E-commerce sales intelligent information recommendation system

Abstract

The invention, which belongs to the technical field of e-commerce sales information recommendation, discloses an e-commerce sales intelligent information recommendation system comprising a user module, a retrieval module and a recommendation module. The user module is used for inputting demand information by a user and sending the identified demand information to the retrieval module; the retrieval module is used for performing sales information retrieval according to the demand information and setting target channels, and the target channels refer to various selected e-commerce platforms; inputting the obtained sales information into each target channel for retrieval to obtain a large amount of sales information, evaluating the obtained sales information to obtain corresponding recommendation values, and arranging the sales information according to a sequence of the recommendation values from high to low to obtain a first sequence; supplementing corresponding quality characteristic data; and the recommendation module is used for recommending the sales information to the user, acquiring a corresponding first sequence, and recommending the sales information to the user according to the first sequence.

Description

[0001] This application is a divisional application of the application filed on November 4, 2024, with application number 2024115566735 and invention name “An intelligent information recommendation system for online sales”. Technical Field

[0002] The present invention belongs to the technical field of sales information recommendation, and specifically is an e-commerce sales intelligent information recommendation system. Background Art

[0003] In order to meet the growing shopping and personalized needs of consumers. With the rapid development of the Internet and e-commerce, people can shop online easily, but the numerous products and information also bring users the problems of difficulty in selection and information overload.

[0004] Moreover, the existing sales information recommendation system has unsatisfactory recommendation effects in actual application, especially as more and more consumers are tired of message push and basically directly delete the pushed sales information without browsing it at all, or directly block the message push of various shopping platforms. As a result, the existing sales information recommendation system is less effective and constitutes harassment information for consumers. There is a lack of a way to determine relevant sales information. Most consumers cannot understand the details of the sales product information and have concerns about product quality and being deceived. Therefore, in order to solve the above problems and realize sales information recommendation for consumers, the present invention provides an e-commerce sales intelligent information recommendation system. Summary of the invention

[0005] In order to solve the problems existing in the above solutions, the present invention provides an e-commerce sales intelligent information recommendation system.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An e-commerce sales intelligent information recommendation system, including a user module, a retrieval module and a recommendation module; The user module is used for the user to input demand information and send the identified demand information to the search module; The retrieval module is used to retrieve sales information based on demand information and set target channels, which refer to various selected e-commerce platforms; input the obtained demand information into each target channel for retrieval, obtain a large amount of sales information, evaluate the obtained sales information, obtain corresponding recommendation values, arrange each sales information in order from high to low according to the recommendation value, and obtain a first sequence; and supplement the corresponding quality characteristic data.

[0007] Further methods for setting up goal funnels include: Identify the sales channels available, and calculate the average recommendation value corresponding to each product category in the sales channels; Obtain the market share corresponding to each sales channel, and match the corresponding correction factor based on the market share; Mark the obtained correction factor and average recommendation value as ε and PTZ respectively. Calculate the corresponding screening value SP according to the screening formula SP = ε × PTZ, and remove the product categories with the screening value lower than the threshold X2 from the sales channels; Set the target channels based on the processing results of each product category, and assign the corresponding target classification labels.

[0008] Further, for the calculation of the average recommendation value, sampling is used for the calculation.

[0009] Further, the recommendation value is calculated based on the product quality and price corresponding to the sales information.

[0010] Further, the methods for evaluating the recommendation value include: Identify the quality data and price data corresponding to each sales information, evaluate the obtained quality data to obtain the corresponding quality value, and mark the obtained quality value as PZ; Set the corresponding present value and marked value based on the price data, and mark the obtained present value and marked value as ZX and BZ respectively; Calculate the corresponding recommendation value according to the recommendation value formula TZ = PZ / (BZ - ZX).

[0011] Further, optimize the recommendation value of each sales information according to the user usage records. Real-time count the number of times users select each target channel, calculate the usage proportion of each target channel, integrate the usage proportions into optimization features, analyze the optimization features to obtain the optimization coefficient corresponding to each target channel, and mark it as c; Identify the target channels corresponding to each sales information, match the corresponding optimization coefficient, then the calculation formula of the recommendation value is optimized to: TZ = c × PZ / (BZ - ZX).

[0012] Further, the methods for evaluating the quality data include: Identify each quality item in the quality data, mark it as i, i = 1, 2, ……, n, n is a positive integer; Evaluate the data of each quality item to obtain the corresponding single-item quality value, mark the obtained single-item quality value as PZi, and calculate the corresponding quality value PZ according to the quality value evaluation formula PZ = (∑PZi) / n.

[0013] Further, the methods for analyzing the price data include: Set the discount channel, input the sales information into the discount channel to obtain the corresponding discount data, and obtain the corresponding present value according to the discount data; Identify the marked value in the sales information.

[0014] Furthermore, the method for obtaining quality characteristic data includes: Obtain quality item data with a single-item quality value lower than threshold X1, extract the cause data from the quality item data, where the cause data is the data that makes the single-item quality value lower than threshold X1; obtain the corresponding impact data for the cause data, and combine and integrate each cause data and impact data into quality characteristic data.

[0015] The recommendation module is used to recommend sales information to users, obtain the corresponding first sequence, and recommend sales information to users according to the first sequence.

[0016] Furthermore, before the recommendation module recommends sales information to users according to the first sequence, it identifies large items in the first sequence, obtains the user's location, obtains the location information of large items sold corresponding to the user's location according to the user's location, and supplements the obtained large item location information to the first sequence.

[0017] Compared with the prior art, the beneficial effects of the present invention are: Through the mutual cooperation among the user module, the retrieval module, and the recommendation module, intelligent recommendation of sales information to users is realized, breaking the platform barrier, obtaining appropriate sales information according to the user's needs; and supplementing corresponding quality characteristic data in the recommended sales information, enabling users to intuitively understand information such as the quality of each commodity, solving the problem that the vast majority of consumers cannot understand the detailed information of the sold commodities, and having concerns about commodity quality, being deceived, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a block diagram of the principle of the present invention; Figure 2 It is a working principle diagram of the retrieval module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] Such as Figures 1 to 2As shown in the figure, an intelligent information recommendation system for e-commerce sales includes a user module, a retrieval module, and a recommendation module; The user module is used for users to input demand information, including information such as product names and price ranges; send the identified demand information to the retrieval module; and the user module has a user information management function for users to manage personal information.

[0022] The retrieval module is used to retrieve sales information according to demand information. The specific methods include: Set the target channels, where the target channels refer to various selected e-commerce platforms; input the obtained demand information into each target channel for retrieval to obtain a large amount of sales information, including corresponding source information; evaluate the obtained sales information to obtain corresponding recommendation values, arrange the sales information in descending order of the recommendation values to obtain the first sequence; and supplement the corresponding quality characteristic data.

[0023] The methods for setting the target channels include: Obtain various sales channels available in the current market, as long as they are regular and secure sales channels that can be retrieved and transactions can be conducted; evaluate the recommendation values corresponding to each product information. The specific calculation method of the recommendation value refers to the evaluation of the obtained sales information below; calculate the average recommendation value corresponding to this product category. If the number of products is too large, sampling can be used to calculate the average recommendation value; identify the market share of this sales channel, match the corresponding correction coefficient according to the market share for correcting the sales channel with the first share, and the correction coefficient is greater than or equal to 1. Specifically, set the correction coefficient corresponding to a certain market share manually. For shares that are too low or too high, there is no need to set them one by one. The correction coefficient is 1 for all shares below a certain share, and for shares higher than a certain share, it can be directly considered up to standard and regarded as infinite; only mark the corresponding coefficients one by one for the shares within the interval, and set the correction coefficients one by one with a share unit of 1, and then use the interpolation method for calculation later. For example, if the share is 3.8%, use the interpolation method to calculate according to the correction coefficients corresponding to 3% and 4%; reduce the number of correction coefficient settings to prevent sales channels with a certain share from being directly excluded; mark the obtained correction coefficient and average recommendation value as ε and PTZ respectively, calculate the corresponding screening value according to the screening formula SP = ε × PTZ, and exclude the product categories with screening values lower than the threshold X2 from this sales channel until all product categories of this sales channel are evaluated. Mark the sales channels with product categories not all excluded as target channels and assign corresponding target classification labels. The classification labels refer to the product categories not excluded.

[0024] In other embodiments, the target channels can also be directly specified manually.

[0025] The method for evaluating the obtained sales information includes: Identify the quality data and price data corresponding to each sales information. Quality data refers to data related to the quality of the product, including the corresponding ingredient list, material, manufacturer, reviews, etc. Price data refers to relevant data such as price, discount coupons, cashback, etc. For example, evaluate according to the current channels for obtaining cashback and discount coupons for various products, and the channels for cashback and discount coupons are preset by the platform side. For example, current various chat group cashback, discount groups, etc. are uniformly marked as discount channels. After inputting the corresponding sales link into the discount channel, obtain data such as discount coupons and cashback in the corresponding relevant price data; that is, the discount channel is set by the platform side itself. Evaluate the corresponding marked value and discounted value according to the price data. The marked value refers to the marked price in the sales information, and the discounted value refers to the maximum combined price reduction, cashback, etc. that can be used obtained through each discount channel. For example, the total price of discount plus cashback is the discounted value; according to whether each discount channel can be used together, etc., the corresponding discounted value can be obtained using existing identification and calculation methods; mark the obtained discounted value and marked value as ZX and BZ respectively. Evaluate the obtained quality data to obtain the corresponding quality value, and mark the obtained quality value as PZ; calculate the corresponding recommended value according to the recommended value formula TZ = PZ / (BZ - ZX).

[0026] The method for evaluating the obtained quality data includes: The quality data of each corresponding product category has fixed quality items. For example, the quality data of food products generally includes data such as ingredient list, manufacturer, reviews, etc. The specific quality items that the quality data corresponding to each product category field should include are set by the expert group according to the directions related to the product quality in the corresponding product field. For example, for manufacturer information, understand the registration information, origin of the manufacturer, and other production quality-related data of the manufacturer that can be obtained based on the current big data; and when setting the quality items of products in each field, an initial value will be preset. That is, when the data of this quality item cannot be obtained, this initial value will be used as the data of this quality item and used as the single quality value of this quality item in the follow-up. Because in the actual retrieval process, some information may not be obtained due to the product, and the initial values in different fields may not be the same because the weights of the same quality item in different fields in the quality evaluation of this product are different. Therefore, when setting each quality item, set the corresponding initial value simultaneously. The initial value is a percentage value, that is, the value range is [0, 100]. Identify each quality item in the quality data, marked as i, where i = 1, 2, ……, n, and n is a positive integer; evaluate the data of each quality item to obtain the corresponding single-item quality value, mark the obtained single-item quality value as PZi, and calculate the corresponding quality value PZ according to the quality value evaluation formula PZ = (∑PZi) / n, where i = 1, 2, ……, n.

[0027] Evaluate the data of each quality item, that is, establish the corresponding judgment criteria based on the corresponding specification data for evaluation. For example, set the corresponding judgment criteria based on the latest version of the food standard, the harm data of relevant additives to the human body, etc.; taking the ingredient list as an example, first evaluate whether it meets the food standard. If it does not meet, assign a single-item quality value. If it meets, subtract from the full score of 100, that is, then identify whether there are harmful elements to the human body, and make corresponding deductions according to its content, type, and number of types to obtain the corresponding single-item quality value. The corresponding judgment criteria can be set through various current research data. Because for each quality item in each industry field, there will be a corresponding quality evaluation standard, and there is a corresponding consensus on what kind of material has the best quality. Therefore, the corresponding judgment criteria can be sorted out, and the corresponding single-item quality value can be evaluated in combination with the corresponding judgment criteria; existing methods can be used to evaluate each quality item; for example, establish the corresponding quality evaluation model based on the CNN network or DNN network, and establish the corresponding training set through artificial means for training. The training set includes various simulated quality data of the product and the corresponding single-item quality values corresponding to each quality item; evaluate through the quality evaluation model after successful training to obtain the single-item quality values corresponding to each quality item; because the neural network is an existing technology in this field, the specific establishment and training process will not be described in detail in the present invention.

[0028] Supplement the corresponding quality characteristic data. The quality characteristic data is to extract the reason data of each single-item quality value in the quality data that is lower than the threshold X1 from the quality item data, obtain its corresponding influence data, and integrate it into the quality characteristic data to help users directly understand the defects of the product, such as a harmful additive in food, the additive content, and the corresponding influence.

[0029] The recommended module is used to recommend the sales information to the user, obtain the corresponding first sequence, and recommend the sales information to the user according to the first sequence.

[0030] The recommended information includes corresponding discount information, such as discount channels, etc., and can also have corresponding tutorials to help users save costs.

[0031] Through the mutual cooperation among the user module, the retrieval module, and the recommendation module, intelligent recommendation of the user's sales information is realized, breaking the platform barrier, obtaining appropriate sales information according to the user's needs; and supplementing corresponding quality characteristic data in the recommended sales information, enabling the user to intuitively understand information such as the quality of each commodity, solving the problem that the vast majority of consumers cannot understand the detailed information of the sales commodities, and having concerns such as commodity quality and being deceived.

[0032] In one embodiment, it is often difficult to understand the real offline situation through image information during the online shopping process. For large-sized commodities, due to reasons such as inconvenient return and exchange, some people will not make online purchases because of this; therefore, to solve this problem, the following method is proposed: Identify the large-sized commodities in the first sequence, evaluate the large-sized commodities from two aspects of volume and price. If it exceeds a certain price or a certain volume, it is directly recognized as a large-sized commodity, and other corresponding weights can be preset for comprehensive calculation; or the corresponding evaluation criteria for large-sized commodities can be set using other existing technologies. Obtain the user's location, and identify the large-sized location information around the user where the corresponding large-sized commodities are sold according to the user's location, such as the locations of each store selling the large-sized commodity; supplement the obtained large-sized location information to the first sequence.

[0033] In one embodiment, as the number of user uses increases, the tendency of the user towards a certain or certain target channels can be understood. Therefore, the first sequence can be optimized based on the user's usage records. The specific method is as follows: Real-time count the number of times the user selects each target channel, calculate the usage proportion of each target channel, and integrate each usage proportion into an optimization feature. For example, if the usages are 0.5, 0.2, 0.1, 0.1, 0.05, 0.05, 0, 0, 0 respectively, then the optimization feature is (0.5, 0.2, 0.1, 0.1, 0.05, 0.05, 0, 0, 0); establish a corresponding optimization analysis model based on the CNN network or DNN network, and establish a corresponding training set for training through artificial means. The training set includes various simulated optimization features and the corresponding optimization coefficients of each target channel set. Through analysis by the optimized analysis model after successful training, obtain the optimization coefficients corresponding to each target channel, and mark them as c. Identify the target channels corresponding to each sales information, match the corresponding optimization coefficients, and then the calculation formula of the recommended value is optimized to: TZ = c × PZ / (BZ - ZX).

[0034] The above formulas are all calculated by removing the dimension and taking their numerical values. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained through a large amount of data simulation.

[0035] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent information recommendation system for e-commerce sales, characterized in that, It includes a user module, a retrieval module, and a recommendation module; The user module is used for the user to input demand information and send the identified demand information to the retrieval module; The retrieval module is used to retrieve sales information according to the demand information, set target channels, where the target channels refer to various selected e-commerce platforms; input the obtained demand information into each target channel for retrieval, obtain a large amount of sales information, evaluate the obtained sales information, obtain corresponding recommendation values, arrange the sales information in descending order of the recommendation values to obtain a first sequence; and supplement corresponding quality characteristic data; The recommendation module is used to recommend sales information to the user, obtain the corresponding first sequence, and recommend sales information to the user according to the first sequence; The method for setting target channels includes: Identify existing sales channels and calculate the average recommendation value corresponding to each commodity classification of the sales channels; Obtain the market share corresponding to each sales channel and match a corresponding correction coefficient based on the market share; Mark the obtained correction coefficient and average recommendation value as ε and PTZ respectively, calculate the corresponding screening value SP according to the screening formula SP = ε × PTZ, and eliminate the commodity classifications with screening values lower than the threshold X2 from the sales channels; Set target channels based on the processing results of each commodity classification and mark corresponding target classification labels; Before the recommendation module recommends sales information to the user according to the first sequence, identify large items in the first sequence, obtain the user's location, obtain the large-item location information for selling the corresponding large items according to the user's location, and supplement the obtained large-item location information to the first sequence.

2. The intelligent information recommendation system for e-commerce sales according to claim 1, characterized in that For the calculation of the average recommendation value, sampling is used for calculation.

3. The intelligent information recommendation system for e-commerce sales according to claim 2, characterized in that, The recommendation value is calculated according to the commodity quality and price corresponding to the sales information.

4. An intelligent information recommendation system for e-commerce sales according to claim 3, characterized in that, The method for evaluating the recommendation value includes: Identify the quality data and price data corresponding to each sales information, evaluate the obtained quality data to obtain a corresponding quality value, and mark the obtained quality value as PZ; set corresponding discounted values and marked values based on the price data, and mark the obtained discounted value and marked value as ZX and BZ respectively; Calculate the corresponding recommendation value according to the recommendation value formula TZ = PZ / (BZ - ZX).

5. An intelligent information recommendation system for e-commerce sales according to claim 4, characterized in that Optimize the recommendation values of each sales information according to the user's usage records, count the number of times the user selects each target channel in real time, calculate the usage proportion of each target channel, integrate the usage proportions into optimization features, analyze the optimization features, obtain the optimization coefficient corresponding to each target channel, and mark it as c; Identify the target channels corresponding to each sales information and match the corresponding optimization coefficient, then the calculation formula of the recommendation value is optimized to: TZ = c × PZ / (BZ - ZX).

6. The intelligent information recommendation system for e-commerce sales according to claim 4, characterized in that, The method for evaluating the quality data includes: Identify each quality item in the quality data, mark it as i, i = 1, 2, ……, n, n is a positive integer; evaluate the data of each quality item to obtain a corresponding single-item quality value, mark the obtained single-item quality value as PZi, and calculate the corresponding quality value PZ according to the quality value evaluation formula PZ = (∑PZi) / n.

7. An intelligent information recommendation system for e-commerce sales according to claim 4, characterized in that, The method for analyzing the price data includes: Set a discount channel, input the sales information into the discount channel to obtain corresponding discount data, and obtain the corresponding discount value according to the discount data; identify the marker values in the sales information.

8. An intelligent information recommendation system for e-commerce sales according to claim 6, characterized in that, The method for obtaining quality characteristic data includes: Obtain quality item data with a single quality value lower than the threshold X1, extract the cause data from the quality item data, where the cause data is the data that makes the single quality value lower than the threshold X1; obtain the corresponding impact data for the cause data, and combine and integrate each cause data and impact data into quality characteristic data.

Images