CN117035853A - Potential customer identity marking system based on big data - Google Patents
Potential customer identity marking system based on big data Download PDFInfo
- Publication number
- CN117035853A CN117035853A CN202311297063.3A CN202311297063A CN117035853A CN 117035853 A CN117035853 A CN 117035853A CN 202311297063 A CN202311297063 A CN 202311297063A CN 117035853 A CN117035853 A CN 117035853A
- Authority
- CN
- China
- Prior art keywords
- data
- customer
- client
- completion rate
- analysis
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 238000007405 data analysis Methods 0.000 claims abstract description 44
- 230000000694 effects Effects 0.000 claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims abstract description 3
- 238000007781 pre-processing Methods 0.000 claims description 67
- 239000006185 dispersion Substances 0.000 claims description 33
- 238000011157 data evaluation Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 9
- 230000006399 behavior Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000006467 substitution reaction Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- 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
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of big data, in particular to a potential customer identity marking system based on the big data, which comprises a data acquisition module and a data analysis module, wherein the data acquisition module is used for acquiring historical consumption times of customers, time intervals from the last purchase, times of watching videos of the customers and maximum completion rate of watching the videos of the customers, and the data analysis module determines a plurality of analysis modes for analyzing the customer data according to the evaluation value of the customer consumption data, including a first analysis mode for determining whether to preprocess the customer data according to the maximum completion rate of watching the videos of the customers and a second analysis mode for determining marking categories of the customers according to the activity attenuation rate of the customers.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a potential customer identity marking system based on big data.
Background
With the rapid development of big data technology, enterprises are increasingly focusing on the analysis and mining of customer data to improve customer satisfaction and profitability of enterprises. However, conventional methods of analyzing customer data often fail to accurately distinguish between the interest level and the value level of customers, resulting in a lack of pertinence in the decision of the enterprise in terms of customer management and marketing strategies.
Chinese patent publication No.: CN114372815a discloses a screening method of potential customers, which comprises generating each node corresponding to each customer one by one according to account information of each customer; forming a connection path between two nodes corresponding to any two clients which are in an upstream-downstream relationship with each other and transact in a preset period in the same industry chain so as to generate a directed graph; performing similarity matching on each first node connected with a core node corresponding to a core client in the directed graph and the core node, determining the similarity between each first node and the core node, and performing similarity matching on each second node connected with the same node as the core node in the directed graph and the core node, and determining the similarity between each second node and the core node; and determining at least one target node from each first node and each second node according to each similarity, so as to determine the client corresponding to the target node as a potential client.
It follows that the prior art has the following problems: the interest degree and the value degree of the customers cannot be accurately distinguished, and the screening accuracy of the potential customers is low, so that a more targeted potential customer screening strategy cannot be provided for enterprises.
Disclosure of Invention
Therefore, the invention provides a potential customer identity marking system based on big data, which is used for solving the problem of low screening accuracy of potential customers in the prior art.
To achieve the above object, the present invention provides a big data based potential customer identity marking system, comprising:
the data acquisition module is used for acquiring historical consumption times of clients, time intervals from the last purchase, the times of watching the video by the clients and the maximum completion rate of watching the video;
the data analysis module is connected with the data acquisition module and comprises a data analysis unit and a data preprocessing unit, wherein the data analysis unit is used for determining an analysis mode for analyzing the client data according to the evaluation value of the client consumption data, and the data preprocessing unit is used for determining whether to preprocess the client data according to the maximum completion rate of the client watching the video and determining a preprocessing mode for preprocessing the client data according to the first relative difference;
the analysis methods comprise a first analysis method for determining whether to preprocess client data according to the maximum completion rate of the client watching the video and a second analysis method for determining the mark category of the client according to the activity attenuation rate of the client.
Further, the data analysis unit determines a plurality of analysis modes for analyzing the client data according to the comparison result of the client consumption data evaluation value and the preset client consumption data evaluation value, wherein the analysis modes comprise a first analysis mode determined when the client consumption data evaluation value is smaller than or equal to the preset client consumption data evaluation value and a second analysis mode determined when the client consumption data evaluation value is larger than the preset client consumption data evaluation value.
Further, the data preprocessing unit determines a maximum completion rate of watching the video by the client when the analysis mode of analyzing the client data is determined to be a first analysis mode, so as to determine to preprocess the client data under the condition that the maximum completion rate is less than or equal to a preset maximum completion rate.
Further, the data preprocessing unit determines a plurality of preprocessing modes for preprocessing the client data according to the first relative difference under the condition of determining to preprocess the client data, wherein the plurality of preprocessing modes comprise a first preprocessing mode for filtering the video watching frequency data in the client data by the data preprocessing unit and a second preprocessing mode for determining whether to adjust the maximum completion rate according to the completion rate dispersion, and if not, preprocessing the client data by the first preprocessing mode.
Further, the data preprocessing unit calculates the completion rate dispersion of the video watched by the client according to the following formula under the condition that the client data is preprocessed in the second preprocessing mode is determined, and sets
,
Where Wa represents the completion rate dispersion, wi represents the completion rate of the i-th viewing of the video, μ represents the average of the completion rates of viewing the video, and C represents the number of times the video is viewed by the client;
and determining to adjust the maximum completion rate under the condition that the completion rate dispersion is smaller than or equal to a preset completion rate dispersion, and determining not to adjust the maximum completion rate under the condition that the completion rate dispersion is larger than the preset completion rate dispersion.
Further, the data preprocessing unit determines a plurality of adjustment coefficients for adjusting the maximum completion rate according to the second relative difference under the condition of determining the adjustment of the maximum completion rate, wherein the plurality of adjustment coefficients comprise a first adjustment coefficientSecond adjustment coefficient->Wherein Δwa represents the second relative difference, wherein the second relative difference is determined from the completion rate dispersion and a preset completion rate dispersion.
Further, the data analysis unit determines the interest degree of the client according to the maximum completion rate and the number of times the client views the video after completing the analysis of the client data in the first analysis mode.
Further, the data analysis module further comprises a client identity marking unit, after the data analysis unit analyzes the client data in a first analysis mode, the client identity marking unit determines a plurality of marking types of the client according to a comparison result of the interestingness and a preset interestingness, and the plurality of marking types comprise a first marking type determined under the condition that the interestingness is smaller than or equal to the preset interestingness and a second marking type determined under the condition that the interestingness is larger than the preset interestingness.
Further, the data analysis unit calculates the activity decay rate of the client according to the following formula and sets up the activity decay rate when determining that the analysis mode for analyzing the client data is the second analysis mode
,
Where T represents the time interval from the last purchase and A represents the historical number of consumer consumption.
Further, the data analysis unit determines a plurality of marking categories of the client according to the activity attenuation rate of the client when determining that the analysis mode for analyzing the client data is a second analysis mode, wherein the marking categories comprise a first marking category of the high-value client, a second marking category of the potential client and a third marking category of the general client.
Compared with the prior art, the method has the beneficial effects that the analysis mode for analyzing the client data is flexibly determined according to the comparison result of the client consumption data evaluation value and the preset client consumption data evaluation value, the requirements of different types of client data analysis are better met, and the accuracy and the efficiency of data analysis are improved.
Furthermore, the invention compares the maximum completion rate of the video watching by the client with the preset maximum completion rate to more accurately judge the interest degree and watching behavior of the client in the video content, and better understand the requirements and the favorites of the client, thereby providing a targeted basis for the follow-up personalized recommendation.
Further, the invention calculates the first relative difference between the maximum completion rate of the video watched by the client and the preset maximum completion rate, and determines the preprocessing mode for preprocessing the client data according to the comparison result so as to more accurately perform personalized data preprocessing aiming at the watching behaviors of different clients, thereby improving the accuracy and the efficiency of data analysis.
