Instant retail commodity recommendation method and system, and storage medium

Abstract

The invention discloses an instant retail commodity recommendation method and system, and a storage medium, and belongs to the technical field of commodity recommendation. The method comprises the following steps: acquiring a proportion of attention of a user to logistics speed and quality, and forming a user portrait; distributing weights of recommendation indexes according to the user portraits; calculating the urgency degree according to the commodity name, the system time when the user inputs the search keyword and the geographic position; adjusting the weight of the recommendation index according to the urgency degree; scoring merchants selling the commodities required by the user, and recommending the merchants to the user; and correcting the user portrait according to the evaluation after the user purchases and the acceptability of the recommended commodity. The method does not depend on an artificial intelligence model and gets rid of dependence on chips and large computing power. And although no artificial intelligence support exists, the demand of the user can still be accurately predicted, so that the most suitable merchant is recommended for the user.

Description

[0001] Divisional Application This application is a divisional application of the Chinese invention patent application [Application No.: 2024109465474] [Title: An Instant Retail Commodity Recommendation Method, System, and Storage Medium] filed on July 15, 2024. Technical Field

[0002] The present invention relates to the technical field of commodity recommendation, and particularly to an instant retail commodity recommendation method, system, and storage medium. Background Art

[0003] Instant retail is a retail format that meets local instant needs by placing orders online immediately and fulfilling orders offline immediately, relying on local retail supplies. Instant retail fills the "vacuum zone" of the integration of online and offline. "Localization" is a significant feature of instant retail, realizing the onlineization of the transaction process and the facilitation of order fulfillment and distribution.

[0004] In order to improve local supply capacity and expand consumer demand, each selling platform has deployed commodity recommendation strategies, which can recommend various brands of such commodities and users selling such commodities to users based on the commodities input by the users.

[0005] Existing recommendation methods generally, when a user searches for the required commodity, simply make brute-force recommendations based on the distance or comprehensive score of the store, or make recommendations based on artificial intelligence models and big data. For example, JD.com's "Same-Day Delivery" and Meituan Takeaway, etc.

[0006] In the actual operation process, it is found that although the brute-force recommendation method has low requirements, the recommended items often do not meet the requirements of consumers. Although the commodities recommended by artificial intelligence models and big data have relatively high accuracy, as the user group grows and the data becomes increasingly large, calculating through artificial intelligence models will consume huge computing power and reduce the operating speed of the entire system.

[0007] For example, Chinese Patent Application CNCN202311444961.7 provides a commodity recommendation model training method and a commodity recommendation method, including: determining the target commodity corresponding to the user according to the click sequence of the user, where the click sequence includes the commodity identifiers of the commodities clicked by the user, and the target commodity and the commodities corresponding to the click sequence belong to commodities of different selling platforms; constructing training samples, where one training sample includes the click sequence corresponding to one user and the commodity identifier of the target commodity; training a pre-constructed commodity recommendation model based on each training sample until the commodity recommendation model meets the requirements, and obtaining the trained commodity recommendation model.

[0008] For another example, Chinese Patent Application CN201710833187.7 provides a method for displaying all results of a commodity after a user enters commodity information. The method includes: entering commodity information, including picture information of the commodity or a combination of picture information and text information of the commodity; using a pre-trained neural network to extract picture features in the picture information of the commodity and obtain commodity attributes corresponding to the picture features; and / or extracting keywords in the text information of the commodity and obtaining commodity attributes corresponding to the keywords; matching the commodity attributes obtained from the commodity information with the commodity attributes in the established commodity knowledge graph to determine target commodities having the commodity attributes.

[0009] The above-mentioned existing technologies all require a large number of pre-constructed training samples to train a pre-constructed neural network model, that is, they rely on artificial intelligence. And the dependence on artificial intelligence is actually a dependence on computing power. More specifically, it is a dependence on chips. Therefore, how to get rid of the dependence on chips is an urgent problem to be solved. Summary of the Invention

[0010] The purpose of the present invention is to provide an instant retail commodity recommendation method, system, and storage medium, which partially solve or alleviate the above deficiencies in the prior art, and can recommend the most suitable specified commodities to users as much as possible on the basis of reducing computing power consumption, thereby improving the user experience.

