Method and apparatus for determining potential users

Abstract

Embodiments of the present application provide a method and device for determining potential users, comprising: selecting first potential users according to first behavior data of a plurality of users in a first time period; the first behavior data comprises browsing behavior data in an online promotion process and / or browsing feedback data in an offline promotion process; selecting second potential users from the first potential users according to second behavior data of the first potential users in a second time period; the second behavior data comprises purchase intention behavior data in the online promotion process and / or demand feedback data in the offline promotion process; determining target users from the second potential users according to third behavior data of the second potential users in a third time period; the third behavior data comprises purchase behavior data in the online promotion process and / or purchase feedback data in the offline promotion process. Embodiments of the present application can not only improve the purchase experience of users, but also improve the user conversion rate.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of big data processing, and in particular to a method and device for determining potential users. BACKGROUND

[0002] At present, the cost of many enterprises in the customer acquisition link is high, and how to reduce the customer acquisition cost and better improve the customer acquisition quantity is the key problem that many enterprises are concerned about.

[0003] Among them, a potential user often experiences three stages of attention, consideration and decision before becoming a real customer. When an enterprise promotes a product to a general individual user, due to a large number of users and a lack of corresponding data of user marketing records and marketing feedback, the marketing process perceived by a single user is discontinuous, which may cause problems such as resource waste due to over-marketing of users in the initial stage and passive waiting for user decision without effective marketing activities in the subsequent stage. For example, in the product promotion stage, a user may have received multiple copies of brochures in different places, but when the user needs some consulting demand, unless the user actively inquires, the enterprise is difficult to know which user needs consulting services, which eventually leads to a low user conversion rate. SUMMARY

[0004] Embodiments of the present application provide a method and device for determining potential users, which can effectively improve customer acquisition efficiency and reduce customer acquisition cost.

[0005] In a first aspect, embodiments of the present application provide a method for determining potential users, comprising:

[0006] obtaining first behavior data of a plurality of users in a first time period, and selecting a first potential user from the plurality of users according to the first behavior data; the first behavior data includes browsing behavior data in an online promotion process and / or browsing feedback data in an offline promotion process of a user;

[0007] obtaining second behavior data of the first potential user in a second time period, and selecting a second potential user from the first potential user according to the second behavior data; the second behavior data includes purchase intention behavior data in an online promotion process and / or demand feedback data in an offline promotion process of a user;

[0008] obtaining third behavior data of the second potential user in a third time period, and determining a target user from the second potential user according to the third behavior data; the third behavior data includes purchase behavior data in an online promotion process and / or purchase feedback data in an offline promotion process of a user.

[0009] In an implementation, the selecting the first potential user from the plurality of users according to the first behavior data comprises:

[0010] determining a first purchase probability value of each user in the plurality of users according to the browsing behavior data and / or the browsing feedback data, wherein the browsing behavior data comprises online browsing times and browsing time length, and the browsing feedback data comprises offline communication time length;

[0011] determining a user in the plurality of users as the first potential user if the first purchase probability value of the user is greater than or equal to a first preset threshold value.

[0012] In an implementation, the method further comprises:

[0013] determining a marketing cost of each user in the plurality of users according to the browsing behavior data and / or the browsing feedback data;

[0014] determining a user in the plurality of users as a sleeping user if the first purchase probability value of the user is less than the first preset threshold value and the marketing cost of the user is greater than a first preset cost threshold value, and canceling online promotion and / or offline promotion services provided to the sleeping user within a preset time length.

[0015] In an implementation, the selecting the second potential user from the first potential users according to the second behavior data comprises:

[0016] determining a second purchase probability value of the first potential user according to the purchase intention behavior data and / or the demand feedback data, wherein the purchase intention behavior data comprises times of searching for a target product, times of browsing a target product detail page, times of collecting a target product, and times of adding a target product to a shopping cart, and the demand feedback data comprises times of offline demand feedback and times of offline inquiry;

[0017] determining a user in the first potential users as the second potential user if the second purchase probability value of the user is greater than or equal to a second preset threshold value.

[0018] In an implementation, the method further comprises:

[0019] determining a marketing cost of the first potential user according to the purchase intention behavior data and / or the demand feedback data;

[0020] determining a user in the first potential users as a sleeping user if the second purchase probability value of the user is less than the second preset threshold value and the marketing cost of the user is greater than a second preset cost threshold value, and canceling online promotion and / or offline promotion services provided to the sleeping user within a preset time length.

[0021] In one feasible implementation, determining the target user among the second potential users based on the third behavioral data includes:

[0022] Based on the purchase behavior data and / or the purchase feedback data, identify users among the second potential users who have a purchase failure record;

[0023] Users with a history of failed purchases among the second group of potential users are identified as the target users.

[0024] In one feasible implementation, it further includes:

[0025] Based on the purchase behavior data and / or the purchase feedback data, determine the marketing cost for the second potential user;

[0026] Users among the second potential users who have not made a purchase and whose marketing costs exceed a third preset cost threshold are identified as dormant users, and online and / or offline promotional services provided to the dormant users are cancelled within a preset time period.

[0027] Secondly, embodiments of this application provide a device for determining potential users, the device comprising:

[0028] The first filtering module is used to acquire first behavior data of multiple users within a first time period, and select a first potential user from the multiple users based on the first behavior data; the first behavior data includes browsing behavior data of users during online promotion and / or browsing feedback data during offline promotion.

[0029] The second filtering module is used to obtain the second behavioral data of the first potential user within a second time period, and select the second potential user from the first potential user based on the second behavioral data; the second behavioral data includes the user's purchase intention behavior data during the online promotion process and / or the demand feedback data during the offline promotion process;

[0030] The third filtering module is used to obtain the third behavioral data of the second potential user within a third time period, and to determine the target user among the second potential users based on the third behavioral data; the third behavioral data includes the user's purchase behavior data during the online promotion process and / or purchase feedback data during the offline promotion process.

[0031] Thirdly, embodiments of this application provide an electronic device, including: at least one processor and a memory;

[0032] The memory stores computer-executed instructions;

[0033] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the potential user determination method provided in the first aspect.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, and the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the potential user determination method provided in the first aspect is implemented.

[0035] The potential user determination method and device provided in the embodiments of the present application simulate a process model of converting potential users into actual customers by integrating online and / or offline user behavior and feedback data, perform layer-by-layer screening on multiple users, determine users with high purchase intention, and perform precise marketing activities on these users, so that the purchase experience of users can be improved, and the customer conversion rate can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application or the prior art. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0037] Figure 1 A flowchart of a potential user determination method provided in an embodiment of the present application;

[0038] Figure 2 A model diagram of a potential user determination method provided in an embodiment of the present application;

[0039] Figure 3 Another flowchart of a potential user determination method provided in an embodiment of the present application;

[0040] Figure 4 A program module diagram of a potential user determination device provided in an embodiment of the present application;

[0041] Figure 5 A hardware structure diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application. In addition, although the disclosure is introduced according to one or more exemplary examples, it should be understood that each aspect of the disclosure can also constitute a complete embodiment.

[0043] It should be noted that the brief description of the terms in the present application is only for the convenience of understanding the subsequently described embodiments, and is not intended to limit the embodiments of the present application. Unless otherwise specified, these terms should be understood according to their ordinary and general meanings.

[0044] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit the specific order or sequence, unless otherwise specified. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, for example, those orders other than given in the embodiment illustration or description of the present application can be implemented.

[0045] In addition, the terms "include" and "have" and any variations thereof are intended to cover but not exclusive inclusion, for example, a product or device including a series of components does not have to be limited to the clearly listed components, but can include other components not clearly listed or inherent to the product or device.

[0046] The term "module" used in the present application refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic or combination of hardware or / and software code capable of performing functions related to the element.

[0047] Currently, when promoting business, enterprises will push product information to users who meet the relevant conditions in the relevant application program (Application, referred to as App) according to the account information of the existing customers, or indiscriminately push in the outlets and some places with large flow.

[0048] In the prior art, for some customers who have already intended to purchase the relevant product and have learned about the relevant product, there is a certain probability to select the product of the enterprise, but the non-differential push method cannot attract more customers and can only obtain the average level; and for customers who have relevant needs but still have needs to learn about the product, unless they actively contact, the enterprise cannot convert them. At the same time, the enterprise may also repeatedly sell the product to the customers, track a large number of non-target customers, and cause resource waste.

[0049] Among them, the potential user often experiences three stages of awareness, consideration and decision before becoming a real customer. When the enterprise currently promotes the product to general individual users, due to the large number of users and the lack of corresponding data of user marketing records and marketing feedback, the marketing process perceived by a single user is discontinuous, and problems such as resource waste caused by over-marketing to users in the initial stage and passive waiting for user decision in the subsequent stage and unable to effectively carry out marketing activities may occur. For example, in the product promotion stage, the user may have received multiple copies of the same flyer in different places, but when the user has some consulting needs, unless the user actively inquires, the enterprise is difficult to know which user needs consulting services, and finally leads to a low customer conversion rate.

[0050] In the face of the above technical problems, the embodiment of the present application provides a potential user determination method, which uses digital twin technology to simulate the process model of the conversion of potential users into customers by integrating online and offline marketing data, dynamically promotes the process according to user feedback, and optimizes the algorithm model and intelligently operates and maintains to improve the customer acquisition efficiency and reduce the customer acquisition cost. The following will be described in detail with detailed embodiments.

[0051] Reference Figure 1 , Figure 1 The flowchart of the potential user determination method provided by the embodiment of the present application, in some embodiments, the method comprises:

[0052] S101, acquire first behavior data of a plurality of users in a first time period, and select a first potential user from the plurality of users according to the first behavior data; wherein the first behavior data comprises browsing behavior data of the user in the online promotion process and / or browsing feedback data in the offline promotion process.

[0053] In some embodiments, in the online promotion process, the number of push times, the number of times the user clicks, the page scrolling after the user clicks, the stay time and other data are recorded. After a certain frequency of push, it is found that the user has similar browsing behavior of consideration tendency but fails to convert, a questionnaire is pushed, user feedback is acquired, and subsequent customer acquisition methods are optimized.

[0054] In the offline promotion process, the user can be required to obtain the user unique identification information by scanning the two-dimensional code, retaining the mobile phone number, and the like, and the marketing customer manager records the communication duration and the user preliminary intention feedback, and the like. Meanwhile, the activity participation entry is set at different positions of the promotion material, the user code scanning participation data is collected, and the reading degree of the user to the material is understood.

[0055] In some embodiments, the browsing behavior data of the user in the online promotion process and the browsing feedback data in the offline promotion process can be integrated in the system, the user dimension marketing record and the feedback situation are obtained, and finally it is determined whether the user is the first potential user according to whether the user behavior data reaches the conversion threshold or some key conversion behaviors (for example, adding the shopping cart without payment).

[0056] Among them, if the single marketing cost reaches the upper limit but fails to successfully convert the user, the user needs to enter a potential user sleep period for a period of time, and then the next marketing is performed.

[0057] S102, obtaining second behavior data of the first potential user in a second time period, and selecting a second potential user from the first potential user according to the second behavior data; wherein the second behavior data includes purchase intention behavior data of the user in the online promotion process and / or demand feedback data in the offline promotion process.

[0058] In this embodiment, it is assumed that the first potential user has a preliminary understanding of the related product and needs further detailed understanding of the product: for example, it is known that the term and the yield of a certain financial product, and it is desired to know the past scale, the yield, the investment assets and even how to purchase, and the like.

[0059] In the online promotion process, the user's active search for the product, the staying on the product detail page, and the subsequent product collection and click to add to the shopping cart are recorded. The user has a similar browsing behavior of considering the tendency but fails to convert, a questionnaire is pushed, the user feedback is obtained, and the subsequent customer acquisition mode is optimized.

[0060] In the offline promotion process, the user can be reached by the customer manager through the initiative telephone, the user demand is understood, and the customer manager can be required to make a simple record at the initial stage. In the later stage, the natural language processing is performed according to the record to obtain the common questions and the standardized user process.

[0061] In some embodiments, the purchase intention behavior data of the user in the online promotion process and / or the demand feedback data in the offline promotion process can be integrated in the system, the user dimension marketing record and the feedback situation are obtained, and finally it is determined whether the user belongs to the second potential user according to whether the user behavior data reaches the conversion threshold or some key conversion behaviors.

[0062] S103, acquire third behavior data of the second potential user in a third time period, and determine a target user from the second potential user according to the third behavior data; wherein the third behavior data comprises purchase behavior data in an online promotion process and / or purchase feedback data in an offline promotion process.

[0063] In the embodiment, it is assumed that the second potential user is ready to purchase the target product.

[0064] In the online promotion process, problems that can occur when the user makes a payment can be recorded. If a node with a large decrease in conversion rate occurs, a questionnaire can be pushed to obtain user feedback for subsequent optimization of customer acquisition methods.

[0065] In the offline promotion process, a customer manager can actively call the user to understand the user's needs. The customer manager can be required to make simple records at the initial stage, and common problems can be obtained by natural language processing according to the records at the later stage, and a standardized user process is reached.

[0066] In some embodiments, the purchase behavior data of the user in the online promotion process and / or the purchase feedback data in the offline promotion process can be integrated in the system to obtain user-dimension marketing records and feedback. Finally, whether the user is a target user is determined according to whether the user behavior data reaches a conversion threshold or some key conversion behaviors.

[0067] The method for determining a potential user provided in the embodiments of the application uses digital twin technology, integrates online and offline marketing data, simulates a process model in which a potential user is converted into a customer, dynamically advances the process according to user feedback, and optimizes the algorithm model and intelligently operates and maintains to improve customer acquisition efficiency and reduce customer acquisition costs.

[0068] In some embodiments of the application, online and offline marketing data are integrated to simulate a process model in which a potential user becomes a customer, the process is dynamically advanced according to user feedback, and the algorithm model is optimized and intelligently operated and maintained to improve customer acquisition efficiency and reduce customer acquisition costs.

[0069] The overall operation iteration mode of the model comprises: setting a target conversion rate, determining an initial customer conversion threshold or model score, which can be determined by experience or expert rules, and marketing the user. Subsequently, the customer conversion threshold and the marketing method can be dynamically adjusted according to the actual conversion condition of the existing data until the target conversion rate is reached. Or a cost-effectiveness analysis is performed to decide whether the target conversion rate needs to be adjusted.

[0070] In order to better understand the embodiments of the application, refer to Figure 2 , Figure 2A model schematic diagram of a method for determining a potential user provided by an embodiment of the present application, in some embodiments, the model comprises:

[0071] I. Perception module:

[0072] Online: When pushing the app to inventory users, record the number of pushes, user clicks, page scrolling after user clicks, and dwell time. After a certain number of pushes, if it is found that the user has similar browsing behaviors that show a tendency to consider but fail to convert, a questionnaire is pushed to obtain user feedback for subsequent optimization of customer acquisition methods.

[0073] Offline: During promotion, users are required to obtain unique identification information by scanning a two-dimensional code, leaving a mobile phone number, etc., and the marketing customer manager records the communication duration and user preliminary intention feedback, etc. At the same time, activity participation entrances are set at different positions of the promotion materials to collect user scanning participation data and understand the user's reading level of the materials.

[0074] Data integration: The online and offline are integrated in the system to obtain user dimension marketing records and feedback. Finally, whether the user behavior data reaches the conversion threshold or some key conversion behaviors (such as adding a shopping cart without payment), it is determined whether to enter the related push service of step two.

[0075] Among them, if the user reaches the upper limit of the single marketing cost but fails to convert, the user needs to enter a potential user sleep period for a period of time before the next marketing.

[0076] II. Consideration module

[0077] In this module, the user has already had a preliminary understanding of the related product and needs further detailed understanding of the product: for example, already knows the term and yield of a certain financial product, wants to know the past size, yield, and investment assets, or even how to buy, etc.

[0078] Online: Record the user's active search for products, dwell time on product detail pages, and subsequent product collection and purchase clicks. If it is found that the user has similar browsing behaviors that show a tendency to consider but fail to convert, a questionnaire is pushed to obtain user feedback for subsequent optimization of customer acquisition methods.

[0079] Offline: The customer manager can actively call the user to understand the user's needs, and the customer manager can make a simple record at the initial stage. Later, according to the record, natural language processing is performed to obtain common questions and standardize the user process.

[0080] Data integration: Similar to the data integration method in the above perception module.

[0081] III. Purchase module

[0082] In this module, the default user is ready to buy products.

[0083] Online: Mainly record the problems that may occur when the user pays for the purchase. If there is a node with a large decrease in conversion rate, a questionnaire can be pushed to obtain user feedback in order to optimize subsequent customer acquisition methods.

[0084] Offline: The user can be reached by the customer manager through a phone call to understand the user's needs. In the early stage, the customer manager can be asked to make a simple record, and in the later stage, natural language processing can be used to obtain common problems based on the record to standardize the user process.

[0085] Data integration: Similar to the data integration method in the above perception module.

[0086] Reference Figure 3 , Figure 3 Another flowchart of a potential user determination method provided by an embodiment of the present application. In some embodiments, the potential user determination method includes:

[0087] After entering the perception stage, first behavior data of a plurality of users in a first time period is obtained, and a first potential user is selected from the plurality of users based on the first behavior data. The first behavior data includes browsing behavior data of the user in the online promotion process and / or browsing feedback data in the offline promotion process.

[0088] It is determined whether each user in the above plurality of users belongs to the first potential user. If yes, it is considered that the user is successfully converted and can enter the consideration stage. If no, it is determined whether the marketing cost of the user exceeds the maximum customer acquisition cost. If yes, the user is determined as a sleep user, and the promotion service provided to the sleep user is canceled within a preset time period. If no, the user is continued to be promoted in the perception stage.

[0089] After entering the consideration stage, second behavior data of the first potential user in a second time period is obtained, and a second potential user is selected from the first potential user based on the second behavior data. The second behavior data includes purchase intention behavior data of the user in the online promotion process and / or demand feedback data in the offline promotion process.

[0090] It is determined whether each first potential user belongs to the second potential user. If yes, it is considered that the user is successfully converted and can enter the decision stage. If no, it is determined whether the marketing cost of the user exceeds the maximum customer acquisition cost. If yes, the user is determined as a sleep user, and the promotion service provided to the sleep user is canceled within a preset time period. If no, the user is continued to be promoted in the consideration stage.

[0091] After entering the decision stage, third behavior data of the second potential user in a third time period is acquired, and a target user is determined from the second potential user according to the third behavior data; wherein the third behavior data includes purchase behavior data in an online promotion process and / or purchase feedback data in an offline promotion process of the user.

[0092] It is judged whether each of the above-mentioned second potential users is the target user, if yes, it is considered that the user is successfully converted, and can enter the customer management stage; if not, it is determined whether the marketing cost of the user exceeds the maximum customer acquisition cost, if yes, the user is determined as a sleep user, and the promotion service provided to the sleep user is cancelled within a preset time length, if not, the promotion service is continuously provided to the user in the consideration stage.

[0093] The present application includes three stages: perception, consideration and decision, is customer-centered, integrates multi-dimensional user behavior and feedback data online and offline, abstracts the whole customer acquisition scene into a digital model through digital twin technology, can actively promote the marketing process of the customer, improves the purchase experience of the customer, not only acquires the customer, but also actively cultivates potential customers.

[0094] Based on the content described in the above embodiments, a potential user determination device is further provided in the embodiments of the present application. Referring to Figure 4 , Figure 4 A program module schematic diagram of a potential user determination device provided in the embodiments of the present application is shown in the figure, and the device includes:

[0095] The first screening module 401 is configured to acquire first behavior data of a plurality of users in a first time period, and select a first potential user from the plurality of users according to the first behavior data; the first behavior data includes browsing behavior data in an online promotion process and / or browsing feedback data in an offline promotion process of the user;

[0096] The second screening module 402 is configured to acquire second behavior data of the first potential user in a second time period, and select a second potential user from the first potential user according to the second behavior data; the second behavior data includes purchase intention behavior data in an online promotion process and / or demand feedback data in an offline promotion process of the user;

[0097] The third screening module 403 is configured to acquire third behavior data of the second potential user in a third time period, and determine a target user from the second potential user according to the third behavior data; the third behavior data includes purchase behavior data in an online promotion process and / or purchase feedback data in an offline promotion process of the user.

[0098] The potential user determination device provided by the embodiment of the application simulates a process model of converting potential customers into actual customers by integrating online and / or offline user behavior and feedback data, filters multiple users layer by layer, determines users with high purchase intention, and performs accurate marketing activities on these users, so as to improve the purchase experience of users and the customer conversion rate.

[0099] In some embodiments, the first screening module 401 is configured to:

[0100] According to the browsing behavior data and / or the browsing feedback data, a first purchase probability value of each user in the multiple users is determined; wherein the browsing behavior data comprises online browsing times and browsing time length, and the browsing feedback data comprises offline communication time length; a user whose first purchase probability value is greater than or equal to a first preset threshold value in the multiple users is determined as the first potential user.

[0101] According to the browsing behavior data and / or the browsing feedback data, a marketing cost of each user in the multiple users is determined; a user whose first purchase probability value is less than the first preset threshold value and whose marketing cost is greater than a first preset cost threshold value in the multiple users is determined as a sleep user, and a promotion service provided to the sleep user is cancelled within a preset time length.

[0102] In some embodiments, the second screening module 402 is configured to:

[0103] According to the purchase intention behavior data and / or the demand feedback data, a second purchase probability value of the first potential user is determined; wherein the purchase intention behavior data comprises the number of times of searching for a target product, the time length of browsing a target product detail page, and the behavior of collecting a target product, and the demand feedback data comprises offline demand feedback times and offline inquiry times; a user whose second purchase probability value is greater than or equal to a second preset threshold value in the first potential user is determined as the second potential user.

[0104] According to the purchase intention behavior data and / or the demand feedback data, a marketing cost of the first potential user is determined; a user whose second purchase probability value is less than the second preset threshold value and whose marketing cost is greater than a second preset cost threshold value in the first potential user is determined as a sleep user, and a promotion service provided to the sleep user is cancelled within a preset time length.

[0105] In some embodiments, the third screening module 403 is configured to:

[0106] According to the purchase behavior data and / or the purchase feedback data, a user with a purchase failure record in the second potential user is determined; the user with the purchase failure record in the second potential user is determined as the target user.

[0107] According to the purchase behavior data and / or the purchase feedback data, a marketing cost of the second potential user is determined; a user without a purchase behavior in the second potential user and with a marketing cost greater than a third preset cost threshold is determined as a sleep user, and a promotion service provided to the sleep user is cancelled within a preset time length.

[0108] It should be noted that the specific content executed by the first screening module 401, the second screening module 402, and the third screening module 403 in the embodiments of the present application can be referred to the related content in the embodiments shown in the above Figures 1 to 3 , and details are not repeated here.

[0109] Further, based on the content described in the above embodiments, the embodiments of the present application also provide an electronic device, which includes at least one processor and a memory; wherein the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory to realize each step in the potential user determination method described in the above embodiments, and details are not repeated here.

[0110] In order to better understand the embodiments of the present application, refer to Figure 5 , Figure 5 for a hardware structure schematic diagram of an electronic device provided by the embodiments of the present application.

[0111] As Figure 5 shown, the electronic device 50 of the present embodiment includes a processor 501 and a memory 502; wherein:

[0112] The memory 502 is configured to store computer execution instructions.

[0113] The processor 501 is configured to execute the computer execution instructions stored in the memory to realize each step in the potential user determination method described in the above embodiments, and details are not repeated here, which can be referred to the related description in the foregoing method embodiments.

[0114] Optionally, the memory 502 can be independent or integrated with the processor 501.

[0115] When the memory 502 is independently arranged, the device further includes a bus 503 for connecting the memory 502 and the processor 501.

[0116] Further, based on the content described in the above embodiments, the present embodiment further provides a computer readable storage medium, which stores computer execution instructions, when a processor executes the computer execution instructions, each step in the potential user determination method described in the above embodiments is implemented, and the present embodiment will not be described here.

[0117] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. For example, the above described device embodiments are merely schematic, and the division of the modules is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between modules can be indirect coupling or communication connection through some interface, device or module, and can be electrical, mechanical or in other forms.

[0118] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0119] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more modules can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software function unit.

[0120] The integrated module realized in the form of software function module can be stored in a computer readable storage medium. The software function module stored in the storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to execute part of the steps of the method described in each embodiment of the present application.

[0121] It should be appreciated that the above processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0122] The memory can include a high-speed RAM memory, and can also include a non-volatile storage NVM, such as at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0123] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0124] The above storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0125] An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a host device.

[0126] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a computer readable storage medium. The program executes to perform the steps of the above-mentioned method embodiments; and the foregoing storage medium includes various storage media that can store program codes, such as ROM, RAM, magnetic disk or optical disk.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying potential users, characterized in that, The method includes: Acquire first behavioral data of multiple users within a first time period, and select a first potential user from the multiple users based on the first behavioral data; the first behavioral data includes browsing behavior data of users during online promotion and / or browsing feedback data during offline promotion. Acquire the second behavioral data of the first potential user within a second time period, and select a second potential user from the first potential user based on the second behavioral data; the second behavioral data includes the user's purchase intention behavior data during the online promotion process and / or demand feedback data during the offline promotion process; Acquire the third behavioral data of the second potential user within the third time period, and determine the target user among the second potential users based on the third behavioral data; the third behavioral data includes the user's purchase behavior data during the online promotion process and / or purchase feedback data during the offline promotion process; wherein, the first time period, the second time period, and the third time period constitute a continuous conversion process from user attention to decision-making, and the first behavioral data, the second behavioral data, and the third behavioral data correspond to user behavior data in the perception stage, the consideration stage, and the decision-making stage, respectively. The step of selecting a first potential user from the plurality of users based on the first behavioral data includes: Based on the browsing behavior data and / or the browsing feedback data, a first purchase probability value is determined for each of the plurality of users; wherein the browsing behavior data includes the number of online browsing sessions and the browsing duration, and the browsing feedback data includes the duration of offline communication. Among the plurality of users, those whose first purchase probability value is greater than or equal to a first preset threshold are identified as the first potential users; Also includes: Based on the browsing behavior data and / or the browsing feedback data, determine the marketing cost for each of the multiple users; Users whose first purchase probability value is less than the first preset threshold and whose marketing cost is greater than the first preset cost threshold are identified as dormant users, and online and / or offline promotion services provided to the dormant users are cancelled within a preset time period. The step of selecting a second potential user from the first potential users based on the second behavioral data includes: Based on the purchase intention behavior data and / or the demand feedback data, a second purchase probability value for the first potential user is determined; wherein, the purchase intention behavior data includes the number of times the target product is searched, the duration of browsing the target product details page, the behavior of adding the target product to favorites, and the behavior of adding the target product to the cart, and the demand feedback data includes the number of offline demand feedbacks and the number of offline inquiries; Users whose second purchase probability value is greater than or equal to the second preset threshold among the first potential users are identified as the second potential users.

2. The method according to claim 1, characterized in that, Also includes: Based on the purchase intention behavior data and / or the demand feedback data, determine the marketing cost for the first potential user; Users among the first potential users whose second purchase probability value is less than the second preset threshold and whose marketing cost is greater than the second preset cost threshold are identified as dormant users, and online and / or offline promotion services provided to the dormant users are cancelled within a preset time period.

3. The method according to claim 1, characterized in that, The step of determining the target user among the second potential users based on the third behavioral data includes: Based on the purchase behavior data and / or the purchase feedback data, identify users among the second potential users who have a purchase failure record; Users with a history of failed purchases among the second group of potential users are identified as the target users.

4. The method according to claim 3, characterized in that, Also includes: Based on the purchase behavior data and / or the purchase feedback data, determine the marketing cost for the second potential user; Users among the second potential users who have not made a purchase and whose marketing costs exceed a third preset cost threshold are identified as dormant users, and online and / or offline promotional services provided to the dormant users are cancelled within a preset time period.

5. A device for identifying potential users, characterized in that, The device includes: The first filtering module is used to acquire first behavior data of multiple users within a first time period, and select a first potential user from the multiple users based on the first behavior data; the first behavior data includes browsing behavior data of users during online promotion and / or browsing feedback data during offline promotion. The second filtering module is used to obtain the second behavioral data of the first potential user within a second time period, and select the second potential user from the first potential user based on the second behavioral data; the second behavioral data includes the user's purchase intention behavior data during the online promotion process and / or the demand feedback data during the offline promotion process; The third filtering module is used to obtain the third behavioral data of the second potential user in the third time period, and to determine the target user among the second potential users based on the third behavioral data; the third behavioral data includes the user's purchase behavior data during the online promotion process and / or purchase feedback data during the offline promotion process; wherein, the first time period, the second time period and the third time period constitute a continuous conversion process from user attention to decision, and the first behavioral data, the second behavioral data and the third behavioral data correspond to user behavior data in the perception stage, the consideration stage and the decision stage, respectively. The first filtering module is specifically used to determine a first purchase probability value for each user among the plurality of users based on the browsing behavior data and / or the browsing feedback data; wherein the browsing behavior data includes the number of online browsing sessions and the browsing duration, and the browsing feedback data includes the duration of offline communication; and users among the plurality of users whose first purchase probability value is greater than or equal to a first preset threshold are identified as the first potential users; The first filtering module is further specifically used to determine the marketing cost of each user among the plurality of users based on the browsing behavior data and / or the browsing feedback data; to identify users among the plurality of users whose first purchase probability value is less than the first preset threshold and whose marketing cost is greater than the first preset cost threshold as dormant users, and to cancel the online and / or offline promotion services provided to the dormant users within a preset time period; The second filtering module is specifically used to determine the second purchase probability value of the first potential user based on the purchase intention behavior data and / or the demand feedback data; wherein, the purchase intention behavior data includes the number of times the target product is searched, the duration of browsing the target product details page, the behavior of adding the target product to favorites, and the behavior of adding the target product to the cart, and the demand feedback data includes the number of offline demand feedback and the number of offline inquiries; Users whose second purchase probability value is greater than or equal to the second preset threshold among the first potential users are identified as the second potential users.

6. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method for determining a potential user as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the method for determining potential users as described in any one of claims 1 to 4.

Images