Commodity information processing method, system and equipment based on aggregation platform

Abstract

The invention provides a commodity information processing method, system and equipment based on an aggregation platform. The method comprises the following steps: acquiring commodity information of commodities published by a third-party platform; performing structured analysis and normalization processing on the commodity information to obtain structured text information of the commodity; traversing a database comprising the structured text information of all system commodities of the aggregation platform, calculating semantic similarity between the structured text information of the commodities and the structured text information of each system commodity in the database, and determining the system commodity corresponding to the highest semantic similarity in a preset threshold, and generating a second mapping relationship between the commodity and the system commodity. According to the invention, the commodity mapping relation configuration and maintenance of the third-party platform and the aggregation platform can be completed efficiently and flexibly.

Description

Technical Field

[0001] This application relates to the field of computer information processing technology, and in particular to a technology for processing commodity information based on an aggregation platform. Background Technology

[0002] In the field of digital operations in the food and beverage retail industry, SPU (Standard Product Unit) and SKU (Stock Keeping Unit) are core concepts for merchandise management on instant retail service platforms. An SPU defines the basic attributes of a standardized food and beverage product (e.g., Kung Pao Chicken), while an SKU defines the smallest available unit for inventory control (e.g., Kung Pao Chicken - Large, Kung Pao Chicken - Small). Furthermore, food and beverage products may also include different attribute dimensions, such as spiciness (not spicy, mild, medium, hot), condiments (with / without scallions, with / without cilantro), and preparation methods (with ice, without ice, 70% sugar), etc.

[0003] Different instant retail service platforms typically define and maintain their own product data structures and coding systems, which are independent of each other and incompatible. For example, the data structures of the same product A- in instant retail service platforms 1 and 2 are as follows: Figure 1 As shown, catering enterprises use their self-developed or third-party digital operation service providers' aggregation platform's store management system to connect with each authorized instant retail service platform. This establishes a mapping relationship between their system's products and the products on the instant retail service platforms. When receiving product orders from different instant retail service platforms based on their own defined product data structures and coding systems, the system can "translate" the different product data from each platform into a recognizable unified format, enabling smooth order acceptance, printing, production, and accounting processes. Existing technologies typically use static mapping tables, requiring manual configuration of the mapping relationship between each product on each instant retail service platform (e.g., product specifications / identifiers, attribute values ​​for various attribute dimensions, etc.). This method is inefficient and lacks flexibility, and it passively responds to changes in the product structure and / or coding of the instant retail service platforms, failing to adapt automatically and making timely maintenance difficult to guarantee.

[0004] Therefore, how to efficiently and flexibly configure the product mapping relationship with the instant retail service platform through the aggregation platform of the catering retail digital operation service provider, so as to process the product orders pushed by different instant retail service platforms in a timely manner, is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] To address the aforementioned technical problems, the purpose of this application is to provide a method, system, and device for processing commodity information based on an aggregation platform.

[0006] According to one aspect of this application, a product information processing method based on an aggregation platform is provided, wherein the method includes: Obtain product information for goods published on third-party platforms; The product information is subjected to structured parsing and normalization to obtain the structured text information of the product; Traverse the database containing structured text information of all system products on the aggregation platform, calculate the semantic similarity between the structured text information of the product and the structured text information of each system product in the database, determine the system product corresponding to the highest semantic similarity among the preset thresholds, and generate a second mapping relationship between the product and the system products.

[0007] Optionally, the structured parsing and normalization processing of the product information includes any one of the following: Based on preset rules, the product information is subjected to structured parsing and normalization processing; A large language model is used to perform structured parsing and normalization of the product information.

[0008] Optionally, the step of calculating the semantic similarity between the structured text information of the product and the structured text information of each system product in the database includes: Obtain the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database, respectively; Calculate the cosine of the angle between the first text vector and each second text vector, and determine the semantic similarity between the structured text information of the product and the structured text information of each system product in the database based on the cosine of the angle.

[0009] Optionally, the step of obtaining the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database includes: The structured text information of the product and the structured text information of each system product in the database are respectively input into the text vectorization model to obtain the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database.

[0010] Optionally, before calculating semantic similarity, the method includes: Based on a preset mapping table corresponding to the third-party platform, the structured text information of the product is matched. If the match fails, subsequent steps are executed.

[0011] Optionally, the matching includes any of the following: Encoding matching; Keyword matching.

[0012] Optionally, the product information processing method based on an aggregation platform further includes: Update the preset mapping lookup table according to the second mapping relationship.

[0013] Optionally, the product information processing method based on an aggregation platform further includes: The system receives product orders for the goods pushed by the third-party platform and converts these orders into system product orders for the aggregation platform according to the second mapping relationship.

[0014] According to another aspect of this application, a commodity information processing system based on an aggregation platform is provided, wherein the system includes: The first module is used to obtain product information of products published by third-party platforms; The second module is used to perform structured parsing and normalization processing on the product information to obtain the structured text information of the product; The fourth module is used to traverse the database of structured text information of all system products of the aggregation platform, calculate the semantic similarity between the structured text information of the product and the structured text information of each system product in the database, determine the system product corresponding to the highest semantic similarity among the preset thresholds, and generate a second mapping relationship between the product and the system products.

[0015] Compared with existing technologies, this application provides a product information processing method, system, and device based on an aggregation platform. The method includes: acquiring product information published by a third-party platform; performing structured parsing and normalization on the product information to obtain structured text information of the product; traversing a database containing structured text information of all system products from the aggregation platform; calculating the semantic similarity between the structured text information of the product and the structured text information of each system product in the database; determining the system product corresponding to the highest semantic similarity among preset thresholds; and generating a second mapping relationship between the product and the system products. This application acquires structured text information of products published by a third-party platform (instant retail service platform), calculates the semantic similarity between this information and the structured text information of system products in the database of the aggregation platform, determines the system product corresponding to the highest semantic similarity among preset thresholds as the corresponding mapped product, and generates a mapping relationship between the product on the third-party platform and the system products on the aggregation platform. This allows for efficient and flexible configuration and maintenance of the product mapping relationship between the third-party platform and the aggregation platform. Attached Figure Description

[0016] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 The diagram illustrates an exemplary data structure of the same product across two different instant retail service platforms. Figure 2 A schematic diagram is shown of a product information processing method based on an aggregation platform according to one aspect of this application; Figure 3 This application illustrates one aspect and an exemplary one. Figure 1 A schematic diagram of the data structure of an aggregation platform for the same product; Figure 4 A schematic diagram of a commodity information processing apparatus based on an aggregation platform according to another aspect of this application is shown. The same or similar reference numerals in the accompanying drawings represent the same or similar parts. Detailed Implementation

[0017] The present application will now be described in further detail with reference to the accompanying drawings.

[0018] In a typical configuration of various embodiments of this application, the method execution entity, each trusted party of the system, and / or each module of the device may include one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0019] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0020] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0021] To further illustrate the technical means adopted and the effects achieved in this application, the technical solution of this application will be clearly and completely described below in conjunction with the accompanying drawings and preferred embodiments.

[0022] Figure 2 The diagram illustrates a product information processing method based on an aggregation platform according to one aspect of this application, wherein one embodiment of the method includes: S201 Obtain product information for goods published on third-party platforms; S202 performs structured parsing and normalization on the product information to obtain the structured text information of the product; S204 iterates through the database containing structured text information of all system products on the aggregation platform, calculates the semantic similarity between the structured text information of the product and the structured text information of each system product in the database, determines the system product corresponding to the highest semantic similarity among the preset thresholds, and generates a second mapping relationship between the product and the system products.

[0023] In the application scenario of this application, the aggregation platform provided by the catering retail digital operation service provider can provide digital operation services for numerous merchants and their stores connected to different instant retail service platforms. Through the aggregation platform, it can receive product orders generated and pushed from different third-party platforms (instant retail service platforms) according to their self-defined product data structures and coding systems. Based on the mapping relationship between the products of the instant retail service platforms and the system products of the aggregation platform, the product orders are "translated" into system orders of the aggregation platform, smoothly completing processes such as order acceptance, printing, production, and accounting. The product information processing method based on the aggregation platform provided in this application can automatically configure the mapping relationship of the corresponding system products of the aggregation platform for products published by third parties, implemented through the aggregation platform 100 provided by the catering retail digital operation service provider. The aggregation platform includes computer equipment and / or cloud deployed with the necessary hardware and software environment. The computer equipment includes, but is not limited to, personal computers, laptops, industrial computers, servers, network hosts, single network servers, or network server clusters. The cloud consists of a large number of computers or network servers based on cloud computing, where cloud computing is a type of distributed computing, consisting of a virtual supercomputer composed of a group of loosely coupled computers. The computer equipment and / or cloud described herein are merely examples. Other existing or future equipment and / or resource sharing platforms that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0024] Digital operation service providers in the catering and retail industry can collect product information of goods that can be ordered online in the market. Based on the SKU level, they can define the system products and their information supported by their aggregation platform. According to the data structure and coding system of the products they support, they can build and maintain a database containing structured text information of all system products.

[0025] In this embodiment, in step S201, the aggregation platform 100 can obtain product information of products published by third-party platforms.

[0026] For third-party platforms that have been authorized to connect with the aggregation platform 100, the aggregation platform 100 can obtain product information for each product published by the third-party platform. The product information may be structured text information that conforms to the product data structure system of the third-party platform, or it may be natural language description information that does not conform.

[0027] Continuing in this embodiment, in step S202, the aggregation platform 100 can perform structured parsing and normalization processing on the product information of the product to obtain the structured text information of the product.

[0028] After acquiring product information, the aggregation platform 100 first performs structured parsing of the product information. For example, it parses the product information according to the product data structure and coding system of the third-party platform it belongs to, and then normalizes it by referring to the data structure system supported by the aggregation platform 100. This standardizes different information representing the same concept in product information from different third-party platforms (for example, the optional attribute values ​​of product attributes on different third-party platforms are represented in different forms, or separated by parentheses or brackets, commas or pauses), thereby obtaining structured text information of the product that conforms to the product data structure system of the aggregation platform 100, which can provide standardized data for subsequent processing. An example data structure of product A on an aggregation platform is as follows: Figure 3 As shown. When the aggregation platform 100 obtains natural language description information of products published by third-party platforms, such as "large portion of mildly spicy Kung Pao Chicken with cilantro", the aggregation platform 100 can perform structured parsing and normalization processing on the product information to obtain structured text information of the product that conforms to the product data structure system of the aggregation platform 100, such as {product name: "Kung Pao Chicken", specification: "large portion", attribute: "mildly spicy", condiment: ["cilantro"]}.

[0029] Continuing in this embodiment, after obtaining the structured text information of a product published by a third-party platform, in step S204, the aggregation platform 100 traverses the database containing the structured text information of all system products, calculates the semantic similarity between the structured text information of the product published by the third-party platform and the structured text information of each system product in the database, and determines one or more system products that meet a preset threshold based on the calculation results. If there are multiple system products, the system product with the highest semantic similarity is determined, thereby generating a second mapping relationship between the product published by the third-party platform and the system product of the aggregation platform 100.

[0030] The second mapping relationship should at least include the correspondence between the product ID of the third-party platform and the system product ID of the aggregation platform 100, and may also include the correspondence between the relevant attribute dimensions and attribute values ​​of the products of the third-party platform and the relevant attribute dimensions and attribute values ​​of the system products of the aggregation platform.

[0031] Optionally, in step S202, the structured parsing and normalization processing of the product information includes any one of the following: Based on preset rules, the product information is subjected to structured parsing and normalization processing; A large language model is used to perform structured parsing and normalization of the product information.

[0032] In this optional embodiment, based on the product data structure and coding system customized by the third-party platform and the product data structure and coding system customized by the aggregation platform 100, and by comparing the data structures and coding rules of both parties, rules for structured parsing and normalization of product information for the third-party platform can be pre-configured. When the aggregation platform 100 obtains the product information of the product published by the third-party platform, it can perform structured parsing and normalization of the product information according to the pre-configured rules to obtain structured text information of the product that conforms to the system product data structure and coding system of the aggregation platform 100.

[0033] In addition, large language models that have undergone pre-training and targeted fine-tuning, such as GBT and DeepSeek, can be used to perform structured parsing and normalization of the product information to obtain structured text information of the product that conforms to the system product data structure and coding system of the aggregation platform 100.

[0034] Optionally, in step S204, calculating the semantic similarity between the structured text information of the product and the structured text information of each system product in the database includes: Obtain the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database, respectively; Calculate the cosine of the angle between the first text vector and each second text vector, and determine the semantic similarity between the structured text information of the product and the structured text information of each system product in the database based on the cosine of the angle.

[0035] In this optional embodiment, the aggregation platform 100 can obtain the text vector of the structured text information of the goods published by the third-party platform as the first text vector, obtain the text vector of the structured text information of each system product in the database including the structured text information of all system products as the second text vector (each system product corresponds to a second text vector), then traverse the database, calculate the cosine value of the angle between the first text vector and each second text vector, and determine the semantic similarity between the structured text information of the product and the structured text information of each system product in the database based on each cosine value.

[0036] Optionally, the step of obtaining the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database includes: The structured text information of the product and the structured text information of each system product in the database are respectively input into the text vectorization model to obtain the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database.

[0037] In this optional embodiment, an existing text vectorization model can be used, such as OpenAI's text-embedding-3-small or Hugging Face's bge-small. The structured text information of the products published by the third-party platform can be input into the text vectorization model to obtain the text vector corresponding to the product, which serves as the first text vector. The structured text information of each system product in the database, which includes structured text information of all system products, can be input into the text vectorization model to obtain the text vector corresponding to each system product, which serves as the second text vector.

[0038] Optionally, prior to step S204, the method further includes: S203 performs matching processing on the structured text information of the product based on a preset mapping table corresponding to the third-party platform. If the matching fails, subsequent steps are executed.

[0039] In this optional embodiment, the mapping relationship between the products of the third-party platform and the system products of the aggregation platform 100, which was constructed in advance based on structured text information before obtaining the product information of the third-party platform, can be organized into a preset mapping lookup table. After the aggregation platform 100 obtains the structured text information of the products of the third-party platform through step S202, step S203 can be executed first to match the structured text information of the products with the relevant structured text information of each product of the third-party platform in the preset mapping lookup table. If the matching fails, step S204 is executed, which can improve processing efficiency.

[0040] Optionally, the matching includes any of the following: Encoding matching; Keyword matching.

[0041] In this optional embodiment, the product name encoding information in the structured text information of the product can be obtained and matched with the product name encoding information of each third-party platform in the preset mapping lookup table. If they are completely the same, the match is successful, indicating that the product has already established a mapping relationship with a certain system product of the aggregation platform 100, and there is no need to regenerate it.

[0042] In this process, keyword information (such as different attribute dimensions) in the structured text information of the product can also be obtained and matched with the keyword information in the structured text information of each third-party platform's product in the preset mapping table. If the same keyword exists, the match is successful, and it can also be assumed that the product has already established a mapping relationship with a certain system product of the aggregation platform 100, so there is no need to regenerate it.

[0043] To further improve efficiency, keyword matching can be performed again if the encoding match fails.

[0044] Optionally, the product information processing method based on an aggregation platform further includes: S205 Update the preset mapping lookup table according to the second mapping relationship.

[0045] In this optional embodiment, in step S205, the mapping relationship between the newly generated product and the corresponding system product of the aggregation platform 100 can be consolidated and supplemented into the preset mapping lookup table to update the preset mapping lookup table, which may improve the mapping matching efficiency of new products released by third-party platforms in the future.

[0046] Optionally, the product information processing method based on an aggregation platform further includes: S206 receives the product order pushed by the third-party platform and converts the product order into a system product order of the aggregation platform according to the second mapping relationship.

[0047] In this optional embodiment, when a merchant receives a product order for the product pushed by the third-party platform through the aggregation platform 100, the product order can be converted into a system product order of the aggregation platform 100 according to the second mapping relationship between the product and the relevant system products of the aggregation platform 100 generated in step S204, so as to ensure that the merchant can smoothly complete the processes of order acceptance, printing, production and accounting.

[0048] The product information processing method based on an aggregation platform, provided by the above embodiments and / or optional embodiments, involves the aggregation platform acquiring structured text information of products published by third-party platforms, calculating the semantic similarity between this information and the structured text information of system products in the aggregation platform's database, determining the system product with the highest semantic similarity among preset thresholds as the corresponding mapped product, and generating a mapping relationship between the third-party platform's product and the aggregation platform's system products. This method can efficiently and flexibly configure and maintain the product mapping relationship between third-party platforms and the aggregation platform. To improve efficiency, before calculating semantic similarity, the information is first matched with the structured text information already constructed in a preset mapping lookup table; semantic similarity is only calculated if a match fails.

[0049] Figure 4 The diagram illustrates a product information processing system based on an aggregation platform according to another aspect of this application, wherein, in one embodiment, the system includes: The first module 410 is used to obtain product information of products published by third-party platforms; The second module 420 is used to perform structured parsing and normalization processing on the product information to obtain the structured text information of the product; The fourth module 440 is used to traverse the database of structured text information of all system products of the aggregation platform, calculate the semantic similarity between the structured text information of the product and the structured text information of each system product in the database, determine the system product corresponding to the highest semantic similarity among the preset thresholds, and generate a second mapping relationship between the product and the system products.

[0050] In this system embodiment, the system is deployed on a computer device with the same hardware and software environment as the aggregation platform 100. Through the first module 410 of the system, product information for each product published by the third-party platform can be obtained. This product information may be structured text information conforming to the third-party platform's product data structure system, or it may be natural language description information that does not conform. Through the second module 420 of the system, the product information can first be structured and parsed. For example, the product information can be parsed according to the product data structure and encoding system of the third-party platform, and then normalized by referring to the data structure system supported by the aggregation platform 100. This standardizes different information representing the same concept in product information from different third-party platforms, thereby obtaining structured text information for the product that conforms to the product data structure system of the aggregation platform 100, providing standardized data for subsequent processing. The fourth module 440 of the system can traverse the database containing structured text information of all system products, calculate the semantic similarity between the structured text information of the product published by the third-party platform and the structured text information of each system product in the database, and determine one or more system products that meet the preset threshold based on the calculation results. If there are multiple system products, the system product with the highest semantic similarity is determined, and a second mapping relationship between the product published by the third-party platform and the system product of the aggregation platform 100 is generated.

[0051] Optionally, the commodity information processing system based on the aggregation platform further includes: The third module 430 is used to match the structured text information of the product based on a preset mapping table corresponding to the third-party platform. If the match fails, subsequent steps are executed.

[0052] Specifically, a pre-defined mapping table can be constructed, pre-built based on structured text information, between the products of the third-party platform and the system products of the aggregation platform 100, before obtaining the product information of the third-party platform. In this optional embodiment, after obtaining the structured text information of the product through the second module 420, in order to improve processing efficiency, the third module 430 of the system can first perform matching processing on the structured text information of the product with the relevant structured text information of each third-party platform product in the pre-defined mapping table. If the matching fails, the subsequent steps are then executed through module 440.

[0053] Optionally, the commodity information processing system based on the aggregation platform further includes: The fifth module 450 is used to update the preset mapping lookup table according to the second mapping relationship.

[0054] In this optional embodiment, the fifth module 450 of the system can also consolidate and supplement the mapping relationship between the newly generated product and the corresponding system product of the aggregation platform 100 into the preset mapping lookup table to update the preset mapping lookup table, which may improve the mapping matching efficiency of new products released by third-party platforms in the future.

[0055] Optionally, the commodity information processing system based on the aggregation platform further includes: The sixth module 460 is used to receive the product orders pushed by the third-party platform and convert the product orders into system product orders of the aggregation platform according to the second mapping relationship.

[0056] In this optional embodiment, when a merchant receives a product order for the product pushed by the third-party platform through the aggregation platform 100, the sixth module 460 of the system can convert the product order into a system product order of the aggregation platform 100 according to the second mapping relationship between the product and the relevant system products of the aggregation platform 100 generated by the fourth module 440 of the system, so as to ensure that the merchant can smoothly complete the processes of order acceptance, printing, production and accounting.

[0057] In the above system embodiments and / or optional embodiments, any parts of the system not mentioned are the same as those in the aforementioned related method embodiments and / or optional embodiments, and will not be repeated here.

[0058] The aggregation platform 100, deployed in the above system embodiments and / or optional embodiments, can obtain structured text information of goods published by third-party platforms, calculate the semantic similarity between the structured text information of goods published by third-party platforms and the structured text information of system goods in the database of aggregation platform 100, determine the system goods with the highest semantic similarity among preset thresholds as the corresponding mapped goods, and generate a mapping relationship between the third-party platform's goods and the aggregation platform 100's system goods. This allows for efficient and flexible configuration and maintenance of the product mapping relationship between third-party platforms and aggregation platforms. To improve efficiency, before calculating semantic similarity, it first matches the structured text information already constructed in a preset mapping lookup table; if a match fails, then semantic similarity is calculated.

[0059] According to another aspect of this application, a computer-readable medium is also provided, on which computer-readable instructions are stored, which can be executed by a processor to implement some or all of the foregoing method embodiments and / or optional embodiments.

[0060] It should be noted that the method embodiments and / or optional embodiments in this application do not strictly limit the order of execution of each step, as long as the method embodiments and / or optional embodiments can solve the defects existing in the prior art, achieve the inventive purpose of this application, and obtain beneficial effects. The method embodiments and / or optional embodiments in this application can be implemented in software and / or combinations of software and hardware. The software program involved in this application can be executed by a processor to implement the steps or functions of the above embodiments. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium.

[0061] Furthermore, part or all of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. The program instructions invoking the methods of this application may be stored in a fixed or removable recording medium, and / or transmitted via data streams in broadcast or other signal carrying media, and / or stored in the working memory of a computer device operating according to the program instructions.

[0062] According to another aspect of this application, a commodity information processing device based on an aggregation platform is also provided. The device includes: a memory for storing computer-readable instructions and one or more processors for executing the computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, the device is triggered to run part or all of the methods and / or technical solutions of the foregoing embodiments.

[0063] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0064] In this application, when terms such as "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" are used, the indicated orientation and / or positional relationship is based on the orientation and / or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation. Furthermore, some of the above terms, in addition to indicating orientation or positional relationship, can also be used to indicate other meanings; for example, the term "upper" can also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application according to the specific circumstances. Furthermore, the terms "installation," "setup," "equipped with," "connection," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection via an intermediate medium; and they can refer to an internal connection between two devices, components, or constituent parts. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0065] Furthermore, the terms "first," "second," etc., are primarily used to distinguish different devices, units, modules, elements, circuits, or components (which may be the same or different in specific type and construction), and are not intended to indicate or imply the relative importance, order, and / or quantity of the indicated devices, units, modules, elements, circuits, or components. Unless otherwise stated, "a plurality of" means two or more.

[0066] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device through software and / or hardware.

Claims

1. A method for processing product information based on an aggregation platform, characterized in that, The method includes: Obtain product information for goods published on third-party platforms; The product information is subjected to structured parsing and normalization to obtain the structured text information of the product; Traverse the database containing structured text information of all system products on the aggregation platform, calculate the semantic similarity between the structured text information of the product and the structured text information of each system product in the database, determine the system product corresponding to the highest semantic similarity among the preset thresholds, and generate a second mapping relationship between the product and the system products.

2. The method according to claim 1, characterized in that, The structured parsing and normalization processing of the product information includes any one of the following: Based on preset rules, the product information is subjected to structured parsing and normalization processing; A large language model is used to perform structured parsing and normalization of the product information.

3. The method according to claim 1, characterized in that, The calculation of the semantic similarity between the structured text information of the product and the structured text information of each system product in the database includes: Obtain the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database, respectively; Calculate the cosine of the angle between the first text vector and each second text vector, and determine the semantic similarity between the structured text information of the product and the structured text information of each system product in the database based on the cosine of the angle.

4. The method according to claim 3, characterized in that, The step of obtaining the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database includes: The structured text information of the product and the structured text information of each system product in the database are respectively input into the text vectorization model to obtain the first text vector corresponding to the structured text information of the product and the second text vector corresponding to the structured text information of each system product in the database.

5. The method according to claim 1, characterized in that, Before calculating semantic similarity, the method includes: Based on a preset mapping table corresponding to the third-party platform, the structured text information of the product is matched. If the match fails, subsequent steps are executed.

6. The method according to claim 5, characterized in that, The matching includes any of the following: Encoding matching; Keyword matching.

7. The method according to claim 5, characterized in that, The method further includes: Update the preset mapping lookup table according to the second mapping relationship.

8. The method according to claim 1, characterized in that, The method further includes: The system receives product orders for the goods pushed by the third-party platform and converts these orders into system product orders for the aggregation platform according to the second mapping relationship.

9. A commodity information processing system based on an aggregation platform, characterized in that, The system includes: The first module is used to obtain product information of products published by third-party platforms; The second module is used to perform structured parsing and normalization processing on the product information to obtain the structured text information of the product; The fourth module is used to traverse the database of structured text information of all system products of the aggregation platform, calculate the semantic similarity between the structured text information of the product and the structured text information of each system product in the database, determine the system product corresponding to the highest semantic similarity among the preset thresholds, and generate a second mapping relationship between the product and the system products.

10. The system according to claim 9, characterized in that, The system also includes: The third module is used to match the structured text information of the product based on a preset mapping table corresponding to the third-party platform. If the match fails, subsequent steps are executed.

11. The system according to claim 9, characterized in that, The system also includes: The fifth module is used to update the preset mapping lookup table according to the second mapping relationship.

12. A computer-readable medium, characterized in that, It stores computer-readable instructions that are executed by a processor to implement part or all of the method as claimed in any one of claims 1 to 8.

13. A commodity information processing device based on an aggregation platform, characterized in that, The device includes: One or more processors; and A memory storing computer-readable instructions, which, when executed, cause the processor to perform some or all of the operations of the method as described in any one of claims 1 to 8.

Images