Method, device, electronic device and storage medium for pushing marketing information

Abstract

The present application provides a method, apparatus, electronic device, and storage medium for pushing marketing information. In the method for pushing marketing information, user information of a user to be pushed is obtained. Based on the user information, user tags of the user to be pushed are found from a pre-constructed user tag library. Based on the user tags, merchant tags associated with the user tags are found from a pre-constructed user-merchant association relationship library. The push type of the user to be pushed is determined, and merchant tags of pushable merchants are filtered out from the merchant tags based on the push type. Marketing information of merchants corresponding to the merchant tags of pushable merchants is obtained, and the marketing information is sent to the user to be pushed. By accurately depicting user portrait tags, generating merchant tags, and analyzing the correlation between users and merchants, user information resources and merchant resources are integrated to accurately push marketing resources to users, thereby achieving precise marketing for users and at the same time playing a role in attracting customers for merchants.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular, to a method, device, electronic device, and storage medium for pushing marketing information. Background Art

[0002] With the intensification of market competition, extensive subsidy preferences and universal marketing means can no longer meet the current needs of market marketing. Therefore, targeted marketing information needs to be pushed to customers in order to achieve precise marketing, so as to better explore customers and promote business.

[0003] In the prior art, usually only the description of the user portrait is considered, and the user portrait is obtained by analyzing the basic information, preferences, etc. of the user. However, relying solely on the user portrait cannot accurately match users and merchants, and the purpose of precise marketing cannot be achieved. Summary of the Invention

[0004] In view of this, this application provides a method, device, electronic device, and storage medium for pushing marketing information to solve the problem in the prior art that usually only the description of the user portrait is considered, and the user portrait is obtained by analyzing the basic information, preferences, etc. of the user. However, relying solely on the user portrait cannot accurately match users and merchants to achieve precise marketing.

[0005] To achieve the above object, this application provides the following technical solutions:

[0006] The first aspect of this application discloses a method for pushing marketing information, including:

[0007] Obtain the user information of the user to be pushed;

[0008] Based on the user information, find the user tags of the user to be pushed from the pre-constructed user tag library;

[0009] Based on the user tags, find the merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library;

[0010] Determine the push type of the user to be pushed, and based on the push type, screen out the merchant tags of the merchants that can be pushed from the merchant tags, where the push type includes real-time push and regular push;

[0011] Obtain the marketing information of the merchants corresponding to the merchant tags of the merchants that can be pushed, and send the marketing information to the user to be pushed.

[0012] Optionally, in the above method, the construction process of the user tag library includes:

[0013] Collect the user information of users;

[0014] Perform data verification on the collected user information to obtain user information that passes the data verification;

[0015] Perform data cleaning on the user information that passes the data verification to obtain the cleaned user information;

[0016] Generate user tags based on the cleaned user information and save them to the user tag library.

[0017] Optionally, for the above method, determining the push type of the user to be pushed, and screening out merchant tags of merchants that can be pushed from the merchant tags based on the push type, includes:

[0018] If the push type of the user to be pushed is real-time push, input the user tags and the found merchant tags into a pre-constructed correlation model to obtain merchant tags of merchants that can be pushed;

[0019] If the push type of the user to be pushed is regular push, use all the found merchant tags as merchant tags of merchants that can be pushed.

[0020] Optionally, for the above method, obtaining the marketing information of the merchants corresponding to the merchant tags associated with the user tags and sending the marketing information to the user to be pushed, includes:

[0021] Obtain the merchant scores of the merchants corresponding to the merchant tags associated with the user tags;

[0022] Screen out the merchants whose merchant scores meet the preset conditions;

[0023] Obtain the marketing information of the screened merchants and send the marketing information to the user to be pushed.

[0024] The second aspect of this application discloses a marketing information push device, including:

[0025] An acquisition unit, configured to acquire user information of a user to be pushed;

[0026] A first search unit, configured to search for the user tags of the user to be pushed from a pre-constructed user tag library based on the user information;

[0027] A second search unit, configured to search for merchant tags associated with the user tags from a pre-constructed user-merchant association relationship library based on the user tags;

[0028] A determination unit, configured to determine the push type of the user to be pushed, and screen out the merchant tags of the merchants that can be pushed from the merchant tags based on the push type, where the push type includes real-time push and regular push;

[0029] A push unit, configured to obtain the marketing information of the merchants corresponding to the merchant tags of the merchants that can be pushed, and send the marketing information to the user to be pushed.

[0030] Optionally, for the above device, the first search unit includes:

[0031] An acquisition subunit, configured to acquire the user information of the user;

[0032] A verification subunit, configured to perform data verification on the acquired user information to obtain the user information that passes the data verification;

[0033] A data cleaning subunit, configured to perform data cleaning on the user information that passes the data verification to obtain the cleaned user information;

[0034] A label generation subunit, configured to generate user labels based on the cleaned user information and save them to the user label library.

[0035] Optionally, for the above device, the determination unit includes:

[0036] A first determination subunit, configured to, if the push type of the user to be pushed is real-time push, input the user labels and the found merchant tags into a pre-constructed correlation model to obtain the merchant tags of the merchants that can be pushed;

[0037] A second determination subunit, configured to, if the push type of the user to be pushed is regular push, use all the found merchant tags as the merchant tags of the merchants that can be pushed.

[0038] Optionally, for the above device, the push unit includes:

[0039] An acquisition subunit, configured to obtain the merchant scores of the merchants corresponding to the merchant tags associated with the user labels;

[0040] A screening subunit, configured to screen out the merchants whose merchant scores meet the preset conditions;

[0041] A push subunit, configured to obtain the marketing information of the screened merchants and send the marketing information to the user to be pushed.

[0042] A third aspect of the present application discloses an electronic device, including:

[0043] One or more processors;

[0044] A storage device on which one or more programs are stored;

[0045] When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method described in any one of the first aspects of the present application.

[0046] A fourth aspect of the present application discloses a computer storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any one of the first aspects of the present application is implemented.

[0047] As can be seen from the above technical solutions, in a method for pushing marketing information provided by the present application, user information of a user to be pushed is obtained. Based on the user information, user tags of the user to be pushed are retrieved from a pre-constructed user tag library. Based on the user tags, merchant tags associated with the user tags are retrieved from a pre-constructed user-merchant association relationship library. A push type of the user to be pushed is determined, and merchant tags of pushable merchants are filtered out from the merchant tags based on the push type, where the push type includes real-time push and periodic push. Marketing information of merchants corresponding to the merchant tags of the pushable merchants is obtained, and the marketing information is sent to the user to be pushed. It can be seen that by using the method of the present application, through the accurate description of user portrait tags, the generation of merchant tags, and the analysis of the correlation between users and merchants, the user information resources and merchant resources are integrated, and marketing resources are accurately pushed to users, so as to achieve precise marketing of users and at the same time play a role in attracting customers for merchants. It solves the problem in the prior art that usually only the description of the user portrait is considered, and the user portrait is obtained by analyzing the basic information, preferences, etc. of the user. However, based on the user portrait alone, users and merchants cannot be accurately matched to achieve precise marketing. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0049] Figure 1 It is a flowchart of a method for pushing marketing information disclosed in another embodiment of the present application;

[0050] Figure 2 It is a flowchart of an implementation manner of step S102 disclosed in another embodiment of the present application;

[0051] Figure 3Schematic diagram of a marketing information push device disclosed in another embodiment of the present application;

[0052] Figure 4 Schematic diagram of an electronic device disclosed in another embodiment of the present application. Detailed implementation manners

[0053] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0054] In the present application, the term "including", "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0055] Moreover, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0056] The embodiment of the present application provides a method for pushing marketing information, specifically as Figure 1 shown, including:

[0057] S101. Obtain the user information of the user to be pushed.

[0058] It should be noted that when it is necessary to push the marketing information of the merchant to the user, first obtain the user information of the user to be pushed, including information such as the user name and user age.

[0059] S102. Based on the user information, find out the user tags of the user to be pushed from the pre-constructed user tag library.

[0060] It should be noted that after obtaining the user information of the user to be pushed, then based on the user information, find out the user tags of the user to be pushed from the pre-constructed user tag library. Among them, the user tag library is constructed through the pre-collected user information.

[0061] Optionally, in another embodiment of the present application, the construction process of the user tag library in step S102 is as Figure 2 shown, and may include:

[0062] S201. Collect user information of the user.

[0063] It should be noted that first, determine the data source of the user information, establish a user data preparation server for each data source, deploy a data collection program on the data source, and collect the user information on the data source into the user data preparation server through the data collection program, and upload it to the cloud server for storage. The data transmission uses the secure transfer protocol SFTP. If the data source is the user information stored in the FTP server, ensure the security of sensitive user data. Among them, the user information can be collected through the user's reserved information, the user's transaction information, and the data open source interface provided by the cooperation partner.

[0064] S202. Perform data verification on the collected user information to obtain the user information that passes the data verification.

[0065] It should be noted that establish a data verification microservice, perform data verification on the collected user information to determine whether the user information on the cloud server is valid, and obtain the user information that passes the data verification.

[0066] S203. Perform data cleaning on the user information that passes the data verification to obtain the cleaned user information.

[0067] It should be noted that after obtaining the user information that passes the data verification, perform data cleaning on the user information that passes the data verification, filter out useless information, and obtain the cleaned user information.

[0068] S204. Generate user tags based on the cleaned user information and save them to the user tag library.

[0069] It should be noted that for each user, generate user tags based on the cleaned user information and save them to the user tag library for storage.

[0070] S103. Based on the user tags, search for merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library.

[0071] It should be noted that based on the user tags, merchant tags associated with the user tags are retrieved from a pre-constructed user-merchant association relationship library. Among them, the user-merchant association relationship library is obtained by periodically configuring the matching relationship between all user tags and merchant tags, and manual operation or relevance analysis of user tags and merchant tags based on the user's historical behavior can be adopted. For example, according to the user's past behavior data, the degree of association between user tags and merchant tags is found, and through the matching degree of user tags and merchant tags, the user tag and merchant tag association relationship with the highest matching degree is determined.

[0072] It should also be noted that merchant tags are stored in a pre-constructed merchant tag library. The construction process of the merchant tag library can refer to the construction process of the above-mentioned user tag library, which will not be elaborated here.

[0073] S104. Determine the push type of the user to be pushed, and screen out the merchant tags of the merchants that can be pushed from the merchant tags based on the push type, where the push type includes real-time push and regular push.

[0074] It should be noted that after retrieving the merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library, the push type of the user to be pushed is further determined. Among them, the push type of the user to be pushed includes real-time push and regular push. Real-time push is the situation where, through real-time stream data, it is triggered by the user's real-time operation behavior and pushed to the user in real time. For example, the user actively clicks the push request of the marketing information. Regular push is to push marketing information to the user regularly according to a preset time period. Then, based on the push type, the merchant tags of the merchants that can be pushed are screened out from the merchant tags.

[0075] Optionally, in another embodiment of the present application, an implementation manner of step S104 may include:

[0076] If the push type of the user to be pushed is real-time push, the user tags and the retrieved merchant tags are input into a pre-constructed correlation model to obtain the merchant tags of the merchants that can be pushed.

[0077] If the push type of the user to be pushed is regular push, all the retrieved merchant tags are used as the merchant tags of the merchants that can be pushed.

[0078] It should be noted that if the push type of the user to be pushed is real-time push, the user tags and the retrieved merchant tags are input into a pre-constructed correlation model to obtain the merchant tags of the merchants that can be pushed. Among them, the correlation model includes a dummy variable penalty term and adaptively adjusts the model parameters according to the marketing effect. The form of the model function is as follows:

[0079]

[0080] where C ij is the correlation coefficient between the i-th user label and the j-th merchant label. X i , Y i are the values of the user label i and the merchant label j respectively. σ is a dummy variable with a value of f(Dis) is a function with distance as the independent variable and is used as a penalty term. When the merchant is an offline merchant, a penalty term of -σ·f(Dis) is constructed according to the distance from the user to optimize the overall scoring function. Usually, f(Dis) is a non-linear function, which grows relatively gently within a small range and increases sharply when exceeding the threshold, thereby filtering out offline merchants that are too far from the user. Online merchants are not affected by this item. For example, according to the user's real-time behavior, geographical information and other information, calculate F score , determine the cooperative merchants with a relatively high matching degree, and conduct real-time marketing for the user based on this.

[0081] If the push type of the user to be pushed is regular push, then all the merchant labels found will be used as the merchant labels of the pushable merchants. For example, within a certain period, the user labels and merchant labels of existing users are regularly matched to obtain the merchants suitable for each user for precise marketing.

[0082] S105. Obtain the marketing information of the merchants corresponding to the merchant labels of the pushable merchants, and send the marketing information to the user to be pushed.

[0083] It should be noted that after screening out the merchant labels of the pushable merchants, obtain the marketing information of the merchants corresponding to the merchant labels of the pushable merchants, and send the marketing information to the user to be pushed. For example, push the preferential content of the pushable merchants to the user through channels such as text messages and mini-programs. After the user logs in to the mini-program or mobile APP to operate, they can enjoy the preferential treatment of the merchant.

[0084] Optionally, in another embodiment of the present application, an implementation manner of step 105 may include:

[0085] Obtain the merchant scores of the merchants corresponding to the merchant labels associated with the user labels.

[0086] Screen out the merchants whose merchant scores meet the preset conditions.

[0087] Obtain the marketing information of the screened merchants, and send the marketing information to the user to be pushed.

[0088] It should be noted that when pushing marketing information, in order to improve the quality of message pushing, first obtain the merchant ratings of the merchants corresponding to the merchant tags associated with the user tags, and screen out the merchants whose merchant ratings meet the preset conditions. For example, screen out the top 50 merchants with the highest ratings. Then obtain the marketing information of the screened merchants and push the marketing information to the users through channels such as text messages and mini-programs for the users to be pushed.

[0089] In a method for pushing marketing information provided by an embodiment of the present application, obtain the user information of the user to be pushed. Based on the user information, find out the user tags of the user to be pushed from the pre-constructed user tag library. Based on the user tags, find out the merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library. Determine the push type of the user to be pushed, and based on the push type, screen out the merchant tags of the pushable merchants from the merchant tags, where the push type includes real-time push and regular push. Obtain the marketing information of the merchants corresponding to the merchant tags of the pushable merchants and send the marketing information to the user to be pushed. It can be seen that by using the method of the present application, through the accurate description of the user portrait tags, the generation of merchant tags, and the analysis of the correlation between users and merchants, the user information resources and merchant resources are integrated, and marketing resources are accurately pushed to users, so as to achieve precise marketing of users and at the same time play a role in attracting customers for merchants. It solves the problem in the prior art that usually only the description of the user portrait is considered, and the user portrait is obtained by analyzing the basic information, preferences, etc. of the user. However, based on the user portrait alone, users and merchants cannot be accurately matched to achieve precise marketing.

[0090] Optionally, in another embodiment of the present application, a marketing information push device is also provided, specifically as Figure 3 shown, including:

[0091] An obtaining unit 301, configured to obtain the user information of the user to be pushed.

[0092] A first searching unit 302, configured to find out the user tags of the user to be pushed from the pre-constructed user tag library based on the user information.

[0093] A second searching unit 303, configured to find out the merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library based on the user tags.

[0094] A determining unit 304, configured to determine the push type of the user to be pushed, and screen out the merchant tags of the pushable merchants from the merchant tags based on the push type, where the push type includes real-time push and regular push.

[0095] A push unit 305, configured to obtain marketing information of merchants corresponding to merchant tags of pushable merchants, and send the marketing information to users to be pushed.

[0096] In this embodiment, for the specific execution processes of the obtaining unit 301, the first searching unit 302, the second searching unit 303, the determining unit 304, and the push unit 305, reference may be made to the content of the corresponding Figure 1 method embodiment, which will not be elaborated herein.

[0097] In a marketing information push device provided by an embodiment of the present application, an obtaining unit 301 obtains user information of a user to be pushed. A first searching unit 302, based on the user information, searches for user tags of the user to be pushed from a pre-constructed user tag library. A second searching unit 303, based on the user tags, searches for merchant tags associated with the user tags from a pre-constructed user-merchant association relationship library. A determining unit 304 determines a push type of the user to be pushed, and filters out merchant tags of pushable merchants from the merchant tags based on the push type, where the push type includes real-time push and periodic push. A push unit 305 obtains marketing information of merchants corresponding to the merchant tags of the pushable merchants, and sends the marketing information to the users to be pushed. It can be seen that by using the method of the present application, through the accurate description of user portrait tags, the generation of merchant tags, and the analysis of the correlation between users and merchants, user information resources and merchant resources are integrated, and marketing resources are accurately pushed to users, so as to achieve precise marketing of users and at the same time play a role in attracting customers for merchants. It solves the problem in the prior art that usually only the description of the user portrait is considered, and the user portrait is obtained by analyzing the basic information, preferences, etc. of the user. However, relying solely on the user portrait cannot accurately match users and merchants to achieve precise marketing.

[0098] Optionally, in another embodiment of the present application, an implementation manner of the above optimization unit 203 may include:

[0099] An acquisition subunit, configured to acquire user information of a user.

[0100] A verification subunit, configured to perform data verification on the acquired user information to obtain user information that passes the data verification.

[0101] A data cleaning subunit, configured to perform data cleaning on the user information that passes the data verification to obtain the cleaned user information.

[0102] A tag generation subunit, configured to generate user tags based on the cleaned user information and save them to the user tag library.

[0103] In this embodiment, for the specific execution processes of the acquisition subunit, the verification subunit, the data cleaning subunit, and the tag generation subunit, reference may be made to the correspondingFigure 2 The content of the method embodiment will not be elaborated here.

[0104] Optionally, in another embodiment of the present application, an implementation manner of the above-mentioned determining unit 304 may include:

[0105] A first determining subunit, configured to input the user label and the found merchant label into a pre-constructed correlation model if the push type of the user to be pushed is real-time push, so as to obtain the merchant label of the merchant that can be pushed.

[0106] A second determining subunit, configured to use all the found merchant labels as the merchant labels of the merchants that can be pushed if the push type of the user to be pushed is periodic push.

[0107] In this embodiment, for the specific execution processes of the first determining subunit and the second determining subunit, reference may be made to the content of the corresponding method embodiment above, which will not be elaborated here.

[0108] Optionally, in another embodiment of the present application, an implementation manner of the above-mentioned pushing unit 305 may include:

[0109] An obtaining subunit, configured to obtain the merchant score of the merchant corresponding to the merchant label associated with the user label.

[0110] A screening subunit, configured to screen out the merchants whose merchant scores meet the preset conditions.

[0111] A pushing subunit, configured to obtain the marketing information of the screened merchants and send the marketing information to the user to be pushed.

[0112] In this embodiment, for the specific execution processes of the obtaining subunit, the screening subunit, and the pushing subunit, reference may be made to the content of the corresponding method embodiment above, which will not be elaborated here.

[0113] Another embodiment of the present application further provides an electronic device, as Figure 4 shown, specifically including:

[0114] One or more processors 401.

[0115] A storage device 402, on which one or more programs are stored.

[0116] When one or more programs are executed by one or more processors 401, the one or more processors 401 are caused to implement any one of the methods in the above embodiments.

[0117] Another embodiment of the present application further provides a computer storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, any one of the methods in the above embodiments is implemented.

[0118] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for a system or system embodiment, since it is basically similar to a method embodiment, the description is relatively simple, and reference can be made to the corresponding part of the method embodiment for the relevant content. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0119] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0120] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for pushing marketing information, characterized in that, including: Obtain the user information of the user to be pushed; Based on the user information, find out the user tags of the user to be pushed from the pre-constructed user tag library; Based on the user tags, find out the merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library; Determine the push type of the user to be pushed, and filter out the merchant tags of the merchants that can be pushed from the merchant tags based on the push type, where the push type includes real-time push and regular push; Obtain the marketing information of the merchants corresponding to the merchant tags of the merchants that can be pushed, and send the marketing information to the user to be pushed; Among them, the determining the push type of the user to be pushed, and filtering out the merchant tags of the merchants that can be pushed from the merchant tags based on the push type includes: If the push type of the user to be pushed is real-time push, input the user tags and the found merchant tags into the pre-constructed association degree model to obtain the merchant tags of the merchants that can be pushed; among them, the association degree model is a model constructed according to user tags, merchant tags, the correlation coefficient between user tags and merchant tags, dummy variables, and distance functions, and the association degree model is used to further calculate the matching degree between users and merchants; If the push type of the user to be pushed is regular push, use all the found merchant tags as the merchant tags of the merchants that can be pushed.

2. The method according to claim 1, characterized in that, The construction process of the user tag library includes: Collect the user information of users; Perform data verification on the collected user information to obtain user information that passes the data verification; Perform data cleaning on the user information that passes the data verification to obtain the cleaned user information; Generate user tags based on the cleaned user information and save them to the user tag library.

3. The method according to claim 1, characterized in that, The obtaining the marketing information of the merchants corresponding to the merchant tags of the merchants that can be pushed, and sending the marketing information to the user to be pushed includes: Obtain the merchant scores of the merchants corresponding to the merchant tags associated with the user tags; Filter out the merchants whose merchant scores meet the preset conditions; Obtain the marketing information of the filtered merchants, and send the marketing information to the user to be pushed.

4. A device for pushing marketing information, characterized in that, including: An obtaining unit, configured to obtain the user information of the user to be pushed; A first searching unit, configured to find out the user tags of the user to be pushed from the pre-constructed user tag library based on the user information; A second searching unit, configured to find out the merchant tags associated with the user tags from the pre-constructed user-merchant association relationship library based on the user tags; A determining unit, configured to determine the push type of the user to be pushed, and filter out the merchant tags of the merchants that can be pushed from the merchant tags based on the push type, where the push type includes real-time push and regular push; A pushing unit, configured to obtain the marketing information of the merchants corresponding to the merchant tags of the merchants that can be pushed, and send the marketing information to the user to be pushed; Wherein, the determining unit is further configured to, if the push type of the user to be pushed is real-time push, input the user tag and the found merchant tag into a pre-constructed correlation model to obtain the merchant tag of the merchant that can be pushed; wherein, the correlation model is a model constructed based on user tags, merchant tags, the correlation coefficient between user tags and merchant tags, dummy variables, and distance functions, and the correlation model is used to further calculate the matching degree between the user and the merchant; If the push type of the user to be pushed is regular push, all the found merchant tags are used as the merchant tags of the merchant that can be pushed.

5. The device according to claim 4, characterized in that, The first search unit includes: An acquisition subunit, configured to acquire the user information of the user; A verification subunit, configured to perform data verification on the acquired user information to obtain the user information that passes the data verification; A data cleaning subunit, configured to perform data cleaning on the user information that passes the data verification to obtain the cleaned user information; A tag generation subunit, configured to generate user tags based on the cleaned user information and store them in the user tag library.

6. The device according to claim 4, characterized in that The push unit includes: An acquisition subunit, configured to acquire the merchant score of the merchant corresponding to the merchant tag associated with the user tag; A screening subunit, configured to screen out the merchants whose merchant scores meet the preset conditions; A push subunit, configured to acquire the marketing information of the screened merchants and send the marketing information to the user to be pushed.

7. An electronic device, characterized in that, Includes: One or more processors; A storage device, on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

8. A computer storage medium, characterized in that, On which a computer program is stored, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images