CN109245996B - Mail pushing method and device, computer equipment and storage medium - Google Patents
Mail pushing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109245996B CN109245996B CN201811089140.5A CN201811089140A CN109245996B CN 109245996 B CN109245996 B CN 109245996B CN 201811089140 A CN201811089140 A CN 201811089140A CN 109245996 B CN109245996 B CN 109245996B
- Authority
- CN
- China
- Prior art keywords
- product
- label
- push
- current
- pushing
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/42—Mailbox-related aspects, e.g. synchronisation of mailboxes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/214—Monitoring or handling of messages using selective forwarding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/226—Delivery according to priorities
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application relates to a data analysis technology and provides a mail pushing method, a mail pushing device, computer equipment and a storage medium. The method comprises the following steps: acquiring a label set corresponding to a current user and label weights corresponding to all labels in the label set, sorting the labels in the label set according to the label weights, and selecting a target label according to a label sorting result; acquiring a related product corresponding to the target label to obtain a related product set; acquiring the current push priority of each associated product in the associated product set corresponding to the target label; sorting the associated products in the associated product set according to the pushing priority, and selecting a target associated product according to a sorting result of the associated products; and generating a mail to be pushed according to the target associated product, and pushing the mail to be pushed. By adopting the method, the computer resources can be saved.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a method and an apparatus for pushing a mail, a computer device, and a storage medium.
Background
With the rapid development of internet technology, e-mail is widely used. As one of the communication tools, mail is often used by various large merchants as a marketing tool to market related products by sending product-related mail, such as advertisements, to customers.
In the traditional technology, product marketing is carried out by mails, and mails are often sent to a large number of mailbox users randomly, so that in order to improve the marketing success rate, a large number of mails need to be sent, and the waste of computer resources is caused.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a mail pushing method, apparatus, computer device and storage medium capable of saving computer resources in view of the above technical problems.
A mail pushing method, the method comprising:
acquiring a label set corresponding to a current user and label weights corresponding to all labels in the label set, sorting the labels in the label set according to the label weights, and selecting a target label according to a label sorting result;
acquiring a related product corresponding to the target label to obtain a related product set;
acquiring the current push priority of each associated product in the associated product set corresponding to the target label;
sorting the associated products in the associated product set according to the pushing priority, and selecting a target associated product according to a sorting result of the associated products;
and generating a mail to be pushed according to the target associated product, and pushing the mail to be pushed.
In one embodiment, before the obtaining of the tag set corresponding to the current user and the tag weight corresponding to each tag in the tag set, the method includes:
acquiring a mail set corresponding to the current user, and acquiring a mail template corresponding to the mail set;
acquiring a preset label corresponding to the mail template as a first type label;
extracting keywords from each mail to obtain a second type of label, and obtaining a label set corresponding to the current user according to the first type of label and the second type of label;
and calculating the label weight of each label in the label set by adopting a preset algorithm.
In one embodiment, before pushing the mail to be pushed, the pushing includes:
setting a buried point on a product page corresponding to the target associated product, wherein the buried point is used for acquiring the behavior data of the current user;
after the mail to be pushed is pushed, the method comprises the following steps:
and adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
In one embodiment, before obtaining the current push priority of each associated product in the associated product set corresponding to the target tag, the method includes:
acquiring a corresponding associated label of each product in a current product set;
acquiring push feedback data of each product in the current product set corresponding to the associated label;
and determining the current push priority of each product corresponding to the associated label according to the push feedback data. In one embodiment, the obtaining push feedback data corresponding to the associated tag for each product in the current product set includes:
acquiring a push user set corresponding to the associated label of each product in the current product set within a preset time period;
calculating a first quantity corresponding to all push users in the push user set and a second quantity corresponding to push users of a preset type in the push user set;
calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity;
the determining the current push priority of each product corresponding to its associated tag according to the push feedback data includes:
and determining the current push priority of each product corresponding to the associated label according to the push success rate.
In one embodiment, the obtaining push feedback data of each product in the current product set corresponding to its associated tag includes:
acquiring a push user set corresponding to the associated label of each product in the current product set within a preset time period;
acquiring a pushing score of each pushing user in the pushing user set;
calculating a total pushing score of each product corresponding to the associated label of each product according to the pushing score of each pushing user in the pushing user set;
the determining the current push priority of each product corresponding to its associated tag according to the push feedback data includes:
and determining the current push priority of each product corresponding to the associated label according to the push total score.
A mail pushing device, the device comprising:
the target label selecting module is used for acquiring a label set corresponding to a current user and label weights corresponding to all labels in the label set, sorting the labels in the label set according to the label weights and selecting a target label according to a label sorting result;
the related product acquisition module is used for acquiring related products corresponding to the target tags to obtain a related product set;
a current push priority obtaining module, configured to obtain a current push priority of each associated product in the associated product set, where the current push priority corresponds to the target tag;
the target associated product selection module is used for sorting the associated products in the associated product set according to the pushing priority and selecting the target associated products according to the sorting result of the associated products;
and the mail pushing module is used for generating a mail to be pushed according to the target associated product and pushing the mail to be pushed.
In one embodiment, the apparatus further comprises: the tag set generating module is used for acquiring a mail set corresponding to the current user and acquiring a mail template corresponding to the mail set; acquiring a preset label corresponding to the mail template as a first type label; extracting keywords from each mail to obtain a second type of label, and obtaining a label set corresponding to the current user according to the first type of label and the second type of label; and calculating the label weight of each label in the label set by adopting a preset algorithm.
A computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the mail pushing method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the mail pushing method described above.
According to the mail pushing method, the mail pushing device, the computer equipment and the storage medium, firstly, a label set corresponding to a current user and label weights corresponding to labels in the label set are obtained, the labels in the label set are sorted according to the label weights, a target label is selected according to a label sorting result, a related product corresponding to the target label is obtained, a related product set is obtained, a current pushing priority of each related product in the related product set corresponding to the target label is obtained, related products in the related product set are sorted according to the pushing priority, a target related product is selected according to a related product sorting result, a mail to be pushed is generated according to the target related product, and the mail to be pushed is pushed.
Drawings
FIG. 1 is a diagram of an application scenario of the email push method in one embodiment;
FIG. 2 is a flowchart illustrating a method for pushing an email in one embodiment;
FIG. 3 is a flowchart illustrating the mail pushing step S202 in one embodiment;
FIG. 4 is a block diagram illustrating an exemplary embodiment of an apparatus for pushing mail;
FIG. 5 is a diagram of the internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The email push method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server firstly obtains a label set of a current user, obtains the label weight of each label in the label set, selects a label with a large label weight as a target label, obtains all associated products corresponding to each target label, obtains the current push priority of each associated product corresponding to the target label, sorts the associated products in the associated product set according to the current push priority of each associated product corresponding to the target label, selects the associated products with high current push priority as target associated products, forms a target associated product set corresponding to the current user by the target associated products corresponding to each target label, generates a mail to be pushed for each target associated product in the target associated product set, and pushes the mail to be pushed to a terminal 102 corresponding to the current user. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a mail pushing method is provided, which is described by taking an example that the method is applied to the server in fig. 1, and includes the following steps:
step S202, acquiring a label set corresponding to the current user and label weights corresponding to all labels in the label set, sorting the labels in the label set according to the label weights, and selecting a target label according to a label sorting result.
The label refers to words which can represent characteristics of the user, such as age, assets, whether there is a room, whether there is a car, and the like, the label weight is used for representing the importance of the label, and the greater the label weight is, the more the label can reflect the characteristics of the user. The current user refers to a target user for pushing the current mail, and may be a user randomly selected by the server, or a user selected by the server according to a certain condition, such as a user selected according to a specific region.
Specifically, for all users in the user set, corresponding tags are set in advance, and the tags can be obtained according to data such as behavior data of the users and mail traffic. When a certain user is selected as a current user by the server, the tag set corresponding to the current user can be searched according to the user identifier corresponding to the current user, the tag weights of all tags in the tag set are obtained at the same time, then the tags are sorted according to the tag weights, a preset number of target tags are selected according to a sorting result, for example, the tags can be sorted in a descending order according to the tag weights, and then the preset number of tags which are sorted at the top are selected as the target tags.
And step S204, acquiring the associated product corresponding to the target label to obtain an associated product set.
Specifically, if the label is associated with the product in advance, the label is an associated label of the product, the product is an associated product of the label, for example, a label of "car exists", and the associated label is associated with products such as car loan, car insurance, car credit card, and the like, then the label of "car exists" is an associated label of products such as car loan, car insurance, car credit card, and the like, and the products such as car loan, car insurance, car credit card, and the like are associated products of the label of "car exists". In this embodiment, after the server obtains the target tags, the server may query the associated products corresponding to the target tags according to the target tags, and all associated products corresponding to each target tag form an associated product set corresponding to the target tag.
Step S206, the current push priority of each associated product in the associated product set corresponding to the target label is obtained.
The current push priority refers to the priority for pushing a product promotion mail to the current user for marketing, and the current push priority of the associated product a corresponding to the target tag T can be determined according to feedback data obtained by pushing the marketing mail of the associated product a to the user set corresponding to the target tag T within a preset time period. Each target label may correspond to a plurality of associated products, and the current push priorities of the associated products corresponding to the target label are different, for example, among the associated products corresponding to the "with car", the push priority of the car insurance product is the highest priority, the push priority of the car credit product is the second highest, and the push priority of the car credit card is the lowest.
And S208, sorting the associated products in the associated product set according to the pushing priority, and selecting the target associated product according to the sorting result of the associated products.
Specifically, the associated products in the associated product set corresponding to each target tag may be sorted, for example, if the marketing priority of the car insurance is "high", the marketing priority of the car credit is "medium", the marketing priority of the car credit is "low", and the car credit, the car insurance and the car credit are sorted as follows: car insurance, car credits, car credit cards; and then respectively selecting a preset number of associated products from the associated product set corresponding to each target label according to the sorting result, and finally taking all the selected associated products as target associated products.
Or all the associated products corresponding to all the target tags can be uniformly sorted according to the pushing priority of the products by the target tags, and then a preset number of associated products are selected as the target associated products according to a sorting result obtained by uniform sorting. In one embodiment, when a certain associated product corresponds to two push priorities at the same time, the higher push priority is taken as the push priority of the product; in one embodiment, when the same push priorities of any two products are the same, the labels are sorted according to the label weight of the target label corresponding to the push priorities.
Further, the server selects the target associated product according to the sorting result. In one embodiment, the associated products may be sorted in a descending order, and a preset number of associated products ranked in the top may be selected as the target associated products.
And step S210, generating a mail to be pushed according to the target associated product, and pushing the mail to be pushed.
Specifically, the server may obtain a link corresponding to the target associated product, and then generate a to-be-pushed mail by using a preset mail template, and further, the server may obtain a mailbox address corresponding to the current user, and push the to-be-pushed mail to a mailbox terminal corresponding to the current user according to the mailbox address.
In the mail pushing method, the server firstly obtains a label set corresponding to a current user and label weights corresponding to labels in the label set, sorts the labels in the label set according to the label weights, selects a target label according to a label sorting result, obtains a related product corresponding to the target label to obtain a related product set, obtains a current pushing priority of each related product in the related product set corresponding to the target label, sorts the related products in the related product set according to the pushing priority, selects the target related product according to the related product sorting result, generates a mail to be pushed according to the target related product, and pushes the mail to be pushed.
In an embodiment, as shown in fig. 3, before obtaining the tag set corresponding to the current user and the tag weight corresponding to each tag in the tag set, the method includes:
step S302, a mail set corresponding to the current user is obtained, and a mail template corresponding to the mail set is obtained.
And step S304, acquiring a preset label corresponding to the mail template as a first type label.
In particular, the mail collection of the current user may be the historical mail sent by the server to the current user. In this embodiment, in order to improve the generation efficiency of the email, a plurality of email templates are usually set first, and for each email template, a preset tag, that is, a preset fixed tag may be set. After the server acquires the historical mails, the server can further acquire mail templates corresponding to the historical mails, and then the fixed labels corresponding to the mail templates are used as first-class labels corresponding to the current users.
Step S304, extracting keywords from each mail to obtain a second type of label, and obtaining a label set corresponding to the current user according to the first type of label and the second type of label.
And step S306, calculating the label weight of each label in the label set by adopting a preset algorithm.
Specifically, variable characters fixed for format in the mail, such as gender, age, address, occupation, and the like; matching the field types corresponding to the variable characters with keywords preset by a mail template corresponding to the variable characters to obtain keywords, wherein for example, a certain mail comprises a gender: female "," professional; the contents of a teacher and the like, and if the preset keyword corresponding to the mail template is a career, the teacher is used as a matched keyword; and for the characters with unfixed formats in the mails, extracting keywords by adopting a textrank algorithm.
In one embodiment, the weight corresponding to each label can be obtained by calculating using a TF-IDF algorithm, which specifically includes: for any tag T in the tag set, the TF weight of the tag T is first calculated: TF = the number of the tags T of the current user/the total number of the tags of the current user; and then calculating the IDF weight of the label T, wherein IDF = the sum of all labels of all users/the number of the labels T corresponding to all users, and the weight of the label T is IF IDF.
In the embodiment, the tag set corresponding to the current user is obtained through the first type of tags corresponding to the mail template and the second type of tags obtained from the mail, the tag weight of each tag in the tag set is calculated by adopting a preset algorithm, and the obtained tag set can cover the characteristics of the user more comprehensively, so that the push pertinence of the mail is higher, and the push of the mail is more accurate.
In one embodiment, a buried point is set on a product page corresponding to a target associated product, and the buried point is used for acquiring behavior data of a current user; after pushing the mail to be pushed, the method comprises the following steps: and adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
The behavior data of the user includes clicking connection, browsing a product page, filling data in the product page, submitting data, staying time on the page, purchasing a product, consulting the product, and the like, and at least one of the label and the label weight corresponding to the current user is adjusted, including adjusting the weight of the existing label and adding a new label, and specifically, the proportion of the adjusted weight can be set in advance as required.
In one embodiment, before obtaining the current push priority of each associated product in the associated product set corresponding to the target tag, the method includes: acquiring a corresponding associated label of each product in a current product set; acquiring push feedback data of each product in a current product set corresponding to the associated label of the product; and determining the current push priority of each product corresponding to the associated label according to the push feedback data.
The current product set refers to a set formed by all products to be marketed by pushing mails currently, the associated label refers to a label which establishes an association relationship with the product in advance, and the product is also called as an associated product of the label; a product may correspond to multiple associated tags, and similarly, each tag may correspond to multiple associated products. In this embodiment, after acquiring the association tag of each product in the current product set, the server acquires push feedback data corresponding to the association tag of each product, where the push feedback data is used to represent an effect of pushing a mail related to the product on marketing of the product, and the push feedback data may be a push success rate or a push score. Further, the server may determine, from the push feedback data, a current push priority for each product corresponding to its respective associated tag.
In one embodiment, when the push feedback data is a push success rate, obtaining push feedback data of each product in the current product set corresponding to its associated tag, and determining a current push priority of each product corresponding to its associated tag according to the push feedback data specifically includes: acquiring a push user set of each product in a current product set corresponding to the associated label in a preset time period; calculating a first quantity corresponding to all pushing users in a pushing user set and a second quantity corresponding to pushing users of a preset type in the pushing user set; calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity; and determining the current push priority of each product corresponding to the associated label according to the push success rate.
Specifically, the set of pushing users of the product a corresponding to the associated tag T refers to a set composed of users having the associated tag T among all users pushing the associated product a, for example, a mail marketing product a is pushed to 100 users, wherein 50 users having the tag T constitute a set of pushing users of the product a corresponding to the associated tag T. The preset type of push users refers to users who have succeeded in marketing, i.e., who finally purchased product a. Push success ratio = second number/first number.
Further, the tags are prioritized according to the push success rate, and specifically, the tags may be set to have a highest priority level when the marketing success rate is greater than a first threshold (e.g., 80%), a medium priority level when the marketing success rate is greater than a second threshold and less than the first threshold (e.g., 60%), a lower priority level when the marketing success rate is greater than a third threshold and less than the second threshold (e.g., 40%), and so on.
In one embodiment, when the push feedback data is a push score, acquiring push feedback data of each product in the current product set corresponding to its associated tag, and determining a current push priority of each product corresponding to its associated tag according to the push feedback data includes: acquiring a push user set of each product in a current product set corresponding to the associated label in a preset time period; acquiring a pushing score of each pushing user in a pushing user set; calculating the total pushing score of each product corresponding to the associated label according to the pushing score of each pushing user in the pushing user set; and determining the current push priority of each product corresponding to the associated label according to the push total score.
Specifically, corresponding scores can be set for behaviors of the pushing user, for example, the pushing user corresponding to the associated tag clicks a product link tag 1, a favorite tag two, a consultation tag 3, \8230, and a \8230, after behavior data of the pushing user is obtained according to a preset embedded point, the scores corresponding to the behavior data are accumulated to obtain a pushing score of each pushing user, and the pushing scores of each pushing user in a pushing user set corresponding to each associated tag of the product in a preset time period are accumulated to obtain a total pushing score of the product corresponding to each associated tag. Further, the current push priority of the product corresponding to each associated tag is determined according to the total push score, and specifically, the priority division manner may refer to the method described above, which is not described herein again.
In the above embodiment, the current push priority of the associated tag is determined by obtaining the push feedback data, so that the determination of the current push priority is more accurate.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided a mail pushing apparatus 400, including: a target tag selecting module 402, an associated product obtaining module 404, a current pushing priority obtaining module 406, a target associated product selecting module 408 and a mail pushing module 410, wherein:
the target tag selection module 402 is configured to obtain a tag set corresponding to a current user and tag weights corresponding to tags in the tag set, sort the tags in the tag set according to the tag weights, and select a target tag according to a tag sorting result;
the associated product obtaining module 404 is configured to obtain an associated product corresponding to the target tag, so as to obtain an associated product set;
the current push priority obtaining module 406 is configured to obtain a current push priority of each associated product in the associated product set, where the current push priority corresponds to a target tag;
the target associated product selecting module 408 is configured to sort the associated products in the associated product set according to the pushing priority, and select a target associated product according to a sorting result of the associated products;
the mail pushing module 410 is configured to generate a mail to be pushed according to the target associated product, and push the mail to be pushed.
In one embodiment, the apparatus further comprises: the tag set generating module is used for acquiring a mail set corresponding to a current user and acquiring a mail template corresponding to the mail set; acquiring a preset label corresponding to the mail template as a first type label; extracting keywords from each mail to obtain a second type of label, and obtaining a label set corresponding to the current user according to the first type of label and the second type of label; and calculating the label weight of each label in the label set by adopting a preset algorithm.
In one embodiment, the above apparatus further comprises: the embedded point setting module is used for setting embedded points on a product page corresponding to the target associated product, and the embedded points are used for acquiring the behavior data of the current user; and the adjusting module is used for adjusting at least one of the label and the label weight corresponding to the current user according to the behavior data of the current user.
In one embodiment, the above apparatus further comprises: the current push priority determining module is used for acquiring the associated labels corresponding to the products in the current product set; acquiring push feedback data of each product in the current product set corresponding to the associated label of the product; and determining the current push priority of each product corresponding to the associated label according to the push feedback data.
In one embodiment, the current push priority determining module is further configured to obtain a push user set of each product in the current product set corresponding to its associated tag within a preset time period; calculating a first quantity corresponding to all pushing users in a pushing user set and a second quantity corresponding to pushing users of a preset type in the pushing user set; calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity; and determining the current push priority of each product corresponding to the associated label according to the push success rate.
In one embodiment, the current push priority determining module is further configured to obtain a push user set of each product in the current product set corresponding to its associated tag within a preset time period; acquiring a pushing score of each pushing user in a pushing user set; calculating the total pushing score of each product corresponding to the associated label according to the pushing score of each pushing user in the pushing user set; and determining the current push priority of each product corresponding to the associated label according to the push total score.
For specific limitations of the mail pushing device, reference may be made to the above limitations of the mail pushing method, which is not described herein again. The modules in the mail pushing device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing tag data, product data, etc. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a mail push method.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: acquiring a label set corresponding to a current user and label weights corresponding to all labels in the label set, sorting the labels in the label set according to the label weights, and selecting a target label according to a label sorting result; acquiring a related product corresponding to the target label to obtain a related product set; acquiring the current push priority of each associated product in the associated product set corresponding to the target label; sorting the associated products in the associated product set according to the pushing priority, and selecting a target associated product according to a sorting result of the associated products; and generating a mail to be pushed according to the target associated product, and pushing the mail to be pushed.
In one embodiment, before obtaining the tag set corresponding to the current user and the tag weight corresponding to each tag in the tag set, the processor further implements the following steps when executing the computer program: acquiring a mail set corresponding to a current user, and acquiring a mail template corresponding to the mail set; acquiring a preset label corresponding to the mail template as a first type label; extracting keywords from each mail to obtain a second type of label, and obtaining a label set corresponding to the current user according to the first type of label and the second type of label; and calculating the label weight of each label in the label set by adopting a preset algorithm.
In one embodiment, before pushing the mail to be pushed, the processor executes the computer program to further implement the following steps: setting a buried point on a product page corresponding to the target associated product, wherein the buried point is used for acquiring the behavior data of the current user; after the mail to be pushed is pushed, the processor executes the computer program and further realizes the following steps: and adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
In one embodiment, before obtaining the current push priority of each associated product in the associated product set corresponding to the target tag, the processor, when executing the computer program, further performs the following steps: acquiring a corresponding associated label of each product in a current product set; acquiring push feedback data of each product in a current product set corresponding to the associated label of the product; and determining the current push priority of each product corresponding to the associated label according to the push feedback data.
In one embodiment, obtaining push feedback data corresponding to an associated tag for each product in a current product set includes: acquiring a push user set of each product in a current product set corresponding to the associated label in a preset time period; calculating a first quantity corresponding to all pushing users in a pushing user set and a second quantity corresponding to pushing users of a preset type in the pushing user set; calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity; determining the current push priority of each product corresponding to the associated tag thereof according to the push feedback data, including: and determining the current push priority of each product corresponding to the associated label according to the push success rate.
In one embodiment, obtaining push feedback data corresponding to an associated tag of each product in a current product set includes: acquiring a push user set of each product in a current product set corresponding to the associated label in a preset time period; acquiring a pushing score of each pushing user in a pushing user set; calculating the total pushing score of each product corresponding to the associated label according to the pushing score of each pushing user in the pushing user set; determining the current push priority of each product corresponding to the associated tag thereof according to the push feedback data, including: and determining the current push priority of each product corresponding to the associated label according to the push total score.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of: acquiring a label set corresponding to a current user and label weights corresponding to all labels in the label set, sorting the labels in the label set according to the label weights, and selecting a target label according to a label sorting result; acquiring a related product corresponding to the target label to obtain a related product set; acquiring the current push priority of each associated product in the associated product set corresponding to the target label; sorting the associated products in the associated product set according to the pushing priority, and selecting a target associated product according to a sorting result of the associated products; and generating a mail to be pushed according to the target associated product, and pushing the mail to be pushed.
In one embodiment, before obtaining the label set corresponding to the current user and the label weight corresponding to each label in the label set, the computer program when executed by the processor further implements the following steps: acquiring a mail set corresponding to a current user, and acquiring a mail template corresponding to the mail set; acquiring a preset label corresponding to the mail template as a first type label; extracting keywords from each mail to obtain a second type of label, and obtaining a label set corresponding to the current user according to the first type of label and the second type of label; and calculating the label weight of each label in the label set by adopting a preset algorithm.
In one embodiment, before pushing the mail to be pushed, the computer program when executed by the processor further implements the steps of: setting a buried point on a product page corresponding to the target associated product, wherein the buried point is used for acquiring the behavior data of the current user; after pushing the mail to be pushed, the computer program further realizes the following steps when being executed by the processor: and adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
In one embodiment, before obtaining the current push priority of each associated product in the associated product set corresponding to the target tag, the computer program when executed by the processor further performs the steps of: acquiring a corresponding associated label of each product in a current product set; acquiring push feedback data of each product in the current product set corresponding to the associated label of the product; and determining the current push priority of each product corresponding to the associated label according to the push feedback data.
In one embodiment, obtaining push feedback data corresponding to an associated tag for each product in a current product set includes: acquiring a push user set of each product in a current product set corresponding to the associated label in a preset time period; calculating a first quantity corresponding to all pushing users in a pushing user set and a second quantity corresponding to pushing users of a preset type in the pushing user set; calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity; determining the current push priority of each product corresponding to the associated tag thereof according to the push feedback data, including: and determining the current push priority of each product corresponding to the associated label according to the push success rate.
In one embodiment, obtaining push feedback data corresponding to an associated tag of each product in a current product set includes: acquiring a push user set of each product in a current product set corresponding to the associated label in a preset time period; acquiring a pushing score of each pushing user in a pushing user set; calculating a total pushing score of each product corresponding to the associated label of each product according to the pushing score of each pushing user in the pushing user set; determining the current push priority of each product corresponding to the associated tag thereof according to the push feedback data, including: and determining the current push priority of each product corresponding to the associated label according to the push total score.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A mail pushing method, the method comprising:
acquiring a mail set corresponding to a current user, acquiring a mail template corresponding to the mail set, acquiring preset labels corresponding to the mail template as first-class labels, extracting keywords from all mails to obtain second-class labels, acquiring a label set corresponding to the current user according to the first-class labels and the second-class labels, and calculating the label weight of each label in the label set by adopting a preset algorithm;
sorting the labels in the label set according to the label weights, and selecting target labels according to the label sorting result;
querying a related product corresponding to the target label to obtain a related product set; the related product is a marketing product with a pre-established association relation with the target label;
acquiring an associated label corresponding to each product in a current product set, acquiring push feedback data of each product in the current product set corresponding to the associated label, and determining the current push priority of each product corresponding to the associated label according to the push feedback data; the current product set refers to a set formed by all products to be pushed to market currently; the associated label refers to a label which establishes an association relationship with a product in advance; the current push priority refers to the priority of pushing a product promotion mail for marketing; the pushing feedback data refers to feedback data obtained by pushing marketing mails to the user set corresponding to the associated tag within a preset time period; the feedback data comprises at least one of a push success rate or a push score;
acquiring the current push priority of each associated product in the associated product set corresponding to the target label; sorting the associated products in the associated product set according to the pushing priority, and selecting a target associated product according to a sorting result of the associated products;
acquiring a link corresponding to a target associated product, generating a mail to be pushed by adopting a preset mail template, and pushing the mail to be pushed;
before pushing the mail to be pushed, the method includes: setting buried points on a product page corresponding to the target associated product, wherein the buried points are used for acquiring behavior data of a current user;
after the mail to be pushed is pushed, the method comprises the following steps: and adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
2. The method of claim 1, wherein the obtaining push feedback data corresponding to the associated tag for each product in the current product set comprises:
acquiring a push user set corresponding to the associated labels of each product in the current product set within a preset time period;
calculating a first quantity corresponding to all pushing users in the pushing user set and a second quantity corresponding to pushing users of a preset type in the pushing user set;
calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity;
the determining the current push priority of each product corresponding to its associated tag according to the push feedback data includes:
and determining the current push priority of each product corresponding to the associated label according to the push success rate.
3. The method of claim 1, wherein the obtaining push feedback data corresponding to the associated label of each product in the current product set comprises:
acquiring a push user set corresponding to the associated label of each product in the current product set within a preset time period;
acquiring a pushing score of each pushing user in the pushing user set;
calculating a total pushing score of each product corresponding to the associated label of each product according to the pushing score of each pushing user in the pushing user set;
the determining the current push priority of each product corresponding to its associated tag according to the push feedback data includes:
and determining the current push priority of each product corresponding to the associated label according to the push total score.
4. A mail pushing apparatus, characterized in that the apparatus comprises:
the system comprises a tag set generating module, a tag weight calculating module and a tag weight calculating module, wherein the tag set generating module is used for acquiring a mail set corresponding to a current user, acquiring a mail template corresponding to the mail set, acquiring a preset tag corresponding to the mail template as a first class tag, extracting a keyword from each mail to obtain a second class tag, acquiring the tag set corresponding to the current user according to the first class tag and the second class tag, and calculating the tag weight of each tag in the tag set by adopting a preset algorithm;
the target label selecting module is used for sorting the labels in the label set according to the label weights and selecting the target labels according to the label sorting result;
the associated product acquisition module is used for inquiring the associated product corresponding to the target label to obtain an associated product set; the related product is a marketing product with a pre-established association relation with the target label;
the system comprises a current push priority determining module, a current push priority determining module and a current push priority determining module, wherein the current push priority determining module is used for acquiring associated labels corresponding to products in a current product set, acquiring push feedback data of the products in the current product set corresponding to the associated labels, and determining the current push priority of the products corresponding to the associated labels according to the push feedback data; the current product set refers to a set formed by all products to be pushed to market currently; the associated label refers to a label which establishes an association relationship with a product in advance; the current push priority refers to the priority of pushing a product promotion mail for marketing; the pushing feedback data refers to feedback data obtained by pushing marketing mails to the user set corresponding to the associated tag within a preset time period; the feedback data comprises at least one of a push success rate or a push score;
a current push priority obtaining module, configured to obtain a current push priority of each associated product in the associated product set, where the current push priority corresponds to the target tag;
the target associated product selection module is used for sorting the associated products in the associated product set according to the pushing priority and selecting the target associated products according to the sorting result of the associated products;
the mail pushing module is used for acquiring a link corresponding to a target associated product, generating a mail to be pushed by adopting a preset mail template, and pushing the mail to be pushed;
the device further comprises:
the embedded point setting module is used for setting embedded points on a product page corresponding to the target associated product, and the embedded points are used for acquiring behavior data of a current user;
and the adjusting module is used for adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
5. The apparatus according to claim 4, wherein the current push priority determining module is further configured to obtain a push user set of each product in the current product set corresponding to its associated tag within a preset time period; calculating a first quantity corresponding to all push users in the push user set and a second quantity corresponding to push users of a preset type in the push user set; calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity; and determining the current push priority of each product corresponding to the associated label according to the push success rate.
6. The apparatus according to claim 4, wherein the current push priority determining module is further configured to obtain a push user set of each product in the current product set corresponding to its associated tag within a preset time period; acquiring a pushing score of each pushing user in the pushing user set; calculating a total pushing score of each product corresponding to the associated label of each product according to the pushing score of each pushing user in the pushing user set; and determining the current push priority of each product corresponding to the associated label according to the push total score.
7. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of:
acquiring a mail set corresponding to a current user, acquiring a mail template corresponding to the mail set, acquiring preset labels corresponding to the mail template as first-class labels, extracting keywords from all mails to obtain second-class labels, acquiring a label set corresponding to the current user according to the first-class labels and the second-class labels, and calculating the label weight of each label in the label set by adopting a preset algorithm;
sorting the labels in the label set according to the label weights, and selecting target labels according to the label sorting result;
inquiring the associated product corresponding to the target label to obtain an associated product set; the related product is a marketing product with a pre-established association relation with the target label;
acquiring an associated label corresponding to each product in a current product set, acquiring push feedback data of each product in the current product set corresponding to the associated label, and determining the current push priority of each product corresponding to the associated label according to the push feedback data; the current product set refers to a set formed by all products to be pushed to market currently; the associated label refers to a label which establishes an association relation with a product in advance; the current push priority refers to the priority of pushing a product promotion mail for marketing; the pushing feedback data refers to feedback data obtained by pushing a marketing mail to the user set corresponding to the associated tag within a preset time period; the feedback data comprises at least one of a push success rate or a push score;
acquiring the current push priority of each associated product in the associated product set corresponding to the target label;
sorting the associated products in the associated product set according to the pushing priority, and selecting a target associated product according to a sorting result of the associated products;
acquiring a link corresponding to a target associated product, generating a mail to be pushed by adopting a preset mail template, and pushing the mail to be pushed;
before pushing the mail to be pushed, the method comprises the following steps: setting a buried point on a product page corresponding to the target associated product, wherein the buried point is used for acquiring the behavior data of the current user;
after the mail to be pushed is pushed, the method comprises the following steps: and adjusting at least one of the label and the label weight value corresponding to the current user according to the behavior data of the current user.
8. The computer device of claim 7, wherein the obtaining push feedback data corresponding to the associated label for each product in the current product set comprises:
acquiring a push user set corresponding to the associated labels of each product in the current product set within a preset time period;
calculating a first quantity corresponding to all push users in the push user set and a second quantity corresponding to push users of a preset type in the push user set;
calculating the pushing success rate of each product corresponding to the associated label according to the first quantity and the second quantity;
the determining the current push priority of each product corresponding to its associated tag according to the push feedback data includes:
and determining the current push priority of each product corresponding to the associated label according to the push success rate.
9. The computer device of claim 7, wherein the obtaining push feedback data corresponding to the associated label of each product in the current product set comprises:
acquiring a push user set corresponding to the associated labels of each product in the current product set within a preset time period;
acquiring a pushing score of each pushing user in the pushing user set;
calculating a total pushing score of each product corresponding to the associated label of each product according to the pushing score of each pushing user in the pushing user set;
the determining the current push priority of each product corresponding to its associated tag according to the push feedback data includes:
and determining the current push priority of each product corresponding to the associated label according to the push total score.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811089140.5A CN109245996B (en) | 2018-09-18 | 2018-09-18 | Mail pushing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811089140.5A CN109245996B (en) | 2018-09-18 | 2018-09-18 | Mail pushing method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109245996A CN109245996A (en) | 2019-01-18 |
| CN109245996B true CN109245996B (en) | 2023-04-07 |
Family
ID=65059122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811089140.5A Active CN109245996B (en) | 2018-09-18 | 2018-09-18 | Mail pushing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109245996B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111831894B (en) * | 2019-04-23 | 2024-07-16 | 北京嘀嘀无限科技发展有限公司 | Information matching method and device |
| CN110163301A (en) * | 2019-05-31 | 2019-08-23 | 北京金山云网络技术有限公司 | A kind of classification method and device of image |
| CN110196931B (en) * | 2019-06-28 | 2021-10-08 | 北京蓦然认知科技有限公司 | Image description-based dialog generation method and device |
| CN110602224B (en) * | 2019-09-18 | 2022-11-11 | 上海掌门科技有限公司 | Method, electronic device and computer readable medium for pushing information |
| CN111585870A (en) * | 2020-04-30 | 2020-08-25 | 杭州涂鸦信息技术有限公司 | Mail sending method and related equipment |
| CN112182390B (en) * | 2020-09-29 | 2024-02-09 | 中国平安人寿保险股份有限公司 | Mail pushing method, device, computer equipment and storage medium |
| CN114677189A (en) * | 2020-12-24 | 2022-06-28 | 航天信息股份有限公司 | Data management system, method and device, electronic equipment and storage medium |
| CN117240819B (en) * | 2023-11-10 | 2024-02-09 | 天津异乡好居网络科技股份有限公司 | Mail configuration method, device, equipment and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106686063A (en) * | 2016-12-07 | 2017-05-17 | 乐视控股（北京）有限公司 | Information recommendation method and apparatus, and electronic device |
| CN106709033A (en) * | 2016-12-29 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Business multimedia data processing method and device |
| CN107426328A (en) * | 2017-08-08 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096030B (en) * | 2013-04-23 | 2019-10-15 | 北京奇虎科技有限公司 | The method and apparatus that browser execution is optimized |
| CN105320706B (en) * | 2014-08-05 | 2018-10-09 | 阿里巴巴集团控股有限公司 | The treating method and apparatus of search result |
| CN106250557A (en) * | 2016-08-16 | 2016-12-21 | 青岛海信传媒网络技术有限公司 | The recommendation method and device of application |
| CN106960030B (en) * | 2017-03-21 | 2020-11-10 | 北京百度网讯科技有限公司 | Information pushing method and device based on artificial intelligence |
| CN107767228A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus, terminal device and storage medium |
| CN107908789A (en) * | 2017-12-12 | 2018-04-13 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN108460629A (en) * | 2018-02-10 | 2018-08-28 | 深圳壹账通智能科技有限公司 | User, which markets, recommends method, apparatus, terminal device and storage medium |
-
2018
- 2018-09-18 CN CN201811089140.5A patent/CN109245996B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106686063A (en) * | 2016-12-07 | 2017-05-17 | 乐视控股（北京）有限公司 | Information recommendation method and apparatus, and electronic device |
| CN106709033A (en) * | 2016-12-29 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Business multimedia data processing method and device |
| CN107426328A (en) * | 2017-08-08 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109245996A (en) | 2019-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109245996B (en) | Mail pushing method and device, computer equipment and storage medium | |
| CN109165983B (en) | Insurance product recommendation method, apparatus, computer device and storage medium | |
| CN109241427B (en) | Information pushing method, device, computer equipment and storage medium | |
| WO2021196476A1 (en) | Object recommendation method, electronic device, and storage medium | |
| CN110866181B (en) | Resource recommendation method, device and storage medium | |
| CN108959644B (en) | Search ranking method and device, computer equipment and storage medium | |
| CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN109819015B (en) | Information pushing method, device and equipment based on user portrait and storage medium | |
| CN109063108B (en) | Search ranking method and device, computer equipment and storage medium | |
| CN110598845A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN111651670B (en) | Content retrieval method, device terminal and storage medium based on user behavior patterns | |
| CN110223133B (en) | Product display method, device, computer equipment and storage medium | |
| CN111192025A (en) | Occupational information matching method and device, computer equipment and storage medium | |
| CN111080398A (en) | Commodity recommendation method and device, computer equipment and storage medium | |
| CN111178949B (en) | Service resource matching reference data determining method, device, equipment and storage medium | |
| CN108182633B (en) | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium | |
| TW201843622A (en) | Business customization device, method, and computer readable storage media based on data source | |
| CN110609954A (en) | Data acquisition method and device, computer equipment and storage medium | |
| CN112104505B (en) | Application recommendation method, device, server and computer readable storage medium | |
| CN110880006A (en) | User classification method and device, computer equipment and storage medium | |
| CN115311042A (en) | Commodity recommendation method and device, computer equipment and storage medium | |
| CN113869931A (en) | Advertisement putting strategy determining method and device, computer equipment and storage medium | |
| US10394804B1 (en) | Method and system for increasing internet traffic to a question and answer customer support system | |
| CN110598090A (en) | Interest tag generation method and device, computer equipment and storage medium | |
| CN112182390B (en) | Mail pushing method, device, computer equipment and storage medium |
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 |