CN113095886A - Message pushing method and device, storage medium and computer equipment - Google Patents
Message pushing method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN113095886A CN113095886A CN202110443191.9A CN202110443191A CN113095886A CN 113095886 A CN113095886 A CN 113095886A CN 202110443191 A CN202110443191 A CN 202110443191A CN 113095886 A CN113095886 A CN 113095886A
- Authority
- CN
- China
- Prior art keywords
- crowd
- user
- users
- message
- potential
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Abstract
A message pushing method and device, a storage medium and a computer device are provided, and the method comprises the following steps: the method comprises the steps that information of a plurality of users is obtained from an e-commerce platform, part of the users are selected from the information of the users to form a high-potential crowd, and a communication page is constructed for the high-potential crowd; pushing a first message to the high-potential crowd, wherein the first message comprises an access link of a communication page; after the first message is pushed, the transaction conversion results of all users in the high-potential crowd on the E-commerce platform are obtained from the E-commerce platform, and the users in the high-potential crowd are subjected to priority ranking according to the transaction conversion results of all the users; selecting users from the sorted high-potential crowds to form a target crowd, and constructing an updated communication page; and pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page. The scheme of the invention can improve the message pushing effect.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a message pushing method and device, a storage medium and computer equipment.
Background
With the development of internet technology, message pushing becomes a common message delivery mode, especially in the fields of product publicity, marketing and the like. The existing message pushing usually pushes preset message content to the public or a preselected group, but the existing pushing method has a poor pushing effect.
Disclosure of Invention
The technical problem solved by the invention is how to improve the message pushing effect.
In order to solve the foregoing technical problem, an embodiment of the present invention provides a message pushing method, where the method includes: step A, acquiring information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd; step B, pushing a first message to the high-potential crowd, wherein the first message comprises an access link of the communication page; step C, after the first message is pushed, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform, and carrying out priority sequencing on the users in the high-potential crowd according to the transaction conversion result of each user; d, selecting users from the high-potential crowds after the priority ranking to form a target crowd, and constructing an updated communication page; and E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page.
Optionally, after the step C, the method further includes: selecting users from the prioritized high-latency population to form a seed population, wherein the target population comprises the seed population; the constructing of the updated communication page includes: and constructing the updated communication page according to the seed crowd.
Optionally, the selecting a part of users from the information of the plurality of users to form a high-latency crowd includes: constructing an association vector between each user and a product corresponding to the pushed message according to the information of each user, wherein the association vector comprises a plurality of association dimensions of the user and the product; and adding the users with the length of the association vector exceeding a preset value into the high-potential crowd.
Optionally, the selecting a part of users from the information of the plurality of users to form a high-latency crowd further includes: acquiring a user portrait of each user, wherein the user portrait is constructed according to the transaction history of the user on the E-commerce platform; and selecting users with user figures meeting preset conditions to form the high-potential crowd.
Optionally, after the step C and before the step D, the method further includes: and eliminating users with the priority lower than a preset level in the high-potential crowd.
Optionally, after the first message is pushed, obtaining, from the e-commerce platform, a transaction conversion result of each user in the high-potential crowd on the e-commerce platform, includes: within a preset time after the first message is pushed, transaction data of each user in the high-potential crowd on the E-commerce platform are obtained for multiple times; determining the transaction stage of each user in the transaction data acquired each time; constructing a transaction stage flow chart of each user in the preset time; and analyzing according to the stage circulation diagram to obtain a transaction conversion result of each user in a preset time.
Optionally, the selecting users from the high-latency groups after the priority ranking to form a target group includes: obtaining the target cost of the current release; and obtaining the scale of the target population according to the target cost, and selecting the target population from the high-potential population after the priority ranking according to the scale.
Optionally, the communication page is constructed in a manner that: acquiring a current crowd corresponding to the communication page, and acquiring a user portrait of each user in the current crowd; extracting material commonalities of the current crowd according to the user portrait of each user in the current crowd; acquiring corresponding materials according to the material commonality, and generating a communication page according to the selected materials; wherein the current population comprises a high-latency population and a target population.
Optionally, the communication page is constructed in a manner that: further comprising: and responding to a re-pushing request, and jumping to the step C and re-executing the step C to the step E by taking the target crowd as the high-potential crowd.
Optionally, the message pushing includes advertisement pushing, and when the user triggers the pushed advertisement, the access link of the communication page is accessed.
The embodiment of the invention also provides a message pushing device, which comprises: the high-potential crowd composition module is used for executing the step A, acquiring information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd; a first pushing module, configured to execute step B, and push a first message to the high-potential crowd, where the first message includes an access link of the communication page; the priority ranking module is used for executing the step C, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform after the first message is pushed, and ranking the priority of the users in the high-potential crowd according to the transaction conversion result of each user; the target crowd selecting module is used for executing the step D, selecting users from the high-potential crowd after the priority ranking to form a target crowd, and constructing an updated communication page; and E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page.
Embodiments of the present invention also provide a storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above method.
The embodiment of the present invention further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a message pushing method, which comprises the following steps: step A, acquiring information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd; step B, pushing a first message to the high-potential crowd, wherein the first message comprises an access link of the communication page; step C, after the first message is pushed, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform, and carrying out priority sequencing on the users in the high-potential crowd according to the transaction conversion result of each user; d, selecting users from the high-potential crowds after the priority ranking to form a target crowd, and constructing an updated communication page; and E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page. Compared with the prior art, the scheme of the embodiment of the invention can construct the communication page aiming at the characteristics of the high-potential crowd to carry out the pushing of the first message so as to be accessed by the high-potential crowd, and after the pushing of the first message, the target crowd (generally the crowd with higher priority after the priority ranking) is excavated according to the transaction conversion result pushed by the first message, the communication page is updated so as to be more consistent with the characteristics of the target crowd, and then the second message is pushed to the target crowd. And the selection of the target crowd is determined according to the transaction conversion result, so that the updated communication pages are beneficial to realizing efficient user touch, and the message pushing effect is improved.
Further, the high-potential crowd is determined by using the length of the association vector between each user and the product, or the high-potential crowd can be determined according to the user portrait of each user, so that the characteristics of the user can be analyzed and obtained more accurately and comprehensively. The communication page is constructed aiming at the characteristics of the high-latency crowd and has strong pertinence, so that the user touch is improved, and the conversion rate is further improved.
Further, after the first message is pushed, transaction data of the high-potential crowd on the e-commerce platform are obtained, the transaction stages of the users in the whole transaction process at different time points are analyzed, and a transaction stage flow diagram (which may include the flow relation of each transaction stage) is constructed, for example, the transaction stage flow diagram may be constructed according to the operation of each user receiving the first message on the e-commerce platform. The transaction conversion result obtained by the method contains the circulation relation of the user in each stage in the whole transaction process, so that the transaction conversion result is more comprehensive and accurate, the priority ranking is carried out based on the transaction conversion result, the ranking result is more accurate, the selection of target crowds or seed crowds with higher association degree with products is facilitated, and the updating of the communication page is more targeted.
Further, when the communication page is constructed, user figures of users in the high-potential crowd, the target crowd or the seed crowd are analyzed, material commonalities are extracted, and materials are selected according to the extracted material commonalities to construct or update the communication page. Because the selection of the materials is carried out according to the user figures of the high-potential crowd, the target crowd or the seed crowd, the generated or updated communication page is more targeted, the realization of efficient user touch is facilitated, and the pushing effect is improved.
Drawings
Fig. 1 is a schematic flowchart of a message pushing method according to an embodiment of the present invention;
FIG. 2 is a schematic view of a specific process flow of step C in FIG. 1;
fig. 3 is a schematic flow chart illustrating a construction method of a communication page according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating another message pushing method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a message pushing apparatus according to an embodiment of the present invention.
Detailed Description
As mentioned in the background, the message pushing effect in the prior art is poor. The applicant has found through research that one of the main reasons is that currently, the pushed message is often preset, and the content, the presentation form and the interaction mode contained in the message are all unchanged, so that the user reach rate is low, and the transaction conversion rate is also low.
In order to solve the problem, an embodiment of the present invention provides a message pushing method, including: step A, acquiring information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd; step B, pushing a first message to the high-potential crowd, wherein the first message comprises an access link of the communication page; step C, after the first message is pushed, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform, and carrying out priority sequencing on the users in the high-potential crowd according to the transaction conversion result of each user; d, selecting users from the high-potential crowds after the priority ranking to form a target crowd, and constructing an updated communication page; and E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page. Through the scheme, efficient user touch can be achieved, and the message pushing effect is improved.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. The invention relates to the technical field of internet, in particular to big data analysis and application of an electronic commerce platform.
Referring to fig. 1, an embodiment of the present invention provides a message pushing method, where the method is performed by a terminal or a server, where the terminal may be a mobile phone, a computer, or the like, and the server may include a single server or a server cluster, and more specifically, the method may be performed by an e-commerce platform or a terminal or a server coupled to the e-commerce platform. The method includes steps a through E, which are described in detail below.
Step A, obtaining information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd.
The e-commerce platform is a platform for product transaction, can be an existing e-commerce platform, such as the existing a-baba, the existing kyoto and the like, and can also be a platform specially built for a brand to which the product belongs or a product line, such as an online store of the brand a, a wechat applet and the like. The information of the user may refer to an identity (identity, abbreviated as ID) of the user or information such as a device number and a mobile phone number of the target user.
The high-latency crowd refers to a crowd of users mined from a plurality of users and having a high probability of completing a transaction. Optionally, the possibility of completing the transaction by each user can be calculated according to the information of the user, the historical transaction of the user, the information in the portrait of the user and the like, and the user with the possibility higher than a certain threshold value is added into the high-potential crowd.
Constructing a communication page for the high-potential crowd may include: the communication page is constructed for the high-potential crowd according to the characteristics of part or all of the users in the high-potential crowd, wherein the characteristics of the users can be obtained in the modes of user portrait analysis or questionnaires and the like, and the characteristics represent the characters and the preference of the users. The content, the presentation mode, the interaction mode and the like contained in the communication page can be customized according to the characteristics of the high-potential crowd, for example, materials such as dialogs, patterns, display effects and the like can be selected according to the characteristics of part or all of users in the high-potential crowd, so that the communication page can be obtained. The communication page can be an e-commerce communication page used for receiving the questions of the user or facilitating the user to access the sales connection of the product and the like.
Optionally, the message pushing includes advertisement pushing, at this time, topics of communication pages for different high-potential crowds may all use products targeted by the advertisement pushing as topics, and different materials are designed only for characteristics of users in the high-potential crowds.
And step B, pushing a first message to the high-potential crowd, wherein the first message comprises an access link of the communication page.
The first message is designed for the high-potential crowd, can be sent to a terminal of an appointed user in a short message mode, an email mode, a network message mode and the like to finish pushing, and can also be delivered to a plurality of uncertain users in a video mode, an advertisement mode, a broadcast mode and the like to finish pushing. The access link of the communication page is a link for accessing the communication page, such as an Address (e.g., an Internet Protocol Address, abbreviated as an IP Address)) corresponding to the communication page.
Optionally, the message pushing includes advertisement pushing, and when the user triggers the pushed advertisement, the access link of the communication page is accessed. That is, the access link of the communication page may be implicitly included in the first message. As a variant, the access link may also be explicitly included in the first message.
And step C, after the first message is pushed, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform, and carrying out priority sequencing on the users in the high-potential crowd according to the transaction conversion result of each user.
After the message is pushed to the high-potential crowd, part of users in the high-potential crowd may be interested in the product or the activity targeted by the message, so that corresponding operations (such as purchasing the product, adding the product into a shopping cart or collecting the product, participating in the activity and the like) are performed in the e-commerce platform, and the transaction conversion result can be determined according to the operations of each user in the high-potential crowd in the e-commerce platform.
And sorting the priorities of the users according to the transaction conversion results of different users in the high-potential crowd. Specifically, the priority may be determined according to the transaction conversion rate, and the higher the transaction conversion rate, the higher the priority. Wherein the transaction conversion rate refers to a proportion of the user performing a corresponding operation (e.g., purchasing a product) according to the content of the push message after receiving the push message. Or, the priority may be determined according to the circulation of the transaction stages, the whole transaction flow is divided into a plurality of stages according to the time sequence, and the closer the stage is to the rear stage of the time sequence (i.e., the closer to the completion of the transaction), the higher the priority is. For example, users who purchase products are ranked as the highest priority, users who add products to shopping carts or collections are ranked as the second priority, users who only view products on the e-commerce platform are ranked as the third priority, users who do not perform any message push related operations on the e-commerce platform are ranked as the fourth priority, and so on. It should be noted that, the prioritization of the users in the high-potential crowd according to the transaction conversion result of each user may be according to any set prioritization rule, including but not limited to the foregoing examples.
Optionally, after the step C and before the step D, the method further includes: and eliminating users with the priority lower than a preset level in the high-potential crowd.
According to the first pushing effect, users with lower priorities are removed from the users in the high-potential crowd, so that the data volume of subsequent analysis is reduced, and the analysis efficiency is improved.
And D, selecting users from the high-potential crowds after the priority ranking to form a target crowd, and constructing an updated communication page.
And D, constructing an updated communication page according to the target crowd, reconstructing the communication page at the moment, and adjusting and updating the communication page on the basis of the communication page in the step A. If the communication page is reconstructed, the updated communication page construction mode can refer to the communication page construction mode, and details are not repeated here; if the communication page is adjusted and updated on the basis of the previous communication page, the previous communication page can be updated according to the characteristics of the target crowd, for example, material deletion, addition, replacement and the like can be performed.
And E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page.
The target population is the population targeted by the second message, and the number of users in the target population can be determined according to the number of people who want to reach by pushing the second message or the cost of the push plan. And selecting users meeting the determined target population from the high-potential population according to the determined target population from the high-potential population in the order of high priority to low priority to form a target population.
The second message is the message pushed again, and the content of the second message except the communication page can be the same as or different from the first message, but the themes of the second message and the first message are consistent. For example, when advertising, the first message and the second message should both be advertisements for the same product. The relationship between the second message and the updated access link of the communication page may be determined by referring to the relationship between the first message and the access link of the communication page, which is not described herein again.
In this embodiment, a communication page can be constructed according to characteristics of a high-latency crowd to push a first message so as to enable the high-latency crowd to access, after the first message is pushed, a target crowd (usually, the crowd with a higher priority after the priority ranking) is continuously mined according to a transaction conversion result pushed by the first message, the communication page is updated so as to be more consistent with the characteristics of the target crowd, and then a second message is pushed to the target crowd. And the selection of the target crowd is determined according to the transaction conversion result, so that the updated communication pages are beneficial to realizing efficient user touch, and the message pushing effect is improved.
In one embodiment, step C in fig. 1 is followed by: selecting users from the prioritized high-latency population to form a seed population, wherein the target population comprises the seed population; the step D of establishing an updated communication page comprises the following steps: and constructing the updated communication page according to the seed crowd.
The seed population is a population consisting of users of the first level or the first few levels with the highest priority in the high-potential population, namely the seed population is a population consisting of users which are mined from the high-potential population and have the highest possibility of completing transactions. Typically, the seed population is a subset of the high potential population.
The communication page in the step D can be constructed according to the characteristics of the seed crowd, and the pertinence of the communication page is stronger so as to match with the users with the highest possibility of completing the transaction in the target crowd. The method for constructing the updated communication page according to the characteristics of the seed group may be referred to as the method for constructing the updated communication page according to the characteristics of the target group in step D in fig. 1, and details are not repeated here.
In one embodiment, the step a of selecting a part of users from the information of the plurality of users to form a high-latency crowd includes: constructing an association vector between each user and a product corresponding to the pushed message according to the information of each user, wherein the association vector comprises a plurality of association dimensions of the user and the product; and adding the users with the length of the association vector exceeding a preset value into the high-potential crowd.
Wherein the association vector is used to indicate the probability of each user (e.g., the user corresponding to each account) completing the transaction, and the probability can be expressed as a vector length. The higher the likelihood, the longer the vector length, and vice versa, etc. The association vector is a multi-dimensional vector that includes a plurality of association dimensions. The respective association dimensions are used to represent factors that may influence the user's purchase of the product, such as the frequency with which the user purchased other products of the brand to which the product belongs in the past, the degree of interest of the user in the product obtained through a questionnaire, the geographic location of the user, and the like. That is, more specifically, each association dimension is used to represent the association of a user with the product in a single aspect, which may be a variety of suitable settings, including but not limited to the various examples listed above.
It should be noted that the setting of the association dimension of each user and the product may be the same or different, that is, in the association vectors of different users, each association dimension may be the same, or some association dimensions or all association dimensions may be different. For example, obtaining the associated dimension of user a includes: the frequency (for example, 3 times) that the user a purchases other products of the brand to which the product belongs in the past, the interest level (for example, level a) of the user a in the product, and obtaining the associated dimension of the user B includes: frequency (e.g., 1) that user B purchased other products of the brand to which the product belongs in the past, geographic location of user B in M city (M city being the best-selling place of the brand to which the product belongs). By constructing the association vector of each user and the product, different association dimensions of different users can be quantified in a uniform manner, and the possibility of each user completing a transaction is converted into a uniform comparison standard, namely the length of the association vector.
In addition, the step a of selecting a part of users from the information of the plurality of users to form a high-latency crowd may further include: acquiring a user portrait of each user, wherein the user portrait is constructed according to the transaction history of the user on the E-commerce platform; and selecting users with user figures meeting preset conditions to form the high-potential crowd.
The user portrait is an abstract portrait constructed for the user according to the information and historical operations (such as data related to transactions) of the user, and is used for analyzing the behavior habits, consumption habits and the like of the user. The data basis of the user portrait construction is the transaction history of the user on the e-commerce platform, and the construction mode can refer to the existing mode and is not repeated herein. In addition, the user may be analyzed for characteristics based on the user's basic information (e.g., gender, age, constellation, geographic location, type of product being traded, etc.), and the analyzed characteristics may be added to the user representation.
And selecting part or all of the users to form the high-potential crowd according to the behavior habits, consumption habits, characteristics and the like of the users reflected by the user figures of the users.
In this embodiment, the high-potential crowd is determined by using the length of the association vector between each user and the product, or the high-potential crowd can be determined according to the user figure of each user, so that the characteristics of the user can be more accurately and comprehensively analyzed and obtained. The communication page is constructed aiming at the characteristics of the high-latency crowd and has strong pertinence, so that the user touch is improved, and the conversion rate is further improved.
With reference to fig. 1 and fig. 2, in an embodiment, in step C, the step of obtaining, from the e-commerce platform, the transaction conversion result of each user in the high-potential crowd on the e-commerce platform after pushing the first message may include steps S201 to S204, which are described in detail below.
Step S201, obtaining transaction data of each user in the high-potential crowd on the E-commerce platform for multiple times within preset time after the first message is pushed.
Wherein the transaction data is data generated by a user performing transaction-related operations on the e-commerce platform, which may include searching for products, collecting products, querying customer service, adding products to shopping carts, making payments, and the like.
During a preset time (e.g., within one month after the push) when the first message is pushed, the high potential crowd receiving the first message can be tracked, and the transaction data of the user receiving the first message can be acquired at intervals (e.g., every other day or week). The preset time and the interval of each acquisition of transaction data may be set as needed, and are not limited to the above examples.
Step S202, determining the transaction stage of each user in the transaction data acquired each time.
Step S203, constructing a transaction phase transition diagram of each user within the preset time.
And step S204, analyzing according to the stage circulation diagram to obtain a transaction conversion result of each user in a preset time.
In one non-limiting example, the entire operation may be divided into the following transaction phases: opportunity (O), cognition (a), Interest (I), Purchase (P), and Loyalty (L). The user who does not perform any sub-operation on the execution platform may be determined as an "O" stage, the user who browses the product may be determined as an "a" stage, the user who collects the product, adds the product to a shopping cart, and inquires about the product about customer service may be determined as an "I" stage, the user who purchases the product may be determined as a "P" stage, and the user who purchases the product several times or purchases the product of the same brand several times may be determined as an "L" stage.
The transaction stage flow chart comprises each transaction stage of the user in the whole transaction operation process and the flow relation of different transaction stages in time sequence, the stage of each user can be judged according to the operation corresponding to the transaction data acquired by each user each time, and the transaction stage flow chart is constructed for each target user. Continuing with the above example, user A's transaction phase flow is mapped to "O- > A- > P" and user B's transaction phase flow is mapped to "O- > A- > I- > P". The trading stage transition map scores of the users can be evaluated, so that the trading transition result of each user in a preset time is quantified.
In this embodiment, after the first message is pushed, the transaction data of the high-potential crowd on the e-commerce platform is acquired, the transaction stages of the users in the whole transaction process at different time points are analyzed, and a transaction stage flow diagram (which may include the flow relationship of each transaction stage) is constructed, for example, the transaction stage flow diagram may be constructed according to the operation of each user receiving the first message on the e-commerce platform. The transaction conversion result obtained by the method contains the circulation relation of the user in each stage in the whole transaction process, so that the transaction conversion result is more comprehensive and accurate, the priority ranking is carried out based on the transaction conversion result, the ranking result is more accurate, the selection of target crowds or seed crowds with higher association degree with products is facilitated, and the updating of the communication page is more targeted.
The target population may be determined in various ways, and in a non-limiting example, the target population may be selected from the sorted high-potential populations according to priority, and the user with the priority higher than a preset level is selected as the target population. In another non-limiting example, the target group may also be determined according to the cost of message pushing, which may specifically include: obtaining a target cost (for example, an upper cost limit or a cost range of the message pushing) of the current releasing; and obtaining the scale of the target population according to the target cost, and selecting the target population from the high-potential population after the priority ranking according to the scale.
In one embodiment, referring to fig. 3, the communication page is constructed in a manner that:
step S301, acquiring a current crowd corresponding to the communication page, and acquiring a user portrait of each user in the current crowd; wherein the current population comprises a high-latency population and a target population.
Step S302, extracting material commonalities of the current crowd according to the user portrait of each user in the current crowd;
step S303, obtaining corresponding materials according to the material commonality, and generating a communication page according to the selected materials.
Aiming at the communication pages included in the first message and the second message, the communication pages are respectively established according to the high-potential crowd and the seed crowd. Taking the communication page included in the first message as an example, the construction method includes: the method comprises the steps of obtaining a user portrait of each user in the high-potential crowd, and extracting characteristics used for selecting materials from the obtained user portrait to obtain material commonalities of the high-potential crowd. Optionally, the characteristics of the materials which accord with the preference of most people in the high-potential crowd can be extracted as the commonalities of the materials according to the information such as the corresponding geographic position, age, gender, consumption history and the like of the high-potential crowd.
More specifically, a material library may be pre-established, which includes various materials such as languages, graphics, and interface rendering styles used for constructing the communication page, so that corresponding materials may be selected from the material library according to commonality of the materials, and the communication page may be generated using the selected materials. The materials can also be designed according to the material commonality or the corresponding materials can be obtained by other modes.
In addition, if the updated communication page is constructed according to the characteristics of the seed population, the current population can also be referred to as the seed population.
In the embodiment, when the communication page is constructed, the user figures of the users in the high-potential crowd, the target crowd or the seed crowd are analyzed, the commonality of the materials is extracted, and the materials are selected according to the commonality of the extracted materials to construct or update the communication page. Because the selection of the materials is carried out according to the user figures of the high-potential crowd, the target crowd or the seed crowd, the generated or updated communication page is more targeted, the realization of efficient user touch is facilitated, and the pushing effect is improved.
With continuing reference to fig. 1, optionally, the message pushing method of this embodiment further includes: and responding to a re-pushing request, and jumping to the step C and re-executing the step C to the step E by taking the target crowd as the high-potential crowd.
After the secondary message pushing, the message pushing can be performed again according to the result of the secondary pushing, namely, the target crowd of the secondary pushing is taken as a high-potential crowd, the transaction conversion result of each user receiving the second message on the e-commerce platform is obtained from the e-commerce platform, and the target crowd is excavated again to perform the next pushing. Therefore, users who are possible to conduct transaction conversion can be more accurately touched, and the success rate of transaction conversion is improved.
Referring to fig. 4, fig. 4 is a flowchart illustrating another message pushing method according to an embodiment of the present invention. The method comprises the following steps S401 to S405, specifically:
step S401, mining high-potential crowds from a plurality of users by using a big data tool based on products and/or activities in history, constructing a crowd throwing frame, and designing a communication page according to the characteristics of the high-potential crowds; and carrying out first advertisement putting on the high-potential crowd, wherein the put advertisement comprises an access link of a communication page.
Specifically, when the user triggers the advertisement, the access link of the communication page is accessed. The crowd delivery framework comprises a platform (such as a video platform like an arcade, a shopping platform like a treasure and other platforms) for delivering advertisements to target crowds (in this case, high-potential crowds) to be delivered, delivery forms (such as open screen advertisements, patch advertisements, network messages, short messages, mails and the like) and the like.
Step S402, obtaining the transaction conversion results of all users in the high-potential crowd on the E-commerce platform from the E-commerce platform, carrying out priority ranking on the users in the high-potential crowd according to the transaction conversion results of all the users, and eliminating the users with the priority lower than the preset level in the high-potential crowd.
And S403, building a better crowd launching frame according to the size of the crowd launching the advertisement, the launching budget and the crowd scale involved in launching.
Step S404, selecting partial crowds with the highest priority from the high-potential crowds to form seed crowds, and designing a communication page according to the characteristics of the seed crowds or optimizing the communication page corresponding to the high-potential crowds.
And S405, selecting users with higher priorities from the high-potential crowd according to the better crowd launching frame to form a target crowd, and launching secondary advertisements to the target crowd.
Optionally, the target crowd is taken as the high-latency crowd, the step S402 is skipped to, and the step S402 to the step S405 are executed again to perform iterative optimized delivery.
It should be noted that, although the pushed message in the above embodiments is described by taking an advertisement as an example, those skilled in the art should understand that the pushed message is not limited to an advertisement, and may also be other content or type of message, such as information. In a variation, the pushed transaction may be an introduction of an information channel, an introduction of a wechat public number, and the like, and the corresponding transaction conversion operation may be a subscription of the information channel, a focus of the wechat public number, and the like, and the corresponding e-commerce platform may be an operation platform of the information channel, the wechat public number, and the like.
Referring to fig. 5, an embodiment of the present invention further provides a message pushing apparatus 50, where the apparatus 50 includes:
a high-potential crowd composition module 501, configured to execute step a, obtain information of a plurality of users from an e-commerce platform, select a part of users from the information of the plurality of users to form a high-potential crowd, and construct a communication page for the high-potential crowd;
a first pushing module 502, configured to execute step B, and push a first message to the high-potential crowd, where the first message includes an access link of the communication page;
a priority ranking module 503, configured to execute step C, after the first message is pushed, obtain, from the e-commerce platform, a transaction conversion result of each user in the high-potential crowd on the e-commerce platform, and perform priority ranking on the users in the high-potential crowd according to the transaction conversion result of each user;
a target crowd selecting module 504, configured to execute step D, select users from the high-potential crowd after the priority ranking to form a target crowd, and construct an updated communication page;
a second pushing module 505, configured to push a second message to the target crowd in step E, where the second message includes the access link of the updated communication page.
In one embodiment, said step C further comprises, after said step C: selecting users from the prioritized high-latency population to form a seed population, wherein the target population comprises the seed population; the constructing of the updated communication page includes: and constructing the updated communication page according to the seed crowd.
In one embodiment, the high-potential crowd composition module 501 is further configured to construct an association vector between each user and a product corresponding to the pushed message according to information of each user, where the association vector includes multiple association dimensions of the user and the product; and adding the users with the length of the association vector exceeding a preset value into the high-potential crowd.
In one embodiment, the high-latency crowd composition module 501 further includes: the user portrait acquisition unit is used for acquiring a user portrait of each user, and the user portrait is constructed according to the transaction history of the user on the E-commerce platform; and the user selection unit is used for selecting users with user figures meeting preset conditions to form the high-potential crowd.
In one embodiment, after the prioritization module 503 and before the seed population selection module 504, the message pushing apparatus 50 further includes: and the rejecting module is used for rejecting the users with the priority lower than the preset level in the high-potential crowd.
In one embodiment, the prioritization module 503 includes: the transaction data acquisition unit is used for acquiring transaction data of each user in the high-potential crowd on the E-commerce platform for multiple times within preset time after the first message is pushed; the transaction stage determining unit is used for determining the transaction stage of each user in the transaction data acquired each time; the transaction phase flow chart construction unit is used for constructing a transaction phase flow chart of each user within the preset time; and the transaction conversion result analysis unit is used for analyzing and obtaining the transaction conversion result of each user in the preset time according to the stage flow chart.
In one embodiment, the push module comprises: a target cost obtaining unit, configured to obtain a target cost of the current release; and the target crowd selecting unit is used for obtaining the scale of the target crowd according to the target cost and selecting the target crowd from the high-potential crowd after the priority ranking according to the scale.
In one embodiment, referring to fig. 3, the message pushing apparatus 50 further includes: the current crowd acquisition module is used for acquiring a current crowd corresponding to the communication page and acquiring a user portrait of each user in the current crowd; the material commonality extraction module is used for extracting the material commonality of the current crowd according to the user portrait of each user in the current crowd; the material selection module is used for acquiring corresponding materials according to the material commonality and generating a communication page according to the selected materials; wherein the current population comprises a high-latency population and a target population.
In one embodiment, the message pushing device 50 further includes: and the iteration optimization module is used for responding to the re-pushing request, taking the target crowd as the high-potential crowd, skipping to the step C and re-executing the step C to the step E.
Optionally, the message pushing includes advertisement pushing, and when the user triggers the pushed advertisement, the access link of the communication page is accessed.
For more details on the working principle and working manner of the message pushing apparatus, reference may be made to the above description of the message pushing method in fig. 1 to fig. 4, which is not repeated herein.
Further, the embodiment of the present invention also discloses a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program performs the steps of the message pushing method in the foregoing embodiment. For example, the steps of the message pushing method shown in fig. 1 to 4 described above may be performed.
Further, the embodiment of the present invention also discloses a computer device, which includes a memory and a processor, where the memory stores a computer program capable of running on the processor, and the processor executes the steps of the message pushing method in the foregoing embodiments when running the computer program. For example, the steps of the message pushing method shown in fig. 1 to 4 described above may be performed. The computer device may be various terminal devices with computing capabilities, such as a server, a Personal Computer (PC), a smartphone, a tablet, etc.
Specifically, in the embodiment of the present invention, the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will also be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example and not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (enhanced SDRAM), SDRAM (SLDRAM), synchlink DRAM (SLDRAM), and direct bus RAM (DR RAM).
It should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this document indicates that the former and latter related objects are in an "or" relationship.
The "plurality" appearing in the embodiments of the present application means two or more.
The descriptions of the first, second, etc. appearing in the embodiments of the present application are only for illustrating and differentiating the objects, and do not represent the order or the particular limitation of the number of the devices in the embodiments of the present application, and do not constitute any limitation to the embodiments of the present application.
The term "connect" in the embodiments of the present application refers to various connection manners, such as direct connection or indirect connection, to implement communication between devices, which is not limited in this embodiment of the present application.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (13)
1. A message pushing method, the method comprising:
step A, acquiring information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd;
step B, pushing a first message to the high-potential crowd, wherein the first message comprises an access link of the communication page;
step C, after the first message is pushed, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform, and carrying out priority sequencing on the users in the high-potential crowd according to the transaction conversion result of each user;
d, selecting users from the high-potential crowds after the priority ranking to form a target crowd, and constructing an updated communication page;
and E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page.
2. The method of claim 1, further comprising, after step C:
selecting users from the prioritized high-latency population to form a seed population, wherein the target population comprises the seed population;
the constructing of the updated communication page includes:
and constructing the updated communication page according to the seed crowd.
3. The method of claim 1, wherein the selecting the portion of users from the information of the plurality of users comprises a high-latency group, comprising:
constructing an association vector between each user and a product corresponding to the pushed message according to the information of each user, wherein the association vector comprises a plurality of association dimensions of the user and the product;
and adding the users with the length of the association vector exceeding a preset value into the high-potential crowd.
4. The method of claim 1, wherein the selecting the portion of users from the information of the plurality of users comprises a high-latency group, further comprising:
acquiring a user portrait of each user, wherein the user portrait is constructed according to the transaction history of the user on the E-commerce platform;
and selecting users with user figures meeting preset conditions to form the high-potential crowd.
5. The method of any one of claims 1 to 4, wherein after step C and before step D, further comprising:
and eliminating users with the priority lower than a preset level in the high-potential crowd.
6. The method according to any one of claims 1 to 4, wherein the obtaining, from the e-commerce platform, the transaction conversion result of each user in the high-potential crowd at the e-commerce platform after the first message is pushed comprises:
within a preset time after the first message is pushed, transaction data of each user in the high-potential crowd on the E-commerce platform are obtained for multiple times;
determining the transaction stage of each user in the transaction data acquired each time;
constructing a transaction stage flow chart of each user in the preset time;
and analyzing according to the stage circulation diagram to obtain a transaction conversion result of each user in a preset time.
7. The method according to any one of claims 1 to 4, wherein the selecting users from the prioritized high-latency population to form a target population comprises:
obtaining the target cost of the current release;
and obtaining the scale of the target population according to the target cost, and selecting the target population from the high-potential population after the priority ranking according to the scale.
8. The method according to any one of claims 1 to 4, wherein the communication page is constructed in a manner including:
acquiring a current crowd corresponding to the communication page, and acquiring a user portrait of each user in the current crowd;
extracting material commonalities of the current crowd according to the user portrait of each user in the current crowd;
acquiring corresponding materials according to the material commonality, and generating a communication page according to the selected materials;
wherein the current population comprises a high-latency population and a target population.
9. The method of any of claims 1 to 4, further comprising: in response to the push request again, the server,
and C, taking the target crowd as the high-latency crowd, skipping to the step C and re-executing the step C to the step E.
10. The method of claim 1, wherein the message push comprises an advertisement push, and wherein the access link of the communication page is accessed when a user triggers the pushed advertisement.
11. A message push apparatus, the apparatus comprising:
the high-potential crowd composition module is used for executing the step A, acquiring information of a plurality of users from an e-commerce platform, selecting part of users from the information of the plurality of users to form a high-potential crowd, and constructing a communication page aiming at the high-potential crowd;
a first pushing module, configured to execute step B, and push a first message to the high-potential crowd, where the first message includes an access link of the communication page;
the priority ranking module is used for executing the step C, obtaining the transaction conversion result of each user in the high-potential crowd on the E-commerce platform from the E-commerce platform after the first message is pushed, and ranking the priority of the users in the high-potential crowd according to the transaction conversion result of each user;
the target crowd selecting module is used for executing the step D, selecting users from the high-potential crowd after the priority ranking to form a target crowd, and constructing an updated communication page;
and E, pushing a second message to the target crowd, wherein the second message comprises the access link of the updated communication page.
12. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, realizing the steps of the method according to any of the claims 1 to 10.
13. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 10 when executing the computer program.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2021102718863 | 2021-03-12 | ||
| CN202110271886 | 2021-03-12 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113095886A true CN113095886A (en) | 2021-07-09 |
| CN113095886B CN113095886B (en) | 2023-03-24 |
Family
ID=76679771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110443191.9A Active CN113095886B (en) | 2021-03-12 | 2021-04-23 | Message pushing method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095886B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116846967A (en) * | 2023-08-30 | 2023-10-03 | 苏州盈天地资讯科技有限公司 | Quick pushing method, device and equipment for millions of user messages |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451869A (en) * | 2017-08-07 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107979632A (en) * | 2016-10-25 | 2018-05-01 | 腾讯科技（北京）有限公司 | The processing method of pushed information, apparatus and system |
| CN109300012A (en) * | 2018-10-19 | 2019-02-01 | 中国平安人寿保险股份有限公司 | Product data method for pushing, device, computer equipment and storage medium |
| CN109859002A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | Product method for pushing, device, computer equipment and storage medium |
| CN109858273A (en) * | 2018-11-26 | 2019-06-07 | 平安科技（深圳）有限公司 | Obtaining product information method, apparatus, computer equipment and storage medium |
| CN110097251A (en) * | 2019-02-01 | 2019-08-06 | 北京三快在线科技有限公司 | Product data processing method and processing device, the supply of material method and device, electronic equipment |
| WO2020024555A1 (en) * | 2018-07-31 | 2020-02-06 | 深圳春沐源控股有限公司 | Commodity information push method, related device and storage medium |
| CN110866791A (en) * | 2019-11-25 | 2020-03-06 | 恩亿科(北京)数据科技有限公司 | Commodity pushing method and device, storage medium and electronic equipment |
| US20200320609A1 (en) * | 2019-04-08 | 2020-10-08 | Toshiba Tec Kabushiki Kaisha | Method and system for providing personalized recommendations in real-time |
| CN112070532A (en) * | 2020-08-27 | 2020-12-11 | 中国平安财产保险股份有限公司 | Information pushing method, device, equipment and storage medium |
-
2021
- 2021-04-23 CN CN202110443191.9A patent/CN113095886B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107979632A (en) * | 2016-10-25 | 2018-05-01 | 腾讯科技（北京）有限公司 | The processing method of pushed information, apparatus and system |
| CN107451869A (en) * | 2017-08-07 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| WO2020024555A1 (en) * | 2018-07-31 | 2020-02-06 | 深圳春沐源控股有限公司 | Commodity information push method, related device and storage medium |
| CN109300012A (en) * | 2018-10-19 | 2019-02-01 | 中国平安人寿保险股份有限公司 | Product data method for pushing, device, computer equipment and storage medium |
| CN109858273A (en) * | 2018-11-26 | 2019-06-07 | 平安科技（深圳）有限公司 | Obtaining product information method, apparatus, computer equipment and storage medium |
| CN109859002A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | Product method for pushing, device, computer equipment and storage medium |
| CN110097251A (en) * | 2019-02-01 | 2019-08-06 | 北京三快在线科技有限公司 | Product data processing method and processing device, the supply of material method and device, electronic equipment |
| US20200320609A1 (en) * | 2019-04-08 | 2020-10-08 | Toshiba Tec Kabushiki Kaisha | Method and system for providing personalized recommendations in real-time |
| CN110866791A (en) * | 2019-11-25 | 2020-03-06 | 恩亿科(北京)数据科技有限公司 | Commodity pushing method and device, storage medium and electronic equipment |
| CN112070532A (en) * | 2020-08-27 | 2020-12-11 | 中国平安财产保险股份有限公司 | Information pushing method, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116846967A (en) * | 2023-08-30 | 2023-10-03 | 苏州盈天地资讯科技有限公司 | Quick pushing method, device and equipment for millions of user messages |
| CN116846967B (en) * | 2023-08-30 | 2023-12-05 | 苏州盈天地资讯科技有限公司 | Quick pushing method, device and equipment for millions of user messages |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113095886B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200117675A1 (en) | Obtaining of Recommendation Information | |
| US20220114199A1 (en) | System and method for information recommendation | |
| CA2700030C (en) | Touchpoint customization system | |
| CN108205768B (en) | Database establishing method, data recommending device, equipment and storage medium | |
| CN103164804B (en) | The information-pushing method of a kind of personalization and device | |
| US7937403B2 (en) | Time-based analysis of related keyword searching | |
| US20180374141A1 (en) | Information pushing method and system | |
| CN107590675A (en) | A kind of recognition methods of user's Shopping Behaviors, storage facilities and mobile terminal based on big data | |
| US20150356658A1 (en) | Systems And Methods For Serving Product Recommendations | |
| WO2020043001A1 (en) | Advertisement placement method, method for determining popularization population, server, and terminal | |
| WO2022095701A1 (en) | Method and device for recommending objects, equipment, and storage medium | |
| CN111767466A (en) | Recommendation information recommendation method and device based on artificial intelligence and electronic equipment | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
| CN111767458A (en) | Information pushing method, device, system and storage medium | |
| CN113095886B (en) | Message pushing method and device, storage medium and computer equipment | |
| JP2012150563A (en) | Product recommendation device, method, and program | |
| CN114493786A (en) | Information recommendation method and device | |
| CN111787042B (en) | Method and device for pushing information | |
| CN110209944B (en) | Stock analyst recommendation method and device, computer equipment and storage medium | |
| CN111582901A (en) | Method, device and system for quantizing display link effect and storage medium | |
| CN113704630B (en) | Information pushing method and device, readable storage medium and electronic equipment | |
| CN113781171A (en) | Information pushing method, device, equipment and storage medium | |
| CN112925982B (en) | User redirection method and device, storage medium and computer equipment | |
| KR101985603B1 (en) | Recommendation method based on tripartite graph |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |