CN113919882A - Intelligent design method of personalized discount coupon, electronic device and storage medium - Google Patents
Intelligent design method of personalized discount coupon, electronic device and storage medium Download PDFInfo
- Publication number
- CN113919882A CN113919882A CN202111238638.5A CN202111238638A CN113919882A CN 113919882 A CN113919882 A CN 113919882A CN 202111238638 A CN202111238638 A CN 202111238638A CN 113919882 A CN113919882 A CN 113919882A
- Authority
- CN
- China
- Prior art keywords
- commodity
- sales
- discount
- pedestrian
- commodities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method comprises the steps of obtaining a video stream shot by a camera, executing a target tracking task on pedestrians and commodities in the video stream to obtain a tracking result, calculating commodity sales condition characteristics according to the tracking result, wherein the commodity sales condition characteristics at least comprise commodity browsing times, commodity consulted times, commodity taking times and commodity adding times into a shopping cart, training a regression model by utilizing the commodity sales condition characteristics to obtain a sales prediction model, predicting sales of the commodities under given discounts by utilizing the sales prediction model, and generating discount coupons under the condition of maximizing profits according to the predicted sales; under the condition that the privacy of the user is not invaded, the method and the system can help merchants reasonably control marketing cost and realize profit improvement, and solve the problems of large marketing cost, low sales volume and low profit caused by the mode of issuing discount coupons through personal experience in the prior art.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to an intelligent design method, an electronic device, and a storage medium for a personalized discount coupon.
Background
The issue of discount coupons is a common sales promotion, and a shopping mall attracts a user to consume by means of discount coupons. At present, for a large-scale market or a supermarket, a merchant depends heavily on personal experience on a discount coupon, the amount of the discount coupon cannot be intelligently generated according to specific or different commodities, marketing cost is increased, and improvement of commodity sales volume and profit cannot be achieved.
At present, no effective solution is provided for the problems of increased marketing cost and low sales volume and profit caused by the mode of issuing discount coupons through personal experience in the related technology.
Disclosure of Invention
The embodiment of the application provides an intelligent design method, an electronic device and a storage medium of a personalized discount coupon, and aims to solve the problems of increased marketing cost and low sales volume and profit in a mode of issuing the discount coupon through personal experience in the related art.
In a first aspect, an embodiment of the present application provides an intelligent design method for a personalized discount coupon, where the method includes the following steps:
acquiring a video stream shot by a camera;
executing a target tracking task on the pedestrians and the commodities in the video stream to obtain a tracking result;
calculating commodity sales condition characteristics according to the tracking result, wherein the commodity sales condition characteristics at least comprise the times of browsing commodities, the times of consulting the commodities, the times of taking the commodities and the times of adding the commodities into a shopping cart;
training a regression model by using the commodity sales condition characteristics to obtain a sales prediction model;
predicting the sales volume of the goods under the given discount by using the sales volume prediction model;
and generating the discount coupon under the condition of maximizing the profit according to the predicted sales volume.
In some embodiments, the article sales status features further include the number of times that an article has been viewed for a period of time exceeding a preset threshold but has not been picked up and the number of times that an article has been picked up but has not been added to a shopping cart.
In some embodiments, after the acquiring the video stream captured by the camera, the method further comprises:
identifying the identity of a pedestrian through an image classification model, and judging whether the identity of the pedestrian is a service person or a customer;
when the pedestrian identity is identified as a customer, a temporary ID of the customer is generated, a pedestrian attribute identification task is executed on the customer, the extracted age interval characteristics and sex characteristics of the customer are added to the commodity sales condition characteristics, and when the customer leaves a shooting area, the temporary ID is deleted.
In some embodiments, before identifying the pedestrian identity through the image classification model and determining whether the pedestrian identity is a service person or a customer, the method further comprises:
detecting a rectangular region of a pedestrian position appearing in the video stream picture through a target detection model, and outputting a target detection result;
cutting the pedestrian image according to the target detection result, and performing quality evaluation on the cut pedestrian image through a quality evaluation module;
and if the pedestrian image does not accord with the preset quality evaluation standard of the quality evaluation module, not identifying the identity information of the pedestrian.
In some embodiments, after the calculating the commodity sales status feature according to the tracking result, the method further comprises:
and for a new commodity without the commodity sales condition characteristics, searching the most similar commodity with the commodity sales condition characteristics through the inherent attributes of the new commodity.
In some embodiments, after the calculating the commodity sales status feature according to the tracking result, the method further comprises:
calculating a commodity attention degree score according to the commodity sales condition characteristics;
and screening the commodities according to the attention degree score and the sales volume of the commodities.
