CN118094003A - Activity recommendation method, device, electronic equipment and medium - Google Patents
Activity recommendation method, device, electronic equipment and medium Download PDFInfo
- Publication number
- CN118094003A CN118094003A CN202410223897.8A CN202410223897A CN118094003A CN 118094003 A CN118094003 A CN 118094003A CN 202410223897 A CN202410223897 A CN 202410223897A CN 118094003 A CN118094003 A CN 118094003A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- target client
- client
- customer
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 160
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000004458 analytical method Methods 0.000 claims abstract description 38
- 230000003993 interaction Effects 0.000 claims description 38
- 230000006399 behavior Effects 0.000 claims description 26
- 238000003860 storage Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 238000009877 rendering Methods 0.000 claims description 3
- 230000001172 regenerating effect Effects 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 230000015654 memory Effects 0.000 description 9
- 230000015572 biosynthetic process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004146 energy storage Methods 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 3
- 238000013508 migration Methods 0.000 description 3
- 230000005012 migration Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 235000021152 breakfast Nutrition 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The method, the device, the electronic equipment and the medium for recommending the activities can be applied to the technical field of Internet of things, the technical field of big data and the technical field of artificial intelligence. The method comprises the following steps: responding to the opening application program of a target client, and acquiring a target client portrait of the target client and target client geographic position information; acquiring a target client tag based on the target client representation; selecting a business circle based on the target client geographic position information circle, forming a business circle geofence, and acquiring store marketing information in the business circle geofence; based on the target client tag and the store marketing information, performing client preference analysis through a big data engine to generate activity recommendation information aiming at the target client; and based on the activity recommendation information, performing activity recommendation to the target client.
Description
Technical Field
The invention relates to the technical field of Internet of things, the technical field of big data and the technical field of artificial intelligence, in particular to an activity recommendation method, an activity recommendation device, electronic equipment and a medium.
Background
In the current business environment, service providers at the B-side (business side) typically need to actively open an offline promotional campaign to attract customers at the C-side (consumer side).
At present, although the traditional offline popularization methods such as ground pushing, advertisement putting, heterogeneous cooperation and the like can help the end B to improve the awareness degree and the exposure degree, high individuation and accurate marketing are difficult to realize, and the traditional popularization method is also often accompanied by high labor cost, advertisement cost and communication and attraction cost with clients, so that the cost is high, and the profitability of the end B is reduced.
On the other hand, on an online life service platform, customers are often disturbed by a large amount of marketing campaigns and advertising information. Existing online promotional approaches often lack personalized content that is highly relevant to the interests and needs of the customer, so the customer's impressions of these activities in the brain are often not deep or the customer's interests in these activities are limited. This situation results in the marketing campaign of many merchants not actually attracting and retaining customers, thereby making the marketing effort unable to obtain the desired return.
Disclosure of Invention
In view of the above-mentioned problems, according to a first aspect of the present invention, there is provided an activity recommendation method including: responding to the opening application program of a target client, and acquiring a target client portrait of the target client and target client geographic position information; acquiring a target client tag based on the target client representation; selecting a business circle based on the target client geographic position information circle, forming a business circle geofence, and acquiring store marketing information in the business circle geofence; based on the target client tag and the store marketing information, performing client preference analysis through a big data engine to generate activity recommendation information aiming at the target client; and based on the activity recommendation information, performing activity recommendation to the target client.
According to some exemplary embodiments, the generating the activity recommendation information for the target client by performing a client preference analysis through a big data engine based on the target client tag and the store marketing information specifically includes: integrating and analyzing data of the target client tag and the store marketing information by using a big data processing tool to acquire analysis input data; and generating activity recommendation information for the target client using a machine learning model based on the analysis input data.
According to some exemplary embodiments, the obtaining the target customer representation of the target customer specifically includes: acquiring client information of the target client, wherein the client information comprises personal information, business information, using product information and consumption information; performing feature engineering based on the client information to obtain target client portrait features, wherein the client portrait features are used for describing behaviors and preferences of the target client; and analyzing and modeling the target customer portraits by utilizing a data analysis model to generate target customer portraits of the target customers.
According to some exemplary embodiments, the method for obtaining the target client tag based on the target client portrait specifically includes: acquiring a client tag class predefined based on a business target; acquiring tag class key features from the target customer portrait; and classifying the tag class key features into the client tag class by utilizing a pre-trained tag distribution model to acquire the target client tag.
According to some exemplary embodiments, the method for obtaining the target client tag based on the target client portrait specifically includes: the method comprises the steps of obtaining interaction information of a target client, wherein the interaction information comprises time information, social media information and program embedded point information; acquiring target customer portrait information from the target customer portrait; and acquiring the target client tag by using a context-aware tag distribution model based on the interaction information and the target client portrait information.
According to some exemplary embodiments, the forming a business turn geofence based on the target client geographic location information turns a business turn, specifically includes: acquiring corresponding geographic data based on the geographic position information of the target client, wherein the geographic data comprises urban traffic data, population flow pattern data and a schedule of special events; determining an initial business turn geofence by utilizing a static business turn positioning algorithm according to the target client geographic position information and the corresponding geographic data; and updating corresponding geographic data in real time, and automatically adjusting a business circle range by utilizing a dynamic business circle selection algorithm based on the updated geographic data to form the business circle geofence.
According to some exemplary embodiments, the recommending the activity to the target client based on the activity recommendation information specifically includes: acquiring a store and an activity recommendation list based on the activity recommendation information; and dynamically rendering based on the store and the activity recommendation list to generate an activity display page, wherein the activity display page is used for recommending the activity to the target client.
According to some exemplary embodiments, the method further comprises: responding to the interaction between the target client and the activity display page to acquire interaction information; combining the interactive information with the client information to obtain updated information; and regenerating a target customer representation of the target customer using the updated information.
According to a second aspect of the present invention, there is provided an activity recommendation device, the device comprising: the target customer portrait acquisition module is used for: responding to the opening application program of a target client, and acquiring a target client portrait of the target client and target client geographic position information; the target client tag acquisition module is used for: acquiring a target client tag based on the target client representation; a business turn geofence forming module for: selecting a business circle based on the target client geographic position information circle, forming a business circle geofence, and acquiring store marketing information in the business circle geofence; the activity recommendation information generation module is used for: based on the target client tag and the store marketing information, performing client preference analysis through a big data engine to generate activity recommendation information aiming at the target client; and an activity recommendation module for: and recommending the activities to the target clients based on the activity recommendation information.
According to some example embodiments, the target customer representation acquisition module may include an information acquisition unit, a feature acquisition unit, and a modeling unit.
According to some exemplary embodiments, the information acquiring unit may be configured to acquire client information of the target client, including personal information, business information, usage product information, and consumption information.
According to some exemplary embodiments, the feature acquisition unit may be configured to perform feature engineering based on the client information to acquire a target client portrayal feature, where the client portrayal feature is used to describe behavior and preference of the target client.
According to some example embodiments, the modeling unit may be configured to analyze and model the target customer representation feature using a data analysis model to generate a target customer representation of the target customer.
According to some example embodiments, the target client tag acquisition module may include a first categorization module and a second categorization module.
According to some example embodiments, the first categorization module may include a customer tag category definition unit, a tag category key feature acquisition unit, and a first acquisition unit.
According to some exemplary embodiments, the customer label class definition unit may be configured to obtain a customer label class predefined based on a business objective.
According to some exemplary embodiments, the tag class key feature obtaining unit may be configured to obtain tag class key features from the target customer representation.
According to some example embodiments, the first obtaining unit may be configured to classify the tag class key feature into the client tag class using a pre-trained tag allocation model to obtain the target client tag.
According to some exemplary embodiments, the second categorizing module may include an interaction information obtaining unit, a target customer portrait information obtaining unit, and a second obtaining unit.
According to some exemplary embodiments, the interaction information obtaining unit may be configured to obtain interaction information of the target client, where the interaction information includes time information, social media information, and program embedded point information.
According to some exemplary embodiments, the target customer representation information acquisition unit may be configured to acquire target customer representation information from the target customer representation.
According to some example embodiments, the second obtaining unit may be configured to obtain the target client tag using a context-aware tag allocation model based on the interaction information and the target client representation information.
According to some example embodiments, the business turn geofence formation module includes a geographic data acquisition unit, an initial business turn geofence determination unit, and an automatic adjustment unit.
According to some example embodiments, the geographic data obtaining unit may be configured to obtain corresponding geographic data based on the target customer geographic location information, wherein the geographic data includes urban traffic data, population flow pattern data, and a schedule of special events.
According to some example embodiments, the initial business turn geofence determination unit may be configured to determine an initial business turn geofence using a static business turn positioning algorithm based on the target customer geographic location information and corresponding geographic data.
According to some exemplary embodiments, the automatic adjustment unit may be configured to update corresponding geographic data in real time, and automatically adjust a business turn range based on the updated geographic data by using a dynamic business turn selection algorithm, so as to form the business turn geofence.
According to some example embodiments, the activity recommendation information generation module may include an analysis input data acquisition unit and an activity recommendation information generation unit.
According to some exemplary embodiments, the analysis input data obtaining unit may be configured to integrate and data analyze the target client tag and the store marketing information using a big data processing tool to obtain analysis input data.
According to some example embodiments, the activity recommendation information generation unit may be configured to generate activity recommendation information for the target client using a machine learning model based on the analysis input data.
According to some example embodiments, the activity recommendation module may include a recommendation list acquisition unit and an activity recommendation unit.
According to some example embodiments, the recommendation list obtaining unit may be configured to obtain a store and an activity recommendation list based on the activity recommendation information.
According to some exemplary embodiments, the activity recommendation unit may be configured to dynamically render based on the store and an activity recommendation list, and generate an activity presentation page, where the activity presentation page is configured to make an activity recommendation to the target client.
According to some example embodiments, the activity recommendation device may further comprise a target customer representation optimization module.
According to some example embodiments, the target customer representation optimization module may include an interactive information acquisition unit, an update information acquisition unit, and an update unit.
According to some exemplary embodiments, the interaction information obtaining unit may be configured to obtain the interaction information in response to the interaction between the target client and the activity presentation page.
According to some exemplary embodiments, the update information obtaining unit may be configured to combine the interaction information with the client information to obtain update information.
According to some example embodiments, the updating unit may be configured to regenerate a target customer representation of the target customer using the update information.
According to a third aspect of the present invention, there is provided an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method as described above.
According to a fourth aspect of the present invention there is provided a computer readable storage medium having stored thereon executable instructions which when executed by a processor cause the processor to perform a method as described above.
According to a fifth aspect of the present invention there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.
One or more of the above embodiments have the following advantages or benefits: according to the activity recommendation method provided by the invention, a large amount of data such as target customer portrait, geographical position information, labels, store marketing information and customer preference analysis of customers are processed through the big data engine, so that the calculation and energy storage capacity of a computer can be fully utilized, the efficiency and speed of data processing can be improved, and the system can respond to the request of the customers in real time or near real time; by providing personalized campaign recommendations based on the customer's target customer portraits and store marketing information in the business turn geofence, the customer can more easily find locally nearby relevant category preference stores or business turn recommendations, thereby improving the user experience.
Drawings
The foregoing and other objects, features and advantages of the invention will be apparent from the following description of embodiments of the invention with reference to the accompanying drawings, in which:
fig. 1 schematically illustrates an application scenario diagram of an activity recommendation method, an apparatus, a device and a medium according to an embodiment of the invention.
Fig. 2 schematically shows a flow chart of an activity recommendation method according to an embodiment of the invention.
FIG. 3 schematically illustrates a flow chart of a method of capturing a target customer representation according to an embodiment of the invention.
Fig. 4 schematically shows a flow chart of a method of obtaining a target client tag according to an embodiment of the invention.
Fig. 5 schematically shows a flow chart of a method of obtaining a target client tag according to a further embodiment of the invention.
Fig. 6 schematically illustrates a flow chart of a method of forming a business turn geofence, in accordance with an embodiment of the present invention.
FIG. 7 schematically illustrates a flow chart of a method of customer preference analysis by a big data engine according to an embodiment of the invention.
FIG. 8 schematically illustrates a flow chart of a method of making an activity recommendation to a target client according to an embodiment of the invention.
FIG. 9 schematically illustrates a flow chart of a method of optimizing a target customer representation in real time according to an embodiment of the invention.
Fig. 10 schematically shows a block diagram of an activity recommendation device according to an embodiment of the present invention.
Fig. 11 schematically shows a block diagram of an electronic device adapted for an activity recommendation method according to an embodiment of the invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a convention should be interpreted in accordance with the meaning of one of skill in the art having generally understood the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
In the technical scheme of the invention, the acquisition, storage, application and the like of the related personal information of the user accord with the regulations of related laws and regulations, necessary security measures are taken, and the public order harmony is not violated.
First, technical terms described herein are explained and illustrated as follows.
Business geofencing is a geolocation technique for dividing a particular geographic area for location-related services and activity pushing by determining a set of geographic coordinate points to form a virtual geographic boundary to identify the area of business or the extent of the business. The business district geofence refers to the latitude and longitude range of the business district, and supports business personnel to visually select the regional range on the map through the map. Stores in the geofence range form a store list in the business district, and the preferential activities of the stores are purchased as preferential activity-based information of the business district.
Customer portraits are a description of the situation of a typical user drawn based on real target user data and may include basic data (e.g., gender, age, marital status, issuing entity, etc.), preference data (e.g., food consumption, traffic consumption, hotel consumption), quick payment preference behavior data, transaction data (e.g., commodity name, merchant name, order type, transaction amount, transaction time), usage product information (e.g., high-contribution customers, early warning customers, churned customers, other customers, etc.).
The geographic position is a quantitative depiction of the position, and the longitude and latitude values of each geographic object are specifically depicted by taking the whole earth surface as a coordinate system and taking the longitude and latitude as a measurement standard. The latitude is depicted by taking the equator as 0 degree latitude, which is equivalent to the abscissa axis, so that the north-south directions are respectively measured to the north-south poles of 90 degrees; meanwhile, the longitude value is that the longitude passing through the London Greenning astronomical table old site in England is taken as the 0-degree longitude, which is equivalent to the ordinate in the coordinate system. The longitude and latitude net composed of the longitude and latitude lines can easily determine the geographic position coordinates of each geographic object just like determining the points in the coordinate system.
Big data engines are computing and storage systems for processing and managing large-scale data that are intended to efficiently store, process, analyze, and provide access to large amounts of data. Big data engines typically include a variety of techniques and components to cope with ever-increasing amounts of data and diverse data types.
The B-side campaign includes the offered services of the off-line store and various types of preference information, including, for example, full consumption, group buying, electronic coupon campaigns, discount campaigns (e.g., 9-fold), cashback (e.g., full 100-fold 5-membered) campaigns, buy two-send, etc. preference information.
Buried points refer to the insertion of special codes or markers in a software application or website for recording user behavior and activity data. Such data may be used for a variety of purposes such as analyzing user behavior, performance optimization, user experience improvement, security monitoring, and the like. Buried points are often used to track user interactions with applications or websites to obtain valuable information about user behavior and usage.
With the continuous development and popularization of internet technology, the online life service platform establishes a bridge between the B end and the C end, provides opportunities for merchants to popularize self services and products, and simultaneously provides convenient shopping and consumption experience for consumers. However, in this rapidly evolving digital age, there are often several critical issues faced, two of which are as follows:
1. B-side service list and high cost of preferential active offline promotion: b-side merchants typically need to promote their services and products to attract more consumers. However, traditional offline popularization methods, such as ground pushing, advertisement delivery and heterogeneous collaboration, often involve high manpower and resource costs, especially in the service industry, facing a large number of potential customers, finding suitable target customers and performing accurate marketing becomes difficult and expensive;
2. Marketing campaign correlation of the online life service platform is not high: existing online lifestyle service platforms typically push a variety of marketing campaigns and coupons to customers. However, these activities tend to be voluminous and have limited relevance to the interests and needs of the customer, resulting in a customer's lack of or impression of interest in these activities. Such a promotional approach often fails to achieve good customer engagement, limiting the sales of merchants and the shopping experience of the customers.
Based on this, an embodiment of the present invention provides an activity recommendation method, which includes: responding to the opening application program of a target client, and acquiring a target client portrait of the target client and target client geographic position information; acquiring a target client tag based on the target client representation; selecting a business circle based on the target client geographic position information circle, forming a business circle geofence, and acquiring store marketing information in the business circle geofence; based on the target client tag and the store marketing information, performing client preference analysis through a big data engine to generate activity recommendation information aiming at the target client; and based on the activity recommendation information, performing activity recommendation to the target client. According to the activity recommendation method provided by the invention, a large amount of data such as target customer portrait, geographical position information, labels, store marketing information and customer preference analysis of customers are processed through the big data engine, so that the calculation and energy storage capacity of a computer can be fully utilized, the efficiency and speed of data processing can be improved, and the system can respond to the request of the customers in real time or near real time; by providing personalized campaign recommendations based on the customer's target customer portraits and store marketing information in the business turn geofence, the customer can more easily find locally nearby relevant category preference stores or business turn recommendations, thereby improving the user experience.
It should be noted that the activity recommendation method, device, equipment and medium determined by the invention can be used in the technical field of the internet of things, the technical field of big data and the technical field of artificial intelligence, can also be used in the financial field, and can also be used in various fields except the technical field of the internet of things, the technical field of big data and the technical field of artificial intelligence as well as the financial field. The application fields of the activity recommendation method, the device, the equipment and the medium provided by the embodiment of the invention are not limited.
In the technical scheme of the invention, the related user information (including but not limited to user personal information, user image information, user equipment information, such as position information and the like) and data (including but not limited to data for analysis, stored data, displayed data and the like) are information and data authorized by a user or fully authorized by all parties, and the processing of the related data such as collection, storage, use, processing, transmission, provision, disclosure, application and the like are all conducted according to the related laws and regulations and standards of related countries and regions, necessary security measures are adopted, no prejudice to the public welfare is provided, and corresponding operation inlets are provided for the user to select authorization or rejection.
Fig. 1 schematically illustrates an application scenario diagram of an activity recommendation method, an apparatus, a device and a medium according to an embodiment of the invention.
As shown in fig. 1, an application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication target client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox target clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that, the activity recommendation method provided by the embodiment of the present invention may be generally performed by the server 105. Accordingly, the activity recommendation device provided in the embodiment of the present invention may be generally disposed in the server 105. The activity recommendation method provided by the embodiment of the present invention may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the activity recommendation device provided by the embodiment of the present invention may also be provided in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
It should be understood that the number of devices and networks in fig. 1 is merely illustrative. There may be any number of devices and networks, as desired for implementation.
Fig. 2 schematically shows a flow chart of an activity recommendation method according to an embodiment of the invention.
As shown in fig. 2, the activity recommendation method 200 of this embodiment may include operations S210 to S250.
In operation S210, a target customer representation of the target customer and target customer geographic location information are acquired in response to the target customer opening application.
In an embodiment of the invention, the application may be a mobile application or a Web application of a bank or financial institution for accessing related services or content. The application may require the target client to authenticate to ensure that the client's personal information and data can be securely accessed and used.
In embodiments of the present invention, the application may use location services (e.g., GPS) or IP address information of the device to obtain geographic location information of the target client, which may be implemented by hardware or browser functionality of the device. In addition, the portrait of the target client can be generated or updated periodically according to the related data reserved by the target client in the system.
FIG. 3 schematically illustrates a flow chart of a method of capturing a target customer representation according to an embodiment of the invention.
As shown in fig. 3, the method for acquiring the target client image of this embodiment may include operations S310 to S330, and operations S310 to S330 may at least partially perform operation S210.
In operation S310, customer information of the target customer is acquired, including personal information, business information, usage product information, and consumption information.
In embodiments of the present invention, customer information reserved by a target customer may be collected to generate a corresponding customer representation, e.g., personal information: including customer name, gender, age, contact information (e.g., telephone number, email address), etc.; service information: including the customer's business type at a bank or financial institution, account information, transaction history, loan or credit card information, etc.; using product information: including products or services used by customers at banks or financial institutions, such as savings accounts, investment products, insurance, etc.; consumption information: including consumer consumption history, purchasing behavior, payment means, consumption preferences, and the like. Such information may be obtained from a number of sources, including customer account records, transaction history, online registration information, questionnaires, and the like. When acquiring the information, compliance with privacy regulations and customer data protection policies are ensured, and the privacy of customers is protected.
In operation S320, feature engineering is performed based on the client information, and a target client portrait feature is acquired, where the client portrait feature is used to describe behavior and preference of the target client.
In operation S330, the target customer representation features are analyzed and modeled using a data analysis model to generate a target customer representation for the target customer.
In embodiments of the present invention, suitable machine learning or statistical modeling techniques, such as clustering, classification, regression, etc., may be selected to generate customer representations based on customer characteristics. From the output of the model, a customer representation of the target customer may be generated to describe its behavior, preferences, categories, or other relevant information.
In embodiments of the present invention, the generated customer representation may be used to learn about the needs of the customer, provide personalized services and advice, and conduct accurate marketing for the target customer. For example, the target customer representation may include: the name, sex, age, occupation, job site, hobbies, shopping preferences, health status, social media liveness, dining preferences, consumption habits, and purchasing power level of the target customer.
Referring back to fig. 2, in operation S220, a target client tag is acquired based on the target client portrait.
Fig. 4 schematically shows a flow chart of a method of obtaining a target client tag according to an embodiment of the invention.
As shown in fig. 4, the method of acquiring the target client tag of this embodiment may include operations S410 to S430, and operations S410 to S430 may at least partially perform operation S220.
In operation S410, a client tag class predefined based on a business objective is acquired.
In embodiments of the present invention, categories of customer labels may be predefined based on different business objectives and requirements. For example, the customer label category may include the following aspects: consumption behavior: identifying consumer habits of the customer, such as high consumers, economical customers, regular shoppers, etc.; stage of life: identifying a customer's life stage, such as a student, job site person, retirement person, etc.; dining preference: the customer's dining preferences are identified, such as breakfast favoring coffee, selecting take-away in noon, etc.
In operation S420, tag class key features are obtained from the target customer representation.
In embodiments of the present invention, key features associated with predefined customer label categories, which are data points used to describe a customer's attributes, behaviors, or preferences, may be extracted from the customer image data. For example, if the customer label category includes meal preferences, then the characteristics associated with the meal may include a customer's order record, a meal status for a particular time period, and so on.
In operation S430, the tag class key features are categorized into the customer tag class using a pre-trained tag assignment model to obtain the target customer tag.
In embodiments of the present invention, an appropriate machine learning model or algorithm, such as a classification model, may be selected. The classification model may be trained using a training data set with known labels, which model learns how to map the customer's features to these label categories. For a new target customer, the model will assign it to the most relevant label class based on the characteristics of the customer.
In embodiments of the present invention, once a customer is assigned a tag category, the customer tag category may be associated with its personal information to obtain complete customer tag information. The customer's tag may help better understand their shopping interests in order to provide relevant product recommendations, coupons, personalized advertisements, and the like.
Fig. 5 schematically shows a flow chart of a method of obtaining a target client tag according to a further embodiment of the invention.
As shown in fig. 5, the method for acquiring the target client tag of this embodiment may include operations S510 to S530, and operations S510 to S530 may at least partially perform operation S220.
In operation S510, interaction information of the target client is acquired, where the interaction information includes time information, social media information, and program embedded point information.
In embodiments of the present invention, the time information may record a client's activity time stamp, such as a client's access time, transaction time, etc.; social media information includes the activities of the client on the social media platform, such as posting, commenting, praying, sharing, etc.; program embedded point information is information collected from embedded points of an application or website, such as behavior of a client in the application, clicking, browsing history, and the like. Such information may be obtained by way of applications, website analysis tools, social media platform APIs, and the like.
In operation S520, target customer portrait information is acquired from the target customer portrait.
In the embodiment of the invention, the basic information, behavior characteristics, preference and other information of the client can be obtained from the target client portrait generated before. This information is used to describe the basic properties and known behavior of the client.
In operation S530, the target client tag is acquired using a context-aware tag distribution model based on the interaction information and the target client portrait information.
In the embodiment of the invention, the context-aware label distribution model can consider multidimensional information such as interaction behavior, time information, social media activities and the like of the client so as to more accurately distribute labels to the client. Specifically, the tag assignment model may identify the current interests and needs of the customer based on the customer's interaction behavior and time information. For example, if a customer purchases an outdoor item of equipment at a particular time and shares related content on social media, the model may mark the customer as an "outdoor fan".
Operations S510-S530 provide a better solution for obtaining target customer labels, and context-aware label generation may help banks or financial institutions better understand the actual needs and context of customers and provide more targeted services, thereby improving customer satisfaction and loyalty.
Referring back to FIG. 2, in operation S230, a business turn geofence is formed based on the target customer geographic location information turn, and store marketing information in the business turn geofence is acquired
Fig. 6 schematically illustrates a flow chart of a method of forming a business turn geofence, in accordance with an embodiment of the present invention.
As shown in fig. 6, the method of forming a business turn geofence of this embodiment may include operations S610 to S630, and operations S610 to S630 may at least partially perform operation S230.
In operation S610, corresponding geographic data is acquired based on the target customer geographic location information, wherein the geographic data includes urban traffic data, population flow pattern data, and a schedule of special events.
In an embodiment of the present invention, urban traffic data includes traffic flow, road conditions, public transportation routes, and vehicle operation data for analyzing urban traffic conditions; population migration pattern data comprises population migration, population density, population distribution and other information, and is used for knowing the population migration pattern and distribution in cities; schedules of special events, including local festivals, sporting events, cultural activities, etc., in order to take into account the impact of these events on business circles. Such data may come from a number of sources, such as government authorities, geographic information systems, social media, mobile applications, and the like.
In operation S620, an initial business turn geofence is determined using a static business turn positioning algorithm based on the target customer geographic location information and corresponding geographic data.
In embodiments of the present invention, an initial business turn scope may be defined based on target customer geographic location information and corresponding geographic data, which may be a circle, polygon, or other geometric shape, as desired.
In operation S630, corresponding geographic data is updated in real time, and the business turn scope is automatically adjusted by using a dynamic business turn selection algorithm based on the updated geographic data, so as to form the business turn geofence.
In embodiments of the present invention, updated data may be used to analyze the impact of passenger traffic, population flow, and special events on business turn. Based on the analysis results, the dynamic business turn round selection algorithm automatically adjusts the geofence range and boundaries of the business turn to ensure that the business turn is consistent with the traffic pattern and event changes.
Referring back to fig. 2, in operation S240, based on the target client tag and the store marketing information, client preference analysis is performed through a big data engine, and activity recommendation information for the target client is generated.
FIG. 7 schematically illustrates a flow chart of a method of customer preference analysis by a big data engine according to an embodiment of the invention.
As shown in fig. 7, the method of performing the customer preference analysis by the big data engine of this embodiment may include operations S710 to S720, and operations S710 to S720 may at least partially perform operation S240.
In operation S710, the target customer tag and the store marketing information are integrated and data analyzed using a big data processing tool to obtain analysis input data.
In the embodiment of the invention, the data from different sources can be unified into one data platform by using a big data processing tool such as Hadoop or Spark, and meanwhile, the data preprocessing can be performed to ensure that the data formats are unified so as to perform effective analysis.
In operation S720, activity recommendation information for the target client is generated using a machine learning model based on the analysis input data.
In embodiments of the present invention, a machine learning model suitable for the task, such as a decision tree, random forest, neural network, or collaborative filtering, may be selected to generate actual, personalized activity recommendations. For example, a certain customer's day: man, occupation is IT research and development engineer, age 35 years, job site is XX software garden, breakfast about 9, coffee about 10 am, take-out about 13 am, dinner about 20 like dining in restaurant about 5km, etc., then the system can provide correct activity information for clients at correct time by knowing client position and the above-mentioned behavior, for example, push take-out coupons for clients regularly, push coffee coupons about 5km for clients, etc. Other relevant preferential activities of the business district can be pushed to the clients through the set business district geofence, so that the clients are more likely to consume.
Referring back to fig. 2, in operation S250, an activity recommendation is made to the target client based on the activity recommendation information.
FIG. 8 schematically illustrates a flow chart of a method of making an activity recommendation to a target client according to an embodiment of the invention.
As shown in fig. 8, the method for recommending activities to a target client according to the embodiment may include operations S810 to S820, and operations S810 to S820 may at least partially perform operation S250.
In operation S810, a store and an activity recommendation list are acquired based on the activity recommendation information.
In embodiments of the present invention, stores participating in an activity may be identified, including selecting stores that offer a particular promotion or discount, and creating an activity list for each associated store, each list including recommended activities that the store is or will be conducting. Wherein it should be ensured that the activity list matches the preferences and historical behavior of the target customer and that personalized elements are taken into account, such as adjusting the activity list according to the past purchase history or browsing behavior of the customer.
In operation S820, an activity display page is generated based on the store and the activity recommendation list, where the activity display page is used for performing activity recommendation to the target client.
In embodiments of the present invention, an attractive and easily navigable active presentation page layout may be designed, which may include elements such as images, text descriptions, price information, and the like.
Further, page content is dynamically generated based on store and campaign recommendation lists and client devices and preferences to adjust presentation formats. Wherein, the displayed activities can be personalized adjusted according to the specific preference and the historical behavior of the target client, and the user experience can be enhanced by using the user interface element. For example, user feedback options, such as "like", "not interested" buttons, are provided to collect user preference data.
In addition, in order to help banks to better understand the behaviors and interests of clients and improve the accuracy and instantaneity of client portraits, the embodiment of the invention also provides a method for optimizing target client portraits in real time.
FIG. 9 schematically illustrates a flow chart of a method of optimizing a target customer representation in real time according to an embodiment of the invention.
As shown in fig. 9, the method of optimizing a target customer portrait in real time of this embodiment may include operations S910 to S930.
In operation S910, in response to the target client interacting with the active display page, interaction information is obtained.
In embodiments of the present invention, the behavior of a customer on an active presentation page, such as click, scroll, dwell time, etc., may be tracked and converted into quantifiable data for analysis.
In operation S920, the interaction information and the client information are combined to obtain updated information.
In operation S930, the target customer representation of the target customer is regenerated using the update information.
According to the activity recommendation method provided by the invention, a large amount of data such as target customer portrait, geographical position information, labels, store marketing information and customer preference analysis of customers are processed through the big data engine, so that the calculation and the energy storage capacity of a computer can be fully utilized, the efficiency and the speed of data processing can be improved, and the system can respond to the request of the customers under the real-time or near real-time condition; by providing personalized campaign recommendations based on the customer's target customer portraits and store marketing information in the business turn geofence, the customer can more easily find locally nearby relevant category preference stores or business turn recommendations, thereby improving the user experience. Specifically, the following beneficial effects are brought:
1. Real-time data processing and decision support: by using a big data engine and real-time data analysis, the methods enable enterprises to quickly respond to market changes and generate activity recommendation and decision support information in real time, so that customer experience and market competitiveness are improved;
2. Data driven decision: by utilizing big data and machine learning technology, the enterprise is helped to better understand clients, business circles and markets, and through data-driven decision making, the enterprise can more accurately formulate marketing strategies and activity planning, so that unnecessary cost and risk are reduced;
3. And (3) business circle positioning optimization: the dynamic business turn selection algorithm helps enterprises to adjust business turn ranges in real time and reflect changes of passenger flow and special events, so that accuracy of business turn positioning is improved, and accuracy of customer service is ensured.
4. Customer portrayal and label generation: the customer portrait and the label are generated by using the data of the customer, so that the enterprise is helped to better know the characteristics and the preferences of the customer, and a foundation is provided for accurate marketing, customer maintenance and customer analysis;
5. Personalized services and precision marketing: through analysis based on client labels, behaviors and geographic positions, the personalized touch clients can be provided according to store distances, client consumption habit preferences, order information and the like, and thousands of people and thousands of sides differentiated services are provided. For example, aiming at a store which has coffee preferential activities within 5km recently pushed by a client who drinks more than two times per week, the client is guided to consume, thereby improving the satisfaction of the client and increasing the transaction opportunity;
6. Optimizing resource utilization: through accurate business circle positioning and customer portrayal, the enterprise is helped to better allocate resources, the resource waste is reduced, and the benefit is improved;
7. Labor is saved: the customer portrait and the customer behavior are analyzed by combining positioning and big data, so that automatic digital operation of preferential activities is realized, the operation cost of marketing activities is reduced, and manpower is saved to a certain extent.
Based on the activity recommendation method, the invention further provides an activity recommendation device. The device will be described in detail below in connection with fig. 10.
Fig. 10 schematically shows a block diagram of an activity recommendation device according to an embodiment of the present invention.
As shown in fig. 10, the activity recommendation device 1000 according to this embodiment includes a target customer portrait acquisition module 1010, a target customer label acquisition module 1020, a business turn geofence formation module 1030, an activity recommendation information generation module 1040, and an activity recommendation module 1050.
The target client representation acquisition module 1010 may be configured to acquire target client representations of the target clients and target client geographic location information in response to the target clients opening an application. In an embodiment, the target client portrait acquisition module 1010 may be configured to perform the operation S210 described above, which is not described herein.
The target client tag acquisition module 1020 may be configured to acquire a target client tag based on the target client representation. In an embodiment, the target client tag obtaining module 1020 may be configured to perform the operation S220 described above, which is not described herein.
The business turn geofence formation module 1030 may be configured to turn a business turn based on the target customer geographic location information, form a business turn geofence, and obtain store marketing information in the business turn geofence. In an embodiment, the business turn geofence forming module 1030 may be configured to perform operation S230 described above, which is not described herein.
The activity recommendation information generation module 1040 may be configured to generate activity recommendation information for the target client by performing client preference analysis through a big data engine based on the target client tag and the store marketing information. In an embodiment, the activity recommendation information generation module 1040 may be configured to perform the operation S240 described above, which is not described herein.
The activity recommendation module 1050 may be configured to make activity recommendations to the target client based on the activity recommendation information. In an embodiment, the activity recommendation module 1050 may be configured to perform the operation S250 described above, which is not described herein.
According to an embodiment of the present invention, the target customer representation acquisition module 1010 may include an information acquisition unit, a feature acquisition unit, and a modeling unit.
The information acquisition unit may be configured to acquire client information of the target client, including personal information, service information, usage product information, and consumption information. In an embodiment, the information obtaining unit may be configured to perform the operation S310 described above, which is not described herein.
The feature acquisition unit may be configured to perform feature engineering based on the client information to acquire a target client portrait feature, where the client portrait feature is used to describe behavior and preference of the target client. In an embodiment, the feature obtaining unit may be configured to perform the operation S320 described above, which is not described herein.
The modeling unit may be configured to analyze and model the target customer representation feature using a data analysis model to generate a target customer representation of the target customer. In an embodiment, the modeling unit may be configured to perform the operation S330 described above, which is not described herein.
According to an embodiment of the present invention, the target client tag obtaining module 1020 may include a first categorizing module and a second categorizing module.
According to an embodiment of the present invention, the first classification module may include a customer tag category definition unit, a tag category key feature acquisition unit, and a first acquisition unit.
The client tag class definition unit may be configured to obtain a client tag class predefined based on a business objective. In an embodiment, the client tag class definition unit may be configured to perform the operation S410 described above, which is not described herein.
The tag class key feature obtaining unit may be configured to obtain a tag class key feature from the target customer portrait. In an embodiment, the tag class key feature obtaining unit may be configured to perform the operation S420 described above, which is not described herein.
The first obtaining unit may be configured to classify the tag class key feature into the client tag class by using a pre-trained tag allocation model, so as to obtain the target client tag. In an embodiment, the first obtaining unit may be configured to perform the operation S430 described above, which is not described herein.
According to an embodiment of the present invention, the second classification module may include an interaction information obtaining unit, a target customer portrait information obtaining unit, and a second obtaining unit.
The interaction information obtaining unit may be configured to obtain interaction information of the target client, where the interaction information includes time information, social media information, and program embedded point information. In an embodiment, the interaction information obtaining unit may be configured to perform the operation S510 described above, which is not described herein.
The target customer representation information acquisition unit may be configured to acquire target customer representation information from the target customer representation. In an embodiment, the target customer portrait information acquisition unit may be configured to perform operation S520 described above, which is not described herein.
The second obtaining unit may be configured to obtain the target client tag using a context-aware tag distribution model based on the interaction information and the target client portrait information. In an embodiment, the second obtaining unit may be configured to perform the operation S530 described above, which is not described herein.
According to an embodiment of the present invention, the business turn geofence formation module 1030 includes a geographic data acquisition unit, an initial business turn geofence determination unit, and an automatic adjustment unit.
The geographic data acquisition unit may be configured to acquire corresponding geographic data based on the target client geographic location information, where the geographic data includes urban traffic data, population flow pattern data, and a schedule of special events. In an embodiment, the geographic data obtaining unit may be configured to perform the operation S610 described above, which is not described herein.
The initial business turn geofence determination unit may be configured to determine an initial business turn geofence using a static business turn positioning algorithm based on the target customer geographic location information and corresponding geographic data. In an embodiment, the initial business turn geofence determining unit may be configured to perform operation S620 described above, which is not described herein.
The automatic adjustment unit can be used for updating corresponding geographic data in real time, and automatically adjusting the business district range by utilizing a dynamic business district selection algorithm based on the updated geographic data to form the business district geofence. In an embodiment, the automatic adjustment unit may be used to perform the operation S630 described above, which is not described herein.
According to an embodiment of the present invention, the activity recommendation information generation module 1040 may include an analysis input data acquisition unit and an activity recommendation information generation unit.
The analysis input data acquisition unit may be configured to integrate and data analyze the target client tag and the store marketing information using a big data processing tool to acquire analysis input data. In an embodiment, the analysis input data acquisition unit may be configured to perform the operation S710 described above, which is not described herein.
The activity recommendation information generation unit may be configured to generate activity recommendation information for the target client using a machine learning model based on the analysis input data. In an embodiment, the activity recommendation information generating unit may be configured to perform the operation S720 described above, which is not described herein.
According to an embodiment of the present invention, the activity recommendation module 1050 may include a recommendation list obtaining unit and an activity recommendation unit.
The recommendation list obtaining unit may be configured to obtain a store and an activity recommendation list based on the activity recommendation information. In an embodiment, the recommendation list obtaining unit may be configured to perform the operation S810 described above, which is not described herein.
The activity recommendation unit can be used for dynamically rendering based on the store and an activity recommendation list to generate an activity display page, wherein the activity display page is used for recommending the activity to the target client. In an embodiment, the activity recommendation unit may be configured to perform the operation S820 described above, which is not described herein.
According to an embodiment of the present invention, the activity recommendation device 1000 may further include a target customer portrait optimization module.
According to the embodiment of the invention, the target customer portrait optimization module can comprise an interactive information acquisition unit, an update information acquisition unit and an update unit.
The interaction information obtaining unit may be configured to obtain interaction information in response to interaction between the target client and the activity display page. In an embodiment, the interaction information obtaining unit may be configured to perform the operation S910 described above, which is not described herein.
The update information obtaining unit may be configured to combine the interaction information with the client information to obtain update information. In an embodiment, the update information obtaining unit may be configured to perform the operation S920 described above, which is not described herein.
The updating unit may be adapted to reproduce the target customer representation of the target customer using the updating information. In an embodiment, the updating unit may be configured to perform the operation S930 described above, which is not described herein.
Any of the target customer representation acquisition module 1010, target customer tag acquisition module 1020, business turn geofence formation module 1030, activity recommendation information generation module 1040, and activity recommendation module 1050 may be combined in one module or any of the modules may be split into multiple modules, according to embodiments of the present invention. Or at least some of the functionality of one or more of the modules may be combined with, and implemented in, at least some of the functionality of other modules. According to embodiments of the present disclosure, at least one of the target customer representation acquisition module 1010, the target customer label acquisition module 1020, the business turn geofence formation module 1030, the activity recommendation information generation module 1040, and the activity recommendation module 1050 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or in hardware or firmware in any other reasonable manner of integrating or packaging circuitry, or in any one of, or in any suitable combination of, software, hardware, and firmware. Or at least one of the target customer representation acquisition module 1010, the target customer label acquisition module 1020, the business turn geofence formation module 1030, the activity recommendation information generation module 1040, and the activity recommendation module 1050 may be implemented at least in part as computer program modules that, when executed, perform the corresponding functions.
Fig. 11 schematically shows a block diagram of an electronic device adapted for an activity recommendation method according to an embodiment of the invention.
As shown in fig. 11, an electronic device 1100 according to an embodiment of the present invention includes a processor 1101 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1102 or a program loaded from a storage section 1108 into a Random Access Memory (RAM) 1103. The processor 1101 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 1101 may also include on-board memory for caching purposes. The processor 1101 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flow according to an embodiment of the invention.
In the RAM 1103, various programs and data necessary for the operation of the electronic apparatus 11 00 are stored. The processor 1101, ROM 1102, and RAM 1103 are connected to each other by a bus 1104. The processor 1101 performs various operations of the method flow according to the embodiment of the present invention by executing programs in the ROM 1102 and/or the RAM 1103. Note that the program may be stored in one or more memories other than the ROM 1102 and the RAM 1103. The processor 1101 may also perform various operations of the method flow according to an embodiment of the present invention by executing programs stored in the one or more memories.
According to an embodiment of the invention, the electronic device 1100 may also include an input/output (I/O) interface 1105, the input/output (I/O) interface 1105 also being connected to the bus 1104. The electronic device 1100 may also include one or more of the following components connected to the I/O interface 1105: an input section 1106 including a keyboard, a mouse, and the like; an output portion 1107 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 1108 including a hard disk or the like; and a communication section 1109 including a network interface card such as a LAN card, a modem, and the like. The communication section 1109 performs communication processing via a network such as the internet. The drive 1110 is also connected to the I/O interface 1105 as needed. Removable media 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is installed as needed in drive 1110, so that a computer program read therefrom is installed as needed in storage section 1108.
The present invention also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present invention.
According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the invention, the computer-readable storage medium may include ROM 1102 and/or RAM 1103 described above and/or one or more memories other than ROM 1102 and RAM 1103.
Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the method shown in the flowcharts. The program code means for causing a computer system to carry out the methods provided by embodiments of the present invention when the computer program product is run on the computer system.
The above-described functions defined in the system/apparatus of the embodiment of the present invention are performed when the computer program is executed by the processor 1101. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the invention.
In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program can also be transmitted, distributed over a network medium in the form of signals, downloaded and installed via the communication portion 1109, and/or installed from the removable media 1111. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program can be downloaded and installed from a network via the communication portion 1109, and/or installed from the removable media 1111. The above-described functions defined in the system of the embodiment of the present invention are performed when the computer program is executed by the processor 1101. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the invention.
According to embodiments of the present invention, program code for carrying out computer programs provided by embodiments of the present invention may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or in assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The embodiments of the present invention are described above. These examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the invention, and such alternatives and modifications are intended to fall within the scope of the invention.
Claims (12)
1. A method of campaign recommendation, the method comprising:
responding to the opening application program of a target client, and acquiring a target client portrait of the target client and target client geographic position information;
acquiring a target client tag based on the target client representation;
selecting a business circle based on the target client geographic position information circle, forming a business circle geofence, and acquiring store marketing information in the business circle geofence;
Based on the target client tag and the store marketing information, performing client preference analysis through a big data engine to generate activity recommendation information aiming at the target client; and
And recommending the activities to the target clients based on the activity recommendation information.
2. The method according to claim 1, wherein the generating the activity recommendation information for the target customer by performing customer preference analysis through a big data engine based on the target customer tag and the store marketing information specifically comprises:
integrating and analyzing data of the target client tag and the store marketing information by using a big data processing tool to acquire analysis input data; and
Based on the analysis input data, activity recommendation information for the target customer is generated using a machine learning model.
3. The method according to claim 1, wherein said obtaining a target customer representation of said target customer, in particular comprises:
acquiring client information of the target client, wherein the client information comprises personal information, business information, using product information and consumption information;
performing feature engineering based on the client information to obtain target client portrait features, wherein the client portrait features are used for describing behaviors and preferences of the target client; and
And analyzing and modeling the target customer portrait features by using a data analysis model to generate the target customer portrait of the target customer.
4. A method according to claim 3, wherein said obtaining a target client tag based on said target client representation comprises:
acquiring a client tag class predefined based on a business target;
Acquiring tag class key features from the target customer portrait; and
And classifying the key characteristics of the label category into the client label category by utilizing a pre-trained label distribution model so as to acquire the target client label.
5. A method according to claim 3, wherein said obtaining a target client tag based on said target client representation comprises:
the method comprises the steps of obtaining interaction information of a target client, wherein the interaction information comprises time information, social media information and program embedded point information;
acquiring target customer portrait information from the target customer portrait; and
And acquiring the target client label by using a context-aware label distribution model based on the interaction information and the target client portrait information.
6. The method according to any one of claims 3-5, wherein the forming a business turn geofence based on the target customer geographic location information turn business turn comprises:
Acquiring corresponding geographic data based on the geographic position information of the target client, wherein the geographic data comprises urban traffic data, population flow pattern data and a schedule of special events;
Determining an initial business turn geofence by utilizing a static business turn positioning algorithm according to the target client geographic position information and the corresponding geographic data; and
And updating corresponding geographic data in real time, and automatically adjusting the business district range by utilizing a dynamic business district sorting algorithm based on the updated geographic data to form the business district geofence.
7. The method according to claim 6, wherein said recommending activities to said target client based on said activity recommendation information, comprises:
acquiring a store and an activity recommendation list based on the activity recommendation information; and
And dynamically rendering based on the store and the activity recommendation list to generate an activity display page, wherein the activity display page is used for recommending the activity to the target client.
8. The method of claim 7, wherein the method further comprises:
responding to the interaction between the target client and the activity display page to acquire interaction information;
Combining the interactive information with the client information to obtain updated information; and
And regenerating the target customer portrait of the target customer by using the updated information.
9. An activity recommendation device, the device comprising:
The target customer portrait acquisition module is used for: responding to the opening application program of a target client, and acquiring a target client portrait of the target client and target client geographic position information;
The target client tag acquisition module is used for: acquiring a target client tag based on the target client representation;
a business turn geofence forming module for: selecting a business circle based on the target client geographic position information circle, forming a business circle geofence, and acquiring store marketing information in the business circle geofence;
The activity recommendation information generation module is used for: based on the target client tag and the store marketing information, performing client preference analysis through a big data engine to generate activity recommendation information aiming at the target client; and
An activity recommendation module for: and recommending the activities to the target clients based on the activity recommendation information.
10. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
Wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-8.
11. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-8.
12. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410223897.8A CN118094003A (en) | 2024-02-28 | 2024-02-28 | Activity recommendation method, device, electronic equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410223897.8A CN118094003A (en) | 2024-02-28 | 2024-02-28 | Activity recommendation method, device, electronic equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118094003A true CN118094003A (en) | 2024-05-28 |
Family
ID=91159574
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410223897.8A Pending CN118094003A (en) | 2024-02-28 | 2024-02-28 | Activity recommendation method, device, electronic equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118094003A (en) |
-
2024
- 2024-02-28 CN CN202410223897.8A patent/CN118094003A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tong et al. | Personalized mobile marketing strategies | |
Andrews et al. | Mobile ad effectiveness: Hyper-contextual targeting with crowdedness | |
US9710821B2 (en) | Systems and methods for mobile and online payment systems for purchases related to mobile and online promotions or offers provided using impressions tracking and analysis, location information, 2D and 3D mapping, mobile mapping, social media, and user behavior and | |
Pura | Linking perceived value and loyalty in location‐based mobile services | |
Mogoş | Digital Marketing for Identifying Customers' Preferences--A Solution for SMEs in Obtaining Competitive Advantages. | |
US20130073336A1 (en) | System and method for using global location information, 2d and 3d mapping, social media, and user behavior and information for a consumer feedback social media analytics platform for providing analytic measfurements data of online consumer feedback for global brand products or services of past, present, or future customers, users or target markets | |
US20120284118A1 (en) | Using collective data for targeting of advertisements | |
US20120101896A1 (en) | Online promotional tool | |
US20130046619A1 (en) | System and method for targeted advertising | |
US20130204823A1 (en) | Tools and methods for determining relationship values | |
US20210035128A1 (en) | System for predicting optimal operating hours for merchants | |
Smith | Metrics, locations, and lift: Mobile location analytics and the production of second-order geodemographics | |
Saini et al. | Geo-marketing: A new tool for marketers | |
Bovsh et al. | Digital marketing of hotel business entities | |
US20210397602A1 (en) | Systems and methods for analyzing electronic data to determine faults in a transit system | |
CN118094003A (en) | Activity recommendation method, device, electronic equipment and medium | |
Panian | A new dimension of business intelligence: location-based intelligence | |
Danurdara et al. | DIGITAL MARKETING STRATEGY TO INCREASE BRAND AWARENESS IN INDUSTRY | |
Shekhar et al. | The impact of Location-based Marketing strategies on retail sectors in Al Batinah region during COVID 19 Pandemic | |
US11934973B2 (en) | Methods and systems for determining alternative plans | |
Molitor et al. | The Interplay of Retargeting and Location Revisits in Location-Based Advertising | |
US20240202758A1 (en) | Systems and methods for predictive pricing | |
Panagiotopoulou | Tourism marketing the role of the internet. Tourism destination: Greece | |
Murad | Using customers data for defining retail market size: a GIS approach | |
Bhowmik et al. | Prospects and scope of digital marketing in indian industry: A review |
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 |