CN119006051A

CN119006051A - Accurate marketing method and device based on position, medium and computer equipment

Info

Publication number: CN119006051A
Application number: CN202411047908.8A
Authority: CN
Inventors: 朱秀茵; 许伟; 李�杰; 苏华筠; 温琦舒
Original assignee: Duolichou Technology Guangzhou Co ltd
Current assignee: Duolichou Technology Guangzhou Co ltd
Priority date: 2024-08-01
Filing date: 2024-08-01
Publication date: 2024-11-22

Abstract

The present invention provides a location-based precision marketing method, device, medium and computer equipment, including: forming feature tags based on historical data of users, and constructing user portraits according to the feature tags; delineating trigger areas for marketing activities based on the locations of commodities; and in response to the location change of the smart shopping cart, recommending marketing activities to users based on the user portraits when the smart shopping cart enters the trigger area; adopting the method of the present invention, more suitable marketing activities can be recommended to users based on the locations of users, the routes of shopping carts and historical purchase data of users during the process of shopping in supermarkets, so as to avoid users generating plans among numerous marketing activities, effectively improve the conversion rate of marketing activities by utilizing the interests of users, and improve the satisfaction efficiency of users through personalized recommendations.

Description

Accurate marketing method and device based on position, medium and computer equipment

Technical Field

The invention relates to the technical field of digital marketing, in particular to a position-based accurate marketing method, a position-based accurate marketing device, a position-based accurate marketing medium and computer equipment.

Background

Supermarkets, which are an important component of the retail industry, have long relied on a wide spread-network marketing strategy that aims to cover a wide range of potential customers, attracting customers through large-scale advertising campaigns, promotional campaigns, and discount offers. While this approach may increase customer flow and sales in a short period of time, it has some significant limitations. First, wide spread network marketing strategies tend to ignore individual differences and specific needs of customers. Each customer has its own unique consumer habits, brand preferences, and purchasing power, while traditional marketing approaches rarely capture and meet these personalized needs with precision. As a result, many marketing messages may be inconsequential to customers, even considered spam, thereby reducing the appeal and effectiveness of the marketing campaign. Second, such a policy may not be efficient in resource allocation. Supermarkets may distribute marketing resources, including advertising, inventory and promotional staff, equally across various product lines in order to attract all customers. This approach may result in wasted resources, as not all products need to be promoted to the same extent, and the need for some high value customer groups is ignored.

Disclosure of Invention

Aiming at the defects existing in the prior art, the invention aims to provide a position-based accurate marketing method, a position-based accurate marketing device, a position-based accurate marketing medium and a position-based accurate marketing computer device, so as to overcome the defect that the product popularization effect is difficult to improve by adopting a wide spread-network marketing mode in the prior art.

The technical aim of the invention is realized by the following technical scheme: a precise marketing method based on a position is applied to an intelligent shopping cart; the accurate marketing method comprises the following steps:

Forming a characteristic tag based on historical data of a user, and constructing a user portrait according to the characteristic tag;

Based on the position of the commodity, defining a triggering area of the marketing campaign;

And in response to the change of the position of the intelligent shopping cart, recommending a marketing campaign for the user based on the user portrait in the case that the intelligent shopping cart enters the trigger area.

In one embodiment, the forming a feature tag based on the historical data of the user, and constructing a user portrait according to the feature tag specifically includes:

Acquiring registration information, historical purchase records and browsing data of a user, and forming a corresponding feature tag through data mining analysis, wherein the feature tag comprises: age, gender, consumption ability, preferred merchandise category, shopping frequency, shopping time period, brand preference, price sensitivity;

and distributing corresponding feature labels for each user, and constructing a user portrait.

In one embodiment, the forming the corresponding feature tag through data mining analysis specifically includes:

And counting the acquired registration information, historical purchase records and browsing data of the user by adopting an RFM algorithm, AARRR algorithm, a cluster analysis algorithm or an association rule mining algorithm to obtain a plurality of feature tag types.

In one embodiment, the demarcating the triggering area of the marketing campaign based on the location of the merchandise includes:

constructing a supermarket store map;

Setting interest points in a supermarket store map based on commodity placement of the supermarket store;

correspondingly constructing an electronic fence based on each interest point;

And correlating the commodities participating in the marketing campaign with the corresponding electronic fence to serve as a triggering area of the marketing campaign.

In one embodiment, the recommending marketing activities for the user based on the user portrayal in response to the change of the location of the intelligent shopping cart in the case that the intelligent shopping cart enters the trigger area specifically includes:

And recommending first marketing activity information to the user based on the user image of the user and the current position of the intelligent shopping cart, wherein the distance between the position of the commodity corresponding to the first marketing activity information and the user is smaller than a first distance threshold.

In one embodiment, the recommending marketing campaign for the user based on the user representation in response to the change in the location of the intelligent shopping cart in the event that the intelligent shopping cart enters the trigger area further comprises:

recommending a second marketing campaign information to the user in the case where the user representation includes a price sensitive label; the second marketing campaign information is discount information; and the distance between the position of the commodity corresponding to the second marketing campaign information and the user is smaller than a second distance threshold.

Providing third marketing campaign information to the user based on the user's historical purchase record; the commodity corresponding to the third marketing campaign information is the commodity purchased by the user for more than a preset number of times; and the distance between the position of the commodity corresponding to the third marketing campaign information and the user is smaller than a third distance threshold.

A location-based precision marketing device, comprising:

The user portrait construction unit is used for forming a characteristic tag based on the history data of the user and constructing a user portrait according to the characteristic tag;

the system comprises an activity area dividing unit, a marketing area dividing unit and a marketing area dividing unit, wherein the activity area dividing unit is used for dividing a triggering area of a marketing activity based on the positions of commodities;

And the marketing campaign recommending unit is used for recommending marketing campaigns to users based on the user portrait under the condition that the intelligent shopping cart enters the trigger area in response to the position change of the intelligent shopping cart.

A computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.

A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.

In summary, the invention has the following beneficial effects: a location-based precision marketing method, comprising: forming a characteristic tag based on historical data of a user, and constructing a user portrait according to the characteristic tag; based on the position of the commodity, defining a triggering area of the marketing campaign; recommending a marketing campaign to a user based on the user representation in response to a change in the location of the intelligent shopping cart in the event that the intelligent shopping cart enters the trigger area; by adopting the method, the user can recommend more suitable marketing activities for the user based on the position of the user, the travelling route of the shopping cart and the historical purchase data of the user in the process of shopping in the supermarket, so that the user is prevented from generating schemes in a plurality of marketing activities, the interest points of the user can be utilized, the conversion rate of the marketing activities can be effectively improved, and the satisfaction efficiency of the user can be improved through personalized recommendation.

Drawings

FIG. 1 is a flow chart of a location-based precision marketing method of the present invention;

FIG. 2 is a block diagram of a location-based precision marketing device in an embodiment of the present invention;

Fig. 3 is an internal structural diagram of a computer device in an embodiment of the present invention.

Detailed Description

In order that the objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances. The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.

In the present invention, unless expressly stated or limited otherwise, a first feature "above" or "below" a second feature may include both the first and second features being in direct contact, as well as the first and second features not being in direct contact but being in contact with each other through additional features therebetween. Moreover, a first feature being "above," "over" and "on" a second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature includes the first feature being directly under and obliquely below the second feature, or simply means that the first feature is less level than the second feature. The terms "vertical," "horizontal," "left," "right," "up," "down," and the like are used for descriptive purposes only and are not to indicate or imply that the devices or elements being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the invention.

Example 1

In order to solve the above problems, the present invention provides a location-based accurate marketing method, as shown in fig. 1, comprising:

S1, forming a characteristic tag based on historical data of a user, and constructing a user portrait according to the characteristic tag;

s2, defining a triggering area of a marketing campaign based on the positions of the commodities;

and S3, responding to the position change of the intelligent shopping cart, and recommending a marketing activity for the user based on the user portrait under the condition that the intelligent shopping cart enters the trigger area.

In practical applications, in order to improve the shopping experience of users and the sales situation of commodities, the traditional merchant will engage a promoter in a supermarket to promote various commodities in the supermarket to improve the sales data of the commodities, but many marketing messages may be inconsequential to customers and even regarded as junk messages, thereby reducing the attraction and effectiveness of marketing activities. Second, such a policy may not be efficient in resource allocation. Supermarkets may distribute marketing resources, including advertising, inventory and promotional staff, equally across various product lines in order to attract all customers. This approach may result in wasted resources, as not all products need to be promoted to the same extent, and the need for some high value customer groups is ignored. In order to improve the accuracy of marketing activities, the application provides a precise marketing method based on positions, and in order to realize the method, firstly, an intelligent shopping cart is required to be put in a supermarket, the intelligent shopping cart at least comprises two functional structures, one is a display module for displaying related marketing activities for users, and the other is a positioning module for acquiring the positions of the shopping carts, so that customers can push the shopping carts to shop in the supermarket in the actual use process, and the goods interesting for the users, the goods required to be purchased by the users or the shopping habits of the users and the like can be acquired based on the positions and the travelling routes of the shopping carts and the goods arrangement in the supermarket. The method of the application firstly needs to distribute labels to users according to the historical data of the users, and then creates user images for the users according to the labels of the users. And secondly, a trigger area is defined for each commodity according to the placement position of the commodity, and the corresponding marketing activities can be recommended for the user only when the user arrives at the position of the commodity. Because the marketing activities are personalized, not all marketing activities are recommended for each user, but whether the marketing activities exist in commodities near the periphery of the user or not is judged based on the preference of the user and the current position of the user, if so, the relevant marketing activities are recommended for the user after the user reaches the marketing activity area of the commodities.

By adopting the technical scheme, the method has the following technical advantages: 1. the marketing accuracy is improved: by analyzing the position data of the user shopping in the supermarket, the consumption behavior preference of the user, such as favorite products, brands, price intervals and the like, is known, so that marketing information which meets the requirements and interests of different user groups is pushed, and the pertinence and effectiveness of marketing are improved. 2. Facilitating the promotion of the amount of consumption: through marketing based on the position data, related motivation measures such as coupons, discounts, gifts and the like are pushed in real time in the shopping process of the user, so that the purchasing desire and impulsive consumption of the user are stimulated, and the shopping basket value and the repurchase rate of the user are increased. 3. Enhancing user loyalty and satisfaction: through marketing based on the position data, more personalized, more convenient and interesting shopping experience is provided for the user, such as shopping guide service, commodity recommendation, shopping navigation and the like are provided according to the walking path and the stay time of the user, trust and liking of the user to the supermarket are increased, and loyalty and satisfaction of the user are improved. 4. Acquiring more user data and feedback: through marketing based on the position data, more user data such as behavior tracks, reaction time, click rate, conversion rate and the like of users in supermarkets are collected and analyzed, so that marketing strategies and effects are optimized, and data-driven marketing decisions are realized. 5. Decision assistance of behavior and location data: the intelligent shopping cart solves the problems of low efficiency and poor precision of traditional entity business super acquisition of customer data by acquiring the behavior data and the position information of the customer shopping in the supermarket in real time, and helps the merchant to better know the customer requirements and habits and promote the operation decision effect by accurate and comprehensive user behavior data and position data.

In practical application, firstly, the features of the user need to be mined from all data, then a plurality of labels are formed based on the result of mining analysis of the data, similar features of the user can be obtained by distributing different labels for each customer, then the portrait for each user is formed based on each attribute of the labels of the user, and finally the user portrait of the user is accurately pushed for the user. For example: commodity recommendation: recommending related commodities according to the preference and the current position of the user; price policy: pushing discount information of related commodities aiming at price sensitive users; time sensitivity: pushing time-limited preferential for users shopping only at specific time; brand preferences: providing the latest product information or special offers of the brand for users who prefer a specific brand, and the like, by purposefully pushing the marketing information for each user, the relevance of the marketing information and the users can be stronger, and the interests of the users can be more aroused.

In practical application, by applying various data mining algorithms, data of a user can be mined from different angles, wherein RFM is an analysis method based on last consumption (Recency), consumption Frequency (Frequency) and consumption amount (monetari), and the method specifically includes: the frequency of user purchases, the time of last purchase, and the total amount of consumption can divide the user into different value classes, such as high value, medium value, and low value customers. AARRR is a marketing funnel model representing Acquisition (Acquisition), activation (action), retention (reservation), revenue (Revenue), and recommendation (Referral), respectively; the AARRR model can analyze the behavior mode and the conversion rate of the user from the acquisition of the recommendation; the AARRR model can provide targeted optimization suggestions for each stage, and improve overall user participation and loyalty. The cluster analysis is an unsupervised learning method, and is used for grouping data points, so that the data points in the same group have high similarity, and the data points in different groups have low similarity; the cluster analysis discovers different user groups by analyzing registration information, purchase records and browsing data of users; the cluster analysis can identify user groups with similar behaviors and characteristics, and provides basis for personalized marketing. Association rule mining is a statistical method for finding interesting relations between variables, and is commonly used for market analysis and commodity recommendation, analyzing user purchase records, finding the association relations between commodities, recommending commodities possibly of interest to users based on association rules, and improving opportunities of cross-selling and up-selling. In conclusion, the accuracy of the data characteristics can be effectively improved through the data mining of different intersections, and the accuracy and the effectiveness of marketing campaign pushing are further improved.

In one embodiment, the demarcating the triggering area of the marketing campaign based on the location of the merchandise includes: constructing a supermarket store map; setting interest points in a supermarket store map based on commodity placement of the supermarket store; correspondingly constructing an electronic fence based on each interest point; and correlating the commodities participating in the marketing campaign with the corresponding electronic fence to serve as a triggering area of the marketing campaign.

In practical application, since the commodity arrangement and the commodity type of each supermarket are different, the position of each commodity in the supermarket is firstly required to be divided, then based on the position of the commodity, corresponding interest points are set in the supermarket, the interest points refer to a series of information points or data points associated with specific commodities, and the information points can include but are not limited to: description of goods: the names, models, specifications, characteristics, etc. of the goods. Classification information: the category or classification of the commodity, such as electronic products, clothing, food, etc. Price information: price of goods, discounts, promotional information, etc. Inventory data: inventory quantity of goods, replenishment cycle, etc. Vendor information: details of the manufacturer or supplier of the goods. Sales data: sales of goods, sales amount, sales trend, etc. Customer evaluation: consumer evaluation and feedback of merchandise. Logistics information: the distribution mode, distribution time, and freight of the commodity. Regulations comply with: whether the merchandise meets relevant regulations and standards. Multimedia content: and multimedia display data such as pictures, videos, 3D models and the like of commodities. The commodity POI data may be used for a variety of business analyses and decisions such as market trend analysis, inventory management, price policy formulation, customer preference analysis, and the like. In an e-commerce platform, retail management system, or supply chain management, such data is critical to optimizing merchandise display, improving user experience, and enhancing supply chain efficiency. By setting the interest points of the commodities, the position information of all the commodities in the store can be ensured to be collected. And (3) constructing electronic fences for all the points of interest based on the points of interest of the commodity, so that the mutual correlation between the electronic fences and the commodity contained in the points of interest can be ensured.

In one embodiment, the recommending marketing activities for the user based on the user portrayal in response to the change of the location of the intelligent shopping cart in the case that the intelligent shopping cart enters the trigger area specifically includes: and recommending first marketing activity information to the user based on the user image of the user and the current position of the intelligent shopping cart, wherein the distance between the position of the commodity corresponding to the first marketing activity information and the user is smaller than a first distance threshold.

In practical application, the positions of the user and the intelligent shopping cart can be determined by judging the positions of the intelligent shopping cart, and after the user reaches a certain trigger area, if the user meets the related pushing conditions, marketing information of related commodities is pushed to the user. In the present application, the first distance threshold is the smallest distance threshold, that is, the marketing information is recommended to the user when the range between the user and the commodity is the smallest. This is typically the case for pushing marketing information to users closest to it for the purpose of wide-condition marketing.

In one embodiment, the recommending marketing campaign for the user based on the user representation in response to the change in the location of the intelligent shopping cart in the event that the intelligent shopping cart enters the trigger area further comprises: recommending a second marketing campaign information to the user in the case where the user representation includes a price sensitive label; the second marketing campaign information is discount information; and the distance between the position of the commodity corresponding to the second marketing campaign information and the user is smaller than a second distance threshold.