In some of these embodiments, the regression model is a linear regression model, a random forest model, or a gradient boosting decision tree model.
In some embodiments, the generating the discount coupon under the condition of maximizing the profit comprises:
calculating the discount value when the profit is maximum;
calling a preset discount coupon template, wherein the discount coupon template comprises pages and appearances of discount coupons;
writing the attribute of the discount coupon, the discount date and the discount value into the corresponding position of the discount coupon template, generating the discount coupon, and issuing the discount coupon to the client through the member system.
In a second aspect, an embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor is configured to implement the intelligent design method for personalized discount coupons as described in the first aspect above when the processor runs the computer program.
In a third aspect, an embodiment of the present application provides a storage medium, in which a computer program is stored, where the computer program is configured to implement, when running, the intelligent design method for a personalized discount coupon according to the first aspect.
Compared with the related art, the intelligent design method for the personalized discount coupon, provided by the embodiment of the application, comprises the steps of obtaining a video stream shot by a camera, and executing a target tracking task on pedestrians and commodities in the video stream to obtain a tracking result; thus, the video stream data is processed, the analysis of the behaviors of clients (pedestrians) is realized, the commodity sales condition characteristics are calculated according to the tracking result, the regression model is trained by utilizing the commodity sales condition characteristics to obtain the sales volume prediction model, the commodity sales condition is analyzed without using the personal information of the clients under the condition of not invading the privacy of the clients, the sales volume of commodities under different discount amounts can be accurately predicted by the sales volume prediction model, the detection of the commodity sales condition is realized in a single network (sales volume prediction model), the inference time is reduced by sharing most of calculation, the purpose of performing inference and prediction by video is realized, the sales volume of the commodities under given discount is predicted by utilizing the sales volume prediction model, and therefore, the sales volume can be rapidly predicted by a large number of different commodities, the intelligent degree is high and the practicability is strong, according to the predicted sales volume, the discount coupon is generated under the condition of maximizing the profit, so that the discount coupon is intelligently designed under the condition of not invading the privacy of the user, a merchant can be helped to reasonably control the marketing cost and the profit can be improved, and the problems of increased marketing cost and low sales volume and profit caused by the mode of issuing the discount coupon through personal experience in the prior art are solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a first flowchart of a method for intelligently designing a personalized discount coupon according to an embodiment of the present application;
FIG. 2 is a second flowchart of a method for intelligently designing a personalized discount coupon according to an embodiment of the present application;
FIG. 3 is a third flowchart of a method for intelligently designing a personalized discount coupon according to an embodiment of the present application;
FIG. 4 is a schematic flowchart illustrating a process of obtaining browsing times of a product according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart illustrating a process of obtaining the number of times a commodity is consulted or the time of consultation according to an embodiment of the present disclosure;
FIG. 6 is a schematic flow chart illustrating a process of obtaining the number of times a product is taken and the number of times the product is added to a shopping cart according to an embodiment of the present disclosure;
FIG. 7 is a fourth flowchart illustrating a method for intelligently designing personalized discount coupons, according to an embodiment of the present application;
FIG. 8 is a schematic illustration of a product discount and sales volume according to an embodiment of the present application;
FIG. 9 is a schematic view of a process for generating a discount coupon under a profit-maximizing condition according to an embodiment of the present application;
fig. 10 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference herein to "a plurality" means greater than or equal to two. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The invention provides an intelligent design method of an individualized discount coupon.
Fig. 1 is a first flow diagram of an intelligent design method for a personalized discount certificate according to an embodiment of the present application, and referring to fig. 1, in an embodiment of the present invention, the intelligent design method for a personalized discount certificate provided by the present invention is applied to a large mall/supermarket with a camera installed in a commodity area, and the method includes the following steps:
step S101, acquiring a video stream shot by a camera;
step S102, executing a target tracking task on pedestrians and commodities in a video stream to obtain a tracking result; for example, video stream data is processed to analyze the behavior of a client (pedestrian);
it should be noted that the target tracking task in this embodiment is a single-step multi-target tracking task, commodity detection and Re-ID (pedestrian Re-identification) feature extraction can be simultaneously achieved through a single model, and commodity detection and identity embedding are simultaneously completed in a single network (sales prediction model), so that the inference time is reduced by sharing most of calculations, and the purpose of performing inference and prediction at a video frame rate is achieved; in this embodiment, the target Tracking task is implemented by using a FairMOT (FairMOT, which is called fairmulti-Object Tracking) model, and certainly, in some other embodiments, may also be implemented by using other models, which are not specifically limited herein;
step S103, calculating commodity sales status characteristics according to the tracking result, wherein the commodity sales status characteristics at least comprise the times of browsing commodities, the times of consulting commodities, the times of taking commodities and the times of adding commodities into shopping carts; of course, in some other embodiments, the commodity sales status feature may also include a commodity basic information feature or other features, and no specific feature is made here; for example, the basic information features include information such as an article identification, an article name, an article unit price, and an article discount;
the commodity sales condition characteristics are more, the prediction effect of the subsequent sales prediction model is better, and the prediction accuracy is higher; in this embodiment, the commodity sales status features are calculated according to the tracking result in the previous time span, in other words, the commodity sales status features at least include the number of times that the commodity in the previous time span is browsed, the number of times that the commodity in the previous time span is consulted, the number of times that the commodity in the previous time span is taken, and the number of times that the commodity in the previous time span is added to the shopping cart, where the previous time span refers to a time period in which the price and discount are not changed, such as the time of the previous sales promotion period of the commodity: namely, from 1 month 6, 0 o 'clock 0 min 0 s to 1 month 9, 0 o' clock 0 min 0 s, during which, for example, the selling price of the commodity is 200 yuan, and the discount amount is 180 yuan (9 folds); at a time such as the last promotional period for the item: namely, 1 month 15, 0 o 'clock 0 min 0 s to 1 month 20, 0 o' clock 0 min 0 s, during which, for example, the selling price of the commodity is 100 yuan and the discount amount is 80 yuan (8 yuan); in addition, those skilled in the art can extract the commodity sales status features through the existing video algorithm, which is not described herein.
Step S104, training a regression model by using the commodity sales condition characteristics to obtain a sales prediction model; thus, the sales amount is predicted;
step S105, predicting the sales volume of the commodity under the given discount by using the sales volume prediction model; therefore, the sales volume of a large number of different commodities can be conveniently and rapidly predicted, the intelligent degree is high, and the practicability is high; wherein, according to the user requirement, the given discount can be set according to the user requirement, and the given discount can be a given amount of money or a given discount (for example, 7 folds, 8 folds, 9 folds, etc.), which is not specifically limited herein;
and step S106, generating the discount coupon under the condition of maximizing the profit according to the predicted sales volume. Therefore, the method can help the merchant reasonably control the marketing cost and realize the improvement of profit, and solves the problems of increased marketing cost and low sales volume and profit caused by the prior discount coupon release through personal experience. It should be noted that, different discount coupons can be generated for different commodities, and the discount coupons do not distinguish customers;
it should be noted that, in this embodiment, the above steps S101 to S106 are all completed without violating the privacy of the user, where the non-violating the privacy of the user means that the personal privacy data of the client is not used in the method. It is noted that, in the scenario of the embodiment of the present application, the above steps can be adopted to intelligently generate discount coupons for all commodities in a shopping mall.
Through the steps from S101 to S106, a video stream shot by the camera is obtained, and a target tracking task is executed on pedestrians and commodities in the video stream to obtain a tracking result; thus, the video stream data is processed, the analysis of the behaviors of clients (pedestrians) is realized, the commodity sales condition characteristics are calculated according to the tracking result, the regression model is trained by utilizing the commodity sales condition characteristics to obtain the sales volume prediction model, the commodity sales condition is analyzed without using the personal information of the clients under the condition of not invading the privacy of the clients, the sales volume of commodities under different discount amounts can be accurately predicted by the sales volume prediction model, the detection of the commodity sales condition is realized in a single network (sales volume prediction model), the inference time is reduced by sharing most of calculation, the purpose of performing inference and prediction by video is realized, the sales volume of the commodities under given discount is predicted by utilizing the sales volume prediction model, and therefore, the sales volume can be rapidly predicted by a large number of different commodities, the intelligent degree is high and the practicability is strong, according to the predicted sales volume, the discount coupon is generated under the condition of maximizing the profit, so that the discount coupon is intelligently designed under the condition of not invading the privacy of the user, a merchant can be helped to reasonably control the marketing cost and the profit can be improved, and the problems of increased marketing cost and low sales volume and profit caused by the mode of issuing the discount coupon through personal experience in the prior art are solved.
Since there are a large number of potential customers in the shopping process, many potential customers are in a viewing state and are easily converted into new customers once receiving interest messages, in one embodiment, the merchandise sales status characteristics further include the number of times that the merchandise has been viewed for a period of time exceeding a preset threshold but has not been taken and the number of times that the merchandise has been taken but has not been added to the shopping cart. Therefore, by adding a large number of characteristics of potential customers to commodity behaviors, a sales prediction model can be conveniently and better trained subsequently, and the prediction precision is improved; the preset threshold is set according to a user requirement, for example, the preset threshold may be 1 day, 2 days, or more, and is not specifically limited herein.
Further, in some embodiments, the commodity sales condition is characterized by being formed by splicing the number of times that the commodity is browsed for a time period exceeding a preset threshold value but is not taken, the number of times that the commodity is taken but is not added to a shopping cart and the number of times that the commodity is browsed, the number of times that the commodity is consulted, the number of times that the commodity is taken and the number of times that the commodity is added to the shopping cart, and in the splicing process, the system does not store and record the original data of the client, and does not pay attention to individual data, so that the privacy of the user is not violated.
Fig. 2 is a second flowchart of a method for intelligently designing a personalized discount coupon according to an embodiment of the present application, and referring to fig. 2, in some embodiments, after acquiring a video stream captured by a camera, the method further includes:
step S201, identifying the identity of a pedestrian through an image classification model, and judging whether the identity of the pedestrian is a service person or a customer; the pedestrian identity recognition can be realized by uniform dressing of service personnel (such as a tool with bright color, a uniform LOGO and the like) so as to distinguish the service personnel from customers, in addition, the image classification model can be realized by MoibleNet series models, wherein the MoibleNet series models comprise MoibleNet V1, MoibleNet V2, MobileNet V3 … … and the like, and the MoibleNet series models adopted in the embodiment are light-weight models, so that the number of parameters is small, the calculated amount is small, the operation speed is high, and the training speed of the models is favorably improved;
step S202, when the Pedestrian identity is identified as the customer, generating the temporary ID of the customer, executing a Pedestrian Attribute identification task (PAR) on the customer, adding the extracted age interval characteristic and gender characteristic of the customer into the commodity sales condition characteristic, and deleting the temporary ID when the customer leaves the shooting area. The original data of the user is not saved and the individual data is not concerned, so that the privacy of the user is not invaded. It is easy to understand that the human attribute identification task aims to mine the attribute information (such as age interval characteristics, sex characteristics and the like) of the pedestrian from the input image, and the high-level semantic information of the pedestrian is obtained by identification mining; available training methods include: on the basis of the RAP algorithm of deep learning, the human attribute recognition task can be conveniently trained by using manually designed low-level features, such as HOG (Histogram of Oriented Gradient), SIFT (Scale-invariant feature transform), and combining with a classification algorithm SVM and a Conditional Random Field (CRF), where the prior art of RAP algorithm, HOG, SIFT, classification algorithm SVM and CRF is known to those skilled in the art and thus is not described in detail.
Fig. 3 is a third flow diagram of an intelligent design method for an individualized discount coupon according to an embodiment of the present application, and referring to fig. 3, in an actual application process, since a pedestrian can move freely within a camera view angle, and a moving speed, a posture change, and the like of the pedestrian can change at any time, it is not guaranteed that each frame of a video is clear and usable, in order to improve a feature recognition effect, in some embodiments, a pedestrian identity is recognized by an image classification model, and before it is determined that the pedestrian identity is a service person or a customer, the method further includes:
step S301, detecting a rectangular area of a pedestrian position appearing in a video stream picture through a target detection model, and outputting a target detection result; the target detection model is the prior art in the field, and is not described in detail herein;
step S302, cutting the pedestrian image according to the target detection result, and carrying out quality evaluation on the cut pedestrian image through a quality evaluation module; the quality evaluation module is the prior art in the field and is not described in detail herein;
step S303, if the pedestrian image does not accord with the preset quality evaluation standard of the quality evaluation module, the identity information of the pedestrian is not identified.
Fig. 4 is a schematic flowchart of a process of acquiring browsing times of a product according to an embodiment of the present application, and referring to fig. 4, in some embodiments, acquiring the browsing times of the product includes the following steps:
step S401, when the same temporary ID of the client is detected, the staying time of the client in the target commodity area is calculated;
step S402, if the staying time is longer than the preset staying time and the activity range of the client is smaller than the preset space range, the pedestrian stays in the last time span, the activity range of the client is a circumscribed rectangle of the activity track of the client in the preset staying time, and the activity range is recorded as the number of one-time browsing; the preset stay time is set according to the requirements of customers, and is not specifically limited;
step S403, if the activity range of the client is larger than the preset space range, the activity range of the client is a circumscribed rectangle of the activity track of the client in the staying time and is recorded as the number of one-time browsing;
fig. 5 is a schematic flow chart illustrating a process of obtaining the number of times a commodity is consulted or the time of the commodity is consulted according to an embodiment of the present application, and referring to fig. 5, in an embodiment, obtaining the number of times the commodity is consulted or the time of the commodity is consulted includes the following steps:
step S501, calculating the distance between the client and the service staff, timing a starting communication time T1 when the detected distance is smaller than a preset distance, and timing an ending communication time T2 when the detected distance is equal to the preset distance; the preset distance is set according to the requirements of a user, and is not specifically limited; in this embodiment, whether the user is a customer or a service person can be distinguished through step S201, which is not described herein.
Step S502, calculating the time that the target commodity is consulted in the last time span as the end exchange time T2 minus the start exchange time T1. For example, the timer-start ac time is T1: in 2021, 10 o 'clock 0 min 0 sec, the timing end ac time T2 is 30 min 0 sec at 10 o' clock 2021, and the consultation time is 30 min.
Fig. 6 is a schematic flow chart illustrating a process of acquiring the number of times that a product is taken and the number of times that the product is added to a shopping cart according to an embodiment of the present disclosure, and referring to fig. 6, in an embodiment, acquiring the number of times that the product is taken and the number of times that the product is added to the shopping cart generally includes the following steps:
step S601, detecting the position of a shopping cart and the position of a goods shelf; the position of the goods shelf is fixed, a manual marking mode can be adopted, and in addition, the number of the goods shelf and the fine granularity needing to be marked can be adjusted according to the needs.
Step S602, when the distance between the pedestrian and the shelf position is smaller than a preset fixed threshold value, starting to detect the hand position, and tracking the hand position in real time; the preset fixed threshold is set according to the user requirement, and is not specifically limited herein;
step S603, if the fact that the human hand enters the goods shelf area is detected, recording the times of picking up the goods once;
in step S604, if it is detected that the hand enters the shopping cart area, the number of times of putting an item into the shopping cart is recorded.
In order to solve the cold start problem of the new commodity and improve the practicability, in an embodiment, after the commodity sales condition feature is calculated according to the tracking result, the method further comprises the following steps:
and for new commodities without commodity sales condition characteristics, searching the most similar commodities with commodity sales condition characteristics through the inherent attributes of the new commodities. The inherent attributes of the new product are, among others, category, price, brand, etc. For example, the new commodity is 'jiaduobao', but the jiaduobao has no commodity sales condition features, and the most similar commodity with the commodity sales condition features, namely 'wanglaoji', is searched through the inherent attributes (type, price, brand, and the like) of the 'jiaduobao'; in executing steps S104 to S106, a discount ticket for the new product is generated. Since the commodity sales condition features in this embodiment are calculated from the tracking result in the last time span, in some other embodiments, in order to improve the model effect, the commodity sales condition features of multiple time spans may also be used, for example, the time of three previous commodity sales promotions.
Fig. 7 is a fourth flowchart illustrating an intelligent design method for a personalized discount coupon according to an embodiment of the present application, and referring to fig. 7, in order to meet a requirement that a business wants to stock or promote sales, in an embodiment, after calculating a characteristic of a sales condition of a commodity according to a tracking result, the method further includes:
step S701, calculating a commodity attention degree score according to the commodity sales condition characteristics; the calculation formula of the commodity attention degree score is as follows:
wherein, ScoreItemRepresenting the Item attention score, Item representing a discount Item,
representing weights for different features, which can be set manually according to the actual situation, xiRepresenting the ith commodity sales condition feature, and n is the total number of the commodity sales condition features;
and step S702, screening the commodities according to the attention degree scores and sales volumes of the commodities. Wherein, the screening commodity formula is as follows:
wherein, SaleItemRepresents the sales volume of the Item (Item), ScoreItemRepresentative commodity gateThe attention score.
In addition, considering that the purchase condition and the discount condition in the transaction may affect the sales volume of the goods, in some other embodiments, a person skilled in the art may also analyze the purchase condition and the discount condition in the transaction of the user through some software programs or algorithms to implement quantitative calculation of the sensitivity of the discount of the user to obtain a discount-sales volume curve. The discount and sales curves are different for different commodities; fig. 8 is a schematic diagram of a product discount and sales volume song according to an embodiment of the present application, and referring to fig. 8, it can be seen that the sales volume increases rapidly as the discount increases in the initial period, but the change tends to be stagnant when the discount decreases to a certain extent, and the sales volume stops increasing due to insufficient supply or saturation of purchasing power. In a real scenario, the discount may not reach 100%. Selecting a product that is sensitive to buckle changes can bring about more significant effects. Note that the discount-to-sales curve at this time represents only a rough trend, and therefore cannot be used to accurately predict sales, and is only used to analyze how sensitive the product is to discounts.
In some embodiments, the regression model is a linear regression model, a random forest model, or a gradient boosting decision tree model, and certainly, in some other embodiments, the regression model may also select another model with a better regression effect according to a user requirement, which is not specifically limited herein.
Fig. 9 is a schematic flow chart of the process of generating the discount ticket under the condition of maximizing the profit according to the embodiment of the present application, and referring to fig. 9, in some embodiments, the generating the discount ticket under the condition of maximizing the profit includes:
step S901, calculating a discount value when the profit is the maximum; the discount value of the maximum profit can be calculated by the skilled person through the formula of the total sales amount and the formula of the total profit; wherein, the formula of the total sales volume is as follows: the total sale amount (sale price) (sale amount) (original price-discount amount) and the total profit are expressed by: the total profit (sales) is the single profit (original price-discount amount-cost), and since the sales of the product under different discounts can be predicted through the model, the discount value corresponding to the maximum calculated value can be calculated according to the formula of the total sales or the formula of the total profit;
step S902, a preset discount coupon template is called, wherein the discount coupon template comprises pages and appearances of discount coupons; the page and the appearance can be set according to the requirements of a user, and are not specifically limited;
and step S903, writing the attribute of the discount coupon, the discount date and the discount value calculated in the step S901 into the corresponding position of the discount coupon template to generate the discount coupon, and issuing the discount coupon to the client through the member system. The attribute of the discount coupon, the discount date and the discount value can be set according to the requirements of the user, and are not specifically limited;
the member system is the prior art, some basic information of customers is recorded in the member system, and the usable member system data means that the use of the information is authorized by a user; the table contents are as follows:
| name (R) | Source |
| Customer unique identification | Commodity member system |
| Sex | Commodity member system |
| Age (age) | Commodity member system |
| Situation of purchasing goods by user | Historical transaction data |
| User transaction situation | Historical transaction data |
The unique identification refers to an ID (identity) used for identifying the identity of a user in a member system, the gender refers to the gender of the user, the age refers to the age of the user, and the condition of purchasing commodities by the user refers to the actual purchased commodity identification, type, quantity and the like of the user; the user transaction condition includes a user payment mode, a payment amount, a discount mode, a discount amount and the like.
In order to maximize the conversion rate of the discount coupon, in some other embodiments, with the combination of expert experience and industry knowledge, a person skilled in the art can also obtain the relationship between the usage rate of the discount coupon and the usage time, the valid period of the discount coupon and the type of the product by analyzing the usage condition of the discount coupon through some software algorithms, programs or models, and write the setting method of the valid period of the discount coupon into a rule (that is, if the product a uses the product C discount under the condition B, the valid period is D), so that the appropriate time attribute of the discount coupon is selected for the specific product, the conversion rate of the discount coupon is increased, and the profit of the product is improved.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
The present embodiment also provides an electronic device comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
step S101, acquiring a video stream shot by a camera;
step S102, executing a target tracking task on pedestrians and commodities in the video stream to obtain a tracking result;
step S103, calculating commodity sales status characteristics according to the tracking result, wherein the commodity sales status characteristics at least comprise the times of browsing commodities, the times of consulting commodities, the times of taking commodities and the times of adding commodities into shopping carts;
step S104, training a regression model by using the commodity sales condition characteristics to obtain a sales prediction model;
step S105, predicting the sales volume of the commodity under the given discount by using the sales volume prediction model;
and step S106, generating the discount coupon under the condition of maximizing the profit according to the predicted sales volume.
In addition, in combination with the intelligent design method of the personalized discount coupon in the above embodiment, the embodiment of the application may provide a storage medium to implement. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements the intelligent design method for personalized discount coupons of any of the above embodiments.
In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of intelligently designing a personalized discount coupon. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
In one embodiment, fig. 10 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application, and as shown in fig. 10, there is provided an electronic device, which may be a server, and an internal structure diagram of which may be as shown in fig. 10. The electronic device comprises a processor, a network interface, an internal memory and a non-volatile memory connected by an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used for providing calculation and control capability, the network interface is used for communicating with an external terminal through network connection, the internal memory is used for providing an environment for an operating system and the running of a computer program, the computer program is executed by the processor to realize an intelligent design method of the personalized discount coupon, and the database is used for storing data.
It will be appreciated by those skilled in the art that the configuration shown in fig. 10 is a block diagram of only a portion of the configuration relevant to the present application, and does not constitute a limitation on the electronic device to which the present application is applied, and a particular electronic device may include more or less components than those shown in the drawings, or combine certain components, or have a different arrangement of components.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be understood by those skilled in the art that various features of the above-described embodiments can be combined in any combination, and for the sake of brevity, all possible combinations of features in the above-described embodiments are not described in detail, but rather, all combinations of features which are not inconsistent with each other should be construed as being within the scope of the present disclosure.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An intelligent design method of a personalized discount coupon, characterized by comprising the following steps:
acquiring a video stream shot by a camera;
executing a target tracking task on the pedestrians and the commodities in the video stream to obtain a tracking result;
calculating commodity sales condition characteristics according to the tracking result, wherein the commodity sales condition characteristics at least comprise the times of browsing commodities, the times of consulting the commodities, the times of taking the commodities and the times of adding the commodities into a shopping cart;
training a regression model by using the commodity sales condition characteristics to obtain a sales prediction model;
predicting the sales volume of the goods under the given discount by using the sales volume prediction model;
and generating the discount coupon under the condition of maximizing the profit according to the predicted sales volume.
2. The method of claim 1, wherein the merchandise sales status characteristics further comprise the number of times that the merchandise has been viewed for a period of time exceeding a preset threshold but not picked and the number of times that the merchandise has been picked but not entered into a shopping cart.
3. The method of claim 1, wherein after the obtaining the video stream captured by the camera, the method further comprises:
identifying the identity of a pedestrian through an image classification model, and judging whether the identity of the pedestrian is a service person or a customer;
when the pedestrian identity is identified as a customer, a temporary ID of the customer is generated, a pedestrian attribute identification task is executed on the customer, the extracted age interval characteristics and sex characteristics of the customer are added to the commodity sales condition characteristics, and when the customer leaves a shooting area, the temporary ID is deleted.
4. The method of claim 3, wherein the identifying the pedestrian identity through the image classification model and determining whether the pedestrian identity is a service person or a customer, the method further comprises:
detecting a rectangular region of a pedestrian position appearing in the video stream picture through a target detection model, and outputting a target detection result;
cutting the pedestrian image according to the target detection result, and performing quality evaluation on the cut pedestrian image through a quality evaluation module;
and if the pedestrian image does not accord with the preset quality evaluation standard of the quality evaluation module, not identifying the identity information of the pedestrian.
5. The method according to claim 1, wherein after said calculating the commodity sales status feature according to the tracking result, the method further comprises:
and for a new commodity without the commodity sales condition characteristics, searching the most similar commodity with the commodity sales condition characteristics through the inherent attributes of the new commodity.
6. The method according to claim 1, wherein after said calculating the commodity sales status feature according to the tracking result, the method further comprises:
calculating a commodity attention degree score according to the commodity sales condition characteristics;
and screening the commodities according to the attention degree score and the sales volume of the commodities.
7. The method of any one of claims 1-6, wherein the regression model is a linear regression model, a random forest model, or a gradient boosting decision tree model.
8. The method of claim 1, wherein generating the coupon under the conditions of profit maximization comprises:
calculating the discount value when the profit is maximum;
calling a preset discount coupon template, wherein the discount coupon template comprises pages and appearances of discount coupons;
writing the attribute of the discount coupon, the discount date and the discount value into the corresponding position of the discount coupon template, generating the discount coupon, and issuing the discount coupon to the client through the member system.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and the processor is configured to execute the computer program to perform the method of intelligently designing a personalized discount coupon of any one of claims 1 to 8.