[0011] To solve the above-mentioned technical problems, the present invention specifically adopts the following technical solutions: An instant retail commodity recommendation method includes: Obtaining the ratio between the user's attention to logistics speed and quality to form a user profile; Allocating weights to recommendation indicators according to the user profile, where the recommendation indicators include logistics speed, quality, after-sales service, and price; Obtaining the commodity name of the commodity required by the user according to the search keywords input by the user, and collecting the system time and geographical location when the user inputs the search keywords; Calculating the urgency according to the commodity name, the system time, and the geographical location; Adjusting the weights of the recommendation indicators according to the urgency; Rating the merchants selling the commodity required by the user according to the recommendation indicators, and recommending the commodity sold by the merchant to the user based on the merchant rating; Revising the user profile according to the user's evaluation after purchase and the acceptance of the recommended commodity.

[0012] As an improvement, the step of obtaining the ratio between the user's 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 the logistics speed, and the other end represents the quality; a slider that can slide along the progress bar is set 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 ratio of the logistics speed end and the ratio of the quality end is a constant value.

[0013] As an improvement, the steps of allocating the weights of the recommendation indicators according to the user portrait specifically include: Initialize the weights of the recommendation indicators and assign initial weights to each recommendation indicator; Reallocate the weights of the logistics speed and the quality according to the ratio between the user's attention to the logistics speed and the quality.

[0014] As an improvement, the steps of calculating the urgency according to the commodity name, the system time, and the geographical location specifically include: Preset several urgency scoring templates to build a template library, and the urgency scoring templates score the urgency according to the input commodity type, purchase time type, and delivery address type; Classify the commodity according to the commodity name to obtain the commodity type; classify the time of purchasing the commodity according to the system time to obtain the purchase time type; classify the address of purchasing the commodity according to the geographical location to obtain the delivery address type; Match the urgency scoring template from the template library based on the commodity type, the purchase time type, and the delivery address type to obtain the urgency score.

[0015] As an improvement, the commodity type includes medicines, foods, and daily necessities; the purchase time type includes working hours, dining time, meal preparation time, post-meal time, and night; the delivery address type includes home address, work address, and out address.

[0016] As an improvement, the method of allocating weights to the recommendation indicators according to the urgency includes: The weight of the logistics speed is K1, the weight of the quality is K2, the weight of the after-sales service is K3, and the weight of the price 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%, and 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%, and 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%, and 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%, and K1 + K2 + K3 + K4 = 1.

[0017] As an improvement, a method for rating merchants who sell the goods required by the user according to the recommended indicators includes: Obtain the user evaluations of the merchant, and the individual ratings of each recommended indicator in the user evaluations; Calculate the average value of the individual ratings of each recommended indicator for all users; Multiply the average value of the individual rating of each recommended indicator by the weight of this recommended indicator to obtain the adjusted rating; Sum up the adjusted ratings of all recommended indicators to obtain the merchant rating.

[0018] As an improvement, the steps of recommending merchants to users based on the merchant rating specifically include: Sort the merchants in descending order of the merchant rating, and recommend the goods required by the user sold by the merchants ranked higher than the ranking threshold to the user; or, Recommend the goods required by the user sold by the merchants with a merchant rating higher than the rating threshold to the user.

[0019] As an improvement, the steps of correcting the user portrait according to the user's evaluation after purchase and the acceptance of the recommended goods specifically lie in: Adjust the user portrait when the number of times the user does not accept the recommended merchant exceeds the number threshold; the adjustment steps specifically include: Compare the average rating A1 of a certain recommended indicator of the user with the average rating A2 of all other users for a certain indicator. When A1 < A2, increase the weight of this recommended indicator by the first percentage; when A1 ≥ A2 and A1 is not the full score, increase the weight of this recommended indicator by the second percentage; when A1 is the full score, reduce the weight of this recommended indicator by the third percentage; where the first percentage > the second percentage.

[0020] The present invention also provides an instant retail commodity recommendation system, including: A user portrait construction module, configured to obtain the ratio between the user's attention to the logistics speed and quality, and form a user portrait; A weight distribution module, configured to distribute weights of recommendation metrics according to a user profile, where the recommendation metrics include logistics speed, quality, after-sales service, and price; An urgency calculation module, configured to obtain the product name of the product required by the user according to the search keywords input by the user, and collect the system time and geographical location when the user inputs the search keywords; calculate the urgency according to the product name, the system time when the user inputs the search keywords, and the geographical location; A weight adjustment module, configured to adjust the weights of the recommendation metrics according to the urgency; A recommendation module, configured to score merchants selling the products required by the user according to the recommendation metrics, and recommend the products sold by the merchants to the user based on the merchant scores; A user profile correction module, configured to correct the user profile according to the user's evaluation after purchase and the acceptance of the recommended products.

[0021] The present invention also provides a computer-readable storage medium, which stores computer program instructions, and when the computer program instructions are executed by at least one processor, are used to implement the above-mentioned instant retail product recommendation method.

[0022] The advantages of the present invention are as follows: The present invention forms a user profile by obtaining the ratio between the user's attention to logistics speed and quality. The weights of the recommendation metrics are distributed according to the user profile as a keynote. The urgency is calculated according to the search keywords input by the user, and the weights of the recommendation metrics are adjusted according to the urgency for this shopping. The merchants selling the products required by the user are scored according to the recommendation metrics, and the merchants are recommended to the user based on the merchant scores. Finally, the user profile is corrected according to the user's evaluation after purchase and the acceptance of the recommended products, forming a closed-loop control. Different from conventional online shopping (such as platforms like JD.com or Taobao), instant retail products usually have much higher requirements for logistics than conventional online shopping (for example, arriving the next day or within three days, and users pay more attention to product quality). The reason for the high requirement for logistics is that the urgency of the required products is much higher than that of conventional online shopping. Therefore, when the user inputs the required products, the corresponding weights of the recommendation metrics are dynamically adjusted according to the corresponding urgency and scored, that is, the merchants are ranked from the perspective of user needs. Compared with the way of obtaining a static total score simply from the perspective of 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 sales model of instant retail and can recommend more suitable products for users.

[0023] The present invention does not rely on an artificial intelligence model and gets rid of the dependence on chips and high computing power. Although without the support of artificial intelligence, the present invention can still relatively accurately predict the needs of users, so as to recommend the most suitable merchants for users. The present invention can also self-correct according to user feedback, so as to gradually improve itself and make it more in line with the true appearance of users.

[0024] In addition, the present invention obtains the attention of users to the logistics speed and quality through the mode of progress bars and sliders, which is more acceptable to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts do not necessarily draw according to the actual scale. Obviously, the following-described drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0026] Figure 1 It is a flowchart of a method for recommending instant retail goods according to an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a system for recommending instant retail goods according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] In this article, suffixes such as "module", "component" or "unit" used to represent elements are only for the convenience of the description of the present invention, and they have no specific meaning by themselves. Therefore, "module", "component" or "unit" can be used interchangeably.

[0029] In this text, the orientation or positional relationships indicated by terms such as "upper", "lower", "inner", "outer", "front", "rear", "one end", "the other end", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation on the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0030] In this text, unless otherwise clearly specified and defined, terms such as "installed", "provided with", "connected", etc. shall be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, and can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] In this text, "and / or" includes any and all combinations of one or more of the listed related items.

[0032] In this text, "a plurality of" means two or more, that is, it includes two, three, four, five, etc.

[0033] Embodiment 1 The Chinese patent application CNCN202311444961.7 in the prior art provides a method for training a product recommendation model and a product recommendation method, including: determining a target product corresponding to the user according to the user's click sequence, where the click sequence includes the product identifiers of the products clicked by the user, and the target product and the products corresponding to the click sequence belong to products on different sales platforms; constructing training samples, where one training sample includes the click sequence corresponding to one user and the product identifier 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, and obtaining the trained product recommendation model.

[0034] In the above prior art, it is necessary to construct training samples and train a pre-constructed product recommendation model based on each of the training samples. After the product recommendation model meets the requirements, it is then applied to actual product recommendations. And as the number of users increases, more parameters need to be considered, and the computing power consumed during application is greater.

[0035] For another example, the Chinese patent application CN201710833187.7 in the prior art provides a method for displaying all results of a commodity after a user enters commodity information. The method includes: entering commodity information, including picture information of the commodity or a combination of picture information and text information of the commodity; using a pre-trained neural network to extract picture features in the picture information of the commodity and obtain commodity attributes corresponding to the picture features; and / or extracting keywords in the text information of the commodity and obtaining commodity attributes corresponding to the keywords; matching the commodity attributes obtained from the commodity information with the commodity attributes in the established commodity knowledge graph to determine target commodities having the commodity attributes. In the above prior art, a large number of training samples still need to be pre-constructed to train the pre-constructed neural network model for picture recognition.

[0036] As Figure 1 shown, the present invention provides an instant retail commodity recommendation method that can operate without an artificial intelligence model. The recommendation method in this embodiment is based on the input of a user's desired commodity and specifically includes the following steps: S101 Obtain the ratio between a user's attention to the logistics speed and quality to form a user profile.

[0037] Instant retail refers to a retail model that integrates online and offline channels to meet consumers' needs in a fast and convenient manner. Its characteristics mainly include: First, real-time: Instant retail emphasizes responding to consumers' needs within the shortest possible time. By using technological means, fast order processing, goods delivery, and customer service are achieved. Second, seamless connection: Instant retail emphasizes the seamless connection between online and offline. By integrating multiple channels, the time and space limitations of shopping are eliminated, providing a consistent shopping experience.

[0038] Compared with general online sales, the commodities sold in instant retail are more focused on fast-moving consumer goods such as food, medicine, and daily necessities. In terms of logistics, instant retail emphasizes fast delivery, and its logistics time ranges from dozens of minutes to several hours.

[0039] Therefore, for consumers of instant retail, the logistics speed and commodity quality play a dominant role in their consumption. Based on this, in order to more accurately recommend commodities to users, in this embodiment, it is first necessary to obtain the user's attention to the logistics speed and quality. In order to better express the difference between the attention to the logistics speed and quality, in this embodiment, a ratio method is used to quantify the attention to the two.

[0040] In actual applications, there are various ways to obtain the ratio between a user's attention to the logistics speed and quality. However, existing methods are either cumbersome, requiring data entry or multiple selections. In today's fast-paced life, a large number of users cannot patiently input as required.

[0041] To solve this problem, when a user registers in this embodiment, a progress bar is displayed on the user registration page; one end of the progress bar represents the logistics speed, and the other end represents 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 ratio of the logistics speed end and the ratio of the quality end remains fixed and unchanged.

[0042] When the user pulls the slider, the change in the ratio is displayed at both ends simultaneously. For example, initially, the slider is in the middle, and the ratio of both the logistics speed end and the quality end is 50%. When the user pulls the slider towards the logistics speed end, at this time, the logistics speed end becomes shorter and the ratio decreases; while the quality end becomes longer and the ratio also increases synchronously.

[0043] The above method is very convenient and intuitive when inputting different ratios, facilitating user use, and also making it easier for the background to obtain data.

[0044] Of course, it is also possible that some users are still unwilling to provide the ratio between the attention to the logistics speed and the quality. In this case, only a default template needs to be directly matched for such users.

[0045] S102 Assign weights to the recommendation indicators according to the user profile. The recommendation indicators include logistics speed, quality, after-sales service, and price.

[0046] In addition to logistics speed and quality, users of instant retail also have a certain degree of attention to after-sales service and price. Of course, the attention to after-sales service and price is far less than the attention to logistics speed and quality.

[0047] And there is also a certain correlation between the attention to logistics speed and quality and the attention to after-sales service and price. Generally speaking, in instant retail, users who pay attention to logistics speed generally have a low sensitivity to price. For example, users who buy medicine late at night just need the logistics speed and don't care too much about the price as long as it is within a reasonable range. And users who pay attention to quality don't value after-sales service instead. The reason is that in instant retail, products with large quality differences are mainly food and other products that don't have much after-sales service.

[0048] In this embodiment, the method for assigning weights to the recommendation indicators according to the user profile includes: S1021 Initialize the weights of the recommendation indicators and assign initial weights to each recommendation indicator.

[0049] To avoid users not providing the ratio between the attention to the logistics speed and the quality, this embodiment directly matches a default template for such users. This step can also use this template when initializing the user.

[0050] 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%.

[0051] S1022 Reallocate the weights of logistics speed and quality according to the ratio between the user's attention to logistics speed and quality.

[0052] In step S101, a user profile is obtained. For example, the ratio between the user's attention to logistics speed and quality is 60%:40%. Then, reallocate the weights of logistics speed and quality according to this ratio. After reallocation, the weight of logistics speed is 48% and the weight of quality is 32%.

[0053] S103 Obtain the product name of the product required by the user according to the search keywords input by the user, and collect the system time and geographical location when the user inputs the search keywords.

[0054] When purchasing a product, the user will first enter keywords about the product in the search box. Therefore, it is easy to parse the product name of the product that the user needs to purchase according to the keywords. When inputting the search keywords, synchronously obtain the system time and geographical location.

[0055] S104 Calculate the urgency according to the product name, the system time when the user inputs the search keywords, and the geographical location.

[0056] Based on the product name of the searched product, the search time, and the address, it is possible to roughly judge the urgency of the user's purchase of this product. For example, buying medicine at home at midnight is likely to be very urgent. While searching for food at the workplace during working hours is likely not to be very urgent. Specifically, this step specifically includes: S1041 Preset several urgency scoring templates to build a template library. The urgency scoring templates perform urgency scoring according to the input product type, purchase time type, and delivery address type.

[0057] 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); According to permutations and combinations, several scoring templates can be constructed for backup.

[0058] In this embodiment, the delivery address is defaulted to the geographical location when the search keywords are input.

[0059] S1042 Classify the products according to the product names to obtain the product types; classify the purchase time of the products according to the system time to obtain the purchase time types; classify the delivery addresses of the products according to the geographical locations to obtain the delivery address types.

[0060] In this embodiment, the preset classification conditions are as follows: the product types include medicines, foods, and daily necessities; the purchase time types include working hours, dining hours, meal preparation hours, post-meal hours, and nighttime; the delivery address types include home addresses, work addresses, and out-of-town addresses.

[0061] Based on the above classifications, multiple scoring templates can be constructed. It can be understood that on the basis of the above classifications, the product types, time types, and location types can be further refined. The more detailed the classification, the more scoring templates can be constructed, and the more accurate the urgency scoring will be.

[0062] S1043 Match the urgency scoring template from the template library based on the product type, purchase time type, and delivery address type to obtain the urgency score.

[0063] Match the corresponding templates from the template library for the product type, time type, and address type of the current user, so as to obtain the urgency score for the current user to purchase products.

[0064] S105 Adjust the recommended index weights according to the urgency.

[0065] The purpose of this step is to further adjust the weights assigned according to the user portrait based on the urgency, so as to make an adaptive adjustment for this shopping on the premise that the user portrait is the main tone. The specific steps 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%, and 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%, and 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%, and 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%, and K1 + K2 + K3 + K4 = 1.

[0066] It can be foreseen that the first urgency threshold > the second urgency threshold > the third urgency threshold, thus forming three consecutive intervals.

[0067] For example, if a user's current urgency score is 92, which is greater than the first urgency threshold. The weights assigned to the user according to the user profile are: K1 = 48%, K2 = 32%, K3 = 10%, K4 = 10%.

[0068] According to the above adjustment rules, K1 = 64%, K2 = 16%, K3 = 16%, K4 = 4%.

[0069] Of course, including the weight assignment based on the user profile 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 make specific restrictions and fixations.

[0070] S106 Rate the merchants selling the goods required by the user according to the recommendation indicators, and recommend merchants to the user based on the merchant ratings.

[0071] The method for obtaining the merchant ratings in this step specifically includes: S1061 Obtain the user evaluations of the merchants, and the individual ratings of each recommendation indicator in the user evaluations.

[0072] Suppose a merchant has 1000 user evaluations, and each user evaluation includes individual ratings for each recommendation indicator, that is, separate ratings for logistics speed, quality, after-sales service, and price.

[0073] S1062 Calculate the average value of the individual ratings of each recommendation indicator for all users.

[0074] Add up the individual ratings of each recommendation indicator in the 1000 user evaluations and divide by the corresponding quantity to obtain the average value of the individual ratings of each recommendation indicator.

[0075] S1063 Multiply the average value of the individual rating of each recommendation indicator by the weight of that recommendation indicator to obtain the adjusted rating.

[0076] 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. Multiply the adjusted weights in step S105 by the corresponding recommendation indicators, i.e., 95 * 64% = 60.8, 90 * 16% = 14.4, 100 * 16% = 16, 98 * 4% = 3.92.

[0077] S1064 Sum up the scores of all recommendation indicators after adjustment to obtain the merchant score.

[0078] Sum up the single-item weighted scores obtained in the above steps to obtain the merchant score, i.e., 60.8 + 14.4 + 16 + 3.92 = 95.12.

[0079] After obtaining the merchant score, this embodiment provides two merchant recommendation methods, including: One is to sort the merchants in descending order according to the merchant score, and recommend the goods required by the user sold by the merchants ranked higher than the ranking threshold to the user. For example, recommend the top 10 merchants ranked by merchant score to the user.

[0080] The other is to recommend the goods required by the user sold by the merchants with a merchant score higher than the score threshold to the user. For example, recommend the merchants with a merchant score higher than 90 to the user.

[0081] It can be understood that during the recommendation, it is recommended to the user in the form of displaying the goods sold by the merchant, rather than directly recommending the merchant.

[0082] S107 Modify the user portrait according to the user's evaluation after purchase and the acceptance degree of the recommended goods.

[0083] In this embodiment, after recommending merchants to the user, the user portrait can also be modified according to the user's feedback, so as to achieve closed-loop management, specifically including: The method for adjusting the user portrait when the number of times the user does not accept the recommended merchant exceeds the number threshold includes: Compare the average score A1 of the user for a certain recommendation indicator with the average score A2 of all other users for a certain indicator. When A1 < A2, increase the weight of this recommendation indicator by the first percentage; when A1 ≥ A2 and A1 is not full score, increase the weight of this recommendation indicator by the second percentage; when A1 is full score, reduce the weight of this recommendation indicator by the third percentage; where the first percentage > the second percentage.

[0084] For example, when the user does not choose the merchant recommended by the system for three consecutive times to make a purchase, it indicates that there is a problem with the weight setting of the recommendation parameters, so an adjustment is made.

[0085] In this embodiment, the basis for adjustment is the user's evaluation. This evaluation is not just for a single service, but a comprehensive evaluation of all the user's evaluations.

[0086] For example, when the average score of a user's evaluation of the logistics speed is 80, while the average score of other users' evaluations of the logistics speed is 90, it indicates that this user is very demanding regarding the logistics speed and the weight of the logistics speed needs to be significantly increased, such as increasing it by 30% on the original basis.

[0087] Another example is that another user's average score for the evaluation of the logistics speed is 95, which is higher than the average score of 90 of other users. This indicates that this user still cares about the logistics speed but is more easily satisfied. Therefore, the weight of the logistics speed is slightly increased, such as increasing it by 5% on the original basis.

[0088] Another example is that another user's average evaluation of the logistics speed is full marks, indicating that this user doesn't really care about the logistics speed and is just giving a habitual good review. Therefore, the weight of the logistics speed can be appropriately reduced, such as reducing it by 10% on the original basis.

[0089] It can be foreseen that after the user portrait is corrected, the next recommendation activity will be based on the corrected user portrait.

[0090] Embodiment 2 As Figure 2 shown, the present invention also provides an instant retail product recommendation system, including: A user portrait construction module for obtaining the ratio between the user's attention to the logistics speed and quality to form a user portrait; A weight allocation module for allocating the weights of the recommendation indicators according to the user portrait, and the recommendation indicators include logistics speed, quality, after-sales service, and price; An urgency calculation module for obtaining the product name of the product required by the user according to the search keyword input by the user, and collecting the system time and geographical location when the user inputs the search keyword; calculating the urgency according to the product name, the system time when the user inputs the search keyword, and the geographical location; A weight adjustment module for adjusting the weights of the recommendation indicators according to the urgency; A recommendation module for scoring the merchants selling the products required by the user according to the recommendation indicators, and recommending the products sold by the merchants to the user based on the merchant scores; A user portrait correction module for correcting the user portrait according to the user's evaluation after purchase and the acceptance of the recommended products.

[0091] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element.

[0092] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a computer terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0093] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. A method for recommending instant retail products, characterized in that include: Obtain the ratio of users’ concerns about logistics speed and quality to form a user profile; Allocate weights of recommendation indicators according to user portraits, where the recommendation indicators include logistics speed, quality, after-sales service, and price; Obtain the product name of the product required by the user according to the search keyword entered by the user, and collect the system time and geographical location when the user enters the search keyword; Calculate the urgency according to the product name, the system time and the geographical location; Adjusting the weight of the recommended indicator according to the urgency; Scoring a merchant that sells the product required by the user according to the recommendation index, and recommending the product sold by the merchant to the user based on the merchant score; If the user does not select the recommended merchant for three consecutive times, the user profile will be modified; The step of calculating the urgency according to the product name, the system time and the geographical location specifically includes: A plurality of urgency scoring templates are preset to construct a template library, wherein the urgency scoring template performs urgency scoring according to the input commodity type, purchase time type, and delivery address type; Classify the goods according to the goods names to obtain the goods types; 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 commodity type, the purchase time type, and the delivery address type to obtain an urgency score; The steps of assigning weights to the recommended indicators according to 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 step of adjusting the user portrait specifically includes: comparing the user's average score A1 for logistics speed with the average score A2 for logistics speed of all other users, and when A1<A2, increasing the weight of logistics speed by a first percentage; when A1≥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>the second percentage.

2. A method for recommending instant retail products according to claim 1, characterized in that The step of obtaining the ratio between the user's 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 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; 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 commodity recommendation method according to claim 1, characterized in that The steps of allocating weights of recommendation indicators according to user portraits 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 reallocated according to the ratio between users' concerns about logistics speed and quality.

4. The instant retail commodity 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 time, meal preparation time, after-meal time, and night time; the delivery address types include home address, work address, and out-of-town address.

5. The instant retail commodity recommendation method according to claim 1, characterized in that The steps of scoring merchants selling products required by users according to the recommendation indicators specifically include: Obtain user reviews of the merchant, including individual scores of each recommendation indicator in the user reviews; 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 up to obtain the merchant score.

6. The instant retail commodity recommendation method according to claim 1, characterized in that The steps of recommending products to users based on merchant ratings include: Sort the merchants in descending order according to their ratings, and recommend to the user the products needed by the user sold by merchants whose rankings are higher than the ranking threshold; or The products required by the users sold by merchants whose merchant scores are higher than the score threshold are recommended to the users.

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 as described in any one of claims 1 to 6.

8. An instant retail product recommendation system, characterized in that include: User portrait building module, used to obtain the ratio of users' attention to logistics speed and quality, and form a user portrait; A weight allocation module is used to allocate weights of recommendation indicators according to user portraits, and 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 according to the search keyword input by the user, and collect the system time and geographical location when the user inputs the search keyword; calculate the urgency according to the product name, the system time and geographical location when the user inputs the search keyword; A weight adjustment module is used to adjust the weight of the recommendation indicator according to the urgency; The recommendation module is used to rate the merchants selling the goods required by the user according to the recommendation index, and recommend the goods sold by the merchants to the user based on the merchant ratings; A user portrait correction module is used to correct the user portrait according to the user's post-purchase evaluation when the user does not select 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, and when A1 is less than A2, the weight of logistics speed is increased by a first percentage; when A1 is greater than or equal to A2 and A1 is not a full score, the weight of logistics speed is increased by a second percentage; when A1 is a full 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 used to preset a number of urgency scoring templates to build a template library, wherein the urgency scoring template performs urgency scoring according to the input commodity type, purchase time type, and delivery address type; and classifies commodities according to commodity names to obtain commodity types; classifies the time of commodity purchase according to system time to obtain purchase time types; classifies the address of commodity purchase according to geographical location to obtain delivery address types; and matches the urgency scoring template from the template library based on the commodity type, purchase time type, and delivery address type to obtain the urgency score; The weight adjustment module allocates weights to the recommendation indicators according to the 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; Among them, the first urgency threshold>the second urgency threshold>the third urgency threshold.

Images