Instant retail product recommendation method, system, and storage medium

Abstract

The present invention discloses a method and system for recommending instant retail goods, and a storage medium, which belongs to the technical field of goods recommendation. The method includes: obtaining the ratio between the user's attention to logistics speed and quality to form a user portrait; allocating the weight of the recommendation index according to the user portrait; calculating the urgency according to the product name, the system time when the user enters the search keyword, and the geographical location; adjusting the weight of the recommendation index according to the urgency; scoring the merchants who sell the goods required by the user, and recommending merchants to the user; and revising the user portrait according to the user's post-purchase evaluation and acceptance of the recommended goods. The present invention does not rely on artificial intelligence models and gets rid of the dependence on chips and large computing power. Despite the lack of artificial intelligence support, the present invention can still predict the user's needs more accurately, thereby recommending the most suitable merchants to the user.

Description

[0001] Divisional application

[0002] This application is a divisional application of the Chinese invention patent application [Application Number: 2024109465474] [Name: A method and system for recommending instant retail products, and storage medium] filed on July 15, 2024. Technical Field

[0003] The present invention relates to the field of product recommendation technology, and in particular to a method and system for recommending instant retail products, and a storage medium. Background Art

[0004] Instant retail is a retail format that utilizes instant online ordering and offline fulfillment, leveraging local retail supply to meet immediate local needs. It fills the vacuum left by online and offline integration. Localization is a defining characteristic of instant retail, enabling online transaction processes and streamlined fulfillment and delivery.

[0005] In order to improve local supply capacity and expand consumer demand, each sales platform has deployed a product recommendation strategy, which can recommend similar products of various brands and users who sell such products to users based on the products entered by the users.

[0006] Existing recommendation methods generally rely on brute force recommendations based on store proximity or overall ratings when users search for desired products, or on AI models and big data. Examples include JD.com's "Hourly Delivery" and Meituan Waimai.

[0007] In actual operation, we found that while brute force recommendation methods have low requirements, the recommended items often do not meet consumer needs. While AI models and big data recommendations are highly accurate, as the user base grows and the data becomes increasingly massive, AI model calculations consume enormous computing power, slowing down the entire system.

[0008] For example, Chinese patent application CNCN202311444961.7 provides a product recommendation model training method and a product recommendation method, including: determining the target product corresponding to the user based on the user's click sequence, the click sequence including the product identification of the product clicked by the user, and the target product and the product corresponding to the click sequence belong to products on different sales platforms; constructing training samples, one training sample including the click sequence corresponding to a user and the product identification of the target product; training the pre-constructed product recommendation model based on each of the training samples until the product recommendation model meets the requirements, thereby obtaining the trained product recommendation model.

[0009] For example, Chinese patent application CN201710833187.7 provides a method for displaying all product results after a user enters product information. The method includes: entering product information, including product image information or a combination of product image information and text information; using a pre-trained neural network to extract image features in the product image information, and obtain product attributes corresponding to the image features; and / or extracting keywords in the product text information, and obtaining product attributes corresponding to the keywords; matching the product attributes obtained from the product information with the product attributes in an established product knowledge graph to determine the target product with the product attributes.

[0010] The aforementioned existing technologies all require the pre-built large number of training samples to train pre-built neural network models, which means they rely on artificial intelligence. This reliance on artificial intelligence is actually a reliance on computing power, more specifically, a reliance on chips. Therefore, how to eliminate this reliance on chips is an urgent problem that needs to be solved. Summary of the Invention

[0011] The purpose of the present invention is to provide an instant retail product recommendation method and system, and a storage medium, which partially solve or alleviate the above-mentioned deficiencies in the prior art, and can recommend the most suitable specified products to users as much as possible while reducing computing power consumption, thereby improving user experience.

[0012] In order to solve the above-mentioned technical problems, the present invention specifically adopts the following technical solutions: a method for recommending instant retail products, comprising:

[0013] Obtain the ratio of users' attention to logistics speed and quality to form a user profile;

[0014] Assign weights to recommendation indicators based on user profiles, including logistics speed, quality, after-sales service, and price;

[0015] Obtain the product name of the product required by the user based on the search keyword entered by the user, and collect the system time and geographical location when the user enters the search keyword;

[0016] Calculating the urgency based on the product name, the system time, and the geographical location;

[0017] Adjusting the weights of the recommended indicators according to the urgency;

[0018] Rating merchants that sell the products desired by the user according to the recommendation indicators, and recommending the products sold by the merchants to the user based on the merchant ratings;

[0019] The user profile is modified based on the user's post-purchase evaluation and acceptance of the recommended products.

[0020] As an improvement, the step of obtaining the ratio of the user's attention to logistics speed and quality specifically includes:

[0021] When a user registers, a progress bar is displayed on the user registration page; one end of the progress bar is the logistics speed, and the other end is the quality; a slider that can slide along the progress bar is provided on the progress bar; the user changes the ratio between the logistics speed end and the quality end by dragging the slider, and the sum of the logistics speed end ratio and the quality end ratio is a constant value.

[0022] As an improvement, the steps for allocating weights of recommendation indicators based on user profiles include:

[0023] Initialize the weight of the recommended indicators and assign an initial weight to each recommended indicator;

[0024] The logistics speed weight and quality weight are redistributed according to the ratio between users' attention to logistics speed and quality.

[0025] As an improvement, the step of calculating the urgency based on the product name, the system time, and the geographical location specifically includes:

[0026] A template library is constructed by presetting several urgency scoring templates, wherein the urgency scoring templates perform urgency scoring according to the input commodity type, purchase time type, and delivery address type;

[0027] Classify products by product name to obtain product type; classify the time of purchase of products by system time to obtain purchase time type; classify the address of purchase of products by geographic location to obtain delivery address type;

[0028] An urgency score template is matched from a template library based on the commodity type, the purchase time type, and the delivery address type to obtain an urgency score.

[0029] As an improvement, the commodity types include medicines, food, and daily necessities; the purchase time types include working hours, meal times, meal preparation time, post-meal time, and nighttime; and the delivery address types include home address, work address, and out-of-home address.

[0030] As an improvement, methods for assigning weights to recommendation indicators based on urgency include:

[0031] The logistics speed weight is K1, the quality weight is K2, the after-sales service weight is K3, and the price weight is K4;

[0032] When the urgency score is greater than the first urgency threshold, K1=(K1+K2)*80%, K2=(K1+K2)*20%, K3=(K3+K4)*80%, K4=(K3+K4)*20%, K1+K2+K3+K4=1;

[0033] When the urgency score is between the second urgency threshold and the first urgency threshold, K1=(K1+K2)*60%, K2=(K1+K2)*40%, K3=(K3+K4)*60%, K4=(K3+K4)*40%, K1+K2+K3+K4=1;

[0034] When the urgency score is between the third urgency threshold and the second urgency threshold, K1=(K1+K2)*40%, K2=(K1+K2)*60%, K3=(K3+K4)*40%, K4=(K3+K4)*60%, K1+K2+K3+K4=1;

[0035] When the urgency score is less than the third urgency threshold, K1=(K1+K2)*20%, K2=(K1+K2)*80%, K3=(K3+K4)*20%, K4=(K3+K4)*80%, and K1+K2+K3+K4=1.

[0036] As an improvement, the method of scoring merchants selling products required by users based on recommendation indicators includes:

[0037] Obtain user reviews of the merchant, including individual scores for each recommendation indicator;

[0038] Calculate the average score of each recommendation indicator for all users;

[0039] Multiply the average of the individual scores of each recommended indicator by the weight of the recommended indicator to obtain the adjusted score;

[0040] The adjusted scores of all recommendation indicators are summed to obtain the merchant score.

[0041] As an improvement, the steps for recommending merchants to users based on merchant ratings include:

[0042] Sort merchants by their ratings from highest to lowest, and recommend to users the products they need from merchants whose rankings are higher than the ranking threshold; or

[0043] Recommend to users the products needed by users that are sold by merchants whose merchant ratings are higher than the rating threshold.

[0044] As an improvement, the steps to modify the user profile based on the user's post-purchase evaluation and acceptance of the recommended products are as follows:

[0045] When the number of times a user does not accept a recommended merchant exceeds a threshold, the user profile is adjusted; the adjustment steps specifically include:

[0046] Compare the user's average score A1 for a certain recommendation indicator with the average score A2 of all other users for the same indicator. When A1 is less than A2, increase the weight of the recommendation indicator by a first percentage; when A1 is greater than or equal to A2 and A1 is not a full score, increase the weight of the recommendation indicator by a second percentage; when A1 is a full score, reduce the weight of the recommendation indicator by a third percentage; wherein the first percentage is greater than the second percentage.

[0047] The present invention also provides an instant retail product recommendation system, comprising:

[0048] The user portrait building module is used to obtain the ratio of users' attention to logistics speed and quality to form a user portrait;

[0049] A weight allocation module is used to allocate weights of recommendation indicators based on user profiles. The recommendation indicators include logistics speed, quality, after-sales service, and price;

[0050] The urgency calculation module is used to obtain the product name of the product required by the user based on the search keyword entered by the user, and collect the system time and geographical location when the user enters the search keyword; and calculate the urgency based on the product name, the system time and geographical location when the user enters the search keyword;

[0051] The weight adjustment module is used to adjust the weight of the recommendation indicator according to the urgency;

[0052] The recommendation module is used to rate merchants selling products required by users based on recommendation indicators and recommend the products sold by merchants to users based on the merchant ratings;

[0053] The user portrait correction module is used to correct the user portrait based on the user's post-purchase evaluation and acceptance of the recommended products.

[0054] The present invention also provides a computer-readable storage medium storing computer program instructions, which are used to implement the above-mentioned instant retail product recommendation method when the computer program instructions are executed by at least one processor.

[0055] The benefits of this invention lie in: It forms a user profile by determining the ratio of a user's attention to logistics speed and quality. Recommendation metrics are weighted based on the user profile as a basis. Urgency is calculated based on the search keywords entered by the user, and the weights of the recommendation metrics are adjusted based on the urgency for the current purchase. Merchants selling the user's desired products are rated based on the recommendation metrics, and merchants are recommended to the user based on the merchant ratings. Finally, the user profile is modified based on the user's post-purchase evaluation and their acceptance of the recommended products, forming a closed-loop control system. Different from regular online shopping (for example, platforms such as JD.com or Taobao), instant retail products usually have much higher logistics requirements than regular online shopping (for example, delivery the next day or three days, and users are more concerned about product quality). The reason for the high logistics requirements is that the urgency of the demand for products is much higher than that of regular online shopping. Therefore, when the user enters the required product, the corresponding recommendation indicator weight is dynamically adjusted according to the corresponding urgency and scored, that is, the merchants are ranked from the perspective of user needs. Compared with the static total score obtained by simply evaluating the products and services provided by the merchants (that is, based on consumers' evaluation results of all products, logistics, services, etc.), it is more in line with the instant retail sales model and can recommend more suitable products to users.

[0056] This invention does not rely on artificial intelligence models, nor does it require chips or significant computing power. Despite this lack of AI support, it can still relatively accurately predict user needs and recommend the most suitable merchants. It can also self-correct based on user feedback, gradually improving itself to better reflect the user's needs.

[0057] In addition, the present invention uses the progress bar and slider modes to obtain users' attention to logistics speed and quality, which is more easily accepted by users. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the various elements or parts are not necessarily drawn according to the actual scale. Obviously, the drawings described below are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without inventive work.

[0059] Figure 1 This is a flow chart of a method for recommending instant retail products according to an embodiment of the present invention;

[0060] Figure 2The figure is a structural diagram of an instant retail product recommendation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] Herein, suffixes such as "module," "component," or "unit" used to represent elements are only used to facilitate description of the present invention and have no specific meaning. Therefore, "module," "component," or "unit" may be used interchangeably.

[0063] As used herein, terms such as "upper," "lower," "inner," "outer," "front," "back," "one end," and "the other end" indicate positions or locations based on those shown in the accompanying drawings. These terms are intended solely to facilitate and simplify the description of the present invention and are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0064] As used herein, unless otherwise expressly specified or limited, the terms "installed," "provided with," and "connected" should be understood broadly. For example, "connected" may refer to a fixed connection, a detachable connection, or an integral connection; it may refer to a mechanical connection, a direct connection, an indirect connection via an intermediate medium, or internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention on a case-by-case basis.

[0065] As used herein, "and / or" includes any and all combinations of one or more of the associated listed items.

[0066] Herein, "plurality" means two or more than two, ie, it includes two, three, four, five, etc.

[0067] Example 1

[0068] Prior art Chinese patent application CNCN202311444961.7 provides a product recommendation model training method and a product recommendation method, including: determining the target product corresponding to the user based on the user's click sequence, the click sequence including the product identification of the product clicked by the user, and the target product and the product corresponding to the click sequence belong to products on different sales platforms; constructing training samples, one training sample including the click sequence corresponding to a user and the product identification of the target product; training a pre-constructed product recommendation model based on each of the training samples until the product recommendation model meets the requirements, thereby obtaining the trained product recommendation model.

[0069] The above-mentioned existing technologies require the construction of training samples and the training of pre-built product recommendation models based on these training samples. Once the product recommendation model meets the requirements, it is then applied to actual product recommendations. Furthermore, as the number of users increases, more parameters need to be considered, and the computing power consumed during application increases.

[0070] For example, prior art Chinese patent application CN201710833187.7 provides a method for displaying full product results after a user enters product information. The method includes: entering product information, including product image information or a combination of product image information and text information; using a pre-trained neural network to extract image features from the product image information to obtain product attributes corresponding to the image features; and / or extracting keywords from the product text information to obtain product attributes corresponding to the keywords; matching the product attributes obtained from the product information with the product attributes in an established product knowledge graph to determine a target product with the product attributes. In the above prior art, a large number of training samples still need to be pre-built to train the pre-built neural network model for image recognition.

[0071] like Figure 1 As shown, the present invention provides a method for recommending instant retail products that can be run independently of an artificial intelligence model. The recommendation method in this embodiment recommends products based on the user's input of the desired products, and its specific steps include:

[0072] S101 obtains the ratio of users' attention to logistics speed and quality to form a user profile.

[0073] Instant retail refers to a retail model that integrates online and offline channels to meet consumer needs quickly and conveniently. Its key characteristics include: 1. Real-time: Instant retail emphasizes responding to consumer needs in the shortest possible time. By leveraging technology, it enables rapid order processing, delivery, and customer service. 2. Seamless integration: Instant retail emphasizes seamless integration between online and offline channels, eliminating time and space constraints for shopping through the integration of multiple channels, and providing a consistent shopping experience.

[0074] Compared to general online sales, instant retail focuses more on fast-moving consumer goods (FMCG) such as food, medicine, and daily necessities. In terms of logistics, instant retail emphasizes fast delivery, with delivery times ranging from tens of minutes to several hours.

[0075] Therefore, for instant retail consumers, logistics speed and product quality are the primary factors driving their purchases. Based on this, to more accurately recommend products to users, this example first requires obtaining the user's level of concern for logistics speed and quality. To better represent the difference in their level of concern for logistics speed and quality, this example uses a ratio to quantify their level of concern.

[0076] In real-world applications, there are many ways to determine the relative importance users place on logistics speed and quality. However, existing methods require either filling in data or multiple clicks, both of which are cumbersome. In today's fast-paced world, many users are unable to patiently input the required information.

[0077] In order to solve this problem, in this implementation, when a user registers, a progress bar is displayed on the user registration page; one end of the progress bar is the logistics speed, and the other end is the quality; a slider that can slide along the progress bar is provided on the progress bar; the user changes the ratio between the logistics speed end and the quality end by dragging the slider, and the sum of the logistics speed end ratio and the quality end ratio is fixed.

[0078] As the user moves the slider, the scale changes simultaneously at both ends. For example, initially, when the slider is in the middle, the scale at both the logistics speed and quality ends is 50%. As the user moves the slider toward the logistics speed end, the logistics speed end becomes shorter, decreasing the scale; while the quality end lengthens, increasing the scale.

[0079] The above method is very convenient and intuitive when inputting different ratios, which is easy for users to use and also makes it easier for the background to obtain data.

[0080] Of course, it is possible that some users are still unwilling to provide the ratio between their concerns about logistics speed and quality. In this case, it is only necessary to directly match a default template for such users.

[0081] S102 assigns weights of recommendation indicators based on the user portrait, where the recommendation indicators include logistics speed, quality, after-sales service, and price.

[0082] In addition to logistics speed and quality, instant retail users also pay attention to after-sales service and price. Of course, their attention to after-sales service and price is far less than that to logistics speed and quality.

[0083] Furthermore, the level of attention paid to logistics speed and quality is correlated with the level of attention paid to after-sales service and price. Generally speaking, in instant retail, users who prioritize logistics speed are generally less sensitive to price. For example, users who purchase medicine late at night prioritize speed and are not overly concerned with price as long as it's within a reasonable range. On the other hand, users who prioritize quality tend to place less emphasis on after-sales service. This is because in instant retail, the quality of products with the highest quality differences are those for food, which often lacks after-sales service.

[0084] In this embodiment, the method for allocating weights of recommendation indicators based on user profiles includes:

[0085] S1021 initializes the weights of the recommendation indicators and assigns an initial weight to each recommendation indicator.

[0086] In order to avoid users not providing the ratio of their concerns about logistics speed and quality, this embodiment directly matches a default template for such users. This template can also be used when initializing the user in this step.

[0087] For example, the weight of logistics speed is 40%, the weight of quality is 40%, the weight of after-sales service is 10%, and the weight of price is 10%.

[0088] S1022 redistributes the logistics speed weight and the quality weight according to the ratio between the user's attention to logistics speed and quality.

[0089] In step S101, a user portrait is obtained. For example, if the ratio of the user's attention to logistics speed and quality is 60%:40%, then the logistics speed weight and quality weight are redistributed according to this ratio. After redistribution, the logistics speed weight is 48%, and the quality weight is 32%.

[0090] S103 obtains the product name of the product required by the user according to the search keyword input by the user, and collects the system time and geographical location when the user inputs the search keyword.

[0091] When a user wants to buy something, they first enter a keyword related to the item in the search box. Therefore, the name of the item the user wants to buy can be easily parsed based on the keyword. When entering the search keyword, the system time and geographic location are obtained synchronously.

[0092] S104 calculates the urgency based on the product name, the system time when the user inputs the search keyword, and the geographical location.

[0093] The urgency of the user's purchase can be roughly determined based on the product name, search time, and address of the searched product. For example, buying medicine at home at midnight is likely to be very urgent. On the other hand, searching for food at work during working hours is likely not too urgent. Specifically, this step includes:

[0094] S1041 presets a plurality of urgency scoring templates to construct a template library, wherein the urgency scoring templates perform urgency scoring according to the input commodity type, purchase time type, and delivery address type.

[0095] In this step, several scoring templates can be preset in advance, for example: product type (medicine) + purchase time type (night) + delivery address (home) = urgency score (100); product type (food) + purchase time type (working hours) + delivery address (workplace) = urgency score (20);

[0096] According to the permutations and combinations, several scoring templates can be constructed for use.

[0097] In this embodiment, the delivery address defaults to the geographic location when the search keyword is entered.

[0098] S1042 classifies the goods according to the goods name to obtain the goods type; classifies the time of purchase of the goods according to the system time to obtain the purchase time type; classifies the address of purchase of the goods according to the geographical location to obtain the delivery address type.

[0099] In this embodiment, the preset classification is: the commodity types include medicines, food, and daily necessities; the purchase time types include working hours, meal times, meal preparation time, post-meal time, and nighttime; the delivery address types include home address, work address, and out-of-home address.

[0100] Based on the above classification, a variety of scoring templates can be constructed. It is understood that, based on the above classification, further refinement can be made by product type, time type, and location type. The more detailed the classification, the more scoring templates can be constructed, and the more accurate the urgency score will be.

[0101] S1043 matches an urgency score template from a template library based on the product type, purchase time type, and delivery address type to obtain an urgency score.

[0102] The current user's product type, time type, and address type are matched with corresponding templates from the template library to obtain the current user's urgency score for purchasing the product.

[0103] S105 adjusts the weight of the recommendation indicator according to the urgency.

[0104] The purpose of this step is to further adjust the weights assigned to the user profile based on urgency, thereby making adaptive adjustments to this purchase based on the user profile as the overall tone. The specific steps include:

[0105] The logistics speed weight is K1, the quality weight is K2, the after-sales service weight is K3, and the price weight is K4;

[0106] When the urgency score is greater than the first urgency threshold, K1=(K1+K2)*80%, K2=(K1+K2)*20%, K3=(K3+K4)*80%, K4=(K3+K4)*20%, K1+K2+K3+K4=1;

[0107] When the urgency score is between the second urgency threshold and the first urgency threshold, K1=(K1+K2)*60%, K2=(K1+K2)*40%, K3=(K3+K4)*60%, K4=(K3+K4)*40%, K1+K2+K3+K4=1;

[0108] When the urgency score is between the third urgency threshold and the second urgency threshold, K1=(K1+K2)*40%, K2=(K1+K2)*60%, K3=(K3+K4)*40%, K4=(K3+K4)*60%, K1+K2+K3+K4=1;

[0109] When the urgency score is less than the third urgency threshold, K1=(K1+K2)*20%, K2=(K1+K2)*80%, K3=(K3+K4)*20%, K4=(K3+K4)*80%, and K1+K2+K3+K4=1.

[0110] It can be foreseen that the first urgency threshold>the second urgency threshold>the third urgency threshold, thereby forming three consecutive intervals.

[0111] For example, if a user's current urgency score is 92, which is greater than the first urgency threshold, the weights assigned to this user based on the user profile are: K1 = 48%, K2 = 32%, K3 = 10%, and K4 = 10%.

[0112] According to the above adjustment rules, K1=64%, K2=16%, K3=16%, K4=4%.

[0113] Of course, including the weight allocation based on user portrait in step S102 and the weight adjustment in this step, the specific values ​​of the weights can be adaptively modified according to the specific situation, and this step does not impose specific restrictions or solidification.

[0114] S106 scores merchants that sell the products required by the user according to the recommendation indicators, and recommends merchants to the user based on the merchant scores.

[0115] The methods for obtaining merchant ratings in this step include:

[0116] S1061 obtains user evaluations of the merchant, including individual scores of each recommendation indicator in the user evaluations.

[0117] Suppose a merchant has 1,000 user reviews, and each user review consists of a single score for each recommendation indicator, namely, a separate score for logistics speed, quality, after-sales service, and price.

[0118] S1062 calculates the average value of the individual scores of each recommendation indicator of all users.

[0119] The average value of the individual scores of each recommendation indicator can be obtained by adding up the individual scores of each recommendation indicator in 1,000 user reviews and dividing them by the corresponding number.

[0120] S1063 multiplies the average of the individual scores of each recommended indicator by the weight of the recommended indicator to obtain an adjusted score.

[0121] For example, among 1,000 user reviews, the average scores for logistics speed, quality, after-sales service, and price are 95, 90, 100, and 98, respectively. The weights adjusted in step S105 are multiplied by the corresponding recommendation indicators, namely 95*64%=60.8, 90*16%=14.4, 100*16%=16, and 98*4%=3.92.

[0122] S1064 sums the adjusted scores of all recommendation indicators to obtain the merchant score.

[0123] The merchant rating can be obtained by summing up the individual weighted scores obtained in the above steps, that is, 60.8+14.4+16+3.92=95.12.

[0124] After obtaining merchant ratings, this embodiment provides two merchant recommendation methods, including:

[0125] First, merchants are ranked in descending order based on their ratings, and the products sold by merchants whose rankings are above the threshold are recommended to users. For example, the top 10 merchants are recommended to users.

[0126] The second is to recommend to users the products they need from merchants with a merchant rating higher than the rating threshold. For example, merchants with a merchant rating higher than 90 are recommended to users.

[0127] It is understandable that recommendations are made to users by displaying the products sold by the merchant, rather than directly recommending the merchant.

[0128] S107 modifies the user profile based on the user's post-purchase evaluation and acceptance of the recommended products.

[0129] In this implementation, after recommending merchants to users, the user profile can be modified based on user feedback, thereby achieving closed-loop management, specifically including:

[0130] When the number of times that the user does not accept the recommended merchant exceeds a threshold, the method for adjusting the user profile includes:

[0131] Compare the user's average score A1 for a certain recommendation indicator with the average score A2 of all other users for the same indicator. When A1 is less than A2, increase the weight of the recommendation indicator by a first percentage; when A1 is greater than or equal to A2 and A1 is not a full score, increase the weight of the recommendation indicator by a second percentage; when A1 is a full score, reduce the weight of the recommendation indicator by a third percentage; wherein the first percentage is greater than the second percentage.

[0132] For example, when a user does not choose a merchant recommended by the system for purchase three times in a row, it indicates that there is a problem in the weight setting of the recommendation parameters, so adjustments are made.

[0133] In this embodiment, the basis for adjustment is the user's evaluation. This evaluation is not only the evaluation of a single service, but also the comprehensive evaluation of all users.

[0134] For example, when the average score of a user's evaluation of logistics speed is 80, while the average score of other users' evaluation of logistics speed is 90, it means that the user is very demanding on logistics speed and the weight of logistics speed needs to be significantly increased, for example, by 30% on the original basis.

[0135] For example, another user's average score for logistics speed is 95, which is higher than the average score of 90 for other users. This means that the user is still relatively concerned about logistics speed, but is more easily satisfied. Therefore, the weight of logistics speed is slightly increased, for example, by 5% on the original basis.

[0136] For example, the average score of another user's evaluation of logistics speed is full marks, which means that the user does not care much about logistics speed and just habitually gives good reviews. Therefore, the weight of logistics speed can be appropriately reduced, for example, by 10% from the original basis.

[0137] It can be foreseen that after the user portrait is corrected, the next recommendation activity will be based on the corrected user portrait.

[0138] Example 2

[0139] like Figure 2 As shown, the present invention also provides an instant retail product recommendation system, comprising:

[0140] The user portrait building module is used to obtain the ratio of users' attention to logistics speed and quality to form a user portrait;

[0141] A weight allocation module is used to allocate weights of recommendation indicators based on user profiles. The recommendation indicators include logistics speed, quality, after-sales service, and price;

[0142] The urgency calculation module is used to obtain the product name of the product required by the user based on the search keyword entered by the user, and collect the system time and geographical location when the user enters the search keyword; and calculate the urgency based on the product name, the system time and geographical location when the user enters the search keyword;

[0143] The weight adjustment module is used to adjust the weight of the recommendation indicator according to the urgency;

[0144] The recommendation module is used to rate merchants selling products required by users based on recommendation indicators and recommend the products sold by merchants to users based on the merchant ratings;

[0145] The user portrait correction module is used to correct the user portrait based on the user's post-purchase evaluation and acceptance of the recommended products.

[0146] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a computer terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0148] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are protected by the present invention.

Claims

1. A method for recommending instant retail products, characterized in that include: Obtain the ratio of users' attention to logistics speed and quality to form a user profile; Assign weights to recommendation indicators based on user profiles, including logistics speed, quality, after-sales service, and price; Obtain the product name of the product required by the user based on the search keyword entered by the user, and collect the system time and geographical location when the user enters the search keyword; Calculating the urgency based on the product name, the system time, and the geographical location; Adjusting the weights of the recommended indicators according to the urgency; Rating merchants that sell the products desired by the user according to the recommendation indicators, and recommending the products sold by the merchants to the user based on the merchant ratings; If a user does not select a recommended merchant for three consecutive times, the user profile will be modified; The step of calculating the urgency based on the product name, the system time, and the geographical location specifically includes: A template library is constructed by presetting several urgency scoring templates, wherein the urgency scoring templates perform urgency scoring according to the input commodity type, purchase time type, and delivery address type; Classify the goods according to the product name to obtain the product type; classify the time of purchase of the goods according to the system time to obtain the purchase time type; classify the address of purchase of the goods according to the geographical location to obtain the delivery address type; Matching an urgency score template from a template library based on the product type, the purchase time type, and the delivery address type to obtain an urgency score; The steps for assigning weights to recommended indicators based on urgency include: The logistics speed weight is K1, the quality weight is K2, the after-sales service weight is K3, and the price weight is K4; When the urgency score is greater than the first urgency threshold, K1=(K1+K2)*80%, K2=(K1+K2)*20%, K3=(K3+K4)*80%, K4=(K3+K4)*20%, K1+K2+K3+K4=1; When the urgency score is between the second urgency threshold and the first urgency threshold, K1=(K1+K2)*60%, K2=(K1+K2)*40%, K3=(K3+K4)*60%, K4=(K3+K4)*40%, K1+K2+K3+K4=1; When the urgency score is between the third urgency threshold and the second urgency threshold, K1=(K1+K2)*40%, K2=(K1+K2)*60%, K3=(K3+K4)*40%, K4=(K3+K4)*60%, K1+K2+K3+K4=1; When the urgency score is less than the third urgency threshold, K1=(K1+K2)*20%, K2=(K1+K2)*80%, K3=(K3+K4)*20%, K4=(K3+K4)*80%, K1+K2+K3+K4=1; Wherein, the first urgency threshold>the second urgency threshold>the third urgency threshold; The steps of adjusting the user profile specifically include: comparing the user's average score A1 for logistics speed with the average score A2 for logistics speed of all other users; when A1 is less than A2, increasing the weight of logistics speed by a first percentage; when A1 is greater than or equal to A2 and A1 is not a full score, increasing the weight of logistics speed by a second percentage; when A1 is a full score, reducing the weight of logistics speed by a third percentage; wherein the first percentage is greater than the second percentage.

2. The instant retail product recommendation method according to claim 1, characterized in that The step of obtaining the ratio of users' attention to logistics speed and quality specifically includes: When a user registers, a progress bar is displayed on the user registration page; one end of the progress bar represents logistics speed, and the other end represents quality; a slider that can slide along the progress bar is provided on the progress bar; the user changes the ratio between the logistics speed end and the quality end by dragging the slider, and the sum of the logistics speed end ratio and the quality end ratio is a constant value; Initially, the slider is located in the middle of the progress bar, so that the logistics speed end ratio and the quality end ratio are both 50%.

3. The instant retail product recommendation method according to claim 1, characterized in that The steps for allocating weights of recommendation indicators based on user profiles include: A default template is matched for the user; in the default template, the weight of logistics speed is 40%, the weight of quality is 40%, the weight of after-sales service is 10%, and the weight of price is 10%; The logistics speed weight and quality weight are redistributed according to the ratio between users' attention to logistics speed and quality.

4. The instant retail product recommendation method according to claim 3, characterized in that: The commodity types include medicines, food, and daily necessities; the purchase time types include working hours, meal times, meal preparation time, post-meal time, and nighttime; the delivery address types include home address, work address, and out-of-home address.

5. The instant retail product recommendation method according to claim 1, characterized in that The steps for scoring merchants selling products required by users based on recommendation indicators include: Obtain user reviews of the merchant, including individual scores for each recommendation indicator; Calculate the average score of each recommendation indicator for all users; Multiply the average of the individual scores of each recommended indicator by the weight of the recommended indicator to obtain the adjusted score; The adjusted scores of all recommendation indicators are summed to obtain the merchant score.

6. The instant retail product recommendation method according to claim 1, characterized in that The steps for recommending products to users based on merchant ratings include: Sort merchants by their ratings from highest to lowest, and recommend to users the products they need from merchants whose rankings are higher than the ranking threshold; or Recommend to users the products needed by users that are sold by merchants whose merchant ratings are higher than the rating threshold.

7. A computer-readable storage medium having computer program instructions stored therein, characterized in that: When the computer program instructions are executed by at least one processor, they are used to implement the instant retail product recommendation method according to any one of claims 1 to 6.

8. An instant retail product recommendation system, characterized by include: The user portrait building module is used to obtain the ratio of users' attention to logistics speed and quality to form a user portrait; A weight allocation module is used to allocate weights of recommendation indicators based on user profiles. The recommendation indicators include logistics speed, quality, after-sales service, and price; The urgency calculation module is used to obtain the product name of the product required by the user based on the search keyword entered by the user, and collect the system time and geographical location when the user enters the search keyword; and calculate the urgency based on the product name, the system time and geographical location when the user enters the search keyword; The weight adjustment module is used to adjust the weight of the recommendation indicator according to the urgency; The recommendation module is used to rate merchants selling products required by users based on recommendation indicators and recommend the products sold by merchants to users based on the merchant ratings; A user profile correction module is used to correct the user profile based on the user's post-purchase evaluation if the user has not selected the recommended merchant for three consecutive times. Specifically, it is used to compare the user's average score A1 for logistics speed with the average score A2 for logistics speed of all other users. If A1 is less than A2, the weight of logistics speed is increased by a first percentage; if A1 is greater than or equal to A2 and A1 is not a perfect score, the weight of logistics speed is increased by a second percentage; if A1 is a perfect score, the weight of logistics speed is reduced by a third percentage; wherein the first percentage is greater than the second percentage; The urgency calculation module is specifically configured to preset a plurality of urgency scoring templates to construct a template library, wherein the urgency scoring templates perform urgency scoring based on the input commodity type, purchase time type, and delivery address type; classify commodities according to commodity names to obtain commodity types; classify the time of purchase of commodities according to system time to obtain purchase time types; classify the addresses of purchase of commodities according to geographic locations to obtain delivery address types; and match urgency scoring templates from the template library based on the matching of commodity type, purchase time type, and delivery address type to obtain urgency scores; The weight adjustment module assigns weights to recommendation indicators based on urgency, specifically including: The logistics speed weight is K1, the quality weight is K2, the after-sales service weight is K3, and the price weight is K4; When the urgency score is greater than the first urgency threshold, K1=(K1+K2)*80%, K2=(K1+K2)*20%, K3=(K3+K4)*80%, K4=(K3+K4)*20%, K1+K2+K3+K4=1; When the urgency score is between the second urgency threshold and the first urgency threshold, K1=(K1+K2)*60%, K2=(K1+K2)*40%, K3=(K3+K4)*60%, K4=(K3+K4)*40%, K1+K2+K3+K4=1; When the urgency score is between the third urgency threshold and the second urgency threshold, K1=(K1+K2)*40%, K2=(K1+K2)*60%, K3=(K3+K4)*40%, K4=(K3+K4)*60%, K1+K2+K3+K4=1; When the urgency score is less than the third urgency threshold, K1=(K1+K2)*20%, K2=(K1+K2)*80%, K3=(K3+K4)*20%, K4=(K3+K4)*80%, K1+K2+K3+K4=1; The first urgency threshold>the second urgency threshold>the third urgency threshold.

Images