CN112767081A - Cross-border bonded bin commodity classification method and device - Google Patents
Cross-border bonded bin commodity classification method and device Download PDFInfo
- Publication number
- CN112767081A CN112767081A CN202110070797.2A CN202110070797A CN112767081A CN 112767081 A CN112767081 A CN 112767081A CN 202110070797 A CN202110070797 A CN 202110070797A CN 112767081 A CN112767081 A CN 112767081A
- Authority
- CN
- China
- Prior art keywords
- category
- commodity
- classification
- word segmentation
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
Abstract
The application discloses a cross-border bonded bin commodity classification method and device, a preset word segmentation model is used for carrying out word segmentation analysis on commodities according to commodity information of the commodities to obtain word segmentation results, the word segmentation results are scored with matching results of a preset category keyword library to obtain scores of the word segmentation results in each category, so that the weight of the categories to which the commodities belong is obtained, the category categories of the commodities are further obtained, and the technical problems of low efficiency, commodity classification solidification and judgment result deviation of existing cross-border commodity classification are solved by means of automatic and scientific modes of word segmentation, matching and scoring.
Description
Technical Field
The application relates to the technical field of warehouse management, in particular to a cross-border bonded bin commodity classification method and device.
Background
In the cross-border supply chain circulation or e-commerce sales, the cross-border e-commerce imported goods need to be classified so as to facilitate the related statistics of goods categories, but in the cross-border e-commerce imported goods sales link, the goods classification and the customs imported goods classification rule have certain difference.
At present, the general process of importing goods by cross-border e-commerce is as follows: 1. establishing classification categories; 2. the method mainly comprises the following steps of classifying commodities into corresponding categories according to classification categories, such as: when the newly warehoused commodity is logged into the warehouse management system of the cross-border bonded warehouse, the logging personnel select the classification category of the commodity on the warehouse management system, and after confirmation, the warehouse management system records the commodity classification.
The current cross-border commodity classification is mainly based on a mode of artificial subjective judgment, because the artificial decision is taken as a main part, when the affiliation classification of the commodity is selected, if the commodity is a known commodity or a commodity close to the known commodity, the commodity can be classified by a pre-classification system and then manually checked, and if the commodity is a new commodity or a commodity unknown to the system, the commodity can be judged only manually. And if the new commodity does not belong to any existing category, the new adding treatment of the commodity category is needed manually. If the new commodity exceeds the artificial cognition range, the commodity information needs to be acquired manually, the classification information of the commodity is acquired through tools such as various search engines, the cognition of each person is different, different classification results may occur on the same commodity, and a series of service logic confusion is caused. In summary, the existing cross-border commodity classification has the technical problems of low efficiency, solidified commodity classification and deviation of judgment results.
Disclosure of Invention
The application provides a cross-border bonded bin commodity classification method and device, and solves the technical problems of low efficiency, commodity classification solidification and judgment result deviation of the existing cross-border commodity classification.
In view of the above, a first aspect of the present application provides a cross-border bonded bin commodity classification method, including:
acquiring commodity information of commodities to enter a cross-border bonded bin;
analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
and matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity.
Optionally, before the matching the word segmentation result with the preset category keyword library, the method further includes:
constructing at least one category of a cross-border commodity;
constructing a keyword library of the category, wherein the keyword library comprises at least one keyword associated with the category;
and correspondingly associating the categories with the keyword library to generate a preset category keyword library.
Optionally, the matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and using the category to which the keyword library with the highest category score belongs as the classification category of the commodity specifically includes:
matching the word segmentation of the word segmentation result with the keywords of a preset category keyword library one by one;
according to the position weight of the word segmentation in the commodity information, performing category scoring on the matched keywords;
and taking the category to which the keyword library with the highest category score belongs as the category of the commodity.
Optionally, the matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity further includes:
if the highest category score is lower than a preset threshold value, commodity information of the commodity is used as input, and a prediction classification result and a prediction percentage thereof are obtained by utilizing a preset commodity classification neural network model;
and taking the prediction classification result with the highest prediction percentage as the final classification category of the commodity.
Optionally, the method further comprises:
constructing a training sample set, wherein the training sample set comprises training commodity information and training classification categories, and the training classification categories are target labels;
and training the commodity classification neural network model through the training sample set to obtain a preset commodity classification neural network model.
Optionally, the matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity further includes:
and if the highest category score is higher than the preset threshold value, adding the commodity information of the commodity and the classification category of the commodity into the training sample set.
A second aspect of the present application provides a cross-border bonded bin commodity sorting device, the device comprising:
the acquiring unit is used for acquiring commodity information of commodities to enter the cross-border bonded bin;
the analysis unit is used for analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
and the first classification unit is used for matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity.
Optionally, the method further comprises:
the first construction unit is used for constructing at least one category of the cross-border commodities;
the second construction unit is used for constructing a keyword library of the category, and the keyword library comprises at least one keyword associated with the category;
and the association unit is used for correspondingly associating the categories with the keyword library to generate a preset category keyword library.
Optionally, the method further comprises:
the prediction unit is used for taking the commodity information of the commodity as input and obtaining a prediction classification result and a prediction percentage thereof by utilizing a preset commodity classification neural network model if the highest category score is lower than a preset threshold value;
and the second classification unit is used for taking the prediction classification result with the highest prediction percentage as the final classification category of the commodity.
Optionally, the method further comprises:
the third construction unit is used for constructing a training sample set, wherein the training sample set comprises training commodity information and training classification categories, and the training classification categories are target labels;
and the training unit is used for training the commodity classification neural network model through a training sample set to obtain a preset commodity classification neural network model.
According to the technical scheme, the embodiment of the application has the following advantages:
according to the commodity information of the commodity, a preset word segmentation model is used for carrying out word segmentation analysis on the commodity to obtain word segmentation results, the word segmentation results are scored with matching results of a preset category keyword library to obtain scores of the word segmentation results in each category, so that the weight of the category to which the commodity belongs is obtained, the category of the commodity is further obtained, and the technical problems of low efficiency, commodity classification solidification and judgment result deviation of the existing cross-border commodity classification are solved by means of automatic and scientific modes of word segmentation, matching and scoring.
Drawings
FIG. 1 is a flowchart illustrating a cross-border bonded bin commodity classification method according to an embodiment of the present application;
FIG. 2 is another flow chart of a cross-border bonded bin commodity classification method according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a cross-border bonded bin commodity sorting device according to an embodiment of the present application;
fig. 4 is another schematic structural diagram of a cross-border bonded bin commodity sorting device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The application designs a cross-border bonded bin commodity classification method and device, and solves the technical problems of low efficiency, commodity classification solidification and judgment result deviation of the existing cross-border commodity classification.
For easy understanding, please refer to fig. 1, in which fig. 1 is a flowchart illustrating a first method of a cross-border bonded bin commodity classification method according to an embodiment of the present application, and as shown in fig. 1, the method specifically includes:
101. acquiring commodity information of commodities to enter a cross-border bonded bin;
it should be noted that, for a commodity to enter the cross-border bonded warehouse, commodity information needs to be obtained first, and the commodity information may generally include information such as a commodity name, a commodity component, a commodity origin, and a commodity customs classification.
102. Analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
it should be noted that after the commodity information is obtained, the commodity information is subjected to word segmentation processing by using a preset word segmentation model, the complete commodity information is segmented into single words, a word segmentation result of the commodity is output, the word segmentation result contains position information of each word segmentation in the original commodity information besides the single word segmentation of the commodity, for example, a commodity name in the commodity information is called "some card knitting sweater", the word segmentation result displays "some card-1", "knitting-1-2", "knitting-1-3", "clothing-1-4", wherein a front bit in the digital mark represents which information belongs to the commodity information, and a rear bit in the digital mark represents a second word segmentation of the word segmentation in the commodity information.
103. Matching the word segmentation result with a preset category keyword library, obtaining category scores of the keywords according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity;
it should be noted that after the word segmentation result is obtained, the word segmentation result needs to be further matched with the preset category keyword library, each word in the word segmentation result is matched with the keyword library of each category of the preset category keyword library one by one, and each word is matched with the keyword in the keyword library of the previous category, that is, the corresponding category scoring is performed. And finally, the category to which the keyword library with the highest accumulated category score belongs is the category of the commodity.
According to the commodity information of the commodity, a preset word segmentation model is used for carrying out word segmentation analysis on the commodity to obtain word segmentation results, the word segmentation results are scored with matching results of a preset category keyword library to obtain scores of the word segmentation results in each category, so that the weight of the category to which the commodity belongs is obtained, the category of the commodity is further obtained, and the technical problems of low efficiency, commodity classification solidification and judgment result deviation of the existing cross-border commodity classification are solved by means of automatic and scientific modes of word segmentation, matching and scoring.
Referring to fig. 2, fig. 2 is a flowchart illustrating a second method of classifying commodities in a cross-border bonded bin according to an embodiment of the present application, as shown in fig. 2, specifically:
201. constructing at least one category of a cross-border commodity;
it should be noted that, before performing matching of the word segmentation result, at least one category of the cross-border product needs to be constructed first, and the constructed category covers category information of most cross-border products according to actual requirements.
202. Constructing a keyword library of categories, wherein the keyword library comprises at least one keyword associated with the categories;
it should be noted that, common keywords of each category are defined empirically, so as to construct a keyword library forming the category, for example, the category is "makeup", and the corresponding keyword library may include keywords such as "lipstick", "pressed powder", "eyeliner", and the like.
203. Correspondingly associating the categories with the keyword library to generate a preset category keyword library;
it should be noted that after the category and the keyword library are sequentially constructed, the category and the keyword library are associated to generate a preset category keyword library, so as to prepare for matching of subsequent word segmentation.
204. Acquiring commodity information of commodities to enter a cross-border bonded bin;
it should be noted that, for a commodity to enter the cross-border bonded warehouse, commodity information needs to be obtained first, and the commodity information may generally include information such as a commodity name, a commodity component, a commodity origin, and a commodity customs classification.
205. Analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
it should be noted that after the commodity information is obtained, the commodity information is subjected to word segmentation processing by using a preset word segmentation model, the complete commodity information is segmented into single words, a word segmentation result of the commodity is output, the word segmentation result contains position information of each word segmentation in the original commodity information besides the single word segmentation of the commodity, for example, a commodity name in the commodity information is called "some card knitting sweater", the word segmentation result displays "some card-1", "knitting-1-2", "knitting-1-3", "clothing-1-4", wherein a front bit in the digital mark represents which information belongs to the commodity information, and a rear bit in the digital mark represents a second word segmentation of the word segmentation in the commodity information.
206. Matching the word segmentation of the word segmentation result with the keywords of a preset category keyword library one by one;
it should be noted that the word segmentation in the obtained word segmentation result is matched with the keywords in the preset category keyword library one by one.
207. According to the position weight of the participles in the commodity information, performing category scoring on the matched keywords;
it should be noted that after the segmentation is matched with the keywords in the preset category keyword library, the category scoring is performed on the matched keywords according to the positions and weights of the segmentation in the commodity information displayed in the segmentation result.
208. And taking the category to which the keyword library with the highest category score belongs as the category of the commodity.
It should be noted that the category to which the keyword library with the highest final cumulative category score belongs is the category of the product.
According to the commodity information of the commodity, a preset word segmentation model is used for carrying out word segmentation analysis on the commodity to obtain word segmentation results, the word segmentation results are scored with matching results of a preset category keyword library to obtain scores of the word segmentation results in each category, so that the weight of the category to which the commodity belongs is obtained, the category of the commodity is further obtained, and the technical problems of low efficiency, commodity classification solidification and judgment result deviation of the existing cross-border commodity classification are solved by means of automatic and scientific modes of word segmentation, matching and scoring. Furthermore, the influence of the keywords on the commodities is more accurate by considering the position weight of the participles in the commodity information, so that the commodity classification accuracy is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a third method of classifying commodities in a cross-border bonded bin according to an embodiment of the present application, as shown in fig. 3, specifically:
301. acquiring commodity information of commodities to enter a cross-border bonded bin;
it should be noted that, for a commodity to enter the cross-border bonded warehouse, commodity information needs to be obtained first, and the commodity information may generally include information such as a commodity name, a commodity component, a commodity origin, and a commodity customs classification.
302. Analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
it should be noted that after the commodity information is obtained, the commodity information is subjected to word segmentation processing by using a preset word segmentation model, the complete commodity information is segmented into single words, a word segmentation result of the commodity is output, the word segmentation result contains position information of each word segmentation in the original commodity information besides the single word segmentation of the commodity, for example, a commodity name in the commodity information is called "some card knitting sweater", the word segmentation result displays "some card-1", "knitting-1-2", "knitting-1-3", "clothing-1-4", wherein a front bit in the digital mark represents which information belongs to the commodity information, and a rear bit in the digital mark represents a second word segmentation of the word segmentation in the commodity information.
303. Matching the word segmentation result with a preset category keyword library, obtaining category scores of the keywords according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity;
it should be noted that after the word segmentation result is obtained, the word segmentation result needs to be further matched with the preset category keyword library, each word in the word segmentation result is matched with the keyword library of each category of the preset category keyword library one by one, and each word is matched with the keyword in the keyword library of the previous category, that is, the corresponding category scoring is performed. And finally, the category to which the keyword library with the highest accumulated category score belongs is the category of the commodity.
304. Constructing a training sample set, wherein the training sample set comprises training commodity information and training classification categories, and the training classification categories are target labels;
it should be noted that, a training sample set is further constructed to train the commodity classification neural network model, where the training sample set includes training commodity information and training classification categories, where the training classification categories are target labels, that is, the commodity information and the classification categories are mapped by training the commodity classification neural network model.
305. Training the commodity classification neural network model through a training sample set to obtain a preset commodity classification neural network model;
it should be noted that after the training sample set is constructed, the commodity classification neural network model is trained to obtain a preset commodity classification neural network model.
306. If the highest category score is lower than a preset threshold value, commodity information of the commodity is used as input, and a prediction classification result and a prediction percentage thereof are obtained by utilizing a preset commodity classification neural network model;
it should be noted that if the highest category score is lower than the preset threshold, the category is not representative enough, and commodity information of the commodity needs to be further input into the preset commodity classification neural network model, so as to obtain various prediction classification results and prediction percentages thereof through the preset commodity classification neural network.
307. Taking the prediction classification result with the highest prediction percentage as the final classification category of the commodity;
it should be noted that the prediction classification result with the highest prediction percentage is the final classification category of the product.
308. And if the highest category score is higher than a preset threshold value, adding commodity information of the commodities and the category of the commodities into the training sample set.
It should be noted that, if the highest category score is higher than the preset threshold, which indicates that the classification category is representative, the commodity information and the classification category of the commodity can be further used as a training sample of the preset commodity classification neural network, and the training sample set is added to further optimize the preset commodity classification neural network.
Referring to fig. 4, fig. 4 is a first schematic structural diagram of a cross-border bonded bin commodity sorting device according to an embodiment of the present application, as shown in fig. 4, specifically:
an obtaining unit 401, configured to obtain commodity information of a commodity to enter a cross-border bonded bin;
the analysis unit 402 is configured to analyze the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
the first classification unit 403 is configured to match the word segmentation result with a preset category keyword library, obtain a category score of the keyword according to the matching result, and use the category to which the keyword library with the highest category score belongs as the classification category of the commodity.
Referring to fig. 5, fig. 5 is a second schematic structural diagram of a cross-border bonded bin commodity sorting device according to an embodiment of the present application, as shown in fig. 5, specifically:
a first construction unit 501, configured to construct at least one category of a cross-border commodity;
a second constructing unit 502, configured to construct a keyword library of categories, where the keyword library includes at least one keyword associated with a category;
the associating unit 503 is configured to associate the category with the keyword library correspondingly, and generate a preset category keyword library;
an obtaining unit 504, configured to obtain commodity information of a commodity to enter the cross-border bonded bin;
the analysis unit 505 is configured to analyze the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
the first classification unit 506 is configured to match the word segmentation result with a preset category keyword library, obtain a category score of the keyword according to the matching result, and use the category to which the keyword library with the highest category score belongs as the classification category of the commodity.
Referring to fig. 6, fig. 6 is a third schematic structural diagram of a cross-border bonded bin commodity classification device in an embodiment of the present application, as shown in fig. 6, specifically:
an obtaining unit 601, configured to obtain commodity information of a commodity to enter a cross-border bonded bin;
the analysis unit 602 is configured to analyze the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
a first classification unit 603, configured to match the word segmentation result with a preset category keyword library, obtain a category score of the keyword according to the matching result, and use a category to which the keyword library with the highest category score belongs as a classification category of the commodity;
a third constructing unit 604, configured to construct a training sample set, where the training sample set includes training commodity information and training classification categories, and the training classification categories are target labels;
the training unit 605 is configured to train the commodity classification neural network model through a training sample set to obtain a preset commodity classification neural network model;
the prediction unit 606 is configured to, if the highest category score is lower than a preset threshold, take commodity information of a commodity as input, and obtain a prediction classification result and a prediction percentage thereof by using a preset commodity classification neural network model;
and a second classification unit 607 for using the prediction classification result with the highest prediction percentage as the final classification category of the commodity.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A cross-border bonded bin commodity classification method is characterized by comprising the following steps:
acquiring commodity information of commodities to enter a cross-border bonded bin;
analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
and matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity.
2. The cross-border bonded bin commodity classification method according to claim 1, wherein before matching the word segmentation result with a preset category keyword library, the method further comprises:
constructing at least one category of a cross-border commodity;
constructing a keyword library of the category, wherein the keyword library comprises at least one keyword associated with the category;
and correspondingly associating the categories with the keyword library to generate a preset category keyword library.
3. The cross-border bonded bin commodity classification method according to claim 2, wherein the step of matching the word segmentation result with a preset category keyword library, obtaining a category score of a keyword according to the matching result, and the step of taking a category to which the keyword library with the highest category score belongs as the classification category of the commodity specifically comprises the steps of:
matching the word segmentation of the word segmentation result with the keywords of a preset category keyword library one by one;
according to the position weight of the word segmentation in the commodity information, performing category scoring on the matched keywords;
and taking the category to which the keyword library with the highest category score belongs as the category of the commodity.
4. The method for classifying commodities in a cross-border bonded bin according to claim 1, wherein the step of matching the word segmentation result with a preset category keyword library, obtaining a category score of a keyword according to the matching result, and the step of taking a category to which the keyword library with the highest category score belongs as the classification category of the commodities further comprises the steps of:
if the highest category score is lower than a preset threshold value, commodity information of the commodity is used as input, and a prediction classification result and a prediction percentage thereof are obtained by utilizing a preset commodity classification neural network model;
and taking the prediction classification result with the highest prediction percentage as the final classification category of the commodity.
5. The cross-border bonded bin commodity classification method according to claim 4, further comprising:
constructing a training sample set, wherein the training sample set comprises training commodity information and training classification categories, and the training classification categories are target labels;
and training the commodity classification neural network model through the training sample set to obtain a preset commodity classification neural network model.
6. The method for classifying commodities in a cross-border bonded bin according to claim 5, wherein the step of matching the word segmentation result with a preset category keyword library, obtaining a category score of a keyword according to the matching result, and the step of taking the category to which the keyword library with the highest category score belongs as the classification category of the commodities further comprises the steps of:
and if the highest category score is higher than the preset threshold value, adding the commodity information of the commodity and the classification category of the commodity into the training sample set.
7. A cross-border bonded bin commodity classification device, comprising:
the acquiring unit is used for acquiring commodity information of commodities to enter the cross-border bonded bin;
the analysis unit is used for analyzing the commodity information by using a preset word segmentation model to obtain a word segmentation result of the commodity;
and the first classification unit is used for matching the word segmentation result with a preset category keyword library, obtaining a category score of the keyword according to the matching result, and taking the category to which the keyword library with the highest category score belongs as the classification category of the commodity.
8. The cross-border bonded bin commodity sorting device according to claim 7, further comprising:
the first construction unit is used for constructing at least one category of the cross-border commodities;
the second construction unit is used for constructing a keyword library of the category, and the keyword library comprises at least one keyword associated with the category;
and the association unit is used for correspondingly associating the categories with the keyword library to generate a preset category keyword library.
9. The cross-border bonded bin commodity sorting device according to claim 7, further comprising:
the prediction unit is used for taking the commodity information of the commodity as input and obtaining a prediction classification result and a prediction percentage thereof by utilizing a preset commodity classification neural network model if the highest category score is lower than a preset threshold value;
and the second classification unit is used for taking the prediction classification result with the highest prediction percentage as the final classification category of the commodity.
10. The cross-border bonded bin commodity sorting device of claim 9, further comprising:
the third construction unit is used for constructing a training sample set, wherein the training sample set comprises training commodity information and training classification categories, and the training classification categories are target labels;
and the training unit is used for training the commodity classification neural network model through a training sample set to obtain a preset commodity classification neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110070797.2A CN112767081A (en) | 2021-01-19 | 2021-01-19 | Cross-border bonded bin commodity classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110070797.2A CN112767081A (en) | 2021-01-19 | 2021-01-19 | Cross-border bonded bin commodity classification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112767081A true CN112767081A (en) | 2021-05-07 |
Family
ID=75703234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110070797.2A Pending CN112767081A (en) | 2021-01-19 | 2021-01-19 | Cross-border bonded bin commodity classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112767081A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420196A (en) * | 2021-06-07 | 2021-09-21 | 青岛海信智慧生活科技股份有限公司 | Commodity category determination method, device, equipment and medium |
| CN113674054A (en) * | 2021-08-13 | 2021-11-19 | 青岛海信智慧生活科技股份有限公司 | Configuration method, device and system of commodity categories |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704892A (en) * | 2017-11-07 | 2018-02-16 | 宁波爱信诺航天信息有限公司 | A kind of commodity code sorting technique and system based on Bayesian model |
| CN110490712A (en) * | 2019-08-21 | 2019-11-22 | 浙江中国轻纺城网络有限公司 | A kind of commodity class heading search method, system and storage medium |
| CN110597995A (en) * | 2019-09-20 | 2019-12-20 | 税友软件集团股份有限公司 | Commodity name classification method, commodity name classification device, commodity name classification equipment and readable storage medium |
| CN110766486A (en) * | 2018-07-09 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for determining item category |
-
2021
- 2021-01-19 CN CN202110070797.2A patent/CN112767081A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704892A (en) * | 2017-11-07 | 2018-02-16 | 宁波爱信诺航天信息有限公司 | A kind of commodity code sorting technique and system based on Bayesian model |
| CN110766486A (en) * | 2018-07-09 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for determining item category |
| CN110490712A (en) * | 2019-08-21 | 2019-11-22 | 浙江中国轻纺城网络有限公司 | A kind of commodity class heading search method, system and storage medium |
| CN110597995A (en) * | 2019-09-20 | 2019-12-20 | 税友软件集团股份有限公司 | Commodity name classification method, commodity name classification device, commodity name classification equipment and readable storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420196A (en) * | 2021-06-07 | 2021-09-21 | 青岛海信智慧生活科技股份有限公司 | Commodity category determination method, device, equipment and medium |
| CN113674054A (en) * | 2021-08-13 | 2021-11-19 | 青岛海信智慧生活科技股份有限公司 | Configuration method, device and system of commodity categories |
| CN113674054B (en) * | 2021-08-13 | 2023-12-05 | 青岛海信智慧生活科技股份有限公司 | Commodity category configuration method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223168B (en) | Label propagation anti-fraud detection method and system based on enterprise relationship map | |
| CN106485562B (en) | Commodity information recommendation method and system based on user historical behaviors | |
| CN109872162A (en) | A kind of air control classifying identification method and system handling customer complaint information | |
| CN106326248A (en) | A storage method and device for data of databases | |
| CN106991175A (en) | A kind of customer information method for digging, device, equipment and storage medium | |
| CN112767081A (en) | Cross-border bonded bin commodity classification method and device | |
| US20190392295A1 (en) | Information processing device, method, and program that use deep learning | |
| Choudhury et al. | A machine learning approach to identify potential customer based on purchase behavior | |
| CN113204603B (en) | Category labeling method and device for financial data assets | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN112685635A (en) | Item recommendation method, device, server and storage medium based on classification label | |
| CN112395881A (en) | Material label construction method and device, readable storage medium and electronic equipment | |
| CN111833073A (en) | Airline customer segmentation method based on K-Means + + algorithm | |
| KR20210001649A (en) | A program for predicting corporate default | |
| KR20210001625A (en) | A method and an apparatus for providing services of corporate insolvencies information based on automatic sentiment information labelings to news articles | |
| CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
| Alsaç et al. | An integrated customer relationship management and Data Mining framework for customer classification and risk analysis in health sector | |
| CN114155057A (en) | Commodity recommendation system for electronic commerce platform | |
| CN113505117A (en) | Data quality evaluation method, device, equipment and medium based on data indexes | |
| CN112100202A (en) | Product identification and product information completion method, storage medium and robot | |
| KR20210001645A (en) | A method for predicting corporate default | |
| KR20210001707A (en) | An apparatus for providing services of corporate insolvencies information based on automatic sentiment information labelings to news articles | |
| KR20210001670A (en) | A program for predicting corporate default | |
| KR20190104745A (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same | |
| KR20210001693A (en) | A rcording media for recording program for providing a corporate insolvencies information based on automatic sentiment information labelings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |