degree of a node; Denote the eigenvector corresponding to the

[0085] Send into an extremely lightweight MLP to generate the gating parameters of the dynamic filter for the current dimensional spectrogram, as shown in the following formula:

[0086] ;

[0087] Where: Denote the low-pass bandwidth parameter of the dynamic filter for the current dimensional spectrogram; Denote the high-pass gain parameter of the dynamic filter for the current dimensional spectrogram; Denote the weight matrix of the extremely lightweight MLP, which is used to map the statistical vector in the four-dimensional space to the two-dimensional gating space; Denote the bias term of the extremely lightweight MLP; Denote activation function;

[0088] Construct the filter kernel based on the gating parameters of the dynamic filter for the current dimensional spectrogram, as shown in the following formula:

[0089] ;

[0090] Where: Denote the sample set of the Laplacian matrix; Denote for filter kernel;

[0091] In actual inference, no explicit multiplication is done, but order Chebyshev polynomial is approximated as , then we can get:

[0092] ;

[0093] ;

[0094] Where: Denote for filter kernel; Denote the approximation order of the order Chebyshev polynomial, and also denote the convolution order. The larger it is, the farther neighbors can be captured, but the calculation and overfitting risk also increase; Denote the th kernel coefficient of the Chebyshev polynomial, which changes dynamically with Denote order Chebyshev recursive polynomial; Indicates the normalized , , where Indicates The maximum sample value in Indicates the identity matrix, making The frequency domain of is scaled to ; Preset Best sampling points, sampling in , then Indicates The Sample value corresponding to the best sampling point.

[0095] As a preferred implementation of this embodiment, the steps for constructing the enhanced fusion feature of the goods to be warehoused are as follows:

[0096] Collect the weight, volume and density of the goods to be warehoused, and construct them into a physical feature vector of the goods to be warehoused;

[0097] Embed the physical feature vector of the goods to be warehoused into its fusion feature vector to obtain a preliminary enhanced feature vector;

[0098] Construct a feature enhancement model based on the attention mechanism, and perform secondary enhancement on the preliminary enhanced feature vector through the feature enhancement model to obtain the enhanced fusion feature of the goods to be warehoused, as shown in the following formula:

[0099] ;

[0100] ;

[0101] Among them: Indicates the enhanced fusion feature of the goods to be warehoused; Indicates the query vector of the preliminary enhanced feature vector; Indicates the key vector of the preliminary enhanced feature vector; Indicates the value vector of the preliminary enhanced feature vector; Indicates the dimension of the preliminary enhanced feature vector; Indicates the physical interaction matrix; Indicates the weight coefficient; Indicates the interaction weight matrix of the preliminary enhanced feature vector; Indicates the bias term of the physical interaction matrix; Indicates the interaction weight matrix of the physical feature vector of the goods to be warehoused; Indicates the query vector of the physical feature vector of the goods to be warehoused; Indicates the key vector of the physical feature vector of the goods to be warehoused; Indicates the Hadamard product.

[0102] As a preferred embodiment of this embodiment, the calculation formula for the incorrect storage probability of the goods to be warehoused is as follows:

[0103] ;

[0104] Where: represents the incorrect storage probability of the goods to be warehoused; represents the number of samples in the commodity standard feature library; represents the th sample in the commodity standard feature library; represents the similarity normalization coefficient of the th sample in the commodity standard feature library; represents the attenuation width of the th sample in the commodity standard feature library. The smaller the attenuation width, the sharper the attenuation for a slightly larger sample distance. The larger the attenuation width, the greater the influence on a relatively distant sample is still retained; represents the global multiplier, which is used to smooth and overall coordinate all sample distances to prevent extreme values caused by a single nearest neighbor, and is set based on experimental data; represents the balance coefficient of the th sample in the commodity standard feature library, which balances the contributions of each sample distance and is set based on the training iteration of the machine learning model;

[0105] The larger the value of the similarity normalization coefficient, the greater the influence of the sample on the incorrect storage probability. Specifically, it is shown in the following formula:

[0106] ;

[0107] Where: represents the Euclidean distance between and represents the feature distance variance, , represents the feature average distance, ; represents the Euclidean distance between and

[0108] Optionally, when the incorrect storage probability of the goods to be warehoused exceeds the preset threshold, an incorrect judgment recognition algorithm is constructed to determine whether the incorrect storage probability of the current goods to be warehoused is misjudged. The specific steps are as follows:

[0109] Calculate the comprehensive confidence score of the incorrect storage probability of the current goods to be warehoused based on the incorrect judgment recognition algorithm. Specifically, it is shown in the following formula:

[0110] ;

[0111] Where: Represents the comprehensive confidence score of the wrong storage probability of the currently to-be-stored goods; Represents the logistics track consistency index; Represents the learnable weight corresponding to the logistics track consistency sub-index; Represents the credibility loss, and the optimal value is obtained through machine learning model training. , Represents the logit function, Represents the learning rate;

[0112] Set the comprehensive confidence score threshold. When the comprehensive confidence score is less than the comprehensive confidence score threshold, it is judged that the wrong storage probability of the currently to-be-stored goods is misjudged, and storage is allowed, and the corresponding enhanced fusion features are input into the commodity standard feature library.

[0113] In this embodiment, the calculation steps of the logistics track consistency index are as follows:

[0114] Collect the logistics track of the currently to-be-stored goods and query the logistics track corresponding to the goods closest to the to-be-stored goods in the commodity feature standard library;

[0115] The logistics track is a string of longitude and latitude coordinates with timestamps sorted in chronological order. Then the logistics track of the currently to-be-stored goods is expressed as: , where represents the longitude of the th coordinate, represents the latitude of the th coordinate, represents the timestamp of the th coordinate; represents the total number of longitude and latitude coordinates of the logistics track of the to-be-stored goods;

[0116] The logistics track corresponding to the goods closest to the query in the commodity feature standard library is expressed as , where represents the longitude of the th coordinate, represents the latitude of the th coordinate, represents the timestamp of the th coordinate; represents the total number of longitude and latitude coordinates of the logistics track of the goods closest to the query in the commodity feature standard library;

[0117] Based on the logistics track, calculate the spatial deviation distance and time synchronization deviation between the to-be-stored goods and the corresponding goods in the commodity feature standard library, as shown in the following formula:

[0118] ;

[0119] ;

[0120] Wherein: represents the spatial deviation distance; represents finding in the coordinate point closest to the coordinate point to obtain the closest error of the distance ; the nearest error; represents for each in selecting the one with the largest nearest error of its distance ; is symmetrically opposite to to avoid being ignored due to extra loops; represents the time synchronization deviation; represents the differentiable dynamic time warping distance; represents the smoothing coefficient, a larger value makes it smoother and more robust but reduces the resolution, →0 reverts to the classical dynamic time warping distance; represents the scale factor, ;

[0121] Calculate the logistics trajectory consistency index based on the spatial deviation distance and the time synchronization deviation, as shown in the following formula:

[0122] ;

[0123] Wherein: represents the spatial deviation distance weight; represents the time synchronization deviation weight; represents the sensitivity index, which is fine-tuned according to the season.

[0124] Example Two:

[0125] A verification warehousing system based on commodity information, including a data acquisition module, a feature fusion module, a standard feature library construction module, a feature enhancement module, and an incorrect warehousing probability calculation module;

[0126] The data acquisition module is used to collect multi-dimensional data of the goods already warehoused in the warehouse and extract the multi-dimensional feature vectors of the multi-dimensional data of the goods;

[0127] The feature fusion module is used to construct a feature spectrogram for each dimension based on the multi-dimensional feature vectors of all goods, and fuse the multi-dimensional feature vectors of each good with the feature spectrogram of each dimension to obtain the fused feature vector of the good;

[0128] ​The standard feature library construction module is used to construct a commodity standard feature library based on the fusion feature vectors of each commodity;

[0129] The feature enhancement module is used to collect multi-dimensional data of the commodity to be warehoused, extract the fusion feature vector of the commodity to be warehoused through the feature fusion module, and then input it into the constructed feature enhancement model for feature enhancement to obtain the enhanced fusion feature of the commodity to be warehoused;

[0130] The mis-warehousing probability calculation module is used to calculate the mis-warehousing probability of the current commodity to be warehoused based on the enhanced fusion feature of the commodity to be warehoused and the commodity standard feature library. When the mis-warehousing probability of the commodity to be warehoused exceeds the preset threshold, it is determined that the current commodity to be warehoused does not belong to this warehouse and the warehousing is rejected.

[0131] This system is used to implement the method in the first embodiment, which will not be elaborated here.

[0132] Embodiment 3:

[0133] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method described in any embodiment of the present invention.

[0134] Embodiment 4:

[0135] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method described in any embodiment of the present invention.

[0136] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent the situation where A exists alone, A and B exist simultaneously, or B exists alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0137] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0138] 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 foregoing method embodiments and will not be elaborated herein.

[0139] In several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs that can store program codes.

[0140] The above are only the embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A verification and warehousing method based on commodity information, characterized in that, It includes the following steps: Collect multi-dimensional data of the goods already stored in the warehouse, and extract the multi-dimensional feature vectors of the multi-dimensional data of the goods; Construct a feature spectrogram for each dimension based on the multi-dimensional feature vectors of all goods, and fuse the multi-dimensional feature vectors of each good with the feature spectrogram of each dimension to obtain the fused feature vector of the good; Construct a standard feature library of goods based on the fused feature vectors of each good; After collecting the multi-dimensional data of the goods to be stored in the warehouse and extracting the fused feature vector of the goods to be stored in the warehouse through the above steps, input it into the constructed feature enhancement model for feature enhancement to obtain the enhanced fused feature of the goods to be stored in the warehouse. The construction steps of the enhanced fused feature of the goods to be stored in the warehouse are as follows: Collect the weight, volume and density of the goods to be stored in the warehouse, and construct a physical feature vector of the goods to be stored in the warehouse; Embed the physical feature vector of the goods to be stored in the warehouse into its fused feature vector to obtain a preliminary enhanced feature vector; Construct a feature enhancement model based on the attention mechanism, and perform secondary enhancement on the preliminary enhanced feature vector through the feature enhancement model to obtain the enhanced fused feature of the goods to be stored in the warehouse, as shown in the following formula: ； ； Wherein: Represents the enhanced fusion feature of the goods to be warehoused; Represents the query vector of the preliminary enhanced feature vector; Represents the key vector of the preliminary enhanced feature vector; Represents the value vector of the preliminary enhanced feature vector; Represents the dimension of the preliminary enhanced feature vector; Represents the physical interaction matrix; Represents the weight coefficient; Represents the interaction weight matrix of the preliminary enhanced feature vector; Represents the bias term of the physical interaction matrix; Represents the interaction weight matrix of the physical feature vector of the goods to be warehoused; Represents the query vector of the physical feature vector of the goods to be warehoused; Represents the key vector of the physical feature vector of the goods to be warehoused; Represents the Hadamard product; Calculate the wrong storage probability of the current goods to be stored in the warehouse based on the enhanced fused feature of the goods to be stored in the warehouse and the standard feature library of goods. When the wrong storage probability of the goods to be stored in the warehouse exceeds the preset threshold, it is determined that the current goods to be stored in the warehouse do not belong to this warehouse and the storage is rejected.

2. The verification and warehousing method based on commodity information according to claim 1, wherein The multi-dimensional data of the goods includes image data, information data and historical storage time data; The information data includes the purchase order number of the goods, SKU and the batch number of the goods; Extract the features of the image data through the convolutional neural network of the EfficientNet network structure to obtain the image feature vector of the goods; Extract the features of the information data through the Transformer network to obtain the information feature vector of the goods; Extract the storage cycle features corresponding to the historical storage time data based on the long short-term memory network to obtain the storage cycle feature vector of the goods; Construct the multi-dimensional feature vector of the goods based on the image feature vector, information feature vector and storage cycle feature vector of the goods.

3. The verification and warehousing method based on commodity information according to claim 1, characterized in that, The specific steps for constructing the feature spectrogram of each dimension based on the multi-dimensional feature vectors of all goods are as follows: For the feature vectors of each dimension, use the feature vectors of each good in this dimension as nodes, connect the two nodes with an edge, and set the correlation between the two nodes in the current dimension feature space as the edge weight, and finally obtain the feature spectrogram of the current dimension.

4. The verification and warehousing method based on commodity information according to claim 3, wherein, Construct an adjacency matrix for the feature spectrogram of each dimension, as shown in the following formula: ； Wherein: represents the adjacency matrix of the th dimensional feature spectrogram; represents the th node and the th node in the adjacency matrix of the th dimensional feature spectrogram; represents the eigenvector of the th product in the th dimension; represents the eigenvector of the th product in the th dimension; represents the variance of the eigenvector of the th dimension; Construct the Laplacian matrix of the feature spectrogram of each dimension based on the adjacency matrix of the feature spectrogram of each dimension.

5. The verification and warehousing method based on commodity information according to claim 4, characterized in that, Construct a dynamic spectral graph convolution fusion network to fuse the Laplacian matrix of the feature spectrogram of each dimension with the multi-dimensional feature vectors of each good, as shown in the following formula: ； Wherein: represents the fusion feature vector of the current commodity; represents the activation function; represents the dimension set; represents the trainable weight matrix of the th dimension; represents the Laplacian matrix of the feature spectrogram of the th dimension; represents the spectral dynamic filter of the th dimension; represents the transpose operation; represents the feature vector of the current commodity in the th dimension.

6. The verification and warehousing method based on commodity information according to claim 5, wherein The calculation formula for the wrong storage probability of the goods to be stored in the warehouse is: ； Wherein: represents the incorrect warehousing probability of the goods to be warehoused; represents the number of samples in the commodity standard feature library; represents the th sample in the commodity standard feature library; represents the similarity normalization coefficient of the th sample in the commodity standard feature library; represents the th sample attenuation width in the commodity standard feature library; represents the global multiplier; represents the th sample balance coefficient in the commodity standard feature library.

7. A verification warehousing system based on commodity information, characterized in that, For the method described in any one of claims 1 to 6, it includes a data acquisition module, a feature fusion module, a standard feature library construction module, a feature enhancement module and a wrong storage probability calculation module; The data acquisition module is used to collect multi-dimensional data of the goods already stored in the warehouse and extract the multi-dimensional feature vectors of the multi-dimensional data of the goods; The feature fusion module is used to construct a feature spectrogram for each dimension based on the multi-dimensional feature vectors of all goods, and fuse the multi-dimensional feature vectors of each good with the feature spectrogram of each dimension to obtain the fused feature vector of the good; The standard feature library construction module is used to construct a goods standard feature library based on the fused feature vectors of each good; The feature enhancement module is used to collect the multi-dimensional data of the goods to be stored in the warehouse, extract the fused feature vector of the goods to be stored in the warehouse through the feature fusion module, and then input it into the constructed feature enhancement model for feature enhancement to obtain the enhanced fused feature of the goods to be stored in the warehouse; The incorrect storage probability calculation module is used to calculate the incorrect storage probability of the current goods to be stored in the warehouse based on the enhanced fused feature of the goods to be stored in the warehouse and the goods standard feature library. When the incorrect storage probability of the goods to be stored in the warehouse exceeds the preset threshold, it is determined that the current goods to be stored in the warehouse do not belong to this warehouse and the storage is rejected.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method according to any one of claims 1 to 6.

Images