CN-122022951-A - Price verification method, device, equipment and storage medium based on same commodity identification

CN122022951ACN 122022951 ACN122022951 ACN 122022951ACN-122022951-A

Abstract

The application discloses a price verification method, a price verification device, price verification equipment and a price verification storage medium based on same-style commodity identification, and relates to the technical field of commodity price comparison, wherein the method comprises the steps of obtaining heterogeneous commodity data of a plurality of suppliers; the method comprises the steps of processing heterogeneous commodity data to obtain standardized commodity data, carrying out multi-mode feature fusion on the standardized commodity data to generate comprehensive feature vectors corresponding to all commodities, calculating similarity among the commodities according to the comprehensive feature vectors, clustering the commodities with similarity larger than a similarity threshold value into a same commodity set, carrying out price comparison analysis on the commodities in the same commodity set to obtain reference prices of the same commodity set, receiving a purchasing request, determining the same commodity set based on commodity identification in the purchasing request, comparing the commodity prices in the purchasing request with the reference prices of the same commodity set to obtain a verification result, and responding to the purchasing request according to the verification result. The method improves the accuracy of price comparison of the same commodity.

Inventors

YAN BOBO
HE XIN
LIU QIANGQIANG
WANG JINGYA
LIU MING
ZHOU JING
XU WU
LI MAO
YANG LIN
LIU SHIYUAN
TANG HAILONG
WANG YIKE
GUO TIE

Assignees

国网电商科技有限公司
东方电气集团(四川)物产有限公司
通号(北京)物资有限公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. A price verification method based on identification of same type goods, the method comprising: acquiring heterogeneous commodity data of a plurality of suppliers; Processing the heterogeneous commodity data to obtain standardized commodity data; Carrying out multi-mode feature fusion on the standardized commodity data to generate comprehensive feature vectors corresponding to all commodities; calculating the similarity between commodities according to the comprehensive feature vector, and clustering commodities with similarity greater than a similarity threshold value into a same commodity set; carrying out price comparison analysis on the commodities in the same commodity set to obtain a reference price of the same commodity set; Receiving a purchase request, and determining the same commodity set based on the commodity identification in the purchase request; comparing the commodity price in the purchase request with the reference price of the same commodity set to obtain a verification result; And responding to the purchase request according to the verification result.
2. The method of claim 1, wherein the checking results include passing, early warning and intercepting, wherein the comparing the commodity price in the purchase request with the reference price of the same commodity set to obtain the checking results includes: When the commodity price in the purchase request is smaller than or equal to the reference price, the verification result is passed; When the commodity price in the purchase request is larger than the reference price but smaller than or equal to the first proportion of the reference price, the verification result is early warning; And when the commodity price in the purchase request is larger than the second proportion of the reference price, the verification result is interception, and the first proportion is smaller than the second proportion.
3. The method of claim 1, wherein responding to the purchase request based on the verification result comprises: when the verification result is passed, allowing the purchase request; When the verification result is early warning, triggering an approval process, and allowing a purchase request after approval is passed; and when the verification result is interception, not allowing the purchase request.
4. The method of claim 1, wherein the performing multi-modal feature fusion on the standardized commodity data to generate a comprehensive feature vector corresponding to each commodity comprises: extracting characteristics of text information in the standardized commodity data to obtain text characteristic vectors; extracting features of the image information in the standardized commodity data to obtain an image feature vector; and fusing the text feature vector and the image feature vector to obtain the comprehensive feature vector.
5. The method of claim 1, wherein the step of performing a price comparison of the items in the same item set to obtain a reference price for the same item set comprises: calculating the lowest price, average price and highest price of each commodity in the same commodity set; calculating a comprehensive cost performance score of each commodity based on the lowest price, average price, highest price and performance rating; and obtaining the reference price according to the comprehensive cost performance score.
6. The method of claim 5, wherein calculating a composite cost performance score for each commodity based on the minimum price, average price, maximum price, and performance rating comprises: Wherein, the Representing goods Is used for the comprehensive cost performance score of the (a), A first weight is indicated and a second weight is indicated, A second weight is indicated as being indicative of a second weight, The transition function is represented by a function of the transition, Representing goods Is a price of (a) to (b), Representing suppliers Is used for the performance rating of (1), A first coefficient representing a price factor is provided, A second coefficient representing a price factor is provided, A third coefficient representing a price factor is provided, Representing the minimum price to be offered, Indicating the highest price to be made, Representing the average price.
7. The method of claim 5, wherein the performance rating is obtained by: Wherein, the Representing suppliers Is used for the performance rating of (1), The representation is based on vendor The correction factor for the credit rating is used, Represent the first The weight of the item performance index, Representing suppliers In the first place A normalized score on the item performance indicator, Indicating the total number of performance indicators.
8. A price verification device based on identification of same type goods, the device comprising: the acquisition module is used for acquiring heterogeneous commodity data of a plurality of suppliers; the processing module is used for processing the heterogeneous commodity data to obtain standardized commodity data, carrying out multi-mode feature fusion on the standardized commodity data to generate comprehensive feature vectors corresponding to all commodities, calculating the similarity among the commodities according to the comprehensive feature vectors, and clustering the commodities with the similarity larger than a similarity threshold value into a same commodity set; the receiving module is used for receiving a purchase request and determining the same commodity set based on the commodity identification in the purchase request; And the comparison module is used for comparing the commodity price in the purchase request with the reference price of the commodity set of the same type to obtain a verification result, and responding to the purchase request according to the verification result.
9. A computing device comprising a memory and a processor; wherein one or more computer programs are stored in the memory, the one or more computer programs comprising instructions, which when executed by the processor, cause the computing device to perform the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium is for storing a computer program, the computer program is for performing the method of any of claims 1 to 7.

Description

Price verification method, device, equipment and storage medium based on same commodity identification Technical Field The application relates to the technical field of commodity price comparison, in particular to a price verification method, device and equipment based on same type commodity identification and a storage medium. Background At present, a traditional technical scheme based on keyword matching, manual price comparison and post-hoc compliance spot check is commonly adopted in the industry. The scheme generally comprises the following steps that after commodity information is uploaded by a provider autonomously, a system performs preliminary matching through simple commodity name keywords or fixed SKU codes, a purchasing person needs to manually check information such as commodity pictures and parameters to judge whether the commodity is the same commodity, and manually collect and sort out quotations of each provider for comparison, after a purchasing order is generated, a compliance department performs random spot check on the completed order to check whether problems such as high-price purchasing, illegal selection of the provider and the like exist. The scheme is generally structurally composed of a commodity uploading module, a keyword matching module, an order generation module and a post spot check module which are independent of each other, and lacks a unified intelligent analysis and real-time management and control center. However, prior art solutions are less accurate in terms of price ratio for the same type of commodity. Disclosure of Invention The application provides a price verification method, device, equipment and storage medium based on same-money commodity identification, which can improve the accuracy of price comparison of same-money commodities. In order to achieve the above purpose, the application adopts the following technical scheme: in a first aspect, the present application provides a price verification method based on identification of same-type commodities, including: acquiring heterogeneous commodity data of a plurality of suppliers; Processing the heterogeneous commodity data to obtain standardized commodity data; Carrying out multi-mode feature fusion on the standardized commodity data to generate comprehensive feature vectors corresponding to all commodities; calculating the similarity between commodities according to the comprehensive feature vector, and clustering commodities with similarity greater than a similarity threshold value into a same commodity set; carrying out price comparison analysis on the commodities in the same commodity set to obtain a reference price of the same commodity set; Receiving a purchase request, and determining the same commodity set based on the commodity identification in the purchase request; comparing the commodity price in the purchase request with the reference price of the same commodity set to obtain a verification result; And responding to the purchase request according to the verification result. Optionally, the checking result comprises passing, early warning and interception, and the comparing the commodity price in the purchase request with the reference price of the same commodity set to obtain the checking result comprises the following steps: When the commodity price in the purchase request is smaller than or equal to the reference price, the verification result is passed; When the commodity price in the purchase request is larger than the reference price but smaller than or equal to the first proportion of the reference price, the verification result is early warning; And when the commodity price in the purchase request is larger than the second proportion of the reference price, the verification result is interception, and the first proportion is smaller than the second proportion. Optionally, the responding to the purchase request according to the verification result includes: when the verification result is passed, allowing the purchase request; When the verification result is early warning, triggering an approval process, and allowing a purchase request after approval is passed; and when the verification result is interception, not allowing the purchase request. Optionally, the performing multi-mode feature fusion on the standardized commodity data to generate a comprehensive feature vector corresponding to each commodity includes: extracting characteristics of text information in the standardized commodity data to obtain text characteristic vectors; extracting features of the image information in the standardized commodity data to obtain an image feature vector; and fusing the text feature vector and the image feature vector to obtain the comprehensive feature vector. Optionally, the step of performing a price comparison analysis on the commodities in the same commodity set to obtain a reference price of the same commodity set includes: calculating the lowest price, average price and highest price of each com