10. A storage medium having a computer program stored thereon, wherein the computer program is configured to execute the intelligent design method of a personalized discount coupon of any one of claims 1 to 8 when the computer program is executed.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111238638.5A CN113919882A (en) | 2021-10-25 | 2021-10-25 | Intelligent design method of personalized discount coupon, electronic device and storage medium |
| PCT/CN2021/136416 WO2023070844A1 (en) | 2021-10-25 | 2021-12-08 | Intelligent design method for personalized discount coupon, and electronic apparatus and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111238638.5A CN113919882A (en) | 2021-10-25 | 2021-10-25 | Intelligent design method of personalized discount coupon, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113919882A true CN113919882A (en) | 2022-01-11 |
Family
ID=79242609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111238638.5A Pending CN113919882A (en) | 2021-10-25 | 2021-10-25 | Intelligent design method of personalized discount coupon, electronic device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113919882A (en) |
| WO (1) | WO2023070844A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433273A (en) * | 2022-12-16 | 2023-07-14 | 广州飞狮数字科技有限公司 | Method and device for determining commodity sales discount |
| CN117314516A (en) * | 2023-09-19 | 2023-12-29 | 深圳市通商宝科技有限公司 | Digital card management method and system |
| CN118365423A (en) * | 2024-05-15 | 2024-07-19 | 天天向上(北京)网络科技有限公司 | Intelligent electric business data center management system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777571B (en) * | 2023-08-22 | 2023-11-10 | 山东创恩信息科技股份有限公司 | Merchant recommendation and purchase method and system based on big data and Internet platform |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678591A (en) * | 2016-02-29 | 2016-06-15 | 北京时代云英科技有限公司 | Video-analysis-based commercial intelligent operation decision-making support system and method |
| CN108648338B (en) * | 2018-04-12 | 2021-01-12 | 广州杰赛科技股份有限公司 | Commodity information acquisition method and device for vending machine and vending machine |
| CN109509030B (en) * | 2018-11-15 | 2021-06-22 | 北京旷视科技有限公司 | Sales prediction method, training method and device of model thereof, and electronic system |
| CN110287878A (en) * | 2019-06-25 | 2019-09-27 | 秒针信息技术有限公司 | The determination method and device of marketing strategy, storage medium, electronic device |
| JP7508220B2 (en) * | 2019-12-17 | 2024-07-01 | 東芝テック株式会社 | Sales Promotion System |
| CN112288464A (en) * | 2020-10-16 | 2021-01-29 | 杭州贝嘟科技有限公司 | Commodity recommendation method and device, computer equipment and storage medium |
-
2021
- 2021-10-25 CN CN202111238638.5A patent/CN113919882A/en active Pending
- 2021-12-08 WO PCT/CN2021/136416 patent/WO2023070844A1/en unknown
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433273A (en) * | 2022-12-16 | 2023-07-14 | 广州飞狮数字科技有限公司 | Method and device for determining commodity sales discount |
| CN117314516A (en) * | 2023-09-19 | 2023-12-29 | 深圳市通商宝科技有限公司 | Digital card management method and system |
| CN118365423A (en) * | 2024-05-15 | 2024-07-19 | 天天向上(北京)网络科技有限公司 | Intelligent electric business data center management system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023070844A1 (en) | 2023-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Vana et al. | Cashback is cash forward: delaying a discount to entice future spending | |
| Ngai et al. | Machine learning in marketing: A literature review, conceptual framework, and research agenda | |
| CN108665329B (en) | Commodity recommendation method based on user browsing behavior | |
| CN113919882A (en) | Intelligent design method of personalized discount coupon, electronic device and storage medium | |
| CN109582876B (en) | Tourist industry user portrait construction method and device and computer equipment | |
| Chen et al. | Modeling credit card share of wallet: Solving the incomplete information problem | |
| Jain et al. | Customer lifetime value research in marketing: A review and future directions | |
| CN110992097B (en) | Processing method and device for price of revenue product, computer equipment and storage medium | |
| CN111080398A (en) | Commodity recommendation method and device, computer equipment and storage medium | |
| US20160048856A1 (en) | Digital receipts economy | |
| AU2018202369A1 (en) | A method and system for providing a loyalty program | |
| KR20180052489A (en) | method of providing goods recommendation for cross-border E-commerce based on user experience analysis and environmental factors | |
| US20220180379A1 (en) | Transaction-based information processing system, method, and article | |
| WO2022151923A1 (en) | Method and apparatus for processing paperwork for goods, electronic device, medium, and program | |
| CN114202376A (en) | Resource determination method, device, equipment and storage medium | |
| Tekin et al. | Data mining in digital marketing | |
| Zheng et al. | A scalable purchase intention prediction system using extreme gradient boosting machines with browsing content entropy | |
| Goyal | Managing perceived risk for credit card purchase through supplementary services | |
| Guo et al. | The effectiveness of membership-based free shipping: An empirical investigation of consumers’ purchase behaviors and revenue contribution | |
| US20150371238A1 (en) | Personal holiday imputation from payment card transactional data | |
| KR102534837B1 (en) | Methods and systems for marketing online goods and services | |
| Muniasamy et al. | Analyzing online reviews of customers using machine learning techniques | |
| Lipianina-Honcharenko et al. | Intelligent method for forming the consumer basket | |
| JPWO2020084712A1 (en) | Distribution program, distribution method and distribution device | |
| KR102429104B1 (en) | Product catalog automatic classification system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |