CN110675069B - Real estate industry client signing risk early warning method, server and storage medium - Google Patents
Real estate industry client signing risk early warning method, server and storage medium Download PDFInfo
- Publication number
- CN110675069B CN110675069B CN201910919623.1A CN201910919623A CN110675069B CN 110675069 B CN110675069 B CN 110675069B CN 201910919623 A CN201910919623 A CN 201910919623A CN 110675069 B CN110675069 B CN 110675069B
- Authority
- CN
- China
- Prior art keywords
- client
- time
- signing
- coefficient
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 59
- 238000012417 linear regression Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 238000012550 audit Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 230000002411 adverse Effects 0.000 claims 2
- 230000000694 effects Effects 0.000 claims 2
- 238000012360 testing method Methods 0.000 claims 1
- 238000012502 risk assessment Methods 0.000 abstract description 5
- 230000002093 peripheral effect Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a client signing risk early warning method, a server and a storage medium in the geological industry, wherein the method mainly comprises the steps of obtaining access behavior data of a client to be tested, and calculating a client behavior signing intention coefficient; comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result; acquiring event time nodes of a client to be tested in a marketing stage, and calculating a client marketing signing efficiency coefficient; comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result; and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result. The risk assessment index system of the client signing life cycle is constructed by analyzing various factors influencing the client signing risk from the client registration to the signing full life cycle signing principle, and the client signing risk condition is objectively analyzed and judged based on the client access behavior data and each event time node in the marketing stage.
Description
Technical Field
The invention relates to the technical field of data analysis of the real estate industry, in particular to a client signing risk early warning method, a server and a storage medium for the real estate industry.
Background
The traditional landfills industry uses paper customer file record to follow up visiting customers for a long time at marketing building plan field, to different preference type customers, carries out a large amount of follow-up, communications for a long time, but marketing personnel are numerous, and the customer is thousand people thousand faces, can't carry out the science to the risk of signing a contract to the customer and is controlled, wastes time and energy and a lot of results. On one hand, due to the fact that the number of receptions is large and the period is long, marketing personnel can only subjectively communicate with customers to judge the preference and the intention of the customers and cannot objectively judge through data of long-term behaviors and expressions of the customers; on the other hand, marketing managers cannot objectively judge, analyze and manage the signing risk condition of the client by using a large amount of scattered and disordered time and data, so that the time, energy and other resources of the marketing managers are wasted and lost.
Disclosure of Invention
The invention provides a real estate industry client signing risk early warning method, a server and a storage medium, which mainly solve the technical problems that: the signing risk condition of the client cannot be objectively judged, analyzed and managed, and great waste is caused to resources such as time, energy and the like of marketing personnel.
In order to solve the technical problem, the invention provides a client signing risk early warning method for the local production industry, which comprises the following steps:
obtaining access behavior data of a client to be tested, wherein the access behavior data comprises a building detail browsing duration T1Time T for browsing photo album of building2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7；
Calculating weighted time and T' based on the weight coefficients corresponding to various duration indexes;
calculating a client behavior signing intention coefficient according to the weighted time and the T';
comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result;
acquiring event time nodes of the to-be-tested customer in a marketing stage, wherein the event time nodes comprise channel backup customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9；
For the t1、t2、t3、t4、t5、t6、t7、t8Performing one-dimensional linear regression with the regression equation of f (x) ═ a + bx;
calculating the regression coefficient b as a client marketing signing efficiency coefficient;
comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result;
and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result.
Optionally, said pair of said t1、t2、t3、t4、t5、t6、t7、t8Performing a unary linear regression includes: according to the t1、t2、t3、t4、t5、t6、t7、t8And forming a marketing stage trigger time scatter diagram, and performing unary linear regression after filtering interference data.
Optionally, the calculating a client behavior subscription intention coefficient according to the weighted time and T' includes:
mapping the weighted time sum T' to
Calculating a corresponding y value, and taking the y value as the client behavior signing intention coefficient; the k is greater than 0.
Optionally, at said pair of said t1、t2、t3、t4、t5、t6、t7、t8Before performing the unary linear regression, the method further comprises: determining that the current time does not exceed the contracted sign-on time t9。
Optionally, the method further includes: if the current time exceeds the appointed contract signing time t9And directly determining that the second comparison result is that the marketing and signing efficiency coefficient of the client is greater than or equal to the maximum set threshold value in the second set of set threshold values.
Optionally, the obtaining the signing risk level of the customer to be tested according to the first comparison result and the second comparison result includes: and determining a first risk grade corresponding to the first comparison result and a second risk grade corresponding to the second comparison result, comparing the risk grade between the first risk grade and the second risk grade, and taking the risk grade with the highest risk grade as the signing risk grade of the client to be tested.
The invention also provides a server, which comprises a processor, a memory and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute one or more programs stored in the memory to implement the method steps of:
obtaining access behavior data of a client to be tested, wherein the access behavior data comprises a building detail browsing duration T1And the browsing duration T of the building photo album2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5And the search and browsing duration T of the building6Micro chat duration T for client and business consultant7；
Calculating weighted time and T' based on the weight coefficients corresponding to various duration indexes;
calculating a client behavior signing intention coefficient according to the weighted time and the T';
comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result;
acquiring event time nodes of the to-be-tested customer in a marketing stage, wherein the event time nodes comprise channel backup customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9；
For the t1、t2、t3、t4、t5、t6、t7、t8Performing one-dimensional linear regression with the regression equation of f (x) ═ a + bx;
calculating the regression coefficient b as a client marketing signing efficiency coefficient;
comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result;
and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result.
Optionally, the processor is configured to execute one or more programs stored in the memory, so as to implement the calculating the client behavior subscription intention coefficient according to the weighted time and the T' includes:
mapping the weighted time sum T' to
Calculating a corresponding y value, and taking the y value as the client behavior signing intention coefficient; the k is greater than 0.
Optionally, the processor is configured to execute one or more programs stored in the memory, so that obtaining the signing risk level of the customer to be tested according to the first comparison result and the second comparison result includes:
and determining a first risk grade corresponding to the first comparison result and a second risk grade corresponding to the second comparison result, comparing the risk grade between the first risk grade and the second risk grade, and taking the risk grade with the highest risk grade as the signing risk grade of the client to be tested.
The present invention also provides a storage medium storing one or more programs executable by one or more processors to implement the steps of the real estate industry client sign-up risk early warning method as described above.
The invention has the beneficial effects that:
the method mainly comprises the steps of obtaining access behavior data of a client to be detected, wherein the access behavior data comprises the detailed browsing duration T of a building1Time T for browsing photo album of building2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7(ii) a Calculating weighted time and T' based on the weight coefficients corresponding to various duration indexes; calculating the client behavior contract according to the weighted time and TA directional coefficient; comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result; acquiring each event time node of a customer to be tested in a marketing stage, wherein each event time node comprises a channel for reporting customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9(ii) a For t1、t2、t3、t4、t5、t6、t7、t8Performing one-dimensional linear regression with the regression equation of f (x) ═ a + bx; calculating a regression coefficient b as a client marketing signing efficiency coefficient; comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result; and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result. The risk assessment index system of the client signing life cycle is constructed by analyzing various factors influencing the client signing risk from the client registration to the signing full life cycle, the client signing risk condition is objectively analyzed and judged based on the client access behavior data and event time nodes in the marketing stage, the client signing preference and intention are not required to be judged by marketers through communication, the workload of the marketers is reduced, and meanwhile, the timely follow-up processing is facilitated based on the timely control on the client signing risk, so that the client signing efficiency can be improved to a certain extent, and the sales performance of the real estate industry is improved.
Drawings
Fig. 1 is a schematic flow chart of a risk early warning method for signing a contract of a customer in a real estate industry according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of risk assessment indicators according to a first embodiment of the present invention;
FIG. 3 is a scatter diagram of trigger times of a marketing phase according to a first embodiment of the present invention;
fig. 4 is a schematic structural diagram of a server according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following detailed description and accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The first embodiment is as follows:
in order to solve the problem that no objective and accurate analysis method is specially carried out on the signing risk of the client in the current real estate industry, the invention analyzes various factors and indexes influencing the signing risk of the client based on the access behavior data of the full life cycle of the client and the event time nodes in the marketing stage, constructs a client signing risk assessment index system, carries out verification by utilizing the measured data, has higher accuracy and stability and meets the signing risk early warning requirement of the real estate industry.
Referring to fig. 1, fig. 1 is a schematic flow chart of a risk early warning method for a customer signing contract in a real estate industry provided in this embodiment, where the method mainly includes:
s101, obtaining access behavior data of a client to be tested, wherein the access behavior data comprises a building detail browsing duration T1Time T for browsing photo album of building2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7。
Optionally, the server may record access behavior data of (intention of) the client purchasing the house on the client under the authorization condition, for example, information collection storage such as login condition, browsing duration, browsing content and the like of the client. The anchor point can be specifically set under the corresponding functional module of the client side to record the access behavior.
In this embodiment, the following 7 indexes of the client access behavior data are used: time T for browsing details of building1Time T for browsing photo album of building2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5BuildingDisk search viewing browsing duration T6Micro chat duration T for client and business consultant7。
In other embodiments of the invention, more or fewer of the above criteria may be selected.
S102, calculating the weighted time and T' based on the weight coefficients corresponding to the various duration indexes.
Please refer to table 1 below, each index uniquely corresponds to a weight coefficient, which represents the degree of the client to the signing intention, the larger the weight coefficient is, the stronger the signing intention is, the signing risk is relatively controllable, and the smaller the coefficient is, the smaller the signing intention is, the attention needs to be strengthened, and the client loss is prevented.
TABLE 1
| Duration index name | Duration T | Weight coefficient h | Weighted time T' |
| Duration T is browsed to building detail1 | 2.00 | 0.60 | 1.20 |
| Building photo album browsing duration T2 | 2.00 | 0.90 | 1.80 |
| House type browsing duration T3 | 2.00 | 0.60 | 1.20 |
| Duration T of peripheral matching browsing4 | 1.00 | 0.90 | 0.90 |
| Browsing duration T of housing loan calculator5 | 0.90 | 0.90 | 0.81 |
| Search and view duration T for building6 | 0.10 | 0.90 | 0.09 |
| Micro chat duration T for client and place consultant7 | 0.30 | 1.00 | 0.30 |
In this embodiment, the weight coefficients corresponding to the various types of duration indexes may be set according to the experience of the real estate industry, or the weight coefficients of the indexes may be determined by combining layer analysis methods.
And S103, calculating a client behavior subscription intention coefficient according to the weighted time and the T'.
Optionally, the weighted time sum T' is mapped to
Calculating corresponding y value, and making the y value asSigning intention coefficients for customer behavior; k is greater than 0.
As shown in table 1, T' is 6.3, which is mapped to
Assuming that k is 10, y is 6.3/16.3 and 38.65%, which is used as the client behavior subscription intention coefficient. The higher the value is, the stronger the signing intention of the client is, and the lower the signing risk is, otherwise, the weaker the signing intention of the client is, the high signing risk is, and the attrition rate is high.
Please refer to fig. 2, which relates to the mapping function
T' is more than or equal to 0, y is more than or equal to 0 and less than 1, wherein k is more than 0 and can be set according to the experience of the real estate industry, and the higher the k value is, the higher the requirement is.
Preferably, the k value range is set to 10 to 100, for example, 20.
And S104, comparing the client behavior signing intention coefficient with the first set threshold value group to obtain a first comparison result.
In this embodiment, the first set of set thresholds includes a first set threshold i, wherein the first set threshold i can be flexibly set based on property industry experience or based on measured data results. Alternatively, the first set threshold i is set to 90%.
Comparing the client behavior subscription intention coefficient with the first set of threshold values to obtain the following two comparison results:
(1) the customer behavior subscription intention coefficient is larger than or equal to the first set threshold value i. The sign intention of the customer to be tested is strong, and the sign risk is low.
(2) The customer behavior subscription intention coefficient is smaller than the first set threshold value i. The sign-up intention of the customer to be tested is relatively weak, and the sign-up risk is relatively high. And the sales personnel are informed to follow up the processing in time, so that the loss is avoided.
In other embodiments of the invention, the first set of set threshold values may comprise a plurality of threshold values to form a threshold interval, e.g. the first set of set threshold values comprises: a first set threshold j, a first set threshold n and a first set threshold d, wherein j is less than n and less than d; for example, j is 50%, n is 75%, d is 95%; comparing the client behavior subscription intention coefficient with the first set of threshold values to obtain the following four comparison results:
(1) the client behavior subscription intention coefficient is less than j; the signing intention of the client to be tested is relatively weak, or even no signing intention exists, and the signing risk is extremely high.
(2) The client behavior signing intention coefficient is larger than or equal to j and smaller than n; the method indicates that the signing intention of the client to be tested is general, the signing risk is high, guidance follow-up is needed, and signing is possibly promoted.
(3) The client behavior signing intention coefficient is greater than or equal to n and smaller than d; the method indicates that the subscription intention of the customer to be tested is high, the subscription risk is general, and the subscription is possible greatly.
(4) The client behavior signing intention coefficient is more than or equal to d; the method indicates that the subscription intention of the client to be tested is extremely high, and the subscription risk is very low, for example, the client actively requires subscription.
It should be understood that the first set of threshold values is not limited to setting several threshold values, and can be flexibly set in the above manner, which is not limited by the embodiment.
S105, obtaining each event time node of the customer to be tested in the marketing stage, wherein each event time node comprises a channel for reporting customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9。
It should be understood that, before the room-viewing client visits a case and looks at a room, a third party or a salesperson reports client information in advance through the client, such as client name, telephone, room-viewing time and the like, the server sends a corresponding preparation request to a corresponding existing manager for processing, and the existing manager checks the preparation request to be approved through logging in the client; the current management confirms the reception team, correspondingly sends the request to the sales warp of the reception team, logs in the client through the sales warp, checks the distributed request, and appoints the corresponding salesman who is the service advisor to receive; after the customer visits the case, the customer is received by the appointed salesperson and confirmed at the customer terminal. The server collects and stores the operation behaviors of a third party, a current management server, a sales staff or a employment consultant on the client side so as to acquire each event time node of the client to be tested in the marketing stage.
The event time nodes generally have a certain sequence, and the processing efficiency of the previous link will have an absolute influence on the occurrence time node of the next action. For example, the sales can not be assigned to the appointed personnel for reception and can not be built and subscribed without auditing at present. Based on the above, in the embodiment, based on the correlation of each event time node, the client marketing signing coefficient affecting the client signing risk is analyzed, so that the potential risk level of the client signing is objectively, truly and accurately reflected, thereby realizing risk early warning, helping local manufacturers to promote bargain and improving the conversion rate.
In addition, there is no necessarily order of execution for steps S101 and S105, and it should be understood that any serial or parallel processing may be possible.
S106, for t1、t2、t3、t4、t5、t6、t7、t8A one-dimensional linear regression is performed with the regression equation f (x) a + bx.
And performing linear regression on the time nodes, and calculating a regression coefficient of a regression equation to be used as a client marketing contract-signing coefficient. The regression coefficient can reflect the change rate condition of each event node, and the larger the regression coefficient is, the higher the change rate is, which indicates that the longer the time interval between events is, the higher the corresponding potential signing risk is, which is not beneficial to normal signing, and increases the customer churn probability. On the contrary, if the regression coefficient is smaller, the time node of each event is compact and the progress is smooth, and the natural signing risk is reduced.
Optionally, in order to ensure the accuracy of the constructed regression equation and ensure the accuracy of the regression coefficient, the method may be performed according to t1、t2、t3、t4、t5、t6、t7、t8And forming a marketing stage trigger time scatter diagram, filtering interference data, and performing unary primary linear regression to reduce regression errors.
The formed marketing phase trigger time scatter diagram is shown in FIG. 3, in which the filing verification time t7Obviously belong to the interference data, because other data are in an increasing state and the filing verification time t7The points are inflection points, so the points are filtered out and do not participate in the linear regression, and more scattered points are on the regression curve.
Optionally, in the pair t1、t2、t3、t4、t5、t6、t7、t8Before performing the unary linear regression, the method further comprises: determining that the current time does not exceed the contracted sign-on time t9。
If the current time exceeds the appointed contract signing time t9And if the client to be tested is not signed on time, directly determining the second comparison result that the marketing signing efficiency coefficient of the client is greater than or equal to the maximum set threshold value in the second set threshold value group.
It should be noted that one or more second setting threshold values may be set in the second setting threshold value group, and the maximum setting threshold value in the second setting threshold value group, that is, the corresponding subscription risk level, is the highest. If the current time exceeds the appointed contract signing time t9And directly determining that the second comparison result is that the marketing signing efficiency coefficient of the client is greater than or equal to the maximum set threshold value in the second set threshold value group, and determining that the signing risk is in a higher level without a linear regression process so as to improve the data processing efficiency.
And S107, calculating a regression coefficient b as a client marketing signing efficiency coefficient.
And S108, comparing the marketing and signing efficiency coefficient of the client with the second set threshold value group to obtain a second comparison result.
It should be understood that the second setting threshold set in the second setting threshold set can be set by using the setting manner of the first setting threshold set, and will not be described herein.
And S109, obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result.
And determining a first risk grade corresponding to the first comparison result and a second risk grade corresponding to the second comparison result, comparing the risk grade between the first risk grade and the second risk grade, and taking the risk grade with the highest risk grade as the signing risk grade of the client to be tested.
Optionally, two situations, high risk and low risk, are assumed to exist in the first comparison result; the second comparison result is that there are two cases, high risk and low risk; obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result, wherein the following conditions exist:
(1) determining the signing risk grade of the client to be tested as low risk according to the first comparison result and the second comparison result;
(2) determining the signing risk grade of the client to be tested as high risk according to the first comparison result as low risk and the second comparison result as high risk;
(3) determining the signing risk grade of the client to be tested as high risk according to the first comparison result as high risk and the second comparison result as low risk;
(4) and determining the signing risk grade of the client to be tested as high risk according to the first comparison result and the second comparison result.
According to the real estate industry client signing risk early warning method provided by the invention, the access behavior data of the client to be detected is obtained, and the access behavior data comprises the detailed building browsing duration T1Time T for browsing photo album of building2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7(ii) a Calculating weighted time and T' based on the weight coefficients corresponding to various duration indexes; calculating the client based on the weighted time sum TA behavioral signing intention coefficient; comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result; acquiring each event time node of a customer to be tested in a marketing stage, wherein each event time node comprises a channel for reporting customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit-to-departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9(ii) a For t1、t2、t3、t4、t5、t6、t7、t8Performing one-dimensional linear regression with the regression equation of f (x) ═ a + bx; calculating a regression coefficient b as a client marketing signing efficiency coefficient; comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result; and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result. The risk assessment index system of the client signing life cycle is constructed by analyzing various factors influencing the client signing risk from the client registration to the signing full life cycle, the client signing risk condition is objectively analyzed and judged based on the client access behavior data and event time nodes in the marketing stage, the client signing preference and intention are not required to be judged by marketers through communication, the workload of the marketers is reduced, and meanwhile, the timely follow-up processing is facilitated based on the timely control on the client signing risk, so that the client signing efficiency can be improved to a certain extent, and the sales performance of the real estate industry is improved.
Example two:
in this embodiment, on the basis of the first embodiment, a server is provided, please refer to fig. 4, which includes a processor 41, a memory 42 and a communication bus 43; wherein the communication bus 43 is used for realizing connection communication between the processor 41 and the memory 42;
obtainingThe access behavior data of the client to be tested comprise the detailed browsing duration T of the building1Time T for browsing photo album of building2Family type browsing duration T3And a peripheral matching browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7。
And calculating the weighted time and T' based on the weight coefficients corresponding to the various time length indexes.
And calculating a client behavior subscription intention coefficient according to the weighted time and the T'.
Mapping weighted time sums T' to
Calculating a corresponding y value, and taking the y value as the client behavior signing intention coefficient; k is greater than 0.
And comparing the client behavior signing intention coefficient with the first set threshold value group to obtain a first comparison result.
Acquiring each event time node of a customer to be tested in a marketing stage, wherein each event time node comprises a channel for reporting customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9。
For t1、t2、t3、t4、t5、t6、t7、t8A first linear regression is performed with f (x) being a + bx.
And calculating a regression coefficient b as a client marketing signing efficiency coefficient.
And comparing the marketing signing efficiency coefficient of the client with the second set threshold value group to obtain a second comparison result.
And obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result.
And determining a first risk grade corresponding to the first comparison result and a second risk grade corresponding to the second comparison result, comparing the risk grade between the first risk grade and the second risk grade, and taking the risk grade with the highest risk grade as the signing risk grade of the client to be tested.
The server provided in this embodiment is mainly used to implement the steps of the warning method for the risk of signing a contract of a client in the real estate industry described in the first embodiment. For details, please refer to the description in the first embodiment, which is not repeated herein.
The present embodiment also provides a storage medium storing one or more programs, which are executable by one or more processors to implement the steps of the real estate industry client contract risk early warning method as described in the first embodiment. For details, please refer to the description in the first embodiment, which is not repeated herein.
It will be apparent to those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented in program code executable by a computing device, such that they may be stored on a computer storage medium (ROM/RAM, magnetic disks, optical disks) and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The foregoing is a more detailed description of the present invention that is presented in conjunction with specific embodiments, and the practice of the invention is not to be considered limited to those descriptions. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. A client signing risk early warning method for the local production industry is characterized by comprising the following steps: obtaining access behavior data of a client to be tested, wherein the access behavior data comprises a building detail browsing duration T1Time T for browsing photo album of building2Family type browsing duration T3And the surrounding matched browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7(ii) a Calculating weighted time and T' based on the weight coefficients corresponding to various duration indexes; calculating a client behavior signing intention coefficient according to the weighted time and the T'; the calculating the client behavior subscription intention coefficient according to the weighted time and the weighted T' comprises the following steps: mapping the weighted time sum T' to
Calculating a corresponding y value, and taking the y value as the signing intention coefficient of the customer behavior; the k is greater than 0; comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result; acquiring event time nodes of the to-be-tested customer in a marketing stage, wherein the event time nodes comprise channel backup customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9(ii) a For the t1、t2、t3、t4、t5、t6、t7、t8Performing one-dimensional linear regression with the regression equation of f (x) ═ a + bx; calculating a regression coefficient b as a client marketing signing efficiency coefficient, wherein x represents a marketing stage, f (x) represents marketing stage triggering time, and a represents marketing stage triggering initial time; performing linear regression on the time nodes, calculating a regression coefficient b of a regression equation as a marketing and signing coefficient of the client,the regression coefficient b reflects the change rate condition of each event node, the larger the regression coefficient b is, the higher the change rate is, the longer the time interval between each event is, the higher the corresponding potential signing risk is, the adverse effect on normal signing is realized, and the loss probability of a client is increased; comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result; and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result.
2. The real estate industry client sign-on risk early warning method of claim 1 wherein the pair of t1、t2、t3、t4、t5、t6、t7、t8Performing a one-dimensional linear regression comprising: according to the t1、t2、t3、t4、t5、t6、t7、t8And forming a marketing stage trigger time scatter diagram, and performing unary primary linear regression after filtering interference data.
3. The real estate industry client sign-on risk early warning method of any one of claims 1-2 wherein at said pair t1、t2、t3、t4、t5、t6、t7、t8Before performing the unary linear regression, the method further comprises: determining that the current time does not exceed the contracted sign-on time t9。
4. The real estate industry client sign-on risk early warning method of claim 3 further comprising: if the current time exceeds the appointed contract signing time t9And directly determining that the second comparison result is that the marketing and signing efficiency coefficient of the client is greater than or equal to the maximum set threshold value in the second set of set threshold values.
5. The real estate industry client signing risk early warning method of claim 1, wherein obtaining the signing risk level of the client to be tested according to the first comparison result and the second comparison result comprises: and determining a first risk grade corresponding to the first comparison result and a second risk grade corresponding to the second comparison result, comparing the risk grade between the first risk grade and the second risk grade, and taking the risk grade with the highest risk grade as the signing risk grade of the client to be tested.
6. A server, comprising a processor, a memory, and a communication bus; the communication bus is used for realizing connection communication between the processor and the memory; the processor is configured to execute one or more programs stored in the memory to implement the method steps of: obtaining access behavior data of a client to be tested, wherein the access behavior data comprises a building detail browsing duration T1Time T for browsing photo album of building2Family type browsing duration T3And the surrounding matched browsing duration T4The browsing duration T of the house credit calculator5And the search and viewing duration T of the building6Micro chat duration T for client and business consultant7(ii) a Calculating weighted time and T' based on the weight coefficients corresponding to various duration indexes; calculating a client behavior signing intention coefficient according to the weighted time and the T'; the calculating the client behavior subscription intention coefficient according to the weighted time and the weighted T' comprises the following steps: mapping the weighted time sum T' to
Calculating a corresponding y value, and taking the y value as the client behavior signing intention coefficient; the k is greater than 0; comparing the client behavior signing intention coefficient with a first set threshold value group to obtain a first comparison result; acquiring event time nodes of the to-be-tested customer in a marketing stage, wherein the event time nodes comprise channel backup customer time t1And the current audit time t2Present pipe distribution time t3Time t is allocated to the pin4Client visit Start time t5Client visit departure time t6Verification time t for filing7Creating a subscription order time t8Contract time t9(ii) a For the t1、t2、t3、t4、t5、t6、t7、t8Performing one-dimensional linear regression with the regression equation of f (x) ═ a + bx; calculating a regression coefficient b as a client marketing signing efficiency coefficient, wherein x represents a marketing stage, f (x) represents marketing stage triggering time, and a represents marketing stage triggering initial time; performing linear regression on the time nodes, calculating a regression coefficient b of a regression equation, taking the regression coefficient b as a marketing signing coefficient of the client, wherein the regression coefficient b reflects the change rate condition of each event node, the larger the regression coefficient b is, the higher the change rate is, the longer the time interval between events is, the higher the corresponding potential signing risk is, the adverse effect on normal signing is realized, the loss probability of the client is increased, and on the contrary, if the regression coefficient b is smaller, the time node of each event is compact, and the natural signing risk is reduced; comparing the client marketing signing efficiency coefficient with a second set threshold value group to obtain a second comparison result; and obtaining the signing risk grade of the client to be tested according to the first comparison result and the second comparison result.
7. The server according to claim 6, wherein the processor is operative to execute one or more programs stored in the memory to implement the calculating a client behavior subscription intent coefficient based on the weighted time sum T' comprises: mapping the weighted time sum T' to
Calculating a corresponding y value, and taking the y value as the client behavior signing intention coefficient; the k is greater than 0.
8. The server according to claim 6, wherein the processor is configured to execute one or more programs stored in the memory to implement the obtaining of the subscription risk level of the customer under test according to the first comparison result and the second comparison result comprises: and determining a first risk grade corresponding to the first comparison result and a second risk grade corresponding to the second comparison result, comparing the risk grade between the first risk grade and the second risk grade, and taking the risk grade with the highest risk grade as the signing risk grade of the client to be tested.
9. A storage medium storing one or more programs, the one or more programs executable by one or more processors to perform the steps of a real estate industry client sign-up risk early warning method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910919623.1A CN110675069B (en) | 2019-09-26 | 2019-09-26 | Real estate industry client signing risk early warning method, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910919623.1A CN110675069B (en) | 2019-09-26 | 2019-09-26 | Real estate industry client signing risk early warning method, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110675069A CN110675069A (en) | 2020-01-10 |
| CN110675069B true CN110675069B (en) | 2022-05-31 |
Family
ID=69079349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910919623.1A Active CN110675069B (en) | 2019-09-26 | 2019-09-26 | Real estate industry client signing risk early warning method, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110675069B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639299A (en) * | 2020-05-20 | 2020-09-08 | 重庆锐云科技有限公司 | Method, system and storage medium for evaluating follow-up performance of client of business consultant |
| CN112184036A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Case wind control real-time early warning system and method |
| TWI833093B (en) * | 2021-07-14 | 2024-02-21 | 信義房屋股份有限公司 | Activity-based credit scoring device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794428A (en) * | 2010-04-08 | 2010-08-04 | 严海强 | Artificial intelligent building sale system |
| EP3057005A1 (en) * | 2015-02-12 | 2016-08-17 | Maurice Duault | Process for computing a score for a search engine used for accessing a database of real estate properties |
| CN108960467A (en) * | 2018-07-09 | 2018-12-07 | 重庆锐云科技有限公司 | Realty information management and data analysis system |
| CN109615128A (en) * | 2018-12-05 | 2019-04-12 | 重庆锐云科技有限公司 | Real estate client's conclusion of the business probability forecasting method, device and server |
| CN109978621A (en) * | 2019-03-25 | 2019-07-05 | 重庆锐云科技有限公司 | Real estate channel customer and commission settlement management method, integral system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140379397A1 (en) * | 2013-06-21 | 2014-12-25 | Agent Bridge, LLC | Method, system, and/or device for a communication network for real estate professionals (reps) |
-
2019
- 2019-09-26 CN CN201910919623.1A patent/CN110675069B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794428A (en) * | 2010-04-08 | 2010-08-04 | 严海强 | Artificial intelligent building sale system |
| EP3057005A1 (en) * | 2015-02-12 | 2016-08-17 | Maurice Duault | Process for computing a score for a search engine used for accessing a database of real estate properties |
| CN108960467A (en) * | 2018-07-09 | 2018-12-07 | 重庆锐云科技有限公司 | Realty information management and data analysis system |
| CN109615128A (en) * | 2018-12-05 | 2019-04-12 | 重庆锐云科技有限公司 | Real estate client's conclusion of the business probability forecasting method, device and server |
| CN109978621A (en) * | 2019-03-25 | 2019-07-05 | 重庆锐云科技有限公司 | Real estate channel customer and commission settlement management method, integral system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110675069A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6608500B2 (en) | System, method and apparatus for implementing data upload, processing and predictive query API publication | |
| US11436430B2 (en) | Feature information extraction method, apparatus, server cluster, and storage medium | |
| CN110675069B (en) | Real estate industry client signing risk early warning method, server and storage medium | |
| CN109615129B (en) | Real estate customer transaction probability prediction method, server and computer storage medium | |
| WO2016138830A1 (en) | Method and apparatus for recognizing risk behavior | |
| US20170109657A1 (en) | Machine Learning-Based Model for Identifying Executions of a Business Process | |
| US20140143332A1 (en) | Discovering signature of electronic social networks | |
| US20100299128A1 (en) | Automatic generation of hybrid performance models | |
| US20140188565A1 (en) | Customer demographic data change detection based on monitored utility consumption | |
| JP5264981B2 (en) | User behavior analysis method and user behavior analysis system | |
| CN111752731B (en) | System and method for asynchronous selection of compatible components | |
| US20170109638A1 (en) | Ensemble-Based Identification of Executions of a Business Process | |
| Djedovic et al. | Innovative approach in modeling business processes with a focus on improving the allocation of human resources | |
| CN109543940B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN110866698A (en) | Device for assessing service score of service provider | |
| Wang et al. | An unsupervised strategy for defending against multifarious reputation attacks | |
| Miller et al. | Size agnostic change point detection framework for evolving networks | |
| US20170109640A1 (en) | Generation of Candidate Sequences Using Crowd-Based Seeds of Commonly-Performed Steps of a Business Process | |
| Zheng et al. | Analysis and modeling of social influence in high performance computing workloads | |
| Moreno et al. | Combining economic forecasts by using a maximum entropy econometric approach | |
| CN111797942A (en) | User information classification method and device, computer equipment and storage medium | |
| US20170109670A1 (en) | Crowd-Based Patterns for Identifying Executions of Business Processes | |
| US10853820B2 (en) | Method and apparatus for recommending topic-cohesive and interactive implicit communities in social customer relationship management | |
| KR20240055011A (en) | Intelligent Predictive A/B Testing | |
| KR20230165497A (en) | Methods, devices and systems for providing online marketing services |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |