CN114372821A

CN114372821A - User behavior data processing method, system and medium in local production sales

Info

Publication number: CN114372821A
Application number: CN202111678350.XA
Authority: CN
Inventors: 张婧鹤
Original assignee: Gemdale Corp
Current assignee: Gemdale Corp
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2022-04-19

Abstract

The present disclosure discloses a user behavior data processing method and system in a local production sale. The method comprises the following steps: continuously and rollingly acquiring user behavior data from a service system related to real estate sales service; carrying out numerical processing on the user activity times and the intention degree according to the user behavior data to obtain user activity times and intention integral values; setting an active attribute value and an intention attribute value corresponding to a user according to the number of active times and the intention integral value of the user; and marking the user label of the user of the property sales service according to the active attribute value and the intention attribute value. The method and the system provided by the disclosure realize data support of the real estate sales service, quantify the user value of the real estate sales service in numerical value, provide corresponding user tags, facilitate screening of potential users in real estate sales, and obtain the processed user behavior data in a cross-platform manner, so that the decision support of the real estate sales service is not limited to a single platform any more, and the utilization rate of the data is enhanced.

Description

User behavior data processing method, system and medium in local production sales

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a method, a system, and a medium for processing user data in a local production sales.

Background

With the rapid development of internet applications, the realization of data-based support services is gradually increased, and further, support is provided for decisions in various scenes. In the support of marketing business by data, three elements of the latest sales fee (R), the consumption frequency (F) and the consumption amount (M) constitute the best indexes of data analysis, and are widely applied to customer analysis of fast-moving goods.

For a customer, the value status will be described by three indexes, namely the recent purchasing behavior, the total frequency of purchases and how much money is spent.

However, this data processing is only applicable to services requiring frequent consumption, and cannot be applied to data support required for real estate sales.

Disclosure of Invention

In order to solve the technical problem that the implementation based on the data support service in the related art cannot be applied to the local production sales service, the present disclosure provides a user behavior processing method, system and medium in local production sales.

According to an aspect of the disclosed embodiments, a method for processing user behavior data in a local production sale is disclosed, which includes:

continuously and rollingly acquiring user behavior data for a business system related to the real estate sales business, wherein the user behavior data is used for describing user behaviors related to the real estate sales business;

carrying out numerical processing on the user activity times and the intention degree according to the user behavior data to obtain user activity times and intention integral values;

setting an active attribute value and an intention attribute value corresponding to the user according to the active times and the intention integral value of the user, wherein the active attribute value and the intention attribute value are 0 or 1 in numerical value;

and marking the user label of the user of the property sales service according to the active attribute value and the intention attribute value.

According to an aspect of the embodiments of the present disclosure, the continuously and rollingly acquiring user behavior data for a business system related to a real estate sales service includes:

generating user behavior data through a buried point set by the real estate sales service in the service system, wherein the service system is different from the service system in which the real estate sales service is located;

the generated user behavior data is extracted based on the set time window.

According to an aspect of the embodiments of the present disclosure, the continuously and rollingly acquiring user behavior data of a business system related to a set property sales business includes:

and extracting user behavior data based on a set time window for the service system where the real estate sales service is located.

According to an aspect of the embodiments of the present disclosure, the performing a numerical processing on the number of user activities and the intention degree according to the user behavior data to obtain a value of user activity number and an value of intention integral includes:

extracting user events related to the property sales service from the user behavior data;

determining the number of times of business association between the user and the set real estate sales business as the user active number corresponding to the user according to the user event;

and according to the event integral data mapped by the user event, carrying out numerical description on the real estate sales service intention by the user to obtain an intention integral value.

According to an aspect of the disclosed embodiment, before the step of obtaining the intent value from the user's numerical description of the intent of the property sales service according to the event point data of the user event map,

the method for carrying out the numerical processing of the user activity times and the intention degree according to the user behavior data to obtain the user activity times and the intention integral value further comprises the following steps:

analyzing the extracted user event to obtain a user access path;

and executing the duplicate removal processing of the corresponding user event for the user according to the user access path.

According to an aspect of the embodiment of the present disclosure, the setting of the active attribute value and the intention attribute value corresponding to the user according to the number of active times and the intention integral value of the user includes:

mapping a pre-divided interval range of the user activity times and the intention integral value to obtain interval range values respectively corresponding to the user activity times and the intention integral value;

and respectively setting an active attribute value and an intention attribute value for the user according to the size relationship between the interval range value and the threshold value.

According to an aspect of the embodiment of the present disclosure, the setting of the active attribute value and the intention attribute value corresponding to the user according to the number of active times of the user and the intention integral value further includes:

and performing weighted average calculation on the interval range values respectively corresponding to the active times and the intention integral value of all the users to generate a threshold value.

According to an aspect of an embodiment of the present disclosure, the tagging a user tag of the user of the property sales service according to the active attribute value and the intention attribute value includes:

and generating a user tag according to the user value numerically represented by the real estate sales service according to the active attribute value and the intention attribute value, wherein the user tag is used for describing the user value on the occurrence frequency and the intention of events related to the real estate sales service.

According to an aspect of the disclosed embodiments, a user behavior data processing system in a local production sale is disclosed, the system comprising:

the data acquisition module is used for continuously and rollingly acquiring user behavior data for a business system related to the real estate sales business, wherein the user behavior data is used for describing user behaviors related to the real estate sales;

the numerical processing module is used for carrying out numerical processing on the user activity times and the intention degree according to the user behavior data to obtain user activity times and intention integral values;

the attribute setting module is used for setting an active attribute value and an intention attribute value corresponding to the user according to the active times and the intention integral value of the user, and the active attribute value and the intention attribute value are 0 or 1 in numerical value;

and the marking module is used for marking the user label of the property sales service according to the active attribute value and the intention attribute value.

According to an aspect of embodiments of the present disclosure, a computer program medium is disclosed, having computer readable instructions stored thereon, which, when executed by a processor of a computer, cause the computer to perform the method as described above.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

the method comprises the steps of continuously and rollingly acquiring user behavior data for describing user behaviors related to the real estate sales service, then carrying out numerical processing on user activity times and intention degrees according to the user behavior data to obtain user activity times and intention integral values, setting active attribute values and intention attribute values corresponding to users according to the user activity times and the intention integral values, wherein the active attribute values and the intention attribute values are 0 or 1 in numerical value, and finally marking user tags on users of the real estate sales service according to the active attribute values and the intention attribute values, thereby realizing data support of the real estate sales service, quantifying the user values of the real estate sales service in numerical value, providing corresponding user tags, facilitating screening potential users in real estate sales, and regarding the processed user behavior data, the method is obtained in a cross-platform mode, so that decision support of real estate sales service is not limited to a single platform any more, and the utilization rate of data is enhanced.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 is a schematic illustration of an implementation environment according to the present disclosure;

FIG. 2 is a block diagram illustrating an apparatus in accordance with an exemplary embodiment;

FIG. 3 is a flow chart illustrating a method of user behavior data processing in a commodity sale, according to an exemplary embodiment.

Fig. 4 is a flowchart illustrating steps for obtaining user behavior data for a continuous and rolling production sales business related business system according to a corresponding embodiment of fig. 3.

Fig. 5 is a flowchart illustrating steps of obtaining a user activity count and an intention integration value by performing a digitization process on the user activity count and the intention degree according to user behavior data according to an embodiment of the disclosure corresponding to fig. 3.

Fig. 6 is a flowchart illustrating steps of obtaining a user activity count and an intention integration value by performing a digitization process on the user activity count and the intention degree according to user behavior data according to an embodiment of the disclosure corresponding to fig. 3.

Fig. 7 is a flowchart illustrating steps of setting an active attribute value and an intention attribute value corresponding to a user according to the number of active times and an intention integration value of the user according to the corresponding embodiment of fig. 3.

FIG. 8 is an architectural diagram illustrating the various layers of data processing according to one embodiment of the present disclosure.

FIG. 9 is a schematic diagram illustrating user classification according to one embodiment of the present disclosure.

FIG. 10 is a block diagram illustrating a user behavior data processing system in an earth-based sales, according to an example embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

FIG. 1 is a schematic illustration of an implementation environment according to the present disclosure. The implementation environment includes a plurality of service servers 11 and data processing servers 12 related to a property sales service. The plurality of service servers 11 and the data processing server 12 related to the property sales service constitute a set of data processing system.

The service server 11 is configured to implement data acquisition in other platforms and its own platform, where the acquired data is source data, and correspondingly, the data processing server 12 is enabled to execute a processing procedure on data in one or more service servers 11.

FIG. 2 is a block diagram illustrating an apparatus according to an example embodiment. For example, the apparatus 200 may be any machine of a business server and/or any machine of a data processing server in the implementation environment shown in fig. 1.

Referring to FIG. 2, a block diagram of an apparatus is shown in accordance with an exemplary embodiment. For example, the apparatus 200 may be a machine, such as a server, included in the service server 11 and the data processing server 12 in the implementation environment shown in fig. 1.

Referring to fig. 2, the apparatus 200 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 222 (e.g., one or more processors) and a memory 232, one or more storage media 230 (e.g., one or more mass storage devices) storing an application 242 or data 244. Memory 232 and storage medium 230 may be, among other things, transient or persistent storage. The program stored in the storage medium 230 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 222 may be configured to communicate with the storage medium 230 to execute a series of instruction operations in the storage medium 230 on the device 200. The device 200 may also include one or more power supplies 226, one or more wired or wireless network interfaces 250, one or more input-output interfaces 258, and/or one or more operating systems 241, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth. The steps performed by the server described in the embodiments described below may be based on the apparatus structure shown in this fig. 2.

FIG. 3 is a flow chart illustrating a method of user behavior data processing in a commodity sale, according to an exemplary embodiment. The user behavior processing method in the local production and sales is suitable for the implementation environment shown in fig. 1. As shown in fig. 3, the method for processing user behavior data in the local production sales may include the following steps.

Step S310, user behavior data is continuously and rollingly acquired for a business system related to the real estate sales business, and the user behavior data is used for describing user behaviors related to the real estate sales business.

In step S320, a user activity count and an intention degree are digitized according to the user behavior data, and a user activity count and an intention integral value are obtained.

Step S330, setting an active attribute value and an intention attribute value corresponding to the user according to the number of active times and the intention integral value of the user, wherein the active attribute value and the intention attribute are 0 or 1 in value.

Step S340, marking a user label for the user of the local production sales service according to the active attribute value and the intention attribute value.

These 4 steps are described in detail below.

In S310, the property sales service is used to implement online property sales, for example, to exist as an application form at an online sales building. The business system related to the real estate sales business comprises a business system where the real estate sales business is located and other business systems which are different from the business system where the real estate sales business is located. For example, the business system related to the real estate sales service can be a business system capable of being linked to the real estate sales service, a buried point related to the real estate sales service is set on the business system, and the business system is linked to the real estate sales service through the setting of the buried point.

And acquiring user behavior data for the performance of real estate sales service by being connected with one or more service systems and the service system of the service system. The acquired user behavior data can be generated along with the progress of the real estate sales service on one hand, and can be generated at a buried point set by a service system through the real estate sales service on the other hand.

Illustratively, the user behavior data may be online browsing line and interactive behavior data associated with the property sales service. The user behavior data can exist in the form of a data table, and the user behavior data from different service systems are all loaded in different data tables so as to facilitate the ordered acquisition and storage of the user behavior data.

It should be understood that the user behavior data is business data related to the production sales business. Based on the link of the real estate sales service to different service systems, the generated user behavior data are distributed on different service systems, and the user behavior data need to be extracted from each service system for analysis and processing. Each service system is a service data layer of data processing implemented by the present disclosure, and is a data source of user behavior data, and the data is extracted through the execution of step S310 to obtain a copy of the data in the service system.

Referring to fig. 4, fig. 4 is a flowchart illustrating steps for obtaining user behavior data for a business system associated with continuous and rolling real estate sales business according to a corresponding embodiment of fig. 3. The step S310 of continuously and rollingly acquiring user behavior data from a service system related to a real estate sales service in the embodiment of the present disclosure includes:

step S311, generating user behavior data through the buried point set by the real estate sales service in the service system, where the service system is different from the service system in which the real estate sales service is located.

In step S312, the generated user behavior data is extracted based on the set time window.

These steps are described in detail below.

And (4) embedding the behavior events related to the real estate sales service in other service systems different from the service system where the real estate sales service is located, and storing the user behavior data generated by embedding points in the service system where the user behavior data is located.

For example, at the event of a user using an applet associated with a real estate sales service on an alliance platform, corresponding user behavior data is generated once the user uses the applet. At this time, for the data processing to be performed, these pieces of user behavior data are acquired from the alliance platform, and for example, the alliance applet access schedule and the alliance applet event schedule are subjected to the acquisition of the user behavior data to obtain an applet access table and an applet event table on which a plurality of pieces of user behavior data are recorded. The user behavior data in the form of the applet access table and the applet event table will be used for the execution of the subsequent processing.

The data acquisition is performed continuously and in a rolling manner by defining a time window with timeliness for the user behavior data acquisition, and extracting the generated user behavior data based on the set time window, so that the data processing performed subsequently is performed based on the user behavior data in the time window at each moment.

Therefore, timeliness of user line data can be guaranteed, and further data processing can be adapted to characteristics of rapid user inflow, rapid user checking and rapid user loss of real estate sales business, so that acquired user behavior data and data processing are dynamically achieved, and effectiveness is guaranteed.

In another embodiment of the present disclosure, the step S310 includes:

and extracting user behavior data based on a set time window for a business system where the real estate sales business is located.

As indicated above, the service system to which the user behavior data processing is performed is interfaced includes, in addition to an external service system related to the real estate sales service, such as a federation platform, a service system where the real estate sales service is located, such as a messaging system.

Therefore, the user behavior data should be acquired from the service system where the real estate sales service is located, and the timeliness of the acquired user behavior data is guaranteed under the action of the set time window.

In one embodiment, the owned service system of the property sales service, and the user's session related to the property sales, the synchronously generated message is the user behavior data, which is synchronized in the message synchronization table of the service system.

The message synchronization table is used for extracting user behavior data through a set time window and further used for subsequent statistical distribution, for example, the number of times that the user and the business consultant send messages is obtained.

In summary, by continuously scrolling to obtain user behavior data, users who quickly flow in, quickly check, and quickly run off in real estate sales can be effectively captured, thereby achieving dynamic, continuously scrolling user value assessment.

In order to guarantee timeliness, in the execution of step S310, continuous and rolling acquisition of user data is realized through a defined time window, for example, the defined timeliness of the time window may be 7 days, that is, user behavior data within 7 days is acquired for processing.

In the executed user behavior data acquisition, as indicated above, a plurality of service systems including the own service system and the external service system are docked in the service data layer, so that the user behavior data can be widely acquired, the data volume of the data processing is guaranteed, and the accuracy is enhanced.

In step S320, the obtained user behavior data is subjected to a data processing based on two levels of the number of user activities and the degree of intention. It should be noted that the number of times of user activity refers to the number of times of service association between the user and the property sales service, where the service association is triggered by a user's behavior event, such as clicking, browsing, consulting a service counselor, etc. The user activity number describes the attention and approval of a user to the real estate sales service in terms of frequency, particularly the repeated activity represents the approval degree, and the approval degree is higher along with the increase of the user activity number in terms of value.

The intention degree is used for representing the intention of the user to the sold property, and the probability of the sold property is larger when the value of the intention integral value is higher. The degree of intent will also be analyzed and calculated by the user's behavioral events, such as clicking on a reservation to see a room, clicking on an initiated session, browsing a floor details page, interacting with a referring consultant to send a message, etc.

The user behavior event and the corresponding intention integral value have a mapping relation, the behavior event of each user is converted into a score through the mapping relation, and the intention integral value of the user can be obtained through accumulation. In other words, different behavior events correspond to different intention integration values, and for a plurality of behavior events described by a user in the user behavior data of the user, the intention integration value corresponding to each behavior event is accumulated to obtain the intention integration value of the user, and further, the intention of the user to the property sales made by the user is described through the intention integration value of the user.

Referring to fig. 5, fig. 5 is a flowchart illustrating steps of performing a digitization process on the user activity times and the intention degree according to the user behavior data to obtain user activity times and intention integration values according to an embodiment of the disclosure corresponding to fig. 3. The step S320 of performing a digitization process on the user activity number and the intention degree according to the user behavior data to obtain the user activity number and the intention integral value includes:

step S321, extracting user events related to the real estate sales service from the user behavior data.

Step S322, determining the number of times of the association between the user and the set real estate sales service occurrence service as the user active number corresponding to the user according to the user event.

Step S323, according to the event integral data mapped by the user event, the digital description of the user to the intention of the real estate sales service is carried out to obtain the intention integral value

These steps are described in detail below.

In step S321, user events related to the property sales service in the user behavior data are extracted to obtain which events the user triggered on the property for sale, and then statistical analysis is performed.

The user behavior data obtained in step S310 is obtained by preliminary extraction, and therefore a series of preprocessing processes need to be performed, i.e. data is taken as the basis for statistics and reduction, and some useless fields are removed to extract useful information. For the data of the user rows from the same business system, the users need to be associated with each other so as to ensure the integrity and accuracy of the data corresponding to the users.

Correspondingly, step S321 may extract the user event related to the real estate sales service from the user behavior data that has completed the preprocessing.

In step S3212, for the extracted user event, statistics of the corresponding user activity times is performed for the user, where the user activity times reflect the triggering times of online browsing and interaction of the user on the real estate sales, and therefore, it should be noted that the statistics of the user activity times performed include repeated activity statistics.

In step S323, the event tally data includes a mapping relationship between both the user event and the intention tally value. Through the event integration data, the user events extracted from the user behavior data can be described in a data mode to obtain the intention integration value. And flexibly setting and adjusting event point data according to the operation of the real estate sales service.

Referring to fig. 6, fig. 6 is a flowchart illustrating steps of performing a digitization process on the user activity times and the intention degree according to the user behavior data to obtain user activity times and intention integration values according to an embodiment of the present disclosure corresponding to fig. 3. The step S320 of performing the digitization processing on the user activity number and the intention degree according to the user behavior data to obtain the user activity number and the intention integral value shown in the present disclosure further includes, before performing the step S323:

step S325, the extracted user event is analyzed to obtain a user access path.

Step S326, executing deduplication processing of the corresponding user event for the user according to the user access path.

After user events are screened and extracted from user behavior data, for user events outside pages related to the real estate sales service, such as power on, call dialing, consulting business consultants and the like, the user access path obtained through analysis is subjected to deduplication processing, so that one user can be ensured to trigger the user events only once, and repeated conversion of the user events to intention integral values is avoided.

In step S330, the user of the property sales service defines an active attribute and an intention attribute, and sets corresponding attribute values by the number of times the user is active and the value of the intention integration obtained by the numerical processing, respectively.

Specifically, an active attribute value is set according to the number of times the user is active, and an intention attribute value is set according to the magnitude of an intention integral value. For example, for a larger number of active users and a larger intention integration value, the corresponding active attribute value and intention attribute value are both set to 1; for smaller number of user activations and smaller intention integration values, the corresponding active attribute value and intention attribute value are set to 0.

Based on the above, threshold values are respectively set for the number of user activity and the intention integral value, the threshold values are dynamically changed, and the corresponding threshold values are different for different user activity conditions and intentions, so that the adaptivity and reliability of the user evaluation are ensured.

Referring to fig. 7, fig. 7 is a flowchart illustrating steps of setting an active attribute value and an intention attribute value corresponding to a user according to the number of active users and an intention integration value according to an embodiment corresponding to fig. 3. The step S330 of performing the active attribute value and the intention attribute value corresponding to the user according to the number of active times and the intention integral value of the user in the embodiment of the disclosure includes:

step S331, mapping the pre-divided interval range for the user activity number and the intention integration value to obtain interval range values respectively corresponding to the user activity number and the intention integration value.

Step S333, setting an active attribute value and an intention attribute value for the user according to the magnitude relationship between the interval range value and the threshold value.

The method comprises the steps of dividing intervals for the number of active times of a user and an intention integral value in advance, wherein each interval has a corresponding interval range value.

Illustratively, the values are divided into 5 interval ranges from low to high, and the corresponding interval ranges are 1 to 5.

Therefore, the number of user activity and the intention integral value are actually normalized, so that the subsequent calculation is facilitated.

In step S333, when the section range value is higher than the threshold value, the attribute value is set to 1; when the span range value is lower than the threshold value, the attribute value is set to 0.

The threshold value for setting the attribute value may be dynamically generated by a weighted average calculation performed on the section range value.

In an embodiment of the present disclosure, the step S330 of setting the active attribute value and the intention attribute value corresponding to the user according to the number of active times of the user and the intention integral value further includes:

In step S340, according to the set active attribute value and the set intention attribute value, user labels are distributed in the user active and user intention dimensions, and the labeled user labels represent the value of the user.

Specifically, the step S340 includes: and generating a user tag according to the user value numerically represented by the real estate sales service according to the active attribute value and the intention attribute value, wherein the user tag is used for describing the user value on the occurrence frequency and the intention of events related to the real estate sales service.

Thus, the user tag may include: the high frequency high intention, the low frequency high intention, the high frequency low intention and the low frequency low intention correspond to four high-to-low value groups, respectively. For the real estate sales service, a user with a high frequency and high intention belongs to an important value user, and the user can follow the real estate sales service in a Buddha-killing key point; the user label is a user with low frequency and high intention, which is a user with high intention but low activity viewed recently, belongs to an important deep ploughing user and needs to follow up; the user label is a user with high frequency and low intention, which is a user with high active frequency and low intention recently checked, belongs to a potential user, needs to implement guidance and improves the intention; the user label is a user with low frequency and low intention, which is a user with low intention and low active frequency recently viewed, belongs to a new user and needs multiple conversions.

Therefore, in the scene of real estate sales, data processing is carried out through an algorithm, under the condition that consumption time, consumption frequency and consumption amount are not available, dynamic user label marking can be carried out only through browsing of real estate information by a user, the purchase intention of the user is displayed dynamically, convenience is further provided for subsequent personalized communication and service, and decision support is also provided for real estate marketing.

The processing of customer line data in a property sale is described in the conduct of the property sale service.

FIG. 8 is an architectural diagram illustrating the various layers of data processing according to one embodiment of the present disclosure. As shown in fig. 8, the data processing architecture constructed for the production sales service has a business data layer as the bottom layer, and the user behavior data generated by a plurality of business systems form the data existence in the business data layer.

Specifically, as shown in fig. 8, the alliance applet access table and the alliance applet event detail table in the service data layer are all user behavior data related to the real estate sales service uploaded by the alliance platform. And embedding points of events of the users when the users use the small programs through the alliance platform, namely configuring marketing embedding point data, and uploading user behavior data generated by embedding points to a service system where the user behavior data are located, namely an alliance end. That is, the user behavior data stored on the member side, i.e., the member applet access table and the member applet event detail table, constitute part of the data existence of the service data layer.

The im synchronization table in the service data layer is a message synchronization table of the own service system, which stores messages sent by users, and this also constitutes a bottom data source formed by the service data layer.

It can be understood that in the service data layer, the user behavior data exist in different service systems, and need to be extracted for statistical analysis, and thus, the ODS layer is an extracted copy.

By counting and simplifying basic data in the ODS layer, removing useless fields and extracting useful information, user behavior data capable of being processed in a numerical mode is obtained and exists in the forms of an access detail list and an event detail list. And the added item information table is used for associating information such as regional cities and the like with the data so as to facilitate the processing of the data.

And (4) acquiring the intermediate table of the hidden passenger by correlating the access list, the event list and the im synchronization list, wherein the intermediate table is a basic table for carrying out statistical analysis on the DWS layer.

The DWS layer summary table is a table that correlates the intermediate tables of the hidden passengers with an integration rule table, i.e., event integration data, to calculate an RFM value of each user, i.e., an F value (active attribute value) and an M value (intention attribute value) corresponding to R (timeliness) are subtracted through a time window.

The ADS layer further summarizes the table of the DWS layer, different user labels are attached to different RFM attributes of the users, the user levels are further divided according to the user labels, and user values are directly obtained.

To this end, it should be further explained that the intermediate table of the hidden guests in the DWD layer includes the specific events screened according to the service requirements:

(1) events except for p-page, such as power conservation, call dialing, consultation and the like, analyzing json fields to obtain access paths, and removing duplication to ensure that one user only triggers one event;

(2) the p-page event mainly refers to the stay time for browsing each page, and the user stay time needs to be obtained by calculating the time difference between the start and the end of the trigger event.

R, F and M values of each user are calculated in DWS layer cloud, and for R value, under the action of setting a time window, a time interval corresponding to user behavior data is specified, for example 7 days, so that R is reduced, and only two elements of F and M need to be considered.

For the F value, it can be obtained by counting the number of activations of each user in 7 days.

For the value M, through a self-defined event integration rule table, for example, different events or events with different use or stay time durations correspond to different intention integral values, all events of each user are converted into intention integral values, and then accumulation is carried out.

And mapping to 5 interval ranges divided from low to high according to the F value and the M value to obtain corresponding interval range values.

Performing weighted average calculation on all the interval range values to obtain a currently applicable threshold, and setting the corresponding attribute value to be 1 for the interval range value higher than the threshold at the moment; and setting the corresponding attribute value to be 0 for the interval range value lower than the threshold value.

To this end, a user tag of each user can be generated according to the obtained attribute values, and the users are divided into A, B, C and D classes, as shown in fig. 9, that is:

(1) the F value is 1, and the user with the M value of 1 is a class A user (high frequency and high intention);

(2) the F value is 0, and the user with the M value of 1 is a B-class user (low-frequency high intention);

(3) the F value is 1, and the user with the M value of 0 is a C-class user (high-frequency low intention);

(4) the F value is 0, and the user with the M value of 0 is a D-class user (low frequency and low intention).

After the data processing is finished, the data can be derived according to the method, the front-end display is carried out, a one-stop type insight decision tool is provided for operation management personnel, the front-end workload is greatly reduced, and the efficiency and the accuracy of the customer screening of marketing personnel are improved.

It should be added that the RFM model, which is an important tool and means for measuring the value of a customer and the ability of the customer to create profit, describes the value of a room by 3 indexes of recent purchase (R), the overall frequency (F) of purchases and how much money (M, amount of consumption) a customer spends.

However, the RFM model is only widely used in customer analysis of fast-moving goods, and cannot be applied to real estate sales scenarios because of no consumption time, consumption frequency and consumption amount.

According to the data processing implementation of the real estate sales service dynamic analysis method, dynamic analysis is carried out by considering three dimensions, namely R (timeliness), F (frequency) and M (intention), so that the real estate industry can also carry out user value analysis, the division of the users is simple, the practicability is enhanced while the application range is widened, and high-performance user value analysis service can be provided for real estate sales service.

The following are embodiments of the apparatus of the present disclosure that may be used to implement embodiments of the method of the user behavior data processing system in the aforementioned geo-production sales of the present disclosure. For details not disclosed in the embodiments of the device of the present disclosure, please refer to the embodiments of the user behavior data processing system method in the sales of the local production.

FIG. 10 is a block diagram illustrating a user behavior data processing system in an earth-based sales, according to an example embodiment. The user behavior data processing system in the local production sale, as shown in fig. 10, includes but is not limited to:

a data acquisition module 410 for continuously and rollingly acquiring user behavior data describing user behavior associated with a property sale to a business system associated with the property sale;

the numerical processing module 420 is configured to perform numerical processing on the user activity times and the intention degree according to the user behavior data to obtain user activity times and intention integral values;

the attribute setting module 430 is configured to set an active attribute value and an intention attribute value corresponding to the user according to the number of active times and the intention integral value of the user, where the active attribute value and the intention attribute value are 0 or 1 in value;

and the labeling module 440 is used for labeling the user label of the user of the property sales service according to the active attribute value and the intention attribute value.

In one embodiment of the present disclosure, the data acquisition module 410 continuously and rollingly acquires user behavior data describing user behavior related to the sales of a property to a business system related to the sales of the property, comprising:

the generated user behavior data is extracted based on the set time window.

In an embodiment of the disclosure, the digitizing processing module 430 performs digitizing processing on the number of user activities and the degree of intention according to the user behavior data, and obtains a value of the number of user activities and a value of an intention integral, including:

analyzing the extracted user event to obtain a user access path;

Furthermore, for the user event obtained by analysis, a series of preprocessing processes such as screening and integrated calculation are executed according to the service requirement, so that data redundancy is avoided, and data meeting the execution requirement is obtained.

In an embodiment of the disclosure, the setting module 440 sets the active attribute value and the intention attribute value corresponding to the user according to the number of active times and the intention integral value of the user, including:

In one embodiment of the present disclosure, the tagging module 450 tags the user of the property sales service with a user tag according to the active attribute value and the intention attribute value, including:

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer program medium having stored thereon computer readable instructions which, when executed by a processor of a computer, cause the computer to perform the method described in the above method embodiment section.

According to an embodiment of the present disclosure, there is also provided a program product for implementing the method in the above method embodiment, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments 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 disclosed 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 true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A user behavior data processing method in the sale of the local production is characterized by comprising the following steps:

2. The method of claim 1, wherein the continuously and rollingly obtaining user behavior data for a business system associated with a property sales business comprises:

the generated user behavior data is extracted based on the set time window.

3. The method of claim 1, wherein said continuously and rollingly obtaining user behavior data for a business system associated with a set property sales business comprises:

4. The method according to claim 1, wherein the performing a numerical process of the number of user activations and the degree of intention according to the user behavior data to obtain the value of the integrated user activations and the value of the integrated intention includes:

5. The method of claim 4, wherein prior to the step of the user obtaining an intent credit value based on the event credit data of the user event map for the digitized description of the intent of the property sales service,

analyzing the extracted user event to obtain a user access path;

6. The method according to claim 1, wherein the setting of the active attribute value and the intention attribute value corresponding to the user according to the number of active users and the intention integral value comprises:

7. The method according to claim 6, wherein the setting of the active attribute value and the intention attribute value corresponding to the user according to the number of active users and the intention integration value further comprises:

8. The method of claim 1, wherein tagging users of the property sales service with user tags according to the active attribute values and intent attribute values comprises:

9. A system for processing user behavior data in an earth production sale, the system comprising:

10. A computer program medium having computer readable instructions stored thereon, which when executed by a processor of a computer, cause the computer to perform the method of any one of claims 1-8.