CN-121981800-A - Commodity price interval generation method and device

Abstract

One or more embodiments of the present disclosure provide a method and an apparatus for generating a commodity price interval. According to the method, a plurality of order information of a target user in a first time window can be obtained, order information corresponding to a first commodity category in the plurality of order information is determined, and finally a first commodity price interval corresponding to the first commodity category can be generated based on the order information corresponding to the first commodity category and commodity prices in the order information, wherein the first commodity price interval is a price range used when screening commodities corresponding to the first commodity category for the target user in a recall stage.

Inventors

• GUO JIN

Assignees

• 支付宝(杭州)数字服务技术有限公司

Dates

Publication Date

20260505

Application Date

20260116

Claims (18)

1. 1. A method for generating a commodity price interval, the method comprising: Acquiring a plurality of order information of a target user in a first time window, wherein the order information comprises commodity prices; Determining order information corresponding to a first commodity type in the plurality of order information, wherein the first commodity type is a commodity type generated in advance; and generating a first commodity price section corresponding to the first commodity category based on the order information corresponding to the first commodity category and commodity prices in the order information, wherein the first commodity price section is a price range used when screening commodities corresponding to the first commodity category for the target user in a recall stage.
2. 2. The method of claim 1, wherein the order information further comprises a product identification, and determining order information of the plurality of order information corresponding to a first product category comprises: And determining order information corresponding to the first commodity category in the order information based on commodity identifications of the order information.
3. 3. The method of claim 2, wherein the item identification is an item category, wherein determining order information of the plurality of order information corresponding to the first item category based on the item identification of the plurality of order information comprises: acquiring the first commodity category of a plurality of commodity categories and the commodity category of the plurality of order information; and determining order information corresponding to the first commodity category in the plurality of order information based on commodity categories of the plurality of order information.
4. 4. The method of claim 2, wherein the product identifier is a product name, wherein determining order information of the plurality of order information corresponding to the first product category based on the product identifiers of the plurality of order information comprises: acquiring commodity names of the first commodity category and the plurality of order information in a plurality of commodity categories; Acquiring a first mapping relation, wherein the first mapping relation is a mapping relation between a commodity name and a commodity type which are generated in advance; and determining order information corresponding to the first commodity type in the order information based on commodity names of the order information and the first mapping relation.
5. 5. The method of claim 1, wherein generating a first commodity price zone corresponding to the first commodity category based on the order information corresponding to the first commodity category and the commodity price in the order information comprises: acquiring commodity prices in order information corresponding to the first commodity type; Determining the commodity price in order information corresponding to the first commodity type as the commodity price corresponding to the first commodity type; Determining a price average value based on the commodity price corresponding to the first commodity category; Determining a sample standard deviation based on the commodity price corresponding to the first commodity type; determining an adjustment coefficient based on a quantity of commodity prices corresponding to the first commodity category, the quantity of commodity prices corresponding to the first commodity category being inversely proportional to the adjustment coefficient; The first commodity price interval is determined based on the price average, the sample standard deviation, and the adjustment coefficient.
6. 6. The method of claim 5, wherein determining a price average based on the commodity price corresponding to the first commodity category comprises: Determining purchase time corresponding to each commodity price in commodity prices corresponding to the first commodity category; distributing a weight coefficient for each commodity price based on the purchase time corresponding to each commodity price; and calculating a price average value based on the price of each commodity and the weight coefficient.
7. 7. The method of claim 6, wherein assigning a weight coefficient to each commodity price based on the purchase time corresponding to the commodity price comprises: Distributing a first weight coefficient for commodity prices with purchase time within a first time period; Distributing a second weight coefficient for commodity prices with purchase time within a second time period, wherein the second weight coefficient is larger than the first weight coefficient; The first time window comprises the first time period and the second time period, the starting time of the first time period is the starting time of the first time window, the ending time of the first time period is the same as the starting time of the second time period, and the ending time of the second time period is the ending time of the first time window.
8. 8. The method of claim 5, wherein determining a price average based on the commodity price corresponding to the first commodity category comprises: determining the sum of commodity prices corresponding to the first commodity type as a first price sum; Determining the quantity of commodity prices corresponding to the first commodity type as a first quantity; a ratio of the first price sum to the first quantity is determined as a price average.
9. 9. The method of claim 5, wherein determining an adjustment factor based on the quantity of commodity prices corresponding to the first commodity category comprises: K=K1+(K2-K1)×e^(-p); Wherein K is an adjustment coefficient, K1 is a preset first value, K2 is a preset second value, K2 is larger than K1, and p is the number of commodity prices corresponding to the first commodity type.
10. 10. The method of claim 5, wherein determining an adjustment factor based on the quantity of commodity prices corresponding to the first commodity category comprises: obtaining a second mapping relation, wherein the second mapping relation is the mapping relation between the quantity and the adjusting coefficient; And determining the adjustment coefficient based on the second mapping relation and the quantity of commodity prices corresponding to the first commodity type.
11. 11. The method of claim 5, wherein the determining a first commodity price interval based on the price average, the sample standard deviation, and the adjustment coefficient comprises: determining a product of the sample standard deviation and the adjustment coefficient as a fluctuation amplitude value; Determining the sum of the price average value and the fluctuation amplitude value as an upper price limit; Determining a difference between the price average value and the fluctuation amplitude value as a price lower limit; And determining the first commodity price interval based on the upper price limit and the lower price limit, wherein the upper price limit is the maximum value of the first commodity price interval, and the lower price limit is the minimum value of the first commodity price interval.
12. 12. The method of claim 1, wherein generating a first commodity price zone corresponding to the first commodity category based on the order information corresponding to the first commodity category and the commodity price in the order information comprises: acquiring commodity prices in order information corresponding to the first commodity type; Determining the commodity price in order information corresponding to the first commodity type as the commodity price corresponding to the first commodity type; Determining the maximum value of commodity prices corresponding to the first commodity type as a price upper limit; Determining the minimum value in the commodity prices corresponding to the first commodity type as a price lower limit; And determining the first commodity price interval based on the upper price limit and the lower price limit, wherein the upper price limit is the maximum value of the first commodity price interval, and the lower price limit is the minimum value of the first commodity price interval.
13. 13. The method of claim 1, wherein after generating the first commodity price zone corresponding to the first commodity category based on the order information corresponding to the first commodity category and the commodity price in the order information, the method further comprises: Acquiring a second commodity price interval, wherein the second commodity price interval is a price interval of the first commodity type generated according to a plurality of order information of the target user in a second time window, the second time window has the same duration as the first time window, and the starting time of the first time window is later than the starting time of the second time window; And generating a third commodity price zone corresponding to the first commodity type based on the first commodity price zone and the second commodity price zone.
14. 14. The method of claim 13, wherein generating a third commodity price zone corresponding to the first commodity category based on the first commodity price zone and the second commodity price zone comprises: Distributing a third weight coefficient for the first commodity price interval; Distributing a fourth weight coefficient for the second commodity price interval, wherein the third weight coefficient is larger than the fourth weight coefficient; and determining a third commodity price zone corresponding to the first commodity type based on the first commodity price zone, the second commodity price zone, the third weight coefficient and the fourth weight coefficient.
15. 15. The method of claim 14, wherein determining a third commodity price zone corresponding to the first commodity category based on the first commodity price zone, the second commodity price zone, the third weight coefficient, and the fourth weight coefficient comprises: determining a product of the first commodity price interval and the third weight coefficient as a first weighted interval; Determining a product of the second commodity price interval and the fourth weight coefficient as a second weighted interval; determining the sum of the first weighting interval and the second weighting interval as a third commodity price interval corresponding to the first commodity type; wherein the sum of the third weight coefficient and the fourth weight coefficient is equal to 1.
16. 16. A commodity price interval generation apparatus, the apparatus comprising: The acquisition module is used for acquiring a plurality of order information of the target user in the first time window, wherein the order information comprises commodity prices; The determining module is used for determining order information corresponding to a first commodity type in the plurality of order information, wherein the first commodity type is a commodity type generated in advance; The generation module is used for generating a first commodity price section corresponding to the first commodity category based on the order information corresponding to the first commodity category and commodity prices in the order information, wherein the first commodity price section is a price range used when screening commodities corresponding to the first commodity category for the target user in a recall stage.
17. 17. An electronic device, the electronic device comprising: A memory for storing a computer program product; A processor for executing a computer program product stored in said memory, which, when executed, implements the method of any of the preceding claims 1-15.
18. 18. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon computer program instructions which, when executed, implement the method of any of the preceding claims 1-15.

Description

Commodity price interval generation method and device Technical Field One or more embodiments of the present disclosure relate to the field of computer network technologies, and in particular, to a method and an apparatus for generating a commodity price interval. Background Currently, in order to push interesting commodities to users, a recommendation system selects commodities for users based on an information filtering technology and realizes personalized recommendation for the users. In general, the recommendation system recalls a large number of commodities from the commodity library based on a preset recall strategy in a recall stage, sorts the recalled commodities according to a preset sorting condition in a sorting stage, and finally pushes the commodities ranked in the first few to a user. In the recall stage, the recommendation system can divide the users into different purchasing power levels based on the historical consumption total amount of the users, and recall a large number of commodities for the users based on the purchasing power levels corresponding to the users. In some cases, however, certain types of merchandise that the recommender system recalls for the user may not match the actual purchasing capabilities of the user at all, resulting in the recommender system failing to accurately recall merchandise appropriate for the user during the recall phase. Therefore, how to ensure that the recommendation system can accurately recall the commodity suitable for the user in the recall stage becomes a technical problem to be solved in the present day. Disclosure of Invention One or more embodiments of the present disclosure provide a method and an apparatus for generating a commodity price interval, so as to ensure that a recommendation system can accurately recall a commodity suitable for a user in a recall stage. In a first aspect, one or more embodiments of the present disclosure provide a method for generating a commodity price section, where the method includes obtaining a plurality of order information of a target user in a first time window, where the order information includes a commodity price, determining order information corresponding to a first commodity type in the plurality of order information, where the first commodity type is a commodity type that is generated in advance, and generating a first commodity price section corresponding to the first commodity type based on the order information corresponding to the first commodity type and the commodity price in the order information, where the first commodity price section is a price range used when screening a commodity corresponding to the first commodity type for the target user in a recall stage. In one possible implementation, the order information further comprises a commodity identifier, and determining order information corresponding to the first commodity category in the plurality of order information comprises determining order information corresponding to the first commodity category in the plurality of order information based on the commodity identifier of the plurality of order information. In a possible implementation manner, the commodity identification is a commodity type, and the order information corresponding to the first commodity type in the plurality of order information is determined based on the commodity identification of the plurality of order information. In a possible implementation manner, the commodity identification is a commodity name, the order information corresponding to the first commodity category in the plurality of order information is determined based on the commodity identification of the plurality of order information, and the method comprises the steps of obtaining the commodity name of the first commodity category in the plurality of commodity categories and the commodity name of the plurality of order information, obtaining a first mapping relation, wherein the first mapping relation is a mapping relation between the commodity name and the commodity category which are generated in advance, and determining the order information corresponding to the first commodity category in the plurality of order information based on the commodity name and the first mapping relation of the plurality of order information. In one possible implementation, the method comprises the steps of obtaining commodity prices in order information corresponding to a first commodity category, determining the commodity prices in the order information corresponding to the first commodity category as commodity prices corresponding to the first commodity category, determining a price average value based on the commodity prices corresponding to the first commodity category, determining a sample standard deviation based on the commodity prices corresponding to the first commodity category, determining an adjustment coefficient based on the number of commodity prices corresponding to the first commodity category, wherein t