Furthermore, the completion rate distribution condition of the video watched by the client is accurately judged by comparing the completion rate dispersion with the preset completion rate dispersion, so that the watching behavior and preference of the client are better known, and a targeted basis is provided for subsequent personalized recommendation.
Further, the invention determines the adjustment coefficient for adjusting the maximum completion rate according to the comparison result so as to more accurately adjust the personalized completion rate aiming at the watching behaviors of different clients, thereby improving the accuracy and the efficiency of data analysis.
Further, the method and the system can be used for more accurately dividing the clients into the low-interest potential users and the high-interest potential users by setting the interestingness, and enterprises can provide differentiated services according to different user types to better know the demands and interests of the users, so that products and services which are more in line with the demands of the users are provided, and the user experience is improved.
Further, the method and the system determine the marking category of the client according to the activity attenuation rate to more accurately distinguish the value degree of the client, and divide the client into three categories of high-value client, potential client and general client by setting two preset activity attenuation rates so as to more accurately classify the client, thereby adopting different marketing strategies for different types of clients, improving marketing efficiency, providing targeted basis for subsequent personalized recommendation, providing more personalized service, meeting the requirements of different types of clients and further improving the satisfaction degree of the client.
Drawings
FIG. 1 is a schematic diagram of a system for tagging potential customers based on big data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data analysis module of a big data based latent subscriber identity marking system according to an embodiment of the present invention;
FIG. 3 is a flowchart of the operation of a big data based potential customer identity marking system according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
Referring to fig. 1-3, fig. 1 is a schematic structural diagram of a latent subscriber identity marking system based on big data according to an embodiment of the present invention; FIG. 2 is a schematic diagram of a data analysis module of a big data based latent subscriber identity marking system according to an embodiment of the present invention; FIG. 3 is a flowchart of the operation of a big data based potential customer identity marking system according to an embodiment of the present invention.
The embodiment of the invention discloses a potential customer identity marking system based on big data, which comprises the following steps:
the data acquisition module is used for acquiring the historical consumption times A of the clients, the time interval T from the last purchase, the times C of watching the video by the clients and the maximum completion rate Wm of watching the video;
the data analysis module is connected with the data acquisition module and comprises a data analysis unit for determining an analysis mode for analyzing the client data according to the client consumption data evaluation value X, and a data preprocessing unit for determining whether to preprocess the client data according to the maximum completion rate Wm of the client watching the video and determining a preprocessing mode for preprocessing the client data according to the first relative difference;
the analysis methods comprise a first analysis method for determining whether to preprocess the client data according to the maximum completion rate Wm of the client watching the video and a second analysis method for determining the mark type of the client according to the activity attenuation rate L of the client.
Specifically, the data analysis unit determines an analysis mode for analyzing the client data according to a comparison result of the client consumption data evaluation value X and a preset client consumption data evaluation value X0, and sets X=ln (A+1);
if X is less than or equal to X0, the data analysis unit determines to analyze the client data in a first analysis mode;
if X > X0, the data analysis unit determines to analyze the customer data in a second analysis mode.
The first analysis mode is to determine whether to preprocess the client data according to the maximum completion rate Wm of the client watching the video, and the second analysis mode is to determine the mark type of the client according to the activity attenuation rate L of the client.
In the embodiment of the invention, the preset customer consumption data evaluation value X0 is 0, and a person skilled in the art can adjust the preset customer consumption data evaluation value X0 according to specific conditions.
Specifically, according to the comparison result of the customer consumption data evaluation value and the preset customer consumption data evaluation value, the analysis mode for analyzing the customer data is flexibly determined, the requirements of different types of customer data analysis are better met, and the accuracy and the efficiency of data analysis are improved.
Specifically, when the data analysis unit determines that the analysis mode for analyzing the client data is the first analysis mode, the data preprocessing unit determines whether to preprocess the client data according to a comparison result of a maximum completion rate Wm of the client watching the video and a preset maximum completion rate Wm0;
if Wm is less than or equal to Wm0, the data