Commodity map acquisition method and device, equipment and storage medium

By obtaining user historical data and using preset models to process it, the product map is solved, and the problem of e-commerce platforms being difficult to update product planning in a rapidly changing market is achieved, and the rapid iteration of product planning and operational efficiency are improved.

CN119066206APending Publication Date: 2024-12-03阿里巴巴(中国)网络技术有限公司
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411008990.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the rapidly changing market environment, it is difficult for e-commerce platforms to quickly and efficiently capture market information and update product planning methods, resulting in inappropriate planning methods being difficult to eliminate, and there is a lack of semi-automatic or fully automated product organization forms.

Method used

By obtaining user historical data, using trained preset models to process the data, generating product standard data, building category trees, forming product maps, and realizing automatic construction and update of product maps.

Benefits of technology

It has achieved rapid iteration of commodity planning, improved operational efficiency, reduced labor costs, and provided a faster, richer and lower cost commodity organization system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066206A_ABST
    Figure CN119066206A_ABST
Patent Text Reader

Abstract

The invention provides a commodity map acquisition method and device, equipment and a storage medium, and relates to the technical field of e-commerce platform operation. The commodity map acquisition method comprises the following steps: acquiring commodity initial data; performing data processing on the commodity initial data through a trained preset model to generate commodity standard data; and generating a category tree based on the commodity standard data to construct a commodity map corresponding to the category tree. According to the embodiment of the invention, the method can achieve the automatic construction of the commodity map of the CFV system, carries out the real-time automatic updating of data, and meets the intelligent selection demands of an e-commerce platform.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of e-commerce platform operation, and more specifically, to a method, device, equipment and storage medium for obtaining a product map. Background Art

[0002] In the current e-commerce field, product planning is a common and huge topic. The more concentrated issue is how to select the most suitable products for sale based on platform product indicators, product CPV (Category Property Value) and other historical performance and professional knowledge data.

[0003] At this stage, consumer demands and market category structures are changing very rapidly. How to quickly and efficiently capture market information in the face of new concepts, new elements and new trends that are constantly being incubated, so that the platform's product planning methods can self-learn and iterate, gradually eliminate some outdated planning methods, and ultimately achieve the update of semi-automatic or fully automated product organization forms is an important proposition and challenge. Summary of the invention

[0004] According to one aspect of the present application, a method for obtaining a product map is provided, including: obtaining initial product data; performing data processing on the initial product data through a trained preset model to generate product standard data; generating a category tree based on the product standard data to construct a product map corresponding to the category tree.

[0005] According to some embodiments, obtaining initial data of a product includes: obtaining user history data; obtaining entity types of the product from the user history data; and identifying core words of the product from the user history data based on the entity types as initial data of the product, wherein the core words of the product include categories, decision factors, and variables of the product.

[0006] According to some embodiments, the initial data of the goods are processed through a trained preset model to generate standard data for the goods, including: obtaining consumption decision attribute data from user historical data; generating a standard factor dictionary of decision factors based on the consumption decision attribute data and entity type; based on the standard factor dictionary, the initial data of the goods are screened through a preset model to generate standard data for the goods.

[0007] According to some embodiments, the preset model includes a first model, a second model and a third model; based on the standard factor dictionary, the initial data of the commodity is screened through the preset model to generate standard data of the commodity, including: preprocessing the initial data of the commodity, including standardization and normalization; obtaining preset prompt words; according to the prompt words, determining through the first model whether the categories and variables in the preprocessed initial data of the commodity match the standard factor dictionary; screening the categories and variables that match the standard factor dictionary through the second model and the third model to obtain standard data of the commodity.

[0008] According to some embodiments, based on the prompt words, a first model is used to determine whether the categories and variables in the preprocessed initial data of the commodity match the standard factor dictionary, including: if the categories and variables match the standard factor dictionary, heat marking the categories and variables; if the categories and variables do not match the standard factor dictionary, clearing the categories and variables.

[0009] According to some embodiments, based on the standard factor dictionary, the initial data of the goods are screened through a preset model to generate standard data of the goods, and also include: generating a synonym dictionary of categories and a synonym dictionary of variables respectively according to the preprocessed initial data of the goods.

[0010] According to some embodiments, the categories and variables that match the standard factor dictionary are screened through the second model and the third model to obtain commodity standard data, including: based on the synonym dictionary of the category, identifying the decision factors corresponding to the category through the second model; based on the synonym dictionary of the variable, classifying the variables according to the standard factor dictionary of the decision factors through the third model; and combining the category, the decision factors corresponding to the category, and the variables classified according to the standard factor dictionary of the decision factors into commodity standard data.

[0011] According to some embodiments, a category tree is generated based on commodity standard data to construct a commodity map corresponding to the category tree, including: determining the location of the commodity based on the commodity standard data to generate a category tree; and adding the commodity to the corresponding position of the category tree to construct the commodity map.

[0012] According to one aspect of the present application, a device for acquiring a product map is provided, including: an acquisition module for acquiring initial product data; a processing module for processing the initial product data through a trained preset model to generate standard product data; and a construction module for generating a category tree based on the standard product data to construct a product map corresponding to the category tree.

[0013] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the aforementioned method.

[0014] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the method as described above is implemented.

[0015] According to the embodiments of the present application, by combining a model based on generative AI technology with user data of the e-commerce platform, the product map of the e-commerce platform is automatically constructed, and the product map data is automatically updated, providing a faster, richer, and lower-cost CFV system solution for product planning, improving operational efficiency, and reducing labor costs.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application.

[0018] Figure 1 A flowchart of a method for acquiring a product map according to an exemplary embodiment of the present application is shown.

[0019] Figure 2 A flowchart of generating commodity standard data according to an exemplary embodiment of the present application is shown.

[0020] Figure 3 A block diagram of a device for acquiring a product graph according to an exemplary embodiment of the present application is shown.

[0021] Figure 4 A block diagram of an electronic device according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0023] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0024] The described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application may be put into practice without one or more of these specific details, or other modes, components, materials, devices or operations may be adopted. In these cases, known structures, methods, devices, realizations, materials or operations will not be shown or described in detail.

[0025] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0026] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0027] The present application provides a method, device, equipment and storage medium for obtaining a product map, which can realize the automatic construction and update of the product map of an e-commerce platform.

[0028] A method, device, equipment and storage medium for obtaining a product map according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0029] This application refers to the following terms:

[0030] CFV (Category Factor Variable): A relational structure of a product graph based on user decision factors.

[0031] Product graph: A data structure that describes products and is used to store and organize information. It is mainly used in various product delivery scenarios, such as search engines, recommendation systems, shopping guide venues, etc.

[0032] LangEngine: An AI application development framework based on LangChain advanced ideas and Java language, mainly used for LLM engineering modularization capability implementation and can be used for the development and construction of intelligent entities.

[0033] Figure 1 A flowchart of a method for acquiring a product map according to an exemplary embodiment of the present application is shown.

[0034] like Figure 1 As shown, in step S110, the acquisition device acquires initial data of the commodity.

[0035] For example, in step S110, the acquisition device identifies the core words of the product through the user's historical data, and uses the core words as the initial data of the product.

[0036] The acquisition device acquires user history data of the entire network including the platform, wherein the user history data includes user behavior data of the entire network and user behavior logs of the platform.

[0037] According to some embodiments, the user behavior logs of the platform include search terms, trending hot words and other behaviors, which can be obtained through the platform's product information and data embedding. The user behavior data of the entire network can be obtained through data cooperation between different platforms within the entire network.

[0038] The acquisition device acquires the entity type of the commodity from the user's historical data.

[0039] According to some embodiments, the acquisition device may extract the entity type of the product from the user's historical data through the NER (Named Entity Recognition) technology. The entity type of the product includes color, brand, material (such as wood or metal), style (such as sleeve type or collar type), size specification, seasonal festival and functional effect, etc.

[0040] According to the entity type of the commodity, the acquisition device identifies the core words of the commodity from the user's historical data, wherein the core words of the commodity include the category of the commodity, the user's decision factor for purchasing the commodity (hereinafter referred to as the decision factor) and variables.

[0041] According to some embodiments, the core words of the products are distinguished and identified according to the entity type of the products. For example, the core words of the products are retro chic plaid shirt jacket women's spring and autumn 2024 new loose lazy style long-sleeved cardigan shirt, which can be split according to the entity type, and the categories of the products are identified as shirts, jackets, and cardigans, the applicable season is spring and autumn, the style is new and loose, and the style is lazy style.

[0042] The acquisition device uses the identified commodity core words as the commodity initial data for constructing a commodity map.

[0043] In step S120, the acquisition device processes the initial data of the commodity through the trained preset model to generate standard data of the commodity.

[0044] For example, in step S120, the acquisition device first generates a standard factor dictionary of decision factors, and processes the initial data of the commodity through a pre-trained preset model to generate standard data of the commodity.

[0045] The acquisition device acquires the user's consumption decision attribute data from the user's historical data.

[0046] According to some embodiments, the acquisition device may first acquire the commodity CPV data reported by the platform merchants in the user's historical data, and mark the attributes that affect the user's consumption decision as consumption decision attribute data.

[0047] According to the consumption decision attribute data and the entity type of the commodity obtained from the user's historical data, the acquisition device initially defines the user's decision factor and forms a standard factor dictionary of the decision factor.

[0048] Based on the standard factor dictionary, the acquisition device screens the initial data of the goods through a trained preset model to generate standard data of the goods.

[0049] According to some embodiments, the preset model includes a first model, a second model, and a third model. The first model, the second model, and the third model are all pre-trained large models (such as the Qwen_7B large model), which have the same model base and can perform different types of tasks through knowledge fine-tuning.

[0050] First, the acquisition device preprocesses the initial data of the commodity, and determines whether the categories and variables in the preprocessed initial data of the commodity match the standard factor dictionary through the first model in combination with the acquired preset prompt words.

[0051] Furthermore, the acquisition device screens commodity categories and variables that match the standard factor dictionary in the commodity initial data through the second model and the third model to acquire commodity standard data.

[0052] According to some embodiments, the commodity standard data includes commodity categories, decision factors corresponding to the categories, and variables classified according to the standard factor dictionary of the decision factors.

[0053] In step S130, the acquisition device generates a category tree based on the commodity standard data to construct a commodity map corresponding to the category tree.

[0054] For example, in step S130, the acquisition device determines the location of the commodity through the commodity standard data, and generates a category tree of the commodity for use in constructing a commodity map.

[0055] According to the categories of commodities in the commodity standard data and corresponding variables, the acquisition device searches and determines the position location of the commodities of the current category in the platform to form a category path of the commodities of the current category.

[0056] According to a plurality of category paths respectively formed by the position positioning of the commodities of the determined plurality of categories, the acquisition device generates a corresponding category tree.

[0057] For example, a new product of the roasted milk tea category is added to the platform. The acquisition device determines that it belongs to the "food" in the first-level category "shoes, clothing, food, etc." in the commodity standard data based on the commodity standard data. Further, the acquisition device determines that the roasted milk tea category belongs to the "beverages" in the next-level category "food, beverages, ice products, etc." of "food". Finally, the acquisition device locates the roasted milk tea category in the "milk tea beverage" in the next-level category of "beverages". Furthermore, the acquisition device generates a category path for the roasted milk tea category product as "food"-"beverages"-"milk tea beverages".

[0058] According to some embodiments, the acquisition device may determine the location of the commodity through an agent implemented based on the LangEngine framework and the breadth-first algorithm.

[0059] The acquisition device adds the commodities of each category in the platform to the corresponding positions of the category tree accordingly to construct the commodity map of the platform.

[0060] According to some embodiments, the acquisition device may periodically synchronize the product graph to the graph management module of the platform to evaluate and update the product graph.

[0061] According to the embodiments of the present application, the platform's product map can be automatically constructed by combining a model based on generative AI technology with user data, so that the platform can use more product features that users understand to launch products, thereby improving operational efficiency and user experience.

[0062] Figure 2 A flowchart of generating commodity standard data according to an exemplary embodiment of the present application is shown.

[0063] like Figure 2 As shown, in step S210, the acquisition device pre-processes the initial data of the commodity.

[0064] For example, in step S210, the acquisition device pre-processes the initial commodity data acquired from the user history data.

[0065] After identifying the commodity core words as the commodity initial data from the user history data, the acquisition device pre-processes the commodity initial data to prepare data for the generation of commodity standard data.

[0066] According to some embodiments, the preprocessing of the initial data of the commodity includes standardization and normalization. For example, the acquisition device may perform standardization on the initial data of the commodity according to a preset data format of the platform. Further, the acquisition device may perform normalization on the standardized initial data of the commodity according to the e-commerce text embedded in the platform.

[0067] According to some embodiments, after preprocessing the initial data of the commodity, the acquisition device generates a synonym dictionary of the commodity category and a synonym dictionary of the variable based on the initial data of the commodity.

[0068] In step S220, the acquisition device determines whether the categories and variables in the preprocessed initial commodity data match the standard factor dictionary through a preset first model.

[0069] For example, in step S220, according to the preset prompt words, the acquisition device reviews the preprocessed initial commodity data through the preset first model to determine whether the categories and variables therein match the generated standard factor dictionary.

[0070] The acquisition device acquires a preset prompt word, and sets a first model that has been fine-tuned using corresponding selected data and strategies in response to an instruction from the platform.

[0071] According to some embodiments, the first model is a pre-trained large model that has been pre-trained.

[0072] According to the preset prompt words, the acquisition device determines through the first model whether the categories and variables in the preprocessed initial data of the commodity match the standard factor dictionary of the generated decision factors, so as to identify and clean up unreasonable categories and variables in the initial data of the commodity.

[0073] According to some embodiments, when the categories and variables in the preprocessed initial commodity data do not match the standard factor dictionary, the acquisition device clears the corresponding unmatched categories and variables.

[0074] According to some embodiments, when the categories and variables in the preprocessed initial data of the product match the standard factor dictionary, the acquisition device heat-marks the matching categories and variables through the heat of the user behavior log in the user history data and the entity type of the product.

[0075] In step S230, the acquisition device screens the categories and variables that match the standard factor dictionary through the preset second model and third model to obtain commodity standard data.

[0076] For example, in step S230, the acquisition device screens the categories and variables that match the standard factor dictionary through the preset second model and third model respectively, and combines the screened product categories, decision factors and variables into product standard data.

[0077] Based on the generated synonym dictionary of the category, the acquisition device identifies the decision factors corresponding to the category of the commodity cleaned by the first model through the second model.

[0078] Similarly, based on the generated synonym dictionary of the variables, the acquisition device classifies the variables cleaned by the first model according to the standard factor dictionary of the decision factors through the third model.

[0079] According to some embodiments, the second model and the third model are both pre-trained large models that have been pre-trained, and the second model, the third model and the first model have the same model base.

[0080] The second model fine-tunes the model through the training data of the preset category decision factor identification, so as to identify the most suitable decision factor corresponding to the category according to the standard factor dictionary of decision factors. For example, the category of cultural type of names such as "The Wandering Earth" and "Jay Chou" has its corresponding decision factor identified by the second model as "IP co-branding" in the standard factor dictionary.

[0081] The third model is fine-tuned through the training data of the preset variable classification to classify the variables according to the standard factor dictionary of the generated decision factors to achieve multi-layer classification of the variables.

[0082] The acquisition device combines the categories of commodities, the decision factors corresponding to the categories, and the variables classified according to the standard factor dictionary of the decision factors into commodity standard data for constructing a commodity map.

[0083] Figure 3 A block diagram of a device for acquiring a product graph according to an exemplary embodiment of the present application is shown.

[0084] like Figure 3 As shown, the acquisition device 100 includes an acquisition module 110 , a processing module 120 and a construction module 130 .

[0085] The acquisition module 110 acquires user history data of the entire network including the platform.

[0086] The acquisition module 110 acquires the entity type of the commodity from the user's historical data.

[0087] According to the entity type of the product, the acquisition module 110 identifies the core words of the product from the user's historical data.

[0088] The acquisition module 110 uses the identified product core words as the product initial data.

[0089] The processing module 120 obtains the user's consumption decision attribute data from the user's historical data.

[0090] According to the consumption decision attribute data and the entity type of the commodity obtained from the user's historical data, the processing module 120 initially defines the user's decision factors and forms a standard factor dictionary of the decision factors.

[0091] Based on the standard factor dictionary, the processing module 120 filters the initial commodity data through a trained preset model to generate commodity standard data.

[0092] According to the categories of the commodities in the commodity standard data and the corresponding variables, the construction module 130 searches and determines the location of the commodities of the current category in the platform to form a category path of the commodities of the current category.

[0093] According to a plurality of category paths respectively formed by the position positioning of the determined commodities of a plurality of categories, the construction module 130 generates a corresponding category tree.

[0094] The construction module 130 adds the commodities of each category in the platform to the corresponding positions of the category tree to construct the commodity map of the platform.

[0095] Figure 4 A block diagram of an electronic device according to an exemplary embodiment of the present application is shown.

[0096] like Figure 4 As shown, the electronic device 600 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0097] like Figure 4As shown, the electronic device 600 is in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc. The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the methods described in this specification according to various exemplary embodiments of the present application. For example, the processing unit 610 may execute the following: Figure 1 The method shown in .

[0098] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0099] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0100] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0101] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0102] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by combining software with necessary hardware. The technical solution according to the embodiment of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal or a network device, etc.) to execute the method according to the embodiment of the present application.

[0103] The software product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0104] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0105] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0106] The computer-readable medium carries one or more programs. When the one or more programs are executed by a device, the computer-readable medium implements the aforementioned functions.

[0107] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0108] The embodiments of the present application are described in detail above, and the description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, changes or deformations made by those skilled in the art based on the idea of ​​the present application, the specific implementation method and the scope of application of the present application, all belong to the scope of protection of the present application. In summary, the content of this specification should not be construed as limiting the present application.

Claims

1. A method for obtaining a product map, It is characterized in that include: Get the initial data of the product; Processing the initial data of the commodity by using a trained preset model to generate standard data of the commodity; A category tree is generated based on the commodity standard data to construct a commodity map corresponding to the category tree.

2. The method according to claim 1, It is characterized in that Get the initial product data, including: Get user historical data; Acquire the entity type of the commodity from the user history data; Based on the entity type, the core words of the product are identified from the user history data to serve as the initial data of the product, wherein the core words of the product include the category, decision factors and variables of the product.

3. The method according to claim 2, It is characterized in that The initial product data is processed by a trained preset model to generate product standard data, including: Acquire consumption decision attribute data from the user historical data; generating a standard factor dictionary of the decision factor according to the consumption decision attribute data and the entity type; Based on the standard factor dictionary, the commodity initial data is screened by the preset model to generate the commodity standard data.

4. The method according to claim 3, It is characterized in that The preset models include a first model, a second model and a third model; Based on the standard factor dictionary, the initial product data is screened by the preset model to generate the product standard data, including: Preprocessing the initial data of the commodity, including standardization and normalization; Get the preset prompt words; According to the prompt word, determining through the first model whether the categories and variables in the preprocessed initial commodity data match the standard factor dictionary; The categories and variables matching the standard factor dictionary are screened through the second model and the third model to obtain the commodity standard data.

5. The method according to claim 4, It is characterized in that According to the prompt word, determining whether the categories and variables in the preprocessed initial commodity data match the standard factor dictionary through the first model includes: When the category and the variable match the standard factor dictionary, heat marking the category and the variable; In the case where the category and the variable do not match the standard factor dictionary, the category and the variable are cleared.

6. The method according to claim 4, It is characterized in that Based on the standard factor dictionary, the initial product data is screened by the preset model to generate the product standard data, and further includes: According to the preprocessed initial commodity data, a synonym dictionary of the category and a synonym dictionary of the variable are generated respectively.

7. The method according to claim 6, It is characterized in that The categories and variables matching the standard factor dictionary are screened by the second model and the third model to obtain the commodity standard data, including: Based on the synonym dictionary of the category, identifying the decision factor corresponding to the category through the second model; Based on the synonym dictionary of the variable, classifying the variable according to the standard factor dictionary of the decision factor through the third model; and The categories, decision factors corresponding to the categories, and variables classified according to the standard factor dictionary of the decision factors are combined into the commodity standard data.

8. The method according to claim 1, It is characterized in that Generating a category tree based on the commodity standard data to construct a commodity map corresponding to the category tree includes: Determine the location of the commodity according to the commodity standard data to generate the category tree; Add products to corresponding positions of the category tree to construct the product map.

9. A device for obtaining a commodity map, It is characterized in that include: The acquisition module is used to obtain the initial data of the product; A processing module, used for processing the initial commodity data by using a trained preset model to generate commodity standard data; A construction module is used to generate a category tree based on the commodity standard data to construct a commodity map corresponding to the category tree.

10. An electronic device, It is characterized in that include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instruction stored thereon, It is characterized in that When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Intelligent recommendation and dynamic matching method of purchase model

    CN122547957A

  • Intelligent recommendation and dynamic matching method for procurement templates

    CN122547957B