Method for reminding price reduction of goods based on collection duration

Abstract

The application relates to the field of intelligent recommendation systems, and particularly discloses a commodity price reduction reminding method based on collection time length, which comprises the following steps: triggering commodity price reduction reminding according to user collection commodities; collecting data according to the collection commodities, dynamically determining a price reduction triggering threshold according to the collection commodity time length; monitoring the current price of the commodity based on the price reduction triggering threshold; when the current price is reduced to <= the price reduction triggering threshold, sending a price reduction reminding information to the user; when the current price of the commodity is > the price reduction triggering threshold, continuing to monitor; and adjusting the strategy of subsequent price reduction reminding according to the feedback behavior of the user to the price reduction reminding information. The application calculates the collection commodity time length weight through a ladder type weight, quantifies the user demand urgency behind the collection time length, changes the reminding strategy from commodity orientation to user demand orientation, and solves the problem that the reminding is not in line with the user will.

Description

Technical Field

[0001] This invention relates to the field of intelligent recommendation systems, and more particularly to a method for reminding users of price reductions for products based on the duration of their collection. Background Technology

[0002] Current technologies for price reduction alerts on daily necessities generally use fixed thresholds. Platforms or merchants preset fixed price reductions, such as a 10% reduction or a 5 yuan reduction. When the product price reaches this preset threshold, an alert is sent to all users who are interested in the product. For example, a laundry detergent might have a preset 5 yuan price reduction alert, triggering only when the price drops from 30 yuan to below 25 yuan. Another approach is user-defined alert schemes, where users manually input their target price reduction or target price. For instance, if a user sets the alert price for a certain type of tissue to 20 yuan, the system only sends a notification when the product price is lower than the user-set value. Additionally, existing technologies also use simple price comparison alerts. These schemes crawl the prices of the same product on different platforms or compare the product's historical lowest price. When the current price is lower than the historical lowest price / cross-platform lowest price, a "lowest price across the entire network" alert is sent to the user, without linking to the user's active favorites behavior.

[0003] The current technology fails to link reminders to the user's "collecting" of products. Collecting products essentially signals a user's intention to purchase but not yet a decision. Existing technology only triggers reminders based on the product price itself, using fixed thresholds, manual settings, and cross-platform price comparisons. It doesn't reflect the urgency of the user's need through the duration of collection. For example, a user who collects a shampoo for 30 days is generally more likely to buy it than someone who collects it for only one day. Furthermore, there are significant category differences in daily necessities such as food, cosmetics, and household goods. For instance, food has a shelf life, and users are more eager for price reductions nearing their expiration date. Cosmetics have a fixed usage cycle, and users are more sensitive to price drops when they are close to using them up. However, existing technology uses a one-size-fits-all reminder logic, failing to adjust reminder strategies according to the characteristics of different categories. Fixed or manually set thresholds are static values ​​and cannot dynamically adjust based on user behavior, collection duration, or product status, such as the approaching expiration date of food. For example, if a user collects milk with a one-month shelf life, the originally preset 5% price reduction threshold may no longer match the user's urgent need to avoid waste after 15 days, leading to delayed or ineffective reminders.

[0004] Furthermore, the existing solution only sends reminders one-way without taking into account user feedback, such as whether the user views the reminder or makes a purchase to adjust the strategy. In the long run, this may lead to too many invalid reminders, such as frequent reminders for products the user does not need or missed reminders for effective ones, or reminders for products the user urgently needs not being triggered in a timely manner. Summary of the Invention

[0005] The present invention aims to provide a method for reminding customers of price reductions based on the duration of their collection, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: Price drop alerts based on the duration of a product's collection include: Trigger price drop alerts based on user favorites; Data is collected based on the collected items, and the price reduction trigger threshold is dynamically determined according to the collection duration. The current price of the product is monitored based on a price reduction trigger threshold. When the current price drops to or below the price reduction trigger threshold, a price reduction reminder is sent to the user. If the current price of the product is above the price reduction trigger threshold, monitoring continues. The strategy for subsequent price reduction notifications will be adjusted based on user feedback regarding the price reduction alerts.

[0007] Furthermore, the data initialization collection includes the following data being automatically collected by the system after the user completes the product favorites operation: The collection start time records the timestamp of the user clicking the collection button, which is used to calculate the collection duration later; Historical price benchmark: Extract all valid transaction prices of the product within a preset historical period before it is added to the collection, and calculate the arithmetic average as the historical price benchmark. Product category tags identify the specific category of daily necessities to which a product belongs, and are used to determine product characteristic coefficients in subsequent steps.

[0008] Furthermore, based on the subcategories of daily necessities, a product characteristic coefficient is calculated. The product characteristic coefficient value is set in combination with the shelf life and the speed of use. The shorter the shelf life and the faster the use of a product, the higher the sensitivity of users to price reductions, and the larger the product characteristic coefficient.

[0009] Furthermore, the specific categories and product characteristic coefficients of the aforementioned daily necessities include: For food products, which have short shelf lives and quick usage cycles, the product characteristic coefficient is 1.2. Daily chemical cleaning products have a long shelf life and a medium usage cycle, with a product characteristic coefficient of 0.8. Home storage products have a long shelf life but a slow usage cycle, resulting in a product characteristic coefficient of 0.5.

[0010] Furthermore, based on the range of time a product has been saved, the weight of the time spent saving the product is calculated. This weight is then calculated according to a tiered weighting rule: the longer a product has been saved, the higher the user's urgency, and the greater the weight of the time spent saving the product. Specifically: When the collection period is ≤7 days, the user is in the initial attention stage and the urgency of demand is low, so the weight of the collection period is 0.5. When 7 days < collection duration ≤ 30 days, the user is in the continuous attention stage, the urgency of demand is moderate, and the weight of collection duration = 0.8. When the collection period is greater than 30 days, the user is in a high-demand waiting stage with a high degree of urgency, and the weight of the collection period is 1.2. If a user favorites a toothpaste product for 20 days, and this falls within the range of 7 days < favorite duration ≤ 30 days, then the weight of the favorite duration is 0.8.

[0011] Furthermore, a dynamic threshold formula is used to calculate the price reduction trigger threshold. This formula combines historical price benchmarks, the weight of the duration of product collection, and product characteristic coefficients. This ensures that for products with more urgent demand and higher sensitivity, the price reduction trigger threshold is closer to the historical price benchmark, making it easier to trigger alerts. The formula is as follows: S = P0 × (1 - W × K × 0.1), In the formula, S is the price reduction trigger threshold, in yuan; P0 is the historical price benchmark, in yuan; W is the weight of the collection period of the product; and K is the product characteristic coefficient.

[0012] Furthermore, the system collects the current price of the collected items according to a preset period and compares it with the calculated price reduction trigger threshold in real time; If the current price is less than or equal to the price reduction trigger threshold, a price reduction reminder will be sent to the user according to the preset rules. The price reduction reminder includes the identifier of the saved product, the current price, and the comparison result of the current price being lower than the price reduction trigger threshold. If the current price is greater than the price reduction trigger threshold, monitoring will continue until the price reaches the target or the user cancels the bookmark.

[0013] Furthermore, after sending price reduction reminders to users, user feedback behavior is collected, including clicking the reminder and purchasing, clicking the reminder but not purchasing, and ignoring the reminder. The weight of the time spent collecting the product or the product characteristic coefficient is then fine-tuned based on the feedback.

[0014] Furthermore, the weighting of the collection duration or the product characteristic coefficient value based on feedback includes: If a user clicks the reminder and makes a purchase, the weight of the current favorited product duration and the product characteristic coefficient value are matched with the user's needs. When the user favorites similar products in the future, the rules of the weight of the current favorited product duration and the product characteristic coefficient are maintained. If a user clicks the reminder but does not purchase, it indicates that the threshold is still too high and the price reduction is insufficient. If a user clicks the price reduction reminder but does not purchase the product, it is determined that the current price reduction trigger threshold is too high and the price reduction is insufficient. Subsequently, when the user collects similar products, the weight of the collection duration will be increased by a preset adjustment range. That is, the original weight of the collection duration will be adjusted to the sum of the original weight and the preset adjustment range, so that the price reduction trigger threshold is closer to the historical price benchmark.

[0015] Furthermore, the method of fine-tuning the weight of the collection period or the product characteristic coefficient based on feedback also includes: if the user ignores the price reduction reminder, it is determined that the current price reduction trigger threshold is too low or the price reduction is excessive, and the user may think that the product is nearing its expiration date or has defects. When the user subsequently collects similar products, the product characteristic coefficient will be lowered by a preset adjustment range. That is, the original product characteristic coefficient will be adjusted to the difference between the original coefficient and the preset adjustment range, so that the price reduction trigger threshold is higher than the original calculated value.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention calculates the weight of the collection time of products through a tiered weighting system, quantifies the urgency of user needs behind the collection time, and shifts the reminder strategy from product-oriented to user-demand-oriented, solving the problem of reminders being out of touch with user intentions.

[0017] 2. This invention addresses the significant differences in shelf life and usage cycle of daily necessities by transforming category characteristics into calculable commodity characteristic coefficients. This allows the price reduction thresholds for different product categories to be adapted to their own attributes, solving the problems of delayed reminders for food products and redundant reminders for household products caused by the one-size-fits-all approach in existing technologies.

[0018] 3. This invention constructs a dynamic threshold calculation model that combines historical price benchmarks, the weight of the duration of product collection, and product characteristic coefficients. This model simultaneously links the threshold to historical product prices, user demand intensity, and category sensitivity, ensuring the accuracy and flexibility of reminders. Furthermore, it adds a feedback-adjustment closed loop. Based on user feedback on reminder behavior (purchase, non-purchase, ignore), the weight of the duration of product collection or the product characteristic coefficients are fine-tuned, allowing the reminder to continuously adapt to individual users' consumption habits. This solves the problem of declining reminder efficiency due to the lack of self-optimization capabilities in existing technologies.

[0019] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0020] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating the product price reduction notification method based on collection duration provided in this application. Detailed Implementation

[0021] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0022] like Figure 1 As shown in this embodiment, the product price reduction reminder method based on collection duration includes: Trigger price drop alerts based on user favorites; Data is collected initially based on the items collected in the collection, and the price reduction trigger threshold is dynamically determined according to the collection duration. The system monitors the current price of a product based on a price reduction trigger threshold. When the current price drops to or below the price reduction trigger threshold, a price reduction reminder is sent to the user. If the current price of the product is greater than the price reduction trigger threshold, the monitoring continues. We will adjust our subsequent price reduction notification strategy based on user feedback.

[0023] Initial data collection includes the following data automatically collected by the system after a user completes the product favorites action: The start time of collection is the timestamp of when the user clicked the collection button (e.g., 10:00 on [Date] in 2025), which is used to calculate the collection duration T later. Historical price benchmark: Extract all valid transaction prices of the product within a preset historical period before it is added to the collection, and calculate the arithmetic average as the historical price benchmark. The preset historical time period includes, but is not limited to, 30 days, 60 days, and 90 days.

[0024] Specifically, the arithmetic mean of all valid transaction prices of the product within the first 30 days of its collection (excluding abnormal prices such as flash sale prices and employee discounts) is calculated as P0. For example, the transaction prices of a certain brand of laundry detergent within the first 30 days of its collection were 30 yuan, 29 yuan, 30 yuan, 28 yuan, and 30 yuan, respectively. The arithmetic mean P0 = (30 + 29 + 30 + 28 + 30) / 5 = 29.4 yuan. Product category labels identify the specific categories of daily necessities to which the product belongs (such as "food", "daily chemical cleaning", "home storage"), which are used to determine the product characteristic coefficient K later.

[0025] Based on the subcategories of daily necessities, a product characteristic coefficient is calculated. The product characteristic coefficient value is set in combination with the length of shelf life and the speed of use. The shorter the shelf life and the faster the use of a product, the higher the sensitivity of users to price reductions, and the larger the product characteristic coefficient.

[0026] The specific categories and product characteristic coefficients of daily necessities include: For food products, which have short shelf lives and quick usage cycles, the product characteristic coefficient is 1.2. Daily chemical cleaning products have a long shelf life and a medium usage cycle, with a product characteristic coefficient of 0.8. Home storage products have a long shelf life but a slow usage cycle, resulting in a product characteristic coefficient of 0.5.

[0027] Specifically, food items (such as milk, bread, and snacks) have short shelf lives (usually 1-90 days) and quick usage cycles, with K=1.2; Daily chemical cleaning products (such as shampoo, laundry detergent, and toothpaste) have a relatively long shelf life (usually 1-3 years), a moderate usage cycle (usually 1-3 months), and a K=0.8. Home storage items (such as storage boxes, clothes hangers, and trash cans) have a long shelf life (usually 3-5 years) and a slow usage cycle (usually 6-12 months), with K=0.5.

[0028] Specifically, if "toothpaste" belongs to the "daily chemical cleaning category", then K=0.8.

[0029] The weight of the time a product has been saved is calculated based on the range of its saved duration. This weighting follows a tiered weighting rule: the longer a product has been saved, the higher the user's urgency, and the greater the weight given to the saved duration. Details are as follows: When the collection period is ≤7 days, the user is in the initial attention stage and the urgency of demand is low, so the weight of the collection period is 0.5. When 7 days < collection duration ≤ 30 days, the user is in the continuous attention stage, the urgency of demand is moderate, and the weight of collection duration = 0.8. When the collection period is greater than 30 days, the user is in a high-demand waiting stage with a high degree of urgency, and the weight of the collection period is 1.2. If a user favorites a toothpaste product for 20 days, and this falls within the range of 7 days < favorite duration ≤ 30 days, then the weight of the favorite duration is 0.8.

[0030] Specifically, based on the collection duration T, W is calculated using a "step-weighted rule." The rule design logic is that "the longer the collection duration, the higher the urgency of the user's need, and the larger W will be." The specific rules are as follows: When T≤7 days (within 1 week of collection): the user is in the "initial interest" stage, with low urgency of need, W=0.5; When 7 days < T ≤ 30 days (collection within 1 week to 1 month): the user is in the "continuous attention" stage, with a moderate level of urgency, and W = 0.8; When T > 30 days (collected for more than 1 month): the user is in the "high demand waiting" stage, with a high degree of urgency, W = 1.2.

[0031] Specifically, if a user saves a toothpaste for 20 days (in the range of 7 days < T ≤ 30 days), then W = 0.8.

[0032] A dynamic threshold formula is used to calculate the price reduction trigger threshold. This formula combines historical price benchmarks, the weight of the time a product has been saved, and product characteristic coefficients. This ensures that for products with more urgent demand and higher sensitivity, the price reduction trigger threshold is closer to the historical price benchmark, making it easier to trigger an alert. The formula is as follows: S = P0 × (1 - W × K × 0.1), In the formula, S is the price reduction trigger threshold, in yuan; P0 is the historical price benchmark, in yuan; W is the weight of the collection period of the product; and K is the product characteristic coefficient.

[0033] The "0.1" is a fixed adjustment coefficient used to avoid the threshold being too low, resulting in delayed reminders, or too high, resulting in invalid reminders (this coefficient is set based on the average price reduction in the daily necessities industry and does not require manual adjustment by the user).

[0034] Specifically: Combining the parameters (toothpaste P0 = 20 yuan, W = 0.8, K = 0.8), calculate S: S = 20 × (1 - 0.8 × 0.8 × 0.1) = 20 × (1 - 0.064) = 20 × 0.936 = 18.72 yuan; That is, when the current price of the toothpaste is P≤18.72 yuan, a price reduction alert will be triggered.

[0035] The system collects the current price of favorited items at a preset period and compares it with the calculated price reduction trigger threshold in real time. The preset period is preferably 1 hour to 24 hours; If the current price is less than or equal to the price reduction trigger threshold, a price reduction reminder will be sent to the user according to the preset rules. The price reduction reminder includes the identifier of the saved product, the current price, and the comparison result of the current price being lower than the price reduction trigger threshold. If the current price is greater than the price reduction trigger threshold, monitoring will continue until the price reaches the target or the user cancels the bookmark.

[0036] In a preferred embodiment of the present invention, the system's preset cycle is once per hour, and the preset rule is to send a price reduction reminder immediately. The specific wording of the reminder can be: "The item you've saved has been reduced to XX yuan, which is lower than your expected threshold," where XX is the current price of the item, and the expected threshold is the price reduction trigger threshold. In other embodiments, the preset rule can also be adjusted according to actual needs, such as delaying the sending by 1-5 minutes when system resources are limited; the wording of the reminder can also be adjusted, for example, "The [item name] you saved has been reduced in price, currently priced at XX yuan, which is lower than your expected threshold of XX yuan" or "[item name] price reduction reminder: Currently XX yuan, reaching your expected price reduction."

[0037] After sending a price reduction reminder to the user, collect user feedback behavior, including clicking the reminder and purchasing, clicking the reminder but not purchasing, and ignoring the reminder. Based on the feedback, fine-tune the weight of the time the product is saved or the product characteristic coefficient.

[0038] The weighting of the collection duration or the product characteristic coefficient value is adjusted based on feedback, including: If a user clicks the reminder and makes a purchase, the weight of the current collection duration and the product characteristic coefficient value will be matched with the user's needs. When the user collects similar products in the future, the weight of the current collection duration and the product characteristic coefficient rules will be maintained. If a user clicks on the price reduction reminder but does not purchase, it is because the threshold is still too high and the price reduction is insufficient. If a user clicks on the price reduction reminder but does not purchase the product, it is determined that the current price reduction trigger threshold is too high and the price reduction is insufficient. When the user subsequently collects similar products, the weight of the collection duration will be increased by a preset adjustment range. That is, the original weight of the collection duration will be adjusted to the sum of the original weight and the preset adjustment range, so that the price reduction trigger threshold is closer to the historical price benchmark.

[0039] If a user clicks the reminder but does not purchase, it means the threshold is still too high and the price reduction is insufficient. In the future, when the user favorites similar products, the weight of the favorited product duration will be increased by 0.1, and the original favorited product duration weight = 0.8 will be adjusted to 0.9, so that the price reduction trigger threshold is closer to the historical price benchmark.

[0040] In a preferred embodiment of the present invention, the preset adjustment range is 0.1. If the original weight of the user's collection duration was 0.8, the adjusted weight is 0.9. In other embodiments, the preset adjustment range can be flexibly set according to factors such as product category, user consumption habits, and historical price fluctuation range. For example, for food products with large price fluctuations, the preset adjustment range can be set to 0.15; for home storage products with stable prices, the preset adjustment range can be set to 0.05. Regardless of the preset adjustment range used, the goal is to achieve the objective of making the price reduction trigger threshold closer to the historical price benchmark by increasing the collection duration weight.

[0041] The feedback-based fine-tuning of the weight of the collection time or the product characteristic coefficient value also includes: if the user ignores the price reduction reminder, it is determined that the current price reduction trigger threshold is too low or the price reduction is excessive, and the user may think that the product is nearing its expiration date or has defects. When the user subsequently collects similar products, the product characteristic coefficient will be lowered by a preset adjustment range. That is, the original product characteristic coefficient will be adjusted to the difference between the original coefficient and the preset adjustment range, so that the price reduction trigger threshold is higher than the original calculated value.

[0042] The feedback-based fine-tuning of the weighting of the collection duration or the product characteristic coefficient also includes: if the user ignores the reminder, it is because the threshold is too low, the price reduction is excessive, and the user believes that the product may be nearing its expiration date or has defects. In the future, when the user collects the same type of product, the product characteristic coefficient will be lowered by 0.1, and the original product characteristic coefficient = 0.8 will be adjusted to 0.7, so that the price reduction trigger threshold is higher than the original calculated value.

[0043] In a preferred embodiment of the present invention, the preset adjustment range of the product characteristic coefficient is 0.1 for feedback that the user ignores the reminder. If the original product characteristic coefficient is 0.8, the adjusted coefficient is 0.7. In other embodiments, the preset adjustment range can be flexibly set according to the characteristics of the product category. For example, for food products with short shelf life and high risk of near expiration, the preset adjustment range can be set to 0.15 to increase the threshold more quickly and prevent users from ignoring the reminder due to concerns about near expiration. For home storage products without near expiration risk, the preset adjustment range can be set to 0.05 to adjust the threshold gently. Regardless of the preset adjustment range used, the goal is to achieve the objective of lowering the product characteristic coefficient so that the price reduction trigger threshold is higher than the original calculated value.

[0044] The terminology defined in this implementation includes the following: Collection Duration T: The cumulative time from when a user clicks to collect a product to the current time, in days (accurate to the hour, less than 1 day is counted as 1 day). Historical price benchmark P0: The average transaction price of the product in the 30 days prior to the user's favorite (if the product has been listed for less than 30 days, the average transaction price from the listing date to the favorite date is used), in yuan; Current Price P: The current selling price of the product collected in real time (excluding temporary coupons, discounts for purchases over a certain amount, and other non-direct price reduction benefits; only the listed price of the product itself is calculated), in "yuan"; Product collection duration weight W: A dynamic weight built based on the collection duration T, used to quantify the urgency of user needs (the longer the product is collected, the larger W is, indicating a more urgent user need). Product characteristic coefficient K: A coefficient set based on the characteristics of daily necessities (shelf life, usage cycle) to adapt to the price reduction sensitivity of different product categories (e.g., a larger K for categories with shorter shelf life means higher sensitivity to price reductions). Price drop trigger threshold S: The highest price at which the algorithm calculates to trigger a price drop alert. When the current price P≤S, a price drop alert is triggered. The unit is "yuan".

[0045] The foregoing description illustrates and describes several preferred embodiments of this application. However, as previously stated, it should be understood that this application is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the inventive concept described herein through the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of this application should be within the protection scope of the appended claims.

Claims

1. A method for notifying customers of price drops based on the duration of their collection, characterized in that: include: Trigger price drop alerts based on user favorites; Data is collected based on the collected items, and the price reduction trigger threshold is dynamically determined according to the collection duration. The current price of the product is monitored based on a price reduction trigger threshold. When the current price drops to or below the price reduction trigger threshold, a price reduction reminder is sent to the user. If the current price of the product is above the price reduction trigger threshold, monitoring continues. The strategy for subsequent price reduction notifications will be adjusted based on user feedback regarding the price reduction alerts.

2. The method for providing price reduction alerts based on collection duration according to claim 1, characterized in that, The initial data collection includes the following data being automatically collected by the system after a user completes the product favorites action: The collection start time records the timestamp of the user clicking the collection button, which is used to calculate the collection duration later; Historical price benchmark: Extract all valid transaction prices of the product within a preset historical period before it is added to the collection, and calculate the arithmetic average as the historical price benchmark. Product category tags identify the specific category of daily necessities to which a product belongs, and are used to determine product characteristic coefficients in subsequent steps.

3. The method for providing price reduction alerts based on collection duration according to claim 2, characterized in that, Calculate the product characteristic coefficient based on the subcategories of daily necessities.

4. The method for providing price reduction alerts based on collection duration according to claim 3, characterized in that, The specific categories and product characteristic coefficients of the aforementioned daily necessities include: For food products, the product characteristic coefficient is 1.

2. For daily chemical cleaning products, the product characteristic coefficient is 0.

8. For home storage products, the product characteristic coefficient is 0.

5.

5. The method for providing price reduction alerts based on collection duration according to claim 1, characterized in that, The weight of the collection period is calculated based on the range of collection duration, as follows: When the collection period is ≤7 days, the user is in the initial attention stage and the urgency of demand is low, so the weight of the collection period is 0.

5. When 7 days < collection duration ≤ 30 days, the user is in the continuous attention stage, the urgency of demand is moderate, and the weight of collection duration = 0.

8. When the collection period is greater than 30 days, the user is in a high-demand waiting stage with a high degree of urgency, and the weight of the collection period is 1.

2.

6. The method for providing price reduction alerts based on collection duration according to claim 1, characterized in that, The price reduction trigger threshold is calculated using a dynamic threshold formula. This formula combines historical price benchmarks, the weight of the duration of the item's collection, and product characteristic coefficients. The formula is as follows: S = P0 × (1 - W × K × 0.1), In the formula, S is the price reduction trigger threshold, and the unit is yuan; P0 is the historical price benchmark, in yuan; W represents the weight of the time a product is collected, and K represents the product characteristic coefficient.

7. The method for providing price reduction alerts based on collection duration according to claim 1, characterized in that, in, The system collects the current price of favorited products at preset intervals and compares it with the calculated price reduction trigger threshold in real time. If the current price is less than or equal to the price reduction trigger threshold, a price reduction reminder will be sent to the user according to the preset rules. The price reduction reminder includes the identifier of the saved product, the current price, and the comparison result of the current price being lower than the price reduction trigger threshold. If the current price is greater than the price reduction trigger threshold, monitoring will continue until the price reaches the target or the user cancels the bookmark.

8. The method for providing price reduction alerts based on collection duration according to claim 1, characterized in that, After sending a price reduction reminder to the user, collect user feedback behavior, including clicking the reminder and purchasing, clicking the reminder but not purchasing, and ignoring the reminder. Based on the feedback, fine-tune the weight of the time the product is saved or the product characteristic coefficient.

9. The method for providing price reduction alerts based on collection duration according to claim 1, characterized in that, The weighting of the collection duration or the product characteristic coefficient value is adjusted based on feedback, including: If a user clicks the reminder and makes a purchase, the weight of the current favorited product duration and the product characteristic coefficient value are matched with the user's needs. When the user favorites similar products in the future, the rules of the weight of the current favorited product duration and the product characteristic coefficient are maintained. If a user clicks the reminder but does not purchase, it is because the threshold is still too high and the price reduction is insufficient. If a user clicks the price reduction reminder but does not purchase the product, it is determined that the current price reduction trigger threshold is too high and the price reduction is insufficient. When the user subsequently collects similar products, the weight of the collection duration will be increased by a preset adjustment range. That is, the original weight of the collection duration will be adjusted to the sum of the original weight and the preset adjustment range, so that the price reduction trigger threshold is closer to the historical price benchmark.

10. The method for reminding customers of price reductions based on collection duration according to claim 1, characterized in that, The feedback-based fine-tuning of the weight of the collection time or the product characteristic coefficient value also includes: if the user ignores the price reduction reminder, it is determined that the current price reduction trigger threshold is too low or the price reduction is excessive, and the user may think that the product is nearing its expiration date or has defects. When the user subsequently collects similar products, the product characteristic coefficient will be lowered by a preset adjustment range. That is, the original product characteristic coefficient will be adjusted to the difference between the original coefficient and the preset adjustment range, so that the price reduction trigger threshold is higher than the original calculated value.

Images