CN118227870A

CN118227870A - Information pushing method, device, medium and electronic equipment

Info

Publication number: CN118227870A
Application number: CN202211631565.0A
Authority: CN
Inventors: 汤静怡; 冯鹏
Original assignee: Qizhi Technology Co ltd
Current assignee: Qizhi Technology Co ltd
Priority date: 2022-12-19
Filing date: 2022-12-19
Publication date: 2024-06-21

Abstract

The application relates to an information pushing method, an information pushing device, a medium and electronic equipment, wherein the method comprises the following steps: acquiring behavior data of a plurality of access users on an online platform of an enterprise, wherein the behavior data carries user identity identifiers respectively corresponding to the plurality of access users; obtaining a plurality of characteristic labels based on the behavior data, and constructing a label tree according to the characteristic labels; determining a user group with an ordering intention among the plurality of access users according to the tag tree; and sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push information containing the online platform service of the enterprise to the access users corresponding to the user identity identifiers. The application can rapidly identify the user group with the ordering intention among a plurality of access users, and push the information containing the online platform business of the enterprise to the user group by the operation background, thereby improving the ordering intention of the users.

Description

Information pushing method, device, medium and electronic equipment

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method, an apparatus, a medium, and an electronic device for pushing information.

Background

In daily life, as functions of an online platform of an enterprise are continuously perfected, the number of accessed users is continuously increased, generated user data is also continuously increased, and an operation team of the online platform of the enterprise needs to perform operation intervention on corresponding users one by one according to the user data, such as sending a short message, making a call and the like, so as to enable the users to make a final order.

With respect to the related art in the above, the inventors consider that there are the following drawbacks: the operation intervention is carried out on the accessed users one by one, but the mode lacks pertinence, so that the effect on the order placing intention of the user is poor.

Disclosure of Invention

In order to improve the intention of a user for ordering, the application provides an information pushing method, an information pushing device, an information pushing medium and electronic equipment.

In a first aspect of the present application, a method for pushing information is provided, which specifically includes:

Acquiring behavior data of a plurality of access users on an online platform of an enterprise, wherein the behavior data carries user identity identifiers respectively corresponding to the plurality of access users;

Obtaining a plurality of characteristic labels based on the behavior data, and constructing a label tree according to the characteristic labels;

Determining a user group with an ordering intention among the plurality of access users according to the tag tree;

And sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push information containing the online platform service of the enterprise to the access users corresponding to the user identity identifiers.

By adopting the technical scheme, after the behavior data of clicking, exposing, registering and the like of a plurality of access users on an online platform are obtained, the user attributes of a plurality of dimensions and the behavior information in the online platform are extracted from the behavior data to obtain a plurality of feature labels, a label tree reflecting the user attributes of the plurality of access users is constructed according to the plurality of feature labels, then the access users corresponding to the required label values are screened out according to the label values of the plurality of access users under each feature label in the label tree, the access users are determined to be user groups with the ordering intent, and finally the user identity identification of the access users in the user groups is sent to an operation background of an enterprise, so that the operation background can push information to the access users with the ordering intent in a targeted manner, and the ordering intent of the users is improved.

Optionally, the acquiring behavior data of the online platforms of the multiple access users in the enterprise includes:

Acquiring behavior data of a plurality of access users on an online platform of an enterprise, wherein the behavior data are acquired at a plurality of preset buried points;

Identifying user identity identifiers respectively corresponding to the plurality of access users;

and adding the user identity mark into the behavior data of the corresponding access user.

By adopting the technical scheme, buried point setting is carried out aiming at the actions of clicking, exposing, consulting, searching and the like of an on-line platform of an access user. When the access user generates such behavior on the online platform, the embedded point is triggered, and various behavior data of the access user are collected. Meanwhile, when each access user accesses the online platform, the user identity mark of each access user, such as a telephone number, is identified, the behavior data corresponds to the user identity mark one by one, and each collected behavior data carries the corresponding user identity mark, so that each behavior data of each access user can be accurately obtained.

Optionally, the obtaining a plurality of feature labels based on the behavior data, and constructing a label tree according to the plurality of feature labels, includes:

Inputting the behavior data as input parameters into a decision tree algorithm to obtain a plurality of characteristic labels;

Performing hierarchical clustering on the plurality of feature labels to obtain a hierarchical clustering result;

and constructing a tag tree of the access user based on the hierarchical clustering result.

By adopting the technical scheme, after the behavior data of a plurality of access users are obtained, the behavior data are input into a decision tree algorithm, the behavior data of the plurality of access users can be accurately classified through the decision tree algorithm, so that a plurality of feature labels are obtained, hierarchical clustering analysis is carried out on the plurality of feature labels, hierarchical decomposition is carried out, a label tree containing label values of each access user under the feature labels is obtained, and therefore all-link user figures of the plurality of access users are better sketched, and a user group with a next intention is conveniently and subsequently sketched.

Optionally, the determining, according to the tag tree, a user group with a rule of issuing intent among the plurality of access users includes:

acquiring tag values of the plurality of feature tags in the tag tree;

screening out target tag values from the tag values;

Combining the target tag values to obtain target screening tag values;

and screening target behavior data from the behavior data according to the target screening tag value, and determining the access user corresponding to the target behavior data as a user group with the ordering intention.

By adopting the scheme, after the tag tree is determined, the tag values under a plurality of feature tags in the tag tree are selected as screening objects, and then the required target tag values are screened from the screening objects, namely the tag values required when a user group with a ordering intention is selected from a plurality of access users. And combining the cross difference of the screened target label values to obtain target screening label values, namely the final screening condition. And finally, screening the access users corresponding to the final screening condition from the access users according to the target screening tag value to obtain a user group with the ordering intention, so that the access users with the ordering intention can be rapidly identified from the access users of the access online platform.

Optionally, the screening the target tag value from the tag values includes:

acquiring an identity of an off-line client of the enterprise;

judging whether the identity of the off-line client exists in the user identities corresponding to the multiple access users;

if the identity of the off-line client exists in the user identities corresponding to the multiple access users, searching a tag value of a feature tag corresponding to the identity from the tag tree;

And screening the tag values of the characteristic tags corresponding to the identity marks from the tag values, and taking the screened tag values as target tag values.

By adopting the technical scheme, the identity of the off-line client of the enterprise is respectively compared with the user identities of the plurality of access users, and if the identity is consistent, the off-line client is indicated to access the on-line platform on the premise of being the enterprise client, and the off-line client is indicated to have larger issuing intention. And then, searching the label value of each characteristic label corresponding to the identity of the off-line customer from a label tree, and screening out the label values under a plurality of characteristic labels in the label tree to be used as a target label value, so that the user group with the ordering intention can be screened more accurately by utilizing the target label value combination.

Optionally, after determining the user group with the ordering intention among the plurality of access users according to the tag tree, the method further includes:

Acquiring tag values of all access users in the user group under the plurality of feature tags, and determining feature distribution information of the user group according to the tag values;

comparing the characteristic distribution information of the user group with the characteristic distribution information of the plurality of access users to obtain a comparison result;

and if the comparison result does not meet the preset requirement, the user group is redetermined.

After the user group is determined by adopting the technical scheme, the characteristic distribution information of the user group is determined according to the label values corresponding to each access user in the user group in a plurality of characteristic labels, the characteristic distribution information of the user group is compared with the characteristic distribution information of all access users of the online platform, if the access user occupation ratio of a certain label value in the user group is smaller than the access user occupation ratio of a certain label value in all access users, the comparison result does not meet the preset requirement, and the user group with the rule of ordering intention is indicated to have lower referential, the user group is defined again, so that the strategy of an operation target client can be adjusted in time.

Optionally, the method further comprises:

Updating the user identity of each access user in the user group according to a preset updating frequency so as to redetermine the user group.

By adopting the technical scheme, the fixed updating frequency is set, so that the user group screened out according to certain screening conditions can automatically update the bottom user identity according to the updating frequency, namely, the user group can be automatically defined according to the screening conditions according to the updating frequency, the definition is not required to be manually performed, and the efficiency of on-line platform operation is improved well.

In a second aspect of the present application, there is provided an information pushing apparatus, specifically including:

the system comprises a behavior data acquisition module, a behavior data processing module and a behavior data processing module, wherein the behavior data acquisition module is used for acquiring behavior data of online platforms of a plurality of access users in an enterprise, and the behavior data carries user identity identifiers respectively corresponding to the plurality of access users;

the tag tree construction module is used for obtaining a plurality of characteristic tags based on the behavior data and constructing a tag tree according to the characteristic tags;

The user group delineation module is used for determining a user group with a ordering intention among the plurality of access users according to the tag tree;

and the information pushing module is used for sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push the information containing the online platform business of the enterprise to the access users corresponding to the user identity identifiers.

By adopting the technical scheme, the behavior data acquisition module acquires the behavior data of the online platform of the enterprise of the plurality of access users, the behavior data carries the user identity marks corresponding to the access users, the tag tree construction module extracts a plurality of feature tags from the acquired behavior data and constructs a tag tree according to the plurality of feature tags, then the user group delineating module screens out the user group with the ordering intention from the plurality of access users related to the tag tree, and finally the information pushing module pushes the user group to the operation background of the online platform, so that the operation background can send pushing information to each access user in the user group according to the user identity marks corresponding to the access users, and the ordering intention of the users is improved.

In summary, the present application includes at least one of the following beneficial technical effects:

After behavior data of clicking, exposing, registering and the like of a plurality of access users on an online platform are obtained, user attributes of a plurality of dimensions and behavior information in the online platform are extracted from the behavior data, a plurality of feature labels are obtained, a label tree reflecting the user attributes of the plurality of access users is constructed according to the plurality of feature labels, then a user group with a list intention is screened out according to label values of the plurality of access users under each feature label in the label tree, which corresponds to the required label value, and finally user identification marks of the access users in the user group are sent to an operation background of an enterprise, so that the operation background can push short messages to the access users with the list intention in a targeted manner, and the list intention of the users is improved.

Drawings

Fig. 1 is a schematic architecture diagram of a system for pushing information according to an embodiment of the present application;

fig. 2 is a flow chart of a method for pushing information according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a relationship between a feature tag and a tag value according to an embodiment of the present application;

fig. 4 is a flow chart of another method for pushing information according to an embodiment of the present application;

FIG. 5 is a flowchart of another method for pushing information according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a target tag value combination according to an embodiment of the present application;

FIG. 7 is a schematic diagram of another combination of target tag values provided by an embodiment of the present application;

FIG. 8 is a schematic diagram of feature distribution information according to an embodiment of the present application;

Fig. 9 is a schematic structural diagram of an information pushing device according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of another information pushing device according to an embodiment of the present application.

Reference numerals illustrate: 11. a behavior data acquisition module; 12. a label tree construction module; 13. a user group delineating module; 14. and the information pushing module.

Detailed Description

In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments.

In describing embodiments of the present application, words such as "exemplary," "such as" or "for example" are used to mean serving as examples, illustrations or explanations. Any embodiment or design described herein as "illustrative," "such as" or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "illustratively," "such as" or "for example," etc., is intended to present related concepts in a concrete fashion.

In the description of the embodiments of the present application, the term "and/or" is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a alone, B alone, and both A and B. In addition, unless otherwise indicated, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

Referring to fig. 1, an embodiment of the application discloses a flow diagram of an information pushing system, which specifically includes a terminal of an access user, a server and an operation background, wherein the terminal of the access user is a smart phone.

Specifically, an access user accesses the online platform through a terminal, a server obtains behavior data of a plurality of access users through buried points of user behaviors in the online platform, analyzes the behavior data to extract a plurality of characteristic labels, and builds a label tree according to the characteristic labels. And then, screening a user group with a ordering intention from a plurality of access users according to the label tree, and sending the user identity identification and the corresponding label value of each access user in the user group to an operation background so that the operation background pushes information containing the online platform business of the enterprise to each access user in the user group.

Referring to fig. 2, an embodiment of the present application discloses a flow diagram of a method for information push, which may be implemented by a computer program or may be executed on a von neumann system-based information push device. The computer program can be integrated in an application or can be run as a stand-alone tool class application, and specifically comprises:

S101: and acquiring behavior data of the online platforms of the enterprises of the multiple access users, wherein the behavior data carries user identification marks respectively corresponding to the multiple access users.

Specifically, the access user can generate various user behaviors when accessing the online platform of the enterprise through the PC end or the mobile end, and the user behaviors are integrated into data, namely, the behavior data corresponding to the access user is formed. The online platform of the enterprise can be a website, an app product or an applet. The user behavior comprises a series of behaviors such as exposure, clicking, consultation, searching, registration and login, wherein the exposure refers to business information of an online platform of an enterprise, and the number of times the accessed user sees the business information in a search result list and browses list pages according to categories. Concepts such as clicking, consulting, searching, registering, and the like are relatively common and will not be described in detail herein. The behavior data corresponding to the user behavior mainly includes basic information (gender, age, occupation, etc.) of the accessing user, keywords of the accessing user's search, online time of the accessing user, content browsed by the user for a long time, liveness of the accessing user within 7 days, etc.

The method for acquiring the behavior data of the online platforms of the enterprises of the multiple access users is as follows: and performing buried point analysis on specific user behaviors of the access user on-line platform. When the access user generates specific user behaviors, the buried point is triggered to capture the user behaviors of the access user, and behavior data of the access user are obtained. And the behavior data collected each time can carry the user identity corresponding to the access user.

It should be noted that, each access user corresponds to a unique user identification, where the user identification is a phone number of the access user in the embodiment of the present application, and in other embodiments, a mailbox, an identity card information may also be used. The user identity can be used for rapidly identifying whether the access user of the online platform of the enterprise and the offline client of the enterprise are the same person.

S102: and obtaining a plurality of characteristic labels based on the behavior data, and constructing a label tree according to the plurality of characteristic labels.

In particular, a tag refers to an abstract refinement and generalization of a commonality of a feature of multiple access users. The feature tag is a behavior data tag of a user, and is used for analyzing and refining behavior data generated by an access user in an online platform to obtain generalized words with differences. The feature labels comprise three types of user labels, enterprise labels and content labels, wherein the user labels are highly refined feature labels obtained by analyzing user information of access users and are also key factors for forming user portraits. The user portrait refers to a labeled user model abstracted according to user attributes, user preferences and the like. The enterprise tag is a characteristic identifier for accessing enterprise information to which the user belongs. The content label is a characteristic description of the text, graphics context and other contents in the form of keywords or phrases. Three major types of feature tags cover user base attributes, channel sources, behavioral preferences, conversion information, and detail data tags.

The tag tree is a data set of a tree structure obtained by classifying behavior data corresponding to the feature tags in a layering manner. After the behavior data of a plurality of access users are obtained, a plurality of feature labels can be extracted from the behavior data through a decision tree algorithm, and each access user corresponds to at least one feature label. And performing hierarchical decomposition on the set of behavior data according to the feature labels by using a hierarchical clustering algorithm, and finally obtaining label trees of a plurality of access users.

S103: a group of users with an intent to place an order among a plurality of access users is determined based on the tag tree.

Specifically, each feature tag corresponds to a different tag value. Wherein the tag value is an attribute of the tag and is used to represent specific tag content. Fig. 3 is a schematic diagram showing a relationship between a feature tag and a tag value, for example, feature tag a is "the number of logins of 30 days", and then the tag value under the feature tag is: 0 times, 1-5 times, 6-10 times and more than 10 times. For another example, feature tag B is "user lifecycle", then the tag value under feature tag B is: new users, active users, silent users, and lost users.

After the label tree is determined, all the label values under a plurality of characteristic labels in the label tree are selected, then the screening conditions input from the outside are received, such as accurate matching or fuzzy matching, whether the screening conditions are larger or smaller than, contain or not, and the like, a series of label values are screened out, then the screened out label values are combined according to a cross difference mode, so that a label value combination easy to place a list is obtained, finally the access users meeting the requirements are screened out according to the label value combination, and the user group with the intention of placing a list is determined.

For example, the screening condition is that the login times are greater than 5 times in the last 30 days, the life cycle of the user does not contain lost users, and the screened label values are 6-10 times, more than 10 times, newly added users, active users and silent users. If it is determined that 30-day login times are 6-10 and newly added users are finally needed, a user group which simultaneously meets the two users is finally screened out of a plurality of access users.

In one implementation, the user identities of the access users in the user group are updated according to a preset update frequency to redefine the user group.

Specifically, because the number of access users of the online platform is different every day, the user behavior in the online platform is also different, so that each access user in the defined user group is not fixed. If people screened out according to a certain screening condition are promoted and marketed to improve the intention of ordering, operators need to manually select all the people every day and cannot update automatically, so that the operation efficiency is reduced. And the updating frequency is preset, the re-delineation of the user group is automatically and regularly carried out according to the updating frequency, the user identity in the user group is updated, and the operation cost is better saved. The update frequency may be 1 day or 12 hours.

S104: and sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push the information containing the online platform business of the enterprise to the access users corresponding to the user identity identifiers.

Specifically, the operation background is an operation platform used by personnel inside an enterprise, and serves the operation activities of an online platform (a website or app or applet). After the user group with the order is determined, each access user in the user group is used as an operation target user, and the user identities corresponding to the access users in the user group are sent to an operation background, so that the operation background sends information containing online platform business of an enterprise to the access users with the order according to the user identities, and after the access users with the order are rapidly identified, the order of the users is improved through corresponding operation intervention, and even the order of the access users is promoted.

In one implementation manner, a user identity identifier, such as a telephone number, which is input from the outside is received, according to the input user identity identifier, each feature tag corresponding to the user identity identifier and tag values corresponding to each feature tag respectively can be found from a constructed tag tree, and a user portrait formed by a plurality of tag values is displayed, so that personnel can conveniently inquire about the user portraits of all links of each access user, and a customized operation policy can be formulated.

Referring to fig. 4, an embodiment of the present application discloses a flow diagram of another method of information push, which may be implemented in dependence on a computer program, and may also be run on a von neumann system-based information push device. The computer program can be integrated in an application or can be run as a stand-alone tool class application, and specifically comprises:

s201: and acquiring behavior data of a plurality of access users on-line platforms of the enterprise, wherein the behavior data are acquired at a plurality of preset buried points.

Specifically, the embedded points are the corresponding position points developed at the front end, and statistical codes are implanted to record the behaviors of the user. In the embodiment of the application, the embedded point setting is carried out on each behavior of the access user in the online platform of the enterprise through the nerve-policy platform. In other embodiments, the buried point setting may also be performed by a GrowingIO platform. For example, the embedded point setting is performed on the clicking behavior of the access user through the policy platform, and when the user performs active operations such as clicking, refreshing, touching and the like on the online platform of the enterprise through the computer or the smart phone, the embedded point is triggered, and recorded behavior data is sent to the server. For another example, the exposure is buried, and when the data of the on-line platform with the buried point is displayed, the behavior data is acquired by dotting. Specifically, when a page on the online platform is being browsed by the accessing user, i.e. the page is exposed, the buried point is triggered to collect behavior data of the accessing user about the exposure.

S202: and identifying the user identities corresponding to the access users respectively.

S203: and adding the user identity mark into the corresponding behavior data of the access user.

Specifically, the buried point setting is performed on the behavior of the registration login of the access user, when the access user performs real-name registration login operation on the online platform, the buried point is triggered to capture the behavior of the user in real time, and behavior data corresponding to the access user, namely, user identity (telephone number) of the access user is collected, so that the identification of the user identity corresponding to each access user is realized. For example, the embedded point is set at the registration login interface of the online platform, and when the access user clicks the registration or login button, the embedded point triggers the acquisition of the user identity of the access user. After the access user logs in the online platform, various behaviors (clicking, exposing, searching and the like) generated in the online platform are triggered at the embedded point of the corresponding behavior, and the corresponding user identity is added in the behavior data of each time of the access user, so that the behavior data can be corresponding to the user identity.

S204: and (3) taking the behavior data as input parameters and inputting the input parameters into a decision tree algorithm to obtain a plurality of feature labels.

Specifically, a decision tree (decision tree) is a basic classification and regression method. The decision tree model is in a tree structure, and in the classification problem, a process of classifying the instance based on the characteristics is represented. It can be considered as a set of if-then rules, and also as a conditional probability distribution defined over feature space and class space. Its main advantage is that the model has readability and high classifying speed. During learning, training data is utilized, and a decision tree model is established according to the principle of minimizing the loss function. And in the prediction process, classifying the new data by utilizing a decision tree model. This is the prior art and will not be described in detail here. Behavior data of a plurality of access users is input into a decision tree algorithm, so that the behavior data is analyzed and classified, and the behavior data is classified into a plurality of dimensions, namely a plurality of feature labels.

It should be noted that, in other embodiments, the behavior data may be classified according to a preset rule, for example, a rule defining the activity level of the user, the number of login a times a day, and the corresponding activity level of the user is a; the login times are B times a day, and the corresponding user activity degree is B. Thereby enabling the labeling of the characteristics of user activity for a plurality of access users. In this way, a plurality of feature tags corresponding to the behavior data are further determined.

S205: and carrying out hierarchical clustering on the plurality of feature labels to obtain a hierarchical clustering result.

S206: and constructing a tag tree of the access user based on the hierarchical clustering result.

Specifically, hierarchical clustering is to perform hierarchical decomposition on a set of given data objects, and according to a decomposition strategy adopted by the hierarchical decomposition, the hierarchical clustering can be further divided into aggregated (agglomerative) and split (divisive) hierarchical clustering. In the embodiment of the application, hierarchical clustering is adopted to perform hierarchical decomposition on a plurality of feature labels, namely, hierarchical decomposition is performed on behavior data of a plurality of access users, so as to obtain a hierarchical clustering result, namely, a hierarchical decomposition result. And generating a label tree according to the hierarchical clustering result, wherein each layer of branches of the label tree corresponds to a characteristic label, and the label value under each characteristic label corresponds to the upper leaf node of each layer of branches. This is the prior art and will not be described in detail here.

S207: a group of users with an intent to place an order among a plurality of access users is determined based on the tag tree.

S208: and sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push the information containing the online platform business of the enterprise to the access users corresponding to the user identity identifiers.

Specifically, reference may be made to steps S103-S104, which are not described herein.

Referring to fig. 5, a flow diagram of yet another method of information pushing is disclosed, which may be implemented in dependence on a computer program, and may also be run on a von neumann system-based information pushing device. The computer program can be integrated in an application or can be run as a stand-alone tool class application, and specifically comprises:

s301: and acquiring behavior data of the online platforms of the enterprises of the multiple access users, wherein the behavior data carries user identification marks respectively corresponding to the multiple access users.

S302: and obtaining a plurality of characteristic labels based on the behavior data, and constructing a label tree according to the plurality of characteristic labels.

Specifically, reference may be made to steps S101-S102, which are not described herein.

S303: tag values of a plurality of feature tags in a tag tree are obtained.

Specifically, after the label tree is constructed, a plurality of feature labels in the label tree are firstly obtained through a method of obtaining DOM elements through (JavaScript, JS), and then a label value under each feature label is obtained through value. The JS is a lightweight, interpreted or just-in-time compiled programming language with functional preference. For example, the tag tree has two feature tags of user preference and gender, and the tag values under the feature tag of user preference obtained by the method are as follows: preference a, preference B; the tag values under the "gender" feature tag are: male and female.

S304: and screening target tag values from the tag values.

Acquiring an identity of an off-line client of an enterprise;

Judging whether the user identity marks corresponding to the multiple access users exist the identity marks of the clients on line or not;

If the identity of the off-line client exists in the user identities corresponding to the multiple access users, searching a tag value of a feature tag corresponding to the identity from a tag tree;

Specifically, after the tag values corresponding to the feature tags in the tag tree are determined, the identity of the offline customer of the enterprise, that is, the phone number of the offline customer, is obtained through the customer relationship management (Customer Relationship Management, CRM) system of the enterprise. The CRM system refers to an information system for establishing a client information collection, management, analysis and utilization for enterprises by utilizing software, hardware and network technologies. The management of the client data is taken as a core, various interaction behaviors of enterprises and clients in the marketing and sales processes and various states of related activities are recorded, various data models are provided, and support is provided for later analysis and decision.

After the identity of the offline customer of the enterprise is obtained from the CRM system, comparing the identity of the offline customer with the user identities of a plurality of access users of the online platform of the enterprise one by one, if the comparison shows that the online customer of the enterprise exists among the plurality of access users of the online platform under the condition of consistency, further showing that the offline customer has stronger issuing intention, so that the label values of the offline customer under a plurality of characteristic labels in a label tree are screened out to be used as target label values, for example, the characteristic labels related to the behavior data of the online platform accessed by the offline customer are: user preference and liveness, the tag value under the feature tag is preference B and liveness exceeding C, then preference B and liveness exceeding C are taken as target tag values.

It should be noted that, in other embodiments, externally input tag values may be accepted, where the externally input tag values may be tag values that are easier to be ordered by an operator to determine empirically, and these are directly used as target tag values.

S305: and combining the target label values to obtain target screening label values.

S306: and screening target behavior data from the behavior data according to the target screening tag value, and determining the access user corresponding to the target behavior data as a user group with the ordering intention.

Specifically, after the target tag values are determined, intersection sets and/or union sets and/or difference sets are taken from the behavior data corresponding to the target tag values respectively, so that target screening tag values are obtained, namely final screening conditions of the user group are defined. As shown in fig. 6, for example, if the target tag value is the activity level exceeding C and the preference B, if the access user satisfying the activity level exceeding C and the preference B simultaneously is to be screened out, the intersection processing is performed on the two target tag values of the activity level exceeding C and the preference B; as shown in fig. 7, if an access user whose liveness exceeds C and whose preference is B is to be selected, two target tag values are subjected to a union process.

After the target screening tag value is determined, target behavior data meeting the target screening tag value is screened from the behavior data of a plurality of access users, and the user identity identifiers of the corresponding access users are carried in the target behavior data, so that the screened user identity identifiers are determined, and finally, the access users corresponding to the user identity identifiers are determined to be user groups with the ordering intention.

S307: and acquiring tag values of all access users in the user group under a plurality of feature tags, and determining feature distribution information of the user group according to the tag values.

Specifically, after determining the user group with the intent of ordering according to the target screening tag value, each access user in the user group corresponds to a series of behavior data, and corresponds to the tag value under a plurality of feature tags, not just the target screening tag value. And according to the label value of each access user, displaying the characteristic distribution information of each access user in the user group in the form of an icon. For example, the access user with the tag value of "preference B" has a 3% ratio, the access user with the tag value of "liveness exceeding a" has a 5% ratio, and the distribution of the access users with the tag value under each feature tag can be better presented through the feature distribution information of the user group.

S308: and comparing the characteristic distribution information of the user group with the characteristic distribution information of a plurality of access users to obtain a comparison result.

S309: if the comparison result does not meet the preset requirement, the user group is determined again.

Specifically, after the feature distribution information of the user group is determined, feature distribution information of all access users of the online platform is determined in a similar manner, and the feature distribution information of the user group is compared with the feature distribution information of all access users. For example, as shown in fig. 8, a schematic diagram of feature distribution information provided by the embodiment of the present application is shown, the number of access users with a tag value of "near 7 days platform active" in a user group screened according to a target screening tag value ("income exceeds D" and "preference B") accounts for 3% of the number of access users in the user group, while the number of access users with a tag value of "near 7 days platform active" in all access users of an online platform accounts for 5% and 3% is less than 5% of all access users of the online platform (i.e., a comparison result), which indicates that there are many inactive access users in the user group defined this time, the feature distribution situation of the user group is inferior to the feature distribution situation of all access users, the access users with a lower intent in the user group may be fewer, and the requirement of the delineation of the access users with a lower intent is not met. It is necessary to re-conduct the user group and re-determine the operation target client.

S310: and sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push the information containing the online platform business of the enterprise to the access users corresponding to the user identity identifiers.

Specifically, reference may be made to step S104, which is not described herein.

The implementation principle of the information pushing method in the embodiment of the application is as follows: the behavior data of a plurality of access users on an online platform of an enterprise are acquired through buried points, and user identification marks corresponding to the access users are carried in the acquired behavior data each time. And extracting a plurality of characteristic labels from the behavior data through a decision tree algorithm, constructing a label tree according to the plurality of characteristic labels, determining a user group with an order intention among a plurality of access users according to the label tree, and finally transmitting each access user in the user group to an operation background of an enterprise, so that the operation background can transmit information containing an online platform service of the enterprise to the access user, and the order intention of the user is improved.

The following are examples of the apparatus of the present application that may be used to perform the method embodiments of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method of the present application.

Fig. 9 is a schematic structural diagram of an information pushing device according to an embodiment of the present application. The device for information push may be implemented as all or part of the device by software, hardware, or a combination of both. The device 1 comprises a behavior data acquisition module 11, a tag tree construction module 12, a user group delineation module 13 and an information pushing module 14.

The behavior data acquisition module 11 is configured to acquire behavior data of online platforms of multiple access users in an enterprise, where the behavior data carries user identities corresponding to the multiple access users respectively;

a tag tree construction module 12, configured to obtain a plurality of feature tags based on the behavior data, and construct a tag tree according to the plurality of feature tags;

a user group delineation module 13, configured to determine a user group with an ordering intention among a plurality of access users according to the tag tree;

the information pushing module 14 is configured to send the user identities corresponding to the access users in the user group to the operation background, so that the operation background pushes information including the online platform service of the enterprise to the access users corresponding to the user identities respectively.

Optionally, the behavior data acquisition module 11 is specifically configured to:

identifying user identities corresponding to a plurality of access users respectively;

And adding the user identity mark into the corresponding behavior data of the access user.

Optionally, the tag tree construction module 12 is specifically configured to:

the behavior data is used as input parameters to be input into a decision tree algorithm to obtain a plurality of characteristic labels;

Optionally, the user group delineation module 13 is specifically configured to:

Acquiring tag values of a plurality of feature tags in a tag tree;

screening out target tag values from the tag values;

combining the target tag values to obtain target screening tag values;

Optionally, the user group delineation module 13 is specifically further configured to:

acquiring an identity of an off-line client of an enterprise;

Optionally, as shown in fig. 10, the apparatus 1 further includes a feature distribution analysis module 15, specifically configured to:

acquiring tag values of all access users in the user group under a plurality of feature tags, and determining feature distribution information of the user group according to the tag values;

comparing the characteristic distribution information of the user group with the characteristic distribution information of a plurality of access users to obtain a comparison result;

if the comparison result does not meet the preset requirement, the user group is determined again.

Optionally, the apparatus 1 further comprises:

The automatic updating module 16 is configured to update the user identities of the access users in the user group according to a preset updating frequency to redetermine the user group.

It should be noted that, when the information pushing device provided in the foregoing embodiment performs the information pushing method, only the division of the foregoing functional modules is used for illustrating, in practical application, the foregoing functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the information pushing device provided in the above embodiment and the information pushing method embodiment belong to the same concept, which embody the detailed implementation process and are not described herein.

The embodiment of the application also discloses a computer readable storage medium, and the computer readable storage medium stores a computer program, wherein the computer program adopts the information pushing method of the embodiment when being executed by a processor.

The computer program may be stored in a computer readable medium, where the computer program includes computer program code, where the computer program code may be in a source code form, an object code form, an executable file form, or some middleware form, etc., and the computer readable medium includes any entity or device capable of carrying the computer program code, a recording medium, a usb disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, etc., where the computer readable medium includes, but is not limited to, the above components.

The method for pushing information of the above embodiment is stored in the computer readable storage medium through the computer readable storage medium, and is loaded and executed on a processor, so as to facilitate the storage and application of the method.

The embodiment of the application also discloses an electronic device, wherein a computer program is stored in a computer readable storage medium, and the method for pushing the information is adopted when the computer program is loaded and executed by a processor.

The electronic device may be an electronic device such as a desktop computer, a notebook computer, or a cloud server, and the electronic device includes, but is not limited to, a processor and a memory, for example, the electronic device may further include an input/output device, a network access device, a bus, and the like.

The processor may be a Central Processing Unit (CPU), or of course, according to actual use, other general purpose processors, digital Signal Processors (DSP), application Specific Integrated Circuits (ASIC), ready-made programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., and the general purpose processor may be a microprocessor or any conventional processor, etc., which is not limited in this respect.

The memory may be an internal storage unit of the electronic device, for example, a hard disk or a memory of the electronic device, or may be an external storage device of the electronic device, for example, a plug-in hard disk, a Smart Memory Card (SMC), a secure digital card (SD), or a flash memory card (FC) provided on the electronic device, or the like, and may be a combination of the internal storage unit of the electronic device and the external storage device, where the memory is used to store a computer program and other programs and data required by the electronic device, and the memory may be used to temporarily store data that has been output or is to be output, which is not limited by the present application.

The method for pushing information in the embodiment is stored in the memory of the electronic device through the electronic device, and is loaded and executed on the processor of the electronic device, so that the method is convenient to use.

The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.

Claims

1. A method of information pushing, the method comprising:

2. The method for pushing information according to claim 1, wherein the obtaining behavior data of the online platforms of the multiple access users in the enterprise includes:

3. The method for pushing information according to claim 1, wherein the obtaining a plurality of feature labels based on the behavior data, and constructing a label tree according to the plurality of feature labels, comprises:

4. The method of information pushing according to claim 1, wherein the determining, from the tag tree, a user group having an intention to order among the plurality of access users includes:

acquiring tag values of the plurality of feature tags in the tag tree;

screening out target tag values from the tag values;

Combining the target tag values to obtain target screening tag values;

5. The method of information pushing according to claim 4, wherein the screening the target tag value from the tag values includes:

acquiring an identity of an off-line client of the enterprise;

6. The method for pushing information according to claim 1, wherein after determining a user group having an intention to order among the plurality of access users according to the tag tree, further comprising:

7. The method of information pushing according to claim 1, further comprising:

8. An apparatus for pushing information, comprising:

the behavior data acquisition module (11) is used for acquiring behavior data of a plurality of access users on an online platform of an enterprise, wherein the behavior data carries user identity identifiers respectively corresponding to the plurality of access users;

the tag tree construction module (12) is used for obtaining a plurality of characteristic tags based on the behavior data and constructing a tag tree according to the characteristic tags;

A user group delineation module (13) for determining a user group with an ordering intention among the plurality of access users according to the tag tree;

And the information pushing module (14) is used for sending the user identity identifiers corresponding to the access users in the user group to an operation background so that the operation background can respectively push the information containing the online platform business of the enterprise to the access users corresponding to the user identity identifiers.

9. A computer readable storage medium having a computer program stored therein, characterized in that the method according to any of claims 1-7 is employed when the computer program is loaded and executed by a processor.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, characterized in that the method according to any of claims 1-7 is used when the computer program is loaded and executed by the processor.