In practical application, if the user is a price sensitive user, discount information of the commodity is pushed to the user, wherein the second distance threshold value can be larger than the first distance threshold value, so that the nearby user is attracted to pay more attention to the discounted commodity, and the exposure rate of the commodity is improved.

In one embodiment, the recommending marketing campaign for the user based on the user representation in response to the change in the location of the intelligent shopping cart in the event that the intelligent shopping cart enters the trigger area further comprises: providing third marketing campaign information to the user based on the user's historical purchase record; the commodity corresponding to the third marketing campaign information is the commodity purchased by the user for more than a preset number of times; and the distance between the position of the commodity corresponding to the third marketing campaign information and the user is smaller than a third distance threshold.

In practice, if a user often purchases a brand of product, such as a brand A shampoo, more than three times, the user may be stimulated to make purchases by pushing the marketing campaign or discount campaign for the brand A shampoo again based on the screening criteria. In this embodiment, the third distance threshold will also be generally larger than the first distance threshold. Generally, a user has a preference for a certain brand, and can search for the commodity through a longer distance, so that the effect of a commodity marketing campaign can be improved by recommending related commodities for a specific user.

Example two

Referring to fig. 2, a location-based precision marketing device, the location-based precision marketing device comprising:

A user portrait construction unit 1, wherein the user portrait construction unit 1 is used for forming a characteristic tag based on the history data of a user, and constructing a user portrait according to the characteristic tag;

an activity area dividing unit 2, wherein the activity area dividing unit 2 is used for dividing a trigger area of a marketing activity based on the position of the commodity;

And the marketing campaign recommending unit 3 is used for recommending marketing campaigns to users based on the user portrait under the condition that the intelligent shopping cart enters the trigger area in response to the position change of the intelligent shopping cart.

Specific limitations regarding the location-based precision marketing device may be found in the above limitations of the location-based precision marketing method, and are not described in detail herein. The various modules in the location-based precision marketing device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

It will be appreciated by those skilled in the art that the configuration shown in FIG. 2 is a block diagram of only some of the configurations associated with the present inventive arrangements and is not limiting of the present inventive arrangements, and that a particular location-based precision marketing device may include more or less components than those illustrated, or may combine some components, or may have a different arrangement of components

Example III

A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the location-based precision marketing method of embodiment 1.

Example IV

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database 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 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The computer program, when executed by a processor, implements a location-based precision marketing method.

It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of: the intelligent shopping cart is applied to intelligent shopping carts; the accurate marketing method comprises the following steps: forming a characteristic tag based on historical data of a user, and constructing a user portrait according to the characteristic tag; based on the position of the commodity, defining a triggering area of the marketing campaign; and in response to the change of the position of the intelligent shopping cart, recommending a marketing campaign for the user based on the user portrait in the case that the intelligent shopping cart enters the trigger area.

In one embodiment, the forming a feature tag based on the historical data of the user, and constructing a user portrait according to the feature tag specifically includes: acquiring registration information, historical purchase records and browsing data of a user, and forming a corresponding feature tag through data mining analysis, wherein the feature tag comprises: age, gender, consumption ability, preferred merchandise category, shopping frequency, shopping time period, brand preference, price sensitivity; and distributing corresponding feature labels for each user, and constructing a user portrait.

In one embodiment, the forming the corresponding feature tag through data mining analysis specifically includes: and counting the acquired registration information, historical purchase records and browsing data of the user by adopting an RFM algorithm, AARRR algorithm, a cluster analysis algorithm or an association rule mining algorithm to obtain a plurality of feature tag types.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile 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 (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

Example five

Furthermore, the application also provides another specific embodiment.

The method specifically comprises the following steps:

1. Metadata index structure management: and managing an index list, managing a list relation to which an index name is subordinate, managing a value list of the index, and managing business relations among the indexes by the relation between the user and the index and the mutual constraint of the objects and the relation. 2. Offline and real-time statistics of service data are carried out on indexes: the offline statistics of the index can be stored into a relation table of the user and the index according to the three time hierarchy dimensions of day, week and month, the order data of the user and the behavior data of the user and the statistics results of different time dimensions; the index real-time statistics is that after the intelligent shopping cart generates orders or executes certain actions, the service system transmits the orders or the actions to the label factory in an API mode, and the statistics results are stored in a relation table of the user and the index according to different actions. 3. Secondary processing and calculation based on index results: and processing and calculating again on the basis of the index result according to the service data caliber corresponding to the label definition, so as to find out the user conforming to the definition and finish labeling of the user label.

2. Configuration of map POIs: because the scheme of the application is based on marketing of the user position, the digital management of the position information of all commodities in the supermarket is particularly important in the process of accurately marketing the commodities favored by the user on the shopping line of the user. Firstly, map POI (Point of Interest, interest points) configuration is needed, a worker logs in the intelligent shopping cart background management system, and a specific store is selected and a map thereof is loaded by clicking a menu to enter a map management function. The staff member then clicks on the create POI option and selects POI management by navigating to the map management under the marketing module. The staff member needs to fill out parameters of the POI, including name, category, description, etc., and then click on the map to determine the specific location of the POI. After the staff confirms that all the data are accurate, the server can store the data by clicking the storage button. If more POIs need to be added, the user can select a new location and repeat the steps

3. Acquiring commodity POI data: after the map POI configuration operation is completed, the acquisition operation of all commodity POI positions in the supermarket can be performed. In the store commodity POI position acquisition process, a worker first enters a store site and logs in to an intelligent shopping cart. By clicking on "My > common tools > POI acquisitions", they enter the POI acquisitions page and configure account permissions. The system then loads a store map on which the worker selects the shelf location. Using the code scanning device, they scan the merchandise on the shelves in turn, and the system records and locks the merchandise location data. After the data acquisition of one goods shelf is completed, the staff can continue to select other goods shelves to perform the same operation, and finally, the position information of all goods in the store is ensured to be acquired.

4. LBS commodity recommendation configuration: when a customer logs in the intelligent shopping cart to shop in the field, what commodity preferential is acquired in what time and what area, and the system can adapt to the established marketing activities to push according to objective conditions. And entering a marketing center in the intelligent shopping cart management background, and then selecting an LBS commodity recommending function. Next, the basic information of the marketing campaign is filled in, including campaign name, time, etc., and a new button is clicked to create a new marketing campaign. When an activity is set, specific rules of commodity recommendation, such as recommended regional scope, frequency, customer groups, brands, commodities, preferential degree and other dimensions, are defined. Through setting rules, the establishment of the association relation of the marketing strategy based on four important dimensions of commodities, marketing places, audience groups and marketing time is completed. Through the operation of the mode, various operation strategies can be formed in the intelligent shopping cart management background to meet the requirements of different marketing scenes.

5. Setting up of electronic fence in supermarket: after the marketing strategy is established, the electronic fence will play an important key role when considering how to reach the customer at the appropriate location within the supermarket. Logging in the intelligent shopping cart management background to enter a marketing function, and then selecting an electronic fence option under map management. Then, select a particular store and load its map, then click the newly added electronic fence button to begin the creation process. On the map, the user selects an area of the electronic fence and fills in relevant fence parameters (parameters of size, shape, etc.), and decides whether to associate the electronic fence with a specific marketing strategy. After submitting the storage, a specific area is formed, and when the intelligent shopping cart passes through the area, the marketing interaction operation associated with the electronic fence is triggered.

6. Shopping cart position information acquisition: when a user pushes the intelligent shopping cart to make shopping, the positioning module in the intelligent shopping cart interacts with the system through the serial port, the firmware system sets parameters of the module through the instructions, the positioning module reports position information in real time, data are cached through services, the data are packed and sent to corresponding modules, data interaction of each module and real-time performance of the data are achieved through a broadcasting mechanism or inter-process communication, and therefore accuracy of acquiring position information of the shopping cart in a supermarket is guaranteed.

7. Marketing campaign reach: when a customer logs in the intelligent shopping cart to start shopping, the system can acquire member information, historical consumption information, shopping cart operation information and real-time position information of the customer at the same time, and marketing pushing can be carried out on the user in the following scene according to the information. 1) And recommending related commodities and marketing campaign information near the position to the customer by using a recommendation algorithm according to the consumption preference and the current position of the customer. 2) For price sensitive customers, discount information or coupons for the offer items are pushed as they browse or approach certain items. 3) For customers with obvious preference for a specific brand, when the customers travel to a brand special cabinet area, the latest product information and the exclusive offers of the brand are provided in time. 4) And recommending supplementary commodities or collocation commodities by utilizing an association rule mining technology according to shopping cart contents of customers.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the present invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.

Claims

1. A location-based precision marketing method, characterized in that it is applied to a smart shopping cart; the precision marketing method comprises:

Form feature tags based on the user's historical data, and construct a user profile based on the feature tags;

Define trigger areas for marketing activities based on the location of the products;

In response to the change in the position of the smart shopping cart, when the smart shopping cart enters the trigger area, a marketing activity is recommended to the user based on the user portrait.

2. A location-based precision marketing method according to claim 1, characterized in that the forming of feature tags based on the user's historical data and the building of user portraits based on the feature tags specifically include:

Obtain the user's registration information, historical purchase records, and browsing data, and form corresponding feature tags through data mining analysis. The feature tags include: age, gender, spending power, preferred product category, shopping frequency, shopping time period, brand preference, and price sensitivity;

Assign corresponding feature labels to each user and build a user portrait.

3. A location-based precision marketing method according to claim 2, characterized in that the forming of corresponding feature tags through data mining analysis specifically includes:

Adopt RFM algorithm, AARRR algorithm, cluster analysis algorithm or association rule mining algorithm to obtain user registration information, historical purchase records, and browsing data to obtain several types of feature labels.

4. A location-based precision marketing method according to claim 1, characterized in that the triggering area of the marketing activity is defined based on the location of the product, including:

Build a supermarket store map;

Based on the placement of goods in the supermarket store, points of interest are set in the supermarket store map;

Build electronic fences based on each point of interest;

The commodities participating in the marketing activity are associated with the corresponding electronic fences, and the electronic fences are used as triggering areas for the marketing activity.

5. A location-based precision marketing method according to claim 1, characterized in that in response to the location change of the smart shopping cart, when the smart shopping cart enters the trigger area, recommending marketing activities to the user based on the user portrait, specifically comprises:

Based on the user portrait of the user and the current location of the smart shopping cart, first marketing activity information is recommended to the user, and the distance between the location of the commodity corresponding to the first marketing activity information and the user is less than a first distance threshold.

6. A location-based precision marketing method according to claim 1, characterized in that in response to the location change of the smart shopping cart, when the smart shopping cart enters the trigger area, recommending marketing activities to the user based on the user portrait, further comprising:

In a case where the user portrait includes a price-sensitive tag, second marketing campaign information is recommended to the user; the second marketing campaign information is discount information; and the distance between the location of the commodity corresponding to the second marketing campaign information and the user is less than a second distance threshold.

7. A location-based precision marketing method according to claim 1, characterized in that in response to the location change of the smart shopping cart, when the smart shopping cart enters the trigger area, recommending marketing activities to the user based on the user portrait, further comprising:

Based on the user's historical purchase record, third marketing activity information is provided to the user; the product corresponding to the third marketing activity information is a product purchased by the user more than a predetermined number of times; the distance between the location of the product corresponding to the third marketing activity information and the user is less than a third distance threshold.

8. A location-based precision marketing device, characterized in that the location-based precision marketing device comprises:

A user portrait construction unit, the user portrait construction unit is used to form a feature tag based on the user's historical data and construct a user portrait according to the feature tag;

An activity area division unit, the activity area division unit is used to define a trigger area for a marketing activity based on the location of the commodity;

A marketing activity recommendation unit, the marketing activity recommendation unit is used to respond to the position change of the smart shopping cart and recommend a marketing activity to the user based on the user portrait when the smart shopping cart enters the trigger area.

9. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the location-based precision marketing method as described in any one of claims 1 to 7 is implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein when the processor executes the computer program, the location-based precision marketing method as described in any one of claims 1 to 7 is implemented.