Product model attribute recognition method and system, storage medium and electronic device

Abstract

The application provides a product model attribute identification method and system, a storage medium and an electronic device. The method comprises the following steps: receiving product information input by a user; the product information comprises a plurality of product attribute categories; the product attribute categories comprise a product name attribute, a product model attribute and a product quantity attribute; each product attribute category corresponds to a plurality of product attribute data; the possibility that each product attribute data in each product attribute category is product model attribute data is obtained; and based on the possibility that all the product attribute data is product model attribute data, an identification result of the product model attribute is obtained from the plurality of product attribute categories. The application can automatically and accurately identify the product model attribute in the plurality of product attribute categories in the product information under different product model assignment rules, and further obtain corresponding product model attribute data, thereby reducing the cost of manual identification.

Description

Technical Field

[0001] This application belongs to the field of electronic product technology, and in particular relates to a method, system, storage medium and electronic device for identifying product model attributes. Background Technology

[0002] The domestic and international electronics industry is vast, involving numerous manufacturers, each typically employing its own rules and standards for product naming. Even different series or categories of products from the same manufacturer may have significantly different model number rules. Some manufacturers name models based on product function, performance, or market positioning, while others may assign model numbers based on production batches, internal coding, or other custom rules. Therefore, there is no unified industry standard or specification that can accurately cover all product models. This makes identifying electronic product models a complex and challenging task in practice. Typically, this task can only be performed manually. While this method can handle diverse model forms, it is extremely time-consuming and labor-intensive, and due to the subjectivity of human judgment, complete accuracy is difficult to guarantee. Furthermore, manual judgment places high demands on the operator's experience and understanding of the industry.

[0003] Another common method is matching with product models already entered into a database. This method can improve model identification efficiency to some extent, but it relies on the database's update frequency and comprehensiveness. If the database is not updated in a timely manner, or if some manufacturers' new products have not yet been entered, even database matching may fail to identify or make incorrect judgments. More complexly, new products and technologies emerge constantly in the electronics industry, and the rules for assigning product models are constantly evolving and changing. Therefore, existing databases often cannot fully cover all the latest product models. In this situation, simply relying on the database may lead to significant omissions, especially after the release of new products, making timely model updates particularly important.

[0004] In conclusion, both manual identification and database matching have limitations in existing methods for identifying electronic product models, especially in the face of a rapidly changing electronic product market. Summary of the Invention

[0005] The purpose of this application is to provide a method, system, storage medium, and electronic device for identifying product model attributes, in order to solve the technical problem of how to automatically identify the model attributes of electronic products.

[0006] Firstly, this application provides a method for identifying product model attributes, the method comprising:

[0007] The system receives product information input by the user; the product information includes several product attribute categories; the product attribute categories include product name attribute, product model attribute, product parameter attribute, and product quantity attribute; each product attribute category corresponds to several product attribute data.

[0008] The possibility of obtaining each product attribute data under each product attribute category as the product model attribute data;

[0009] Based on the probability that all the acquired product attribute data is the product model attribute data, the identification result of the product model attribute is obtained in several product attribute categories.

[0010] In one implementation of the first aspect, the possibility of obtaining each product attribute data under each product attribute category as the product model attribute includes:

[0011] The trained product model attribute recognition model is used to determine whether each product attribute data under the product attribute category contains empty information or non-ASCII characters.

[0012] If the null information or the non-ASCII character is present, the trained product model attribute recognition model determines that the corresponding product attribute data is not the product model attribute data.

[0013] If the null information and the non-ASCII characters are not present, the trained product model attribute recognition model determines the probability that the corresponding product attribute data is the product model attribute data.

[0014] In one implementation of the first aspect, obtaining the identification result of the product model attribute from among the several product attribute types includes:

[0015] For each product attribute category, obtain the corresponding average probability result; the average probability result is the average probability that the product attribute data is the product model attribute data under each product attribute category;

[0016] The product attribute category with the highest average probability result is determined as the product model attribute.

[0017] In one implementation of the first aspect, the method further includes:

[0018] Obtain the model attribute recognition dataset; the model attribute recognition dataset includes a model attribute recognition training set and a model attribute recognition test set;

[0019] The pre-determined original model is trained based on the model attribute recognition training set and the model attribute recognition test set to obtain the trained product model attribute recognition model; wherein,

[0020] The predetermined original model is trained multiple times on the model attribute recognition training set; if the training loss value does not exceed the loss threshold for multiple consecutive rounds, the product model attribute recognition model is obtained.

[0021] The product model attribute recognition model is tested on the model attribute recognition test set to obtain the trained product model attribute recognition model.

[0022] In one implementation of the first aspect, obtaining the model identification dataset includes:

[0023] Retrieve the product attribute training data from the database;

[0024] The product attribute training data is labeled according to the product attribute categories to obtain a first data table;

[0025] Create a second data table corresponding to the first data table. The second data table is in DataFrame format. The product model attribute category in the second data table is marked as 1, and the non-product model attribute category is marked as 0.

[0026] The first data table and the second data table are merged and randomized to obtain the model identification dataset.

[0027] In one implementation of the first aspect, the pre-determined original model undergoes multiple rounds of training on the model attribute recognition training set, including:

[0028] The product model attribute training data in the model attribute recognition training set is vectorized to obtain several model vectors.

[0029] The product model attribute recognition model is obtained by training the predetermined original model based on several model vectors.

[0030] In one implementation of the first aspect, vectorizing the product model attribute training data in the model attribute recognition training set includes:

[0031] Select adjacent strings of length [1, a] from the product model attribute training data, where a∈(1, b], and b is the character length of the product model attribute training data;

[0032] Obtain the number of occurrences of the adjacent strings in the corresponding product model attribute training data;

[0033] The occurrence count is compared with the number of adjacent strings of length [1, a] in the training data corresponding to the product model attribute to obtain a first result;

[0034] The reciprocal of the proportion of all product model attribute training data containing the adjacent strings in the model attribute recognition training set is obtained as the second result;

[0035] The model vector is obtained based on the first result and the second result.

[0036] Secondly, this application provides a product model attribute identification system, the system comprising:

[0037] The receiving module is used to receive product requirement information input by the user; the product requirement information includes several product attribute categories; the product attribute categories include product name attribute, product model attribute, product parameter attribute and product quantity attribute; each product attribute category corresponds to several product attribute data;

[0038] The acquisition module is used to acquire the probability that each product attribute data under each product attribute category is the product model attribute;

[0039] The identification module is used to obtain the identification result of the product model attribute among several product attribute types based on the probability that all the acquired product attribute data is the product model attribute.

[0040] Thirdly, this application provides an electronic device, the electronic device comprising: a processor and a memory; the memory for storing a computer program; the processor for executing the computer program stored in the memory, so that the electronic device performs the above-described product model attribute identification method.

[0041] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the above-described method for identifying product model attributes.

[0042] As described above, the product model attribute identification method, system, storage medium, and electronic device described in this application have the following beneficial effects: They can automatically and accurately identify product model attributes from multiple product attribute categories in product information under different product model assignment rules, thereby obtaining the corresponding product model attribute data and reducing the cost of manual identification. By applying this application, electronic product retailers can automatically identify the electronic product model that a customer needs to purchase, which helps reduce the sales cost of electronic products and accurately provides the corresponding electronic products to the customer. Attached Figure Description

[0043] Figure 1A This diagram illustrates an application scenario of the product model attribute identification method described in this application.

[0044] Figure 1B This diagram illustrates the structure of the mid-cloud interaction scenario in these implementation methods.

[0045] Figure 2 The diagram shown is a flowchart of one embodiment of the product model attribute identification method described in this application.

[0046] Figure 3 The diagram shown is a flowchart of one embodiment of the product model attribute identification method described in this application.

[0047] Figure 4 The diagram shown is a flowchart of one embodiment of the product model attribute identification method described in this application.

[0048] Figure 5 The diagram shown is a flowchart of one embodiment of the product model attribute identification method described in this application.

[0049] Figure 6 The diagram shown is a flowchart of one embodiment of the product model attribute identification method described in this application.

[0050] Figure 7 The diagram shown is a structural schematic of one embodiment of the product model attribute identification system described in this application.

[0051] Figure 8 The diagram shown is a structural schematic of the electronic device of this application in one embodiment.

[0052] Component designation explanation

[0053] 1. Product model attribute identification device

[0054] 11 processors

[0055] 12 Databases

[0056] 2-Terminal-Cloud Interactive System

[0057] 20 terminals

[0058] 21 Cloud Servers

[0059] 4 Product Model Attribute Identification System

[0060] 41 Receiver Module

[0061] 42 Acquisition Module

[0062] 43 Recognition Module

[0063] 51 Processing Unit

[0064] 52 Memory

[0065] 521 Memory

[0066] 522 cache memory

[0067] 523 Storage System

[0068] 524 Programs / Utilities

[0069] 5241 Program Module

[0070] 53 bus

[0071] 54 I / O interfaces

[0072] 55 Network Adapter

[0073] Steps S1 to S3

[0074] Steps S21 to S23

[0075] Steps S4 to S5

[0076] Steps S41 to S44

[0077] Steps S51 to S55 Detailed Implementation

[0078] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0079] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0080] Furthermore, the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed in this application.

[0081] Currently, with the development of internet technology, e-commerce platforms have become the first choice for many users to purchase electronic components. An e-commerce platform is an online platform specializing in selling electronic products. It typically includes a website, mobile application, and social media integration, offering a wide selection of electronic products. For users who need to purchase electronic products in bulk, they often use Excel spreadsheets to organize information about the electronic products they want to buy, including product name, model number, specifications, and quantity. After receiving the purchase order from the user, the e-commerce platform will pick and ship the corresponding goods, completing the sales process. However, during the picking process, sellers often need to manually identify the product models in the purchase order or compare them with a database. However, because different manufacturers typically use their own rules and standards when naming their electronic products, even different series or categories of products from the same manufacturer may have significantly different model number rules. This adds many obstacles for electronic product sellers in identifying product models.

[0082] To at least address the aforementioned issues, embodiments of this application provide a method for identifying product model attributes, which can automatically and accurately identify product model attributes and corresponding product model attribute data in product information, reducing the cost of manual identification.

[0083] The product model attribute identification method provided in this application embodiment can be applied to, for example... Figure 1A The device for identifying product model attributes. For example... Figure 1A As shown, the product model attribute identification device 1 includes a processor 11 and a database 12. The product model attribute identification method provided in this application embodiment can be applied to the processor 11.

[0084] in, Figure 1A The processor 11 in the text can be a single processor, a processor cluster consisting of multiple processors, or a cloud computing center, etc., and is not specifically limited here. Although Figure 1A Only one processor 11 and one database 12 are shown, but it should be understood that... Figure 1AThe examples in this paper are only for understanding this solution. The specific number of processors 11 and databases 12 should be flexibly determined based on the actual situation.

[0085] In some other embodiments, the product model attribute identification device 1 may not include the database 12, but only a processor 11 with storage function. The product model attribute identification method provided in this application embodiment can be applied to the processor 11. The processor 11 with storage function may include tablet computers, laptops, handheld computers, mobile phones, personal computers (PCs), etc., and is not limited here.

[0086] In some other embodiments, the product model attribute identification method described in this application can be applied to end-to-cloud interaction scenarios. Figure 1B This diagram illustrates the structure of the endpoint-cloud interaction scenario in these implementation methods. For example... Figure 1B As shown, the terminal-cloud interaction system 2 includes a terminal 20 and a cloud server 21. The terminal 20 and the cloud server 21 can communicate with each other, and the communication method is not limited to wired or wireless.

[0087] The terminal 20 can be mobile or fixed. For example, it can be a wireless terminal or a wired terminal. A wireless terminal can refer to a device with wireless transceiver capabilities, which can be deployed indoors, outdoors, and in industrial workshops. The terminal 20 can be a mobile phone, tablet, laptop, etc., and is not limited thereto. The cloud server 21 can include one or more servers, or one or more processing nodes, or one or more virtual machines running on the server. The cloud server 21 can also be referred to as a server cluster, management platform, product model attribute identification center, etc., and is not limited thereto in this embodiment.

[0088] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0089] The following embodiments of this application provide a method for identifying product model attributes, which, for example, can be achieved through... Figure 1A The processor 11 shown or Figure 1B The cloud server 21 shown is used to implement this. Figure 2 The diagram shows a flowchart illustrating the product model attribute identification method described in this application embodiment. Figure 2 As shown, the method for identifying the product model attribute includes steps S1 to S3.

[0090] S1. Receive product information input by the user; the product information includes several product attribute categories; the product attribute categories include product name attribute, product model attribute, product parameter attribute and product quantity attribute; each product attribute category corresponds to several product attribute data.

[0091] In some embodiments, the product information entered by the user is represented as an Excel spreadsheet. Each column in the spreadsheet represents a different product attribute category, and each column contains corresponding product attribute data. The product attribute categories include product name, product model, product parameter, and product quantity. In other words, the Excel spreadsheet entered by the user contains the product information the user wishes to purchase, including product name, product model, product parameters, and product quantity.

[0092] S2. The possibility of obtaining each product attribute data under each product attribute category as the product model attribute data.

[0093] Specifically, the system judges the product information entered by the user and analyzes which product attribute data in the product information are product model attribute data.

[0094] In some embodiments, after receiving an Excel spreadsheet from a user, the seller will identify the spreadsheet, primarily determining which column represents the product model attribute. The product attribute data corresponding to that column is then the product model attribute data. This allows the seller to identify the specific product model attribute data to be sold and prepare the product for sale based on this information.

[0095] Figure 3 The diagram shows a flowchart illustrating the product model attribute identification method described in this application embodiment. Figure 3 As shown, the method for identifying the product model attribute includes steps S21 to S23.

[0096] S21. Use the trained product model attribute recognition model to determine whether each product attribute data under the product attribute category contains empty information or non-ASCII characters.

[0097] S22. If the null information or the non-ASCII character is present, the trained product model attribute recognition model determines that the corresponding product attribute data is not the product model attribute data.

[0098] S23. If the null information and the non-ASCII characters are not present, the trained product model attribute recognition model determines the probability that the corresponding product attribute data is the product model attribute data.

[0099] Specifically, the trained product model attribute recognition model analyzes which product attribute data in the product information are product model attribute data. If the trained product model attribute recognition model determines that the product attribute data packet contains empty information or non-ASCII characters, then the probability that the product attribute data is product model attribute data is 0; if the trained product model attribute recognition model determines that the product attribute data does not contain empty information or non-ASCII characters, then the probability that the corresponding product attribute data is product model attribute data is determined.

[0100] In some embodiments, when a user sends product information in an Excel spreadsheet, each column in the spreadsheet represents a different product attribute type. In this case, the trained product model attribute recognition model provided in this application embodiment judges all cells (product attribute data) in the Excel spreadsheet. If a cell is empty or contains non-ASCII characters, the probability that the cell contains product model attribute data is 0; if a cell is not empty and does not contain non-ASCII characters, the data in that cell may be product model attribute data.

[0101] It should be noted that when the product attribute data does not contain empty information or non-ASCII characters, the trained product model attribute recognition model will automatically determine the probability of the data being the product model attribute based on the previous training process and training dataset. That is, when the model determines that the product attribute data is close to the product model format, it will assign a higher probability; if it does not contain empty information or non-ASCII characters, but the characters are short or exhibit other characteristics, it will assign a lower probability.

[0102] It should be noted that the product model attribute identification method provided in this application embodiment also includes a training method for the product model attribute identification model. Figure 4 The diagram shown is a flowchart illustrating the training method of the product model attribute recognition model described in this application embodiment. Figure 4 As shown, the training method for the product model attribute recognition model includes steps S4 to S5.

[0103] S4. Obtain the model attribute recognition dataset; the model attribute recognition dataset includes a model attribute recognition training set and a model attribute recognition test set.

[0104] Specifically, Figure 5 The diagram shown is a flowchart illustrating the training method of the product model attribute recognition model described in this application embodiment. Figure 5 As shown, the training method for the product model attribute recognition model includes steps S41 to S44.

[0105] S41. Obtain the product attribute training data from the database.

[0106] In some embodiments, raw data related to product attributes, including product model, name, specifications and other details, are obtained from a MongoDB database to serve as the basic training data for training the original model.

[0107] S42. Label the product attribute training data according to the product attribute category to obtain the first data table.

[0108] In some embodiments, product attribute training data obtained from the database is categorized and labeled according to product attribute categories to generate a first data table. Each product is labeled according to its attributes (e.g., model, name), forming a table containing the original product attribute data and its category labels.

[0109] S43. Create a second data table corresponding to the first data table. The second data table is in DataFrame format. The product model attribute category in the second data table is marked as 1, and the non-product model attribute category is marked as 0.

[0110] In some embodiments, a second data table corresponding to the first data table is generated, and its format is DataFrame. DataFrame is a common structured data table format, which can typically be processed using tools such as pandas. The purpose of the second data table is to perform further labeling operations.

[0111] Furthermore, in the second data table, the product model attribute category is marked as 1, while other non-product model attributes are marked as 0. This is to transform the original classification problem into a binary classification problem, facilitating subsequent model training. In this case, identifying whether product attribute data is product model attribute data becomes the objective task.

[0112] S44. Merge and randomize the first data table and the second data table to obtain the model identification dataset.

[0113] In some embodiments, the first data table and the second data table are merged to form a complete dataset containing the original product attributes and binary classification labels. Then, the data is shuffled to ensure randomness during model training, avoid bias in the learning order, and improve the model's generalization ability. Finally, one-quarter of the dataset is used as the model attribute recognition test set, and the remainder as the model attribute recognition training set.

[0114] S5. Train the predetermined original model based on the model attribute recognition training set and the model attribute recognition test set to obtain the trained product model attribute recognition model.

[0115] Specifically, after obtaining the model attribute recognition training set and the model attribute recognition test set, the predetermined original model is trained multiple times on the model attribute recognition training set. If the training loss value does not exceed the loss threshold for multiple consecutive rounds, the product model attribute recognition model is obtained. Then, the product model attribute recognition model is tested on the model attribute recognition test set to obtain the trained product model attribute recognition model.

[0116] In some embodiments, when training the model, the product model attribute training data in the model attribute recognition training set needs to be vectorized to obtain several model vectors. Then, the predetermined original model is trained based on these model vectors to obtain the product model attribute recognition model.

[0117] Figure 6 The diagram shown is a schematic representation of the vectorization process described in the embodiments of this application. Figure 6 As shown, the vectorization process for the product model attribute training data in the model attribute recognition training set includes steps S51 to S55.

[0118] S51. Select adjacent strings of length [1, a] from the product model attribute training data, where a∈(1, b], and b is the character length of the product model attribute training data.

[0119] Specifically, let the product model attribute training data be d. Then, select an adjacent string t of length [1, a] from d. Where a∈(1, b], and b is the character length of the product model attribute training data. That is, if d is xingh, then the length b is 5. Then, select an adjacent string t of length [1, a] from "xingh", and the length of the adjacent string t is at most the same as d.

[0120] It should be noted that the selection of adjacent strings of length [1, a] in the product model attribute training data adopts an exhaustive principle. That is, all adjacent strings of length [1, a] need to be selected.

[0121] In some embodiments, adjacent strings t of length [1,3] are selected from d "xingh" of length 5. Then the adjacent strings t include "x", "i", "n", "g", "h", "xi", "in", "ng", "gh", "xin", "ing", and "ngh".

[0122] S52. Obtain the number of times the adjacent strings appear in the corresponding product model attribute training data.

[0123] Specifically, obtain the number of times f of adjacent strings t appear in the model attribute training data d. t,d .

[0124] S53. Compare the occurrence count with the number of adjacent strings of length [1, a] in the training data corresponding to the product model attribute to obtain a first result.

[0125] Specifically, the first result can be expressed as:

[0126]

[0127] For example, in the above embodiment, the adjacent string t "x" appears once in "xingh", f t,d If the value is 1, then the number of all adjacent strings with length [1, 3] is 12, so the first result is 1 / 12.

[0128] S54. Obtain the reciprocal of the proportion of all product model attribute training data containing the adjacent strings in the model attribute recognition training set, as the second result.

[0129] Specifically, find the reciprocal of the proportion of models containing t in the training set D:

[0130]

[0131] S55. Obtain the model vector based on the first result and the second result.

[0132] Specifically, multiply the first result tf(t,d) and the second result idf(t,D):

[0133] tfidf(t,d,D)=tf(t,d)·idf(t,D) (3)

[0134] This process transforms each string of adjacent characters into numbers, thus converting each product model attribute data into a vector of its adjacent characters, i.e., a model vector.

[0135] In some embodiments, after the product model attribute training data is converted into vectors of its adjacent characters (model vectors) through vectorization processing, a neural network is trained on the obtained model vectors using scikit-learn's Multi-Layer Perceptron Classifier. If the training loss value does not exceed 0.0001 for 10 consecutive rounds, training is stopped, and a product model attribute recognition model is obtained. Then, the product model attribute recognition model is tested on the model attribute recognition test set to obtain the trained product model attribute recognition model.

[0136] In some embodiments, the Adam algorithm can be used to dynamically adjust the learning rate during model training, making parameter updates both stable and efficient. By using an exponentially weighted moving average, the Adam algorithm can effectively handle situations with large gradient changes and adaptively adjust the learning rate of each parameter. Specifically, for each iteration, the following operations are performed:

[0137] (1) Initialization, i.e., setting hyperparameters: learning rate α = 0.0001, momentum decay coefficient β1 = 0.9, mean square decay coefficient β2 = 0.999, smoothing term ∈ = 10. -8 .

[0138] (2) Initialize the first-order momentum estimate and the second-order momentum estimate, i.e. the initial deviation correction term: initialize the initial value m0 of the first-order momentum and the initial value v0 of the second-order momentum to 0.

[0139] (3) Perform the following operations in each iteration:

[0140] - Calculate the gradient: based on the current parameter θ t-1 Calculate the gradient g of the objective function f. t

[0141]

[0142] - Update the first-order momentum estimate (exponentially weighted moving average of momentum).

[0143] m t =β1·m t-1 +(1-β1)g t (5)

[0144] Where, m t This represents the weighted average of the gradient.

[0145] - Update the second-order momentum estimate (exponentially weighted moving average of the squared gradient).

[0146]

[0147] Among them, v t This represents the weighted average of the squared gradients.

[0148] - Perform bias correction on momentum and mean square error (because the initial value of momentum is 0, which may cause estimation bias in the first few iterations).

[0149]

[0150] in, and It is a momentum and mean square error estimate after bias correction.

[0151] - Update parameter θ t Parameter updates are performed using the corrected gradient estimate m. t and the mean square error of the gradient Then multiply by the learning rate α for adjustment.

[0152]

[0153] If the training loss value does not exceed 0.0001 for 10 consecutive rounds, training is stopped, and the product model attribute recognition model is obtained. In some embodiments, the trained product model attribute recognition model can be represented as:

[0154]

[0155] Where x is the input vector of the neural network, E is the set of synapses (connections between neurons), and v t.r Refers to the r-th neuron in layer t, a t,r Refers to its input, o t,r Refers to its output, v t+1.j σ refers to the j-th neuron in the (t+1)-th layer, w refers to the weight function (the input is an element of E), and σ refers to the neuron's activation function.

[0156] In this layer, each neuron is connected to all neurons in the previous layer, and the output of each previous neuron is multiplied and added to the weight of the synapse connecting it. Therefore, the output of the j-th neuron in the (t+1)-th layer can be expressed as:

[0157] o t+1,j (x)=σ(a t+1,j (x)) (11)

[0158] The activation function of a neuron is expressed as:

[0159]

[0160] It should be noted that for product model attribute recognition models, more layers in the neural network generally mean more accurate recognition results. However, too many layers can lead to excessive computation time and may also cause overfitting. More neurons in each layer result in higher accuracy, but also require more computational resources. Furthermore, the number of neurons in each layer can be the same or different. In this application, after extensive training with large amounts of data, it was found that a neural network with two layers, each containing 50 neurons, optimally balances training time, required resources, and recognition performance.

[0161] In some embodiments, the trained product model attribute recognition model is exported and saved in ONNX (Open Neural Networks Exchange) format to obtain the probability that each product attribute data under each product attribute category is the product model attribute data.

[0162] S3. Based on the probability that all the acquired product attribute data is the product model attribute data, obtain the identification result of the product model attribute in several product attribute categories.

[0163] Specifically, for each product attribute category, the corresponding average probability result is obtained; the average probability result is the average of the probability that the product attribute data under each product attribute category is the product model attribute data.

[0164] Specifically, the product attribute category with the highest average probability result is determined as the product model attribute.

[0165] In some embodiments, step S2 can be used to obtain the probability that all product attribute data in the product information is the product model attribute data. Since the product attribute data corresponds to different attribute categories, the average probability that the number of product attributes in each category is the product model attribute data can be calculated. When the average is the highest, it indicates that the corresponding category should be the product model attribute category.

[0166] For example, a user inputs product information in an Excel spreadsheet, where each column corresponds to a different product attribute category. In this case, the seller cannot determine which column represents the product model attribute and needs to manually examine each data point to determine the desired product model. Step S2 calculates the probability that each cell in the Excel spreadsheet represents the product model attribute and calculates the average probability for each column. When the average probability is highest, it indicates that the column should represent the product model attribute category, and all data in that column represents the product model attribute data. This allows the seller to automatically determine the product model attribute from the product information sent by the user and obtain all corresponding product model attribute data.

[0167] The scope of protection for the product model attribute identification method described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0168] This application also provides a product model attribute identification system. The product model attribute identification system can implement the product model attribute identification method described in this application. However, the implementation device of the product model attribute identification system described in this application includes, but is not limited to, the structure of the product model attribute identification system listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0169] Figure 7 The diagram shown is a structural schematic of the product model attribute identification system described in the embodiments of this application. Figure 7 As shown, the product model attribute identification system 4 includes a receiving module 41, an acquisition module 42, and an identification module 43.

[0170] The receiving module 41 is used to receive product requirement information input by the user; the product requirement information includes several product attribute categories; the product attribute categories include product name attribute, product model attribute, product parameter attribute and product quantity attribute; each product attribute category corresponds to several product attribute data;

[0171] The acquisition module 42 is used to acquire the probability that each product attribute data under each product attribute category is the product model attribute;

[0172] The identification module 43 is used to obtain the identification result of the product model attribute among several product attribute types based on the probability that all the acquired product attribute data is the product model attribute.

[0173] It should be noted that the structure and principle of the receiving module 41, the acquiring module 42 and the identifying module 43 correspond one-to-one with the steps in the above-mentioned product model attribute identification method, so they will not be described in detail here.

[0174] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0175] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0176] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0177] This application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0178] This application also provides an electronic device. The electronic device includes a processor and a memory.

[0179] The memory is used to store computer programs.

[0180] The memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0181] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the electronic device performs the above-described product model attribute identification method.

[0182] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0183] like Figure 8As shown, the electronic device of this application is embodied in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors or processing units 51, memory 52, and bus 53 connecting different system components (including memory 52 and processing unit 51).

[0184] Bus 53 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0185] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0186] Memory 52 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 521 and / or cache memory 522. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 523 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 8 Not shown; usually referred to as a "hard drive"). Although Figure 8 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 53 via one or more data media interfaces. Memory 52 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0187] A program / utility 524 having a set (at least one) of program modules 5241 may be stored, for example, in memory 52. ​​Such program modules 5241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 5241 typically perform the functions and / or methods described in the embodiments of this application.

[0188] The electronic device can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network interface card, modem, etc.). This communication can be performed through input / output (I / O) interface 54. Furthermore, the electronic device can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 55. Figure 8 As shown, network adapter 55 communicates with other modules of the electronic device via bus 53. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0189] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0190] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.

[0191] This application provides a method, system, storage medium, and electronic device for identifying product model attributes. Under different product model assignment rules, it can automatically and accurately identify product model attributes from multiple product attribute categories in product information, thereby obtaining the corresponding product model attribute data and reducing the cost of manual identification. By applying this application, electronic product retailers can automatically identify the model of electronic products that customers need to purchase, which helps reduce the sales cost of electronic products and accurately provides customers with the corresponding electronic products.

[0192] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0193] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method of identifying a product model attribute, characterized by, The method comprises: receiving user input product information; the product information comprises several columns of product attribute categories; the product attribute categories comprise product name attributes, product model attributes, product parameter attributes, and product quantity attributes; each column of the product attribute categories corresponds to several product attribute data; acquiring the possibility of each product attribute data in each column of the product attribute categories being product model attribute data through a trained product model attribute recognition model; the product model attribute recognition model comprises two layers of neural networks with the same number of neurons; based on the acquired possibility of all the product attribute data being the product model attribute data, acquiring the recognition result of the product model attribute in the several columns of product attribute categories; wherein the training method of the product model attribute recognition model comprises: selecting adjacent strings with a length of [1, 3] in product model attribute training data, and the character length of the product model attribute training data is not less than 3; obtaining a number of occurrences of the adjacent string t in the product model attribute training data corresponding to the product model attribute ;​ The number of occurrences The first result is obtained by comparing the number of adjacent strings of length [1, 3] in the product model attribute training data d is: Obtain the reciprocal of the proportion of the number of all product model attribute training data d containing the adjacent character string t in the model attribute identification training set D as a second result is: multiplying the first result and the second result to convert the product model attribute data into a model vector including the adjacent string is: training a pre-determined original model based on the model vector to acquire the product model attribute recognition model.

2. The method of identifying a product model attribute according to claim 1, wherein, acquiring the possibility of each product attribute data in each column of the product attribute categories being the product model attribute comprises: using the trained product model attribute recognition model to determine whether each product attribute data in the product attribute category contains empty information or non-ASCII characters; if the empty information or the non-ASCII characters are contained, the trained product model attribute recognition model determines that the corresponding product attribute data is not the product model attribute data; if the empty information and the non-ASCII characters are not contained, the trained product model attribute recognition model determines the possibility of the corresponding product attribute data being the product model attribute data.

3. The method of identifying product model attributes according to claim 1, wherein, acquiring the recognition result of the product model attribute in the several columns of product attribute categories comprises: for each product attribute category, acquiring a corresponding average possibility result; the average possibility result is the average value of the possibility of the product attribute data in each product attribute category being the product model attribute data; determining the product attribute category with the highest average possibility result as the product model attribute.

4. The method of identifying product model attributes according to claim 2, wherein, The training method of the product model attribute recognition model comprises: acquiring a model attribute recognition data set; the model attribute recognition data set comprises a model attribute recognition training set and a model attribute recognition test set; training a pre-determined original model based on the model attribute recognition training set and the model attribute recognition test set to acquire the trained product model attribute recognition model; wherein, the pre-determined original model is trained on the model attribute recognition training set for multiple rounds; if the training loss value of consecutive multiple rounds does not exceed a loss threshold, a product model attribute recognition model is acquired; testing the product model attribute recognition model on the model attribute recognition test set to acquire the trained product model attribute recognition model.

5. The method of identifying a product model attribute according to claim 4, wherein, acquiring a model recognition data set comprises: acquiring the product attribute training data from a database; The product attribute training data is labeled according to the product attribute categories to obtain a first data table; A second data table corresponding to the first data table is created, and the second data table is in a DataFrame data format; in the second data table, the product model attribute category is marked as 1, and the non-product model attribute category is marked as 0; The first data table and the second data table are merged and randomized to obtain the model identification data set.

6. The method of identifying product model attributes according to claim 4, wherein, The pre-determined original model is trained on the model attribute identification training set for multiple rounds, including: The product model attribute training data in the model attribute identification training set is vectorized to obtain a plurality of model vectors; The pre-determined original model is trained based on the plurality of model vectors to obtain the product model attribute identification model.

7. A product model attribute recognition system, characterized by, The system includes: A receiving module for receiving product demand information input by a user; the product demand information includes a plurality of columns of product attribute categories; the product attribute categories include product name attributes, product model attributes, product parameter attributes, and product quantity attributes; each column of the product attribute categories corresponds to a plurality of product attribute data; An obtaining module for obtaining the likelihood that each product attribute data in each column of the product attribute categories is product model attribute data through a trained product model attribute identification model; the product model attribute identification model includes two layers of neural networks with the same number of neurons; An identification module for obtaining an identification result of a product model attribute among a plurality of columns of the product attribute categories based on the likelihood that all the product attribute data is the product model attribute data; wherein the training method of the product model attribute identification model includes: Selecting adjacent strings with a length of [1, 3] in the product model attribute training data, and the character length of the product model attribute training data is not less than 3; obtaining the occurrence times of the adjacent character string t in the product model attribute training data d ; The number of occurrences The first result is obtained by comparing the number of adjacent strings of length [1, 3] in the product model attribute training data d is: Obtain the reciprocal of the proportion of the number of all product model attribute training data d containing the adjacent character string t in the model attribute identification training set D as a second result is: multiplying the first result and the second result to convert the product model attribute data into a model vector comprising the adjacent string is: Training a pre-determined original model based on the model vectors to obtain the product model attribute identification model.

8. An electronic device, comprising: The electronic device includes a processor and a memory; The memory is used to store a computer program; The processor is used to execute the computer program stored in the memory to enable the electronic device to perform the product model attribute identification method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the electronic device to implement the product model attribute identification method of any one of claims 1 to 6.

Images