Recommendation method, device and equipment of intelligent vending machine, medium and program product

Abstract

The invention discloses a recommendation method and device of an intelligent vending machine, equipment, a medium and a program product, and relates to the technical field of intelligent vending machines. And based on the demand characteristics of the product demand of the to-be-purchased customer and the product characteristics of each intelligent vending machine in the existing product sequence of the intelligent vending machine, determining a target product in the existing product sequence through a preset selection model, and recommending the target product to the to-be-purchased customer. Therefore, by learning the preset selection model of the specific association relationship between the demand characteristics and the product characteristics, the target product meeting the demand of the to-be-purchased customer is obtained through screening, so that the selection efficiency and accuracy of the intelligent vending machine are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vending machines, and particularly relates to a recommendation method of an intelligent vending machine, a recommendation device of an intelligent vending machine, a recommendation equipment of an intelligent vending machine, a storage medium and a computer program product. BACKGROUND

[0002] At present, intelligent vending machines can be sold as a whole, and can also be pre-installed and customized for modification. It is difficult to directly and efficiently confirm the vending machine that best meets the needs of customers. Therefore, it is often necessary to communicate with customers multiple times before and after sales and to return to the factory for replacement, so as to formulate an intelligent vending machine that meets and satisfies the final vending needs of customers.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a recommendation method of an intelligent vending machine, a recommendation device of an intelligent vending machine, a recommendation equipment of an intelligent vending machine, a storage medium and a computer program product, and to solve the technical problems of inaccurate selection and low efficiency of intelligent vending machines.

[0005] To achieve the above purpose, the present application provides a recommendation method of an intelligent vending machine, and the recommendation of the intelligent vending machine comprises:

[0006] obtaining product needs of a to-be-purchased customer and an existing product sequence of an intelligent vending machine;

[0007] determining a target product in the existing product sequence based on a demand feature of the product needs and a product feature of each intelligent vending machine in the existing product sequence through a preset selection model;

[0008] recommending the target product to the to-be-purchased customer.

[0009] In an embodiment, the step of determining the target product in the existing product sequence based on the demand feature of the product needs and the product feature of each intelligent vending machine in the existing product sequence through the preset selection model comprises:

[0010] obtaining a first product need of a to-be-purchased customer, a second product need of a purchased customer and an existing product sequence of an intelligent vending machine;

[0011] determining a similar customer of the to-be-purchased customer among the purchased customers based on the first product need and the second product need;

[0012] According to the demand characteristics corresponding to the second product demand of the similar customer and the product characteristics of each intelligent vending machine in the existing product sequence, a target product in the existing product sequence is determined through a preset selection model.

[0013] In an embodiment, the recommendation method of the intelligent vending machine comprises:

[0014] Obtaining the basic demand of the to-be-purchased customer and the existing product sequence of the intelligent vending machine, and preliminarily screening an initial product list from the existing product sequence according to the basic demand;

[0015] Obtaining the in-depth demand of the to-be-purchased customer, and further screening a target product from the initial product list according to the in-depth demand;

[0016] Recommending the target product to the to-be-purchased customer.

[0017] In an embodiment, the step of preliminarily screening an initial product list from the existing product sequence according to the basic demand comprises:

[0018] Identifying the basic demand parameter of the to-be-purchased customer from the basic demand of the to-be-purchased customer;

[0019] Identifying the product parameter of each intelligent vending machine in the existing product sequence from the existing product sequence of the intelligent vending machine;

[0020] Referring to a preliminary screening rule based on the basic demand parameter and the product parameter, an initial product list is determined, wherein the product parameter of each intelligent vending machine in the initial product list meets the requirement of the basic demand parameter.

[0021] In an embodiment, the step of obtaining the in-depth demand of the to-be-purchased customer comprises:

[0022] Displaying a visual interface, wherein the to-be-selected in-depth demand and the priority slider of the to-be-selected in-depth demand are displayed on the visual interface;

[0023] In response to the sliding operation of the to-be-purchased customer on the visual interface, the target in-depth demand of the to-be-purchased customer and the priority weight of each target in-depth demand are determined.

[0024] In an embodiment, the step of further screening a target product from the initial product list according to the in-depth demand comprises:

[0025] Standardizing the product parameter of each intelligent vending machine in the initial product list to obtain the standardized score of each product parameter of each intelligent vending machine in the initial product list;

[0026] determining a priority weight of each of the depth requirements and a target product parameter meeting each of the depth requirements, wherein the priority weight is a custom priority weight of a to-be-purchased customer or a default priority weight;

[0027] determining a weighted total score of each of the intelligent vending machines in the preliminary product list based on the normalized score of the target product parameter and the priority weight;

[0028] determining a target product in the preliminary product list based on the weighted total score.

[0029] In addition, to achieve the above object, the present application further provides a recommendation device of an intelligent vending machine, which comprises:

[0030] an acquisition module, configured to acquire product requirements of a to-be-purchased customer and an existing product sequence of an intelligent vending machine;

[0031] a selection module, configured to determine a target product in the existing product sequence based on a requirement feature of the product requirements and a product feature of each of the intelligent vending machines in the existing product sequence through a preset selection model;

[0032] a recommendation module, configured to recommend the target product to the to-be-purchased customer.

[0033] In addition, to achieve the above object, the present application further provides a recommendation device of an intelligent vending machine, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the recommendation method of the intelligent vending machine as described above.

[0034] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the recommendation method of the intelligent vending machine as described above.

[0035] In addition, to achieve the above object, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the recommendation method of the intelligent vending machine as described above.

[0036] The one or more technical solutions provided by the present application have at least the following technical effects:

[0037] In the present application, a recommendation method of an intelligent vending machine is proposed, based on the demand characteristics of the product demand of a to-be-purchased customer and the product characteristics of each intelligent vending machine in the existing product sequence of the intelligent vending machine, the target product in the existing product sequence is determined through a preset selection model, and the target product is recommended to the to-be-purchased customer. Therefore, through the preset selection model that learns the specific association relationship between the demand characteristics and the product characteristics, the target product that meets the demand of the to-be-purchased customer is screened out, so as to improve the selection efficiency and accuracy of the intelligent vending machine. BRIEF DESCRIPTION OF DRAWINGS

[0038] The drawings incorporated in the specification and constituting a part thereof illustrate embodiments consistent with the present application and together with the specification serve to explain the principles of the application.

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required to be used in the embodiment or prior art description will be briefly introduced as follows, and obviously, other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0040] Figure 1 The flowchart provided for the first embodiment of the recommendation method of the intelligent vending machine of the present application;

[0041] Figure 2 The visual interface schematic diagram provided for the first embodiment of the recommendation method of the intelligent vending machine of the present application;

[0042] Figure 3 The flowchart provided for the second embodiment of the recommendation method of the intelligent vending machine of the present application;

[0043] Figure 4 The module structure schematic diagram of the recommendation device of the embodiment of the intelligent vending machine of the present application;

[0044] Figure 5 The device structure schematic diagram of the hardware running environment involved in the recommendation method of the intelligent vending machine in the embodiment of the present application.

[0045] The purpose implementation, functional characteristics and advantages of the present application will be further explained with reference to the drawings combined with the embodiments. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0047] In order to better understand the technical solutions of the present application, the following will be described in detail combined with the drawings in the specification and specific embodiments.

[0048] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, or an electronic device capable of realizing the above functions, a recommendation device of a smart vending machine, etc. The following takes the recommendation device of the smart vending machine as an example to describe the embodiment and the following embodiments.

[0049] Based on this, the embodiment of the application provides a recommendation method of a smart vending machine, referring to Figure 1 , Figure 1 FIG. 1 is a flowchart of a first embodiment of the recommendation method of the smart vending machine.

[0050] In the embodiment, the recommendation method of the smart vending machine includes steps T10-T30:

[0051] Step T10, obtaining product demand of a to-be-purchased customer and an existing product sequence of a smart vending machine;

[0052] Step T20, determining a target product in the existing product sequence through a preset selection model based on demand features of the product demand and product features of each smart vending machine in the existing product sequence;

[0053] Step T30, recommending the target product to the to-be-purchased customer.

[0054] In the embodiment, after obtaining the product demand of the to-be-purchased customer and the existing product sequence of the smart vending machine, the target product in the existing product sequence is directly determined through a preset selection model based on demand features of the product demand and product features of each smart vending machine in the existing product sequence.

[0055] The demand features refer to converting unstructured demand text or description of the to-be-purchased customer into a numerical vector that can be quantified and calculated by a machine. The product features refer to a vector for quantitatively describing product information (category distribution, price, brand, health degree, etc.) of a single smart vending machine. The historical recommendation scheme refers to a successful recommendation record completed in the past, including customer demand at that time, available vending machine product sequence at that time, and recommendation selection result at that time. The preset selection model refers to a machine learning model trained based on historical data and recommendation results, and the target is to reproduce the matching mode of the historical success according to new demand and new candidate vending machine sequence to select the optimal solution. The target product refers to a specific smart vending machine model and / or product combination output by the model and recommended to the current to-be-purchased customer.

[0056] In an embodiment, a historical recommendation scheme is obtained, in which a historical product demand of a historical to-be-purchasing customer and a historical existing product sequence of a smart vending machine are obtained, and then a historical demand feature of the historical product demand and a historical product feature of each smart vending machine in the historical existing product sequence are obtained. Thus, a training set is constructed, and a selection model is trained.

[0057] In an embodiment, a smart recommendation system is established: for a new smart vending machine of a to-be-purchasing customer, based on its product demand and existing product sequence, a target product most suitable for its product demand is automatically selected from the existing product sequence as a recommended product. In order to achieve this goal, a machine learning model (preset selection model) is trained using historical data, which learns how to make the best choice in a new similar situation according to past successful (or failed) recommendation cases. In the historical data preparation and model training (offline training) stage:

[0058] First, a historical recommendation scheme is obtained, in which a historical product demand of a historical to-be-purchasing customer and a historical existing product sequence of a smart vending machine are obtained, and then a historical demand feature of the historical product demand and a historical product feature of each smart vending machine in the historical existing product sequence are obtained. Thus, a training set is constructed. Among them, the historical product demand of the historical to-be-purchasing customer is converted into a structured and machine-understandable feature vector. For example, through NLP (natural language processing), the text demand is keyword extracted, topic modeling, sentiment analysis, and converted into word embedding vector, through classification label, the demand is mapped to the pre-defined category label (such as working lunch, beverage, snack, health, convenience, high-end, etc.), and One-hot encoding is performed. For location features, relevant features are extracted in combination with the location information of the customer (such as office building, school, scenic spot). Among them, by featureizing each smart vending machine in the historical existing product sequence, the historical product features of the historical existing product sequence are extracted, such as product category distribution, price band distribution, brand distribution, health level, hot-selling attribute, seasonality, new product ratio, and vending machine function features (optional). In this way, the processed data is assembled into a standard supervised learning training set.

[0059] Then, a machine learning model suitable for processing such problems is selected. For example, a ranking model (Learning to Rank): Pointwise (scoring each candidate), Pairwise (comparing candidate pairs), Listwise (optimizing the entire candidate list order), which is suitable for selecting Top1 from the candidate set. Collaborative filtering model based on content features: regarding the intelligent vending machine as "items" and the product demand of the customer to be purchased as "user portrait", hybrid recommendation is performed. Deep matching model (DSSM or ESMM, etc.): learn the similarity of the demand feature vector and the candidate vending machine feature vector in the hidden space, process the demand and vending machine features through a double-tower network respectively, and calculate the matching score. In the training process, the constructed training set is used to train the model, so that it can learn the rule of mapping from [demand features and current candidate vending machine feature set] to [optimal selection]. The goal of the model is to accurately predict the selected vending machine in history on the training set and validation set as much as possible.

[0060] In this embodiment, a model is trained using historical "demand-candidate set-selection result" data, so that it can learn the pattern of matching specific product demand features to target vending machine product feature combinations. When encountering a new customer demand, the model finds the product model and / or combination with the most matching features to the demand from the current available intelligent vending machine product sequence as a recommendation based on the learned pattern.

[0061] In a feasible implementation, step T20 can include steps T201-T203:

[0062] Step T201, obtaining a first product demand of a customer to be purchased, a second product demand of a customer who has purchased, and an existing product sequence of an intelligent vending machine;

[0063] Step T202, determining similar customers of the customer to be purchased among the customers who have purchased based on the first product demand and the second product demand;

[0064] Step T203, determining a target product in the existing product sequence according to demand features corresponding to the second product demand of the similar customers and product features of each intelligent vending machine in the existing product sequence through a preset selection model.

[0065] Before determining the target product in the existing product sequence by using the trained selection model, the customer to be purchased can also be recognized and classified, and similar customers similar to the customer to be purchased are determined. Specifically, similarity matching can be performed according to the first product demand of the customer to be purchased and the second product demand of the customer who has purchased, and similar customers of the customer to be purchased are determined among the customers who have purchased.

[0066] In addition, similar customers can be determined not only based on product demand characteristics, but also based on attribute characteristics for describing customers to be purchased, including or excluding product demand characteristics. In this embodiment, the method for determining similar customers of customers to be purchased is not limited.

[0067] In an embodiment, the first product demand of the customer to be purchased is an explicit demand (such as preference, budget, target population, etc.) of a new customer, and the second product demand of the purchased customer is the actual demand / preference of the historical customer when purchasing or in subsequent operation. It can be derived from pre-purchase survey questionnaires / communication records, actual sales data of vending machines (hot-selling products represent demand), customer operation feedback or adjustment records, and equipment deployment scenarios (such as office buildings = white-collar work meal demand). Then, the unstructured text demand is converted into a machine-computable feature vector. It should be noted that the first / second product demand feature extraction method is consistent. The extracted structured attributes include category distribution (snack ratio, beverage ratio, fast food ratio, healthy food ratio, etc.), price band (low price, middle price, high price ratio; average unit price), functional demand (whether to need refrigeration, heating, large capacity channel, code scanning door opening, etc.), target population label (student, white-collar worker, worker, tourist, community family, etc.), scene label (office building, factory, school, hospital, transportation hub, community, etc.), special preference (low sugar, import, net red brand, local specialty, 24-hour operation, etc.), and then numerical representation is performed through one-hot encoding, word embedding, etc. The above attributes and labels are vectorized, and finally each customer (whether to be purchased or purchased) is represented by a demand feature vector. In the feature space, find the purchased customer feature vector closest to the customer to be purchased feature vector. In this embodiment, the method for determining the closest purchased customer feature vector is not limited, which can be determined by cosine similarity, Euclidean distance, Pearson correlation coefficient, etc. For each customer to be purchased, the similarity score with all purchased customers is calculated and sorted from high to low (or distance from low to high), and similar customers are selected according to the threshold set according to business needs.

[0068] Further, according to the demand characteristics corresponding to the product demand of the similar customer and the product characteristics of each intelligent vending machine in the existing product sequence, the target product in the existing product sequence is determined through a preset selection model, so as to further improve the selection efficiency and accuracy of the intelligent vending machine.

[0069] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above first embodiment can be referred to the above introduction, and will not be described in detail. On this basis, please refer to Figure 3 , the recommendation method of the intelligent vending machine further includes steps S10-S30:

[0070] Step S10, obtaining the basic needs of the to-be-purchased customer and the existing product sequence of the intelligent vending machine, and preliminarily screening the existing product sequence according to the basic needs to obtain an initial product list;

[0071] Step S20, obtaining the in-depth needs of the to-be-purchased customer, and further screening the initial product list according to the in-depth needs to obtain a target product;

[0072] Step S30, recommending the target product to the to-be-purchased customer.

[0073] In this embodiment, another method for determining the target product is proposed.

[0074] In this embodiment, in the basic need layer, irrelevant models are quickly filtered through core limiting conditions such as budget and space size, and in the in-depth need layer, the initial product is finely sorted based on, for example, weighted priority such as payment method diversity and refrigeration capacity, and finally the target product is selected and recommended to the to-be-purchased customer. Therefore, through the hierarchical screening logic of preliminary screening and further screening, the basic needs and in-depth needs of the to-be-purchased customer are highly matched, so as to improve the selection efficiency and accuracy of the intelligent vending machine.

[0075] In an embodiment, through the product database of the intelligent vending machine, the existing vending machine type parameters (size, power consumption, payment interface, etc.) are stored in a structured manner.

[0076] The to-be-purchased customer refers to a customer who is to purchase an intelligent vending machine, and the basic needs of the to-be-purchased customer refer to the minimum threshold requirements that determine whether the equipment can be physically deployed and commercially viable, for example, 1, space size, i.e. the length x width x height of the installation area (including safety passage allowance), if the equipment volume is larger than the site space, it is physically not deployable, 2, price budget, i.e. the total cost interval (equipment + installation + first year maintenance) that the customer can accept, automatically filter models that exceed the budget, 3, deployment environment such as indoor / outdoor / special scene (high temperature / high humidity / freezing area) for determining waterproof level and temperature control capacity, and 4, basic capacity, which can be derived from the daily passenger flow to determine the number of goods channels required, thereby determining the basic capacity.

[0077] The in-depth needs of the to-be-purchased customer refer to the value-added characteristics that affect the user experience and operational efficiency on the premise of meeting the aforementioned basic needs, for example, 1, payment flexibility such as cash / code / face / NFC payment method types, 2, energy efficiency such as single-day power consumption range, whether supporting solar power / cell backup power, 3, intelligent degree such as remote management / dynamic pricing / stockout prediction / AI passenger flow analysis, 4, expansion capability such as goods channel expansion space, advertising screen interface, third-party API interface, and 5, customization needs such as brand LOGO spraying and special goods channel (large goods / irregular package).

[0078] In the embodiment, the method of obtaining the basic demand and the deep demand of the to-be-purchased customer is not limited.

[0079] By the layered demand processing, the customer's implicit value demand is maximized to match under the premise of ensuring the feasibility of deployment, so as to accurately capture the deep demand, which can improve the customer's repurchase rate.

[0080] In a feasible implementation, the step S10 can include steps S101-S103:

[0081] Step S101, identifying the basic demand parameter of the to-be-purchased customer from the basic demand of the to-be-purchased customer;

[0082] Step S102, identifying the product parameter of each intelligent vending machine in the existing product sequence of the intelligent vending machine from the existing product sequence of the intelligent vending machine;

[0083] Step S103, determining the preliminary product list based on the basic demand parameter and the product parameter according to the preliminary screening rule, wherein the product parameter of each intelligent vending machine in the preliminary product list meets the requirement of the basic demand parameter.

[0084] In an embodiment, the basic demand parameter of the to-be-purchased customer identified from the basic demand of the to-be-purchased customer includes the budget interval, the installation site length-width-height, the deployment environment type, the expected daily passenger flow, etc.

[0085] The product parameter of the intelligent vending machine includes but is not limited to: size, capacity, storage capacity, identification method, lock type, door opening method, temperature interval, refrigeration method, number of layers, door body, networking method, customization service (such as machine body sticker, management system, sales application and support OEM production) and applicable scenarios such as school, factory, hospital, office, chess room, hotel, store, community and mall, etc.

[0086] In an application scenario of the embodiment, the basic demand information of the to-be-purchased client is obtained through an online questionnaire or an offline interview, including a budget, a site size, a deployment scenario, and the like. The collected basic demand information is converted into a standardized parameter form, such as a budget range, a size limit, and the like. The product parameters of all intelligent vending machines are extracted from an existing product database, including a price, a size, an applicable scenario, and the like, to ensure that the extracted product parameters are comparable with the basic demand parameters of the to-be-purchased client. According to the preliminarily prepared preliminary screening rules, such as a price range, a size limit, and the like, the product parameters are screened, and the products meeting the basic demand parameters are added to the preliminary product list. In addition, the screening result can be verified to ensure that the products in the preliminary product list indeed meet the basic demand of the client. Furthermore, the preliminary screening rules can be adjusted according to actual conditions to improve the accuracy and efficiency of screening. Through the above steps, the preliminary product list meeting the basic demand can be effectively screened from the actual demand of the to-be-purchased client in combination with the existing product parameters. In the embodiment, the rule content of the preliminary screening rules is not limited, and the basic demand of the to-be-purchased client is met as a criterion.

[0087] In a possible implementation, step S20 can include steps S20A1-S20A2:

[0088] Step S20A1, a visual interface is displayed, wherein the to-be-selected deep demand and the priority slider of the to-be-selected deep demand are displayed on the visual interface;

[0089] Step S20A2, in response to the sliding operation of the to-be-purchased client on the visual interface, the target deep demand of the to-be-purchased client and the priority weight of each target deep demand are determined.

[0090] In the embodiment, a method for obtaining the deep demand of the to-be-purchased client is provided. The to-be-selected deep demand and the priority slider of the to-be-selected deep demand are displayed on the visual interface displayed to the to-be-purchased client, and the to-be-purchased client can set the priority weight of different to-be-selected deep demands by sliding the priority slider.

[0091] In an embodiment, refer to Figure 2 , Figure 2 The visual interface schematic diagram provided for the first embodiment of the recommendation method of the intelligent vending machine is shown. When the to-be-selected deep demand 1 is energy saving, the to-be-selected deep demand 2 is the number of supported payment methods, and the to-be-selected deep demand 3 is the channel expansion capability, the to-be-purchased client sets the priority weight of energy saving to be 40%, the priority weight of the number of supported payment methods to be 25%, and the priority weight of the channel expansion capability to be 15% through the priority slider of each to-be-selected deep demand.

[0092] In another possible implementation, step S20 can further include steps S20B1-S20B4:

[0093] Step S20B1, standardizing the product parameters of each intelligent vending machine in the preliminary product list to obtain a standardized score of each product parameter of each intelligent vending machine in the preliminary product list;

[0094] Step S20B2, determining the priority weight of each depth demand and the target product parameter meeting each depth demand, wherein the priority weight is a custom priority weight of the to-be-purchased customer or a default priority weight;

[0095] Step S20B3, determining the weighted total score of each intelligent vending machine in the preliminary product list based on the standardized score of the target product parameter and the priority weight;

[0096] Step S20B4, determining the target product in the preliminary product list based on the weighted total score.

[0097] In this embodiment, a method for further screening the target product from the preliminary product list according to the depth demand is provided.

[0098] In an embodiment, the parameter standardization can be achieved by converting different types of product parameters (such as more channels are better, lower power consumption is better) into 0-100 or 0-1 score system, thereby eliminating the incomparability between different dimensional parameters and unifying the multi-dimensional parameters into quantifiable standard scores.

[0099] As for different types of product parameters, the more the number of payment methods and the channel capacity, the better the benefit type parameters, the smaller the power consumption and the failure rate, the better the cost type parameters, and the best temperature range is also an interval type parameter. For example, for models A, B, C and D, the original power consumptions are 180W, 210W, 300W and 150W, respectively, and the standardized scores after standardization are (300-180) / (300-150) = 0.8, (300-210) / (300-150) = 0.6, 0.0 and 1.0, respectively.

[0100] Model Energy efficiency requirement (0.25) Payment requirement (0.3) Refrigeration requirement (0.2) Weighted total score A 0.8×0.25＝0.20 1.0×0.3＝0.30 0.7×0.2＝0.14 0.64 B 0.9×0.25＝0.23 0.8×0.3＝0.24 0.9×0.2＝0.18 0.65 C 0.6×0.25＝0.15 0.6×0.3＝0.18 1.0×0.2＝0.20 0.53

[0101] Table 1

[0102] In an embodiment, referring to Table 1 above, each depth requirement and the priority weight of each depth requirement are the energy efficiency requirement (0.25), the payment requirement (0.3), and the refrigeration requirement (0.2), respectively. The target product parameter satisfying the depth requirement of energy efficiency is parameter 1, the target product parameter satisfying the depth requirement of payment is parameter 2, and the target product parameter satisfying the depth requirement of refrigeration is parameter 3. After the product parameter standardization processing, the standardized scores of each intelligent vending machine (A, B, and C) in the initial product list on the target product parameters 1, 2, and 3 are as follows: the standardized score of the target product parameter 1 of the intelligent vending machine A is 0.8, the standardized score of the target product parameter 2 of the intelligent vending machine A is 1.0, and the standardized score of the target product parameter 3 of the intelligent vending machine A is 0.7; the standardized score of the target product parameter 1 of the intelligent vending machine B is 0.9, the standardized score of the target product parameter 2 of the intelligent vending machine B is 0.8, and the standardized score of the target product parameter 3 of the intelligent vending machine B is 0.9; and the standardized score of the target product parameter 1 of the intelligent vending machine C is 0.6, the standardized score of the target product parameter 2 of the intelligent vending machine C is 0.6, and the standardized score of the target product parameter 3 of the intelligent vending machine C is 1.0. Further, the weighted total scores of each intelligent vending machine (A, B, and C) in the initial product list can be determined based on the standardized scores of the target product parameters and the priority weights, which are A: 0.8*0.25+1.0*0.3+0.7*0.2=0.64, B: 0.9*0.25+0.8*0.3+0.9*0.2=0.65, and C: 0.6*0.25+0.6*0.3+1.0*0.2=0.53.

[0103] In this way, the depth requirements of the to-be-purchased customer are further converted into corresponding priority weights, and the product parameters of the intelligent vending machine are further converted into corresponding standardized scores. The target product is further screened from the initial product list according to the priority weights and the standardized scores corresponding to the depth requirements. The parameter incompatibility is eliminated through standardization, the demand is accurately quantified by combining the personalized weight configuration, and the selection efficiency and accuracy of the intelligent vending machine can be further improved.

[0104] It should be noted that the above examples are only used for understanding the present application and do not limit the recommendation method of the intelligent vending machine of the present application. More forms of simple transformation based on the technical concept are within the protection scope of the present application.

[0105] The present application also provides a recommendation device of an intelligent vending machine, which is described in detail with reference to Figure 4 The recommendation device of the intelligent vending machine comprises:

[0106] The acquisition module 10 is configured to acquire the product requirements of the to-be-purchased customer and the existing product sequence of the intelligent vending machine.

[0107] The selecting module 20 is configured to determine the target product in the product sequence based on the demand features of the product demand and the product features of the intelligent vending machines in the product sequence according to a preset selecting model.

[0108] The recommending module 30 is configured to recommend the target product to the to-be-purchased customer.

[0109] In an embodiment, the selecting module 20 is further configured to:

[0110] obtain the first product demand of the to-be-purchased customer, the second product demand of the purchased customer, and the product sequence of the intelligent vending machines;

[0111] determine the similar customers of the to-be-purchased customer from the purchased customers based on the first product demand and the second product demand;

[0112] determine the target product in the product sequence based on the demand features corresponding to the second product demand of the similar customers and the product features of the intelligent vending machines in the product sequence according to the preset selecting model.

[0113] In an embodiment, the recommending device of the intelligent vending machine further comprises:

[0114] The first module is configured to obtain the basic demand of the to-be-purchased customer and the product sequence of the intelligent vending machines, and preliminarily screen the product sequence to obtain a preliminary product list according to the basic demand;

[0115] The second module is configured to obtain the deep demand of the to-be-purchased customer, and further screen the preliminary product list to obtain the target product according to the deep demand;

[0116] The third module is configured to recommend the target product to the to-be-purchased customer.

[0117] In an embodiment, the first module is further configured to:

[0118] identify the basic demand parameter of the to-be-purchased customer from the basic demand of the to-be-purchased customer;

[0119] identify the product parameter of each intelligent vending machine in the product sequence from the product sequence of the intelligent vending machines;

[0120] determine the preliminary product list based on the basic demand parameter and the product parameter according to a preliminary screening rule, wherein the product parameter of each intelligent vending machine in the preliminary product list meets the requirement of the basic demand parameter.

[0121] In an embodiment, the second module is further configured to:

[0122] display a visual interface, wherein the to-be-selected deep demand and a priority slider of the to-be-selected deep demand are displayed on the visual interface.

[0123] In response to the sliding operation of the to-be-purchased customer on the visualization interface, the target depth needs of the to-be-purchased customer and the priority weights of the target depth needs are determined.

[0124] In an embodiment, the second module is further configured to:

[0125] standardize the product parameters of each intelligent vending machine in the preliminary product list to obtain a standardized score of each product parameter of each intelligent vending machine in the preliminary product list;

[0126] determine the priority weights of the depth needs and the target product parameters meeting the depth needs, wherein the priority weights are the custom priority weights or the default priority weights of the to-be-purchased customer;

[0127] determine the weighted total scores of each intelligent vending machine in the preliminary product list based on the standardized scores of the target product parameters and the priority weights;

[0128] determine the target product in the preliminary product list based on the weighted total scores.

[0129] The intelligent vending machine recommendation device provided in the present application adopts the intelligent vending machine recommendation method in the above embodiments, and can solve the technical problems of inaccurate selection and low efficiency of the intelligent vending machine. Compared with the prior art, the intelligent vending machine recommendation device provided in the present application has the same beneficial effects as the intelligent vending machine recommendation method provided in the above embodiments, and other technical features in the intelligent vending machine recommendation device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0130] The present application provides an intelligent vending machine recommendation device, which comprises at least one processor and a memory in communication connection with the at least one processor. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the intelligent vending machine recommendation method in the above embodiment one.

[0131] The following refers to Figure 5This document illustrates a structural schematic diagram of a recommended device suitable for implementing the embodiments of this application for a smart vending machine. The recommended device for the smart vending machine in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The recommended device for the smart vending machine shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0132] like Figure 5 As shown, the recommended device of the smart vending machine may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in the read-only memory 1002 or a program loaded from the storage device 1003 into the random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the recommended device of the smart vending machine. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the recommended device of the smart vending machine to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows recommended devices for smart vending machines with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0133] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0134] The recommendation device for the intelligent vending machine provided in the present application adopts the intelligent vending machine recommendation method in the above-mentioned embodiments, and can solve the technical problems of inaccurate selection and low efficiency of the intelligent vending machine. Compared with the prior art, the recommendation device for the intelligent vending machine provided in the present application has the same beneficial effects as the intelligent vending machine recommendation method provided in the above-mentioned embodiments, and other technical features in the recommendation device for the intelligent vending machine are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0135] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0136] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0137] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the intelligent vending machine recommendation method in the above-mentioned embodiments.

[0138] The computer readable storage medium provided in the present application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination of the above.

[0139] The above computer readable storage medium may be contained in the recommendation device of the intelligent vending machine, or may exist separately and not be assembled into the recommendation device of the intelligent vending machine.

[0140] The above computer readable storage medium carries one or more programs, when the one or more programs are executed by the recommendation device of the intelligent vending machine, the recommendation device of the intelligent vending machine: obtains the basic demand of the to-be-purchased customer and the existing product sequence of the intelligent vending machine, preliminarily filters the existing product sequence according to the basic demand to obtain a preliminary product list; obtains the in-depth demand of the to-be-purchased customer, further filters the preliminary product list according to the in-depth demand to obtain a target product; and recommends the target product to the to-be-purchased customer.

[0141] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0142] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0143] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0144] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., computer programs) for executing the recommendation method of the intelligent vending machine, and can solve the technical problems of inaccurate selection and low efficiency of the intelligent vending machine. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the recommendation method of the intelligent vending machine provided by the above-mentioned embodiments, and will not be described here.

[0145] The application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the recommendation method of the intelligent vending machine as described above.

[0146] The computer program product provided by the application can solve the technical problems of inaccurate selection and low efficiency of the intelligent vending machine. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the recommendation method of the intelligent vending machine provided by the above-mentioned embodiments, and are not described here.

[0147] The above-mentioned is only part of the embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or direct / indirect application in other related technical fields based on the technical concept of the application, the contents of the specification and the drawings are included in the patent protection scope of the application.

Claims

1. A recommendation method for an intelligent vending machine, characterized in that, The recommended smart vending machines include: Obtain the product needs of potential customers and the existing product lineup of smart vending machines; Based on the demand characteristics of the product requirements and the product characteristics of each smart vending machine in the existing product sequence, the target product in the existing product sequence is determined by a preset selection model. The target product is recommended to the prospective customers.

2. The recommendation method for the intelligent vending machine as described in claim 1, characterized in that, The step of determining the target product in the existing product sequence based on the demand characteristics of the product requirements and the product characteristics of each smart vending machine in the existing product sequence through a preset selection model includes: Obtain the first product needs of potential customers, the second product needs of existing customers, and the existing product lineup of the smart vending machine; Based on the first product demand and the second product demand, identify similar customers to the prospective customer from among the existing customers. Based on the demand characteristics corresponding to the second product demand of the similar customers and the product characteristics of each smart vending machine in the existing product series, the target product in the existing product series is determined by a preset selection model.

3. The recommendation method for the intelligent vending machine as described in claim 1, characterized in that, The recommended methods for the smart vending machine include: Obtain the basic needs of potential customers and the existing product series of smart vending machines, and preliminarily filter the existing product series based on the basic needs to obtain a preliminary product list; Obtain the in-depth needs of potential customers, and further filter the target products from the initial product list based on these in-depth needs. The target product is recommended to the prospective customers.

4. The recommendation method for the intelligent vending machine as described in claim 3, characterized in that, The step of initially screening the existing product series to obtain a preliminary product list based on the basic requirements includes: The basic requirement parameters of the potential customers are identified from their basic requirements. Identify the product parameters of each smart vending machine in the existing product series; Based on the basic requirement parameters and the product parameters, and referring to the preliminary screening rules, a preliminary product list is determined, wherein the product parameters of each smart vending machine in the preliminary product list meet the requirements of the basic requirement parameters.

5. The recommendation method for the intelligent vending machine as described in claim 3, characterized in that, The steps for obtaining in-depth needs of potential customers include: A visualization interface is displayed, which shows the depth requirements to be selected and the priority slider of the depth requirements to be selected. In response to a prospective customer's swiping action on the visualization interface, the target depth requirements of the prospective customer and the priority weight of each target depth requirement are determined.

6. The recommendation method for the intelligent vending machine as described in claim 5, characterized in that, The step of further filtering the initial product list to obtain target products based on the depth requirements includes: The product parameters of each smart vending machine in the initial product list are standardized to obtain the standardized score of each product parameter of each smart vending machine in the initial product list. Determine the priority weights of each of the aforementioned depth requirements and the target product parameters that satisfy each of the aforementioned depth requirements, wherein the priority weights are either customer-defined priority weights or default priority weights. Based on the standardized scores of the target product parameters and the priority weights, the weighted total score of each smart vending machine in the initial product list is determined; Based on the weighted total score, the target product is determined from the initial product list.

7. A recommendation device for an intelligent vending machine, characterized in that, The recommended devices for the smart vending machine include: The acquisition module is used to acquire the product needs of potential customers and the existing product series of the smart vending machine; The selection module is used to determine the target product in the existing product sequence based on the demand characteristics of the product requirements and the product characteristics of each smart vending machine in the existing product sequence through a preset selection model. The recommendation module is used to recommend the target product to the prospective customer.

8. A recommended device for an intelligent vending machine, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the recommended method for a smart vending machine as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the recommended method for the smart vending machine as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the recommended method for an intelligent vending machine as described in any one of claims 1 to 6.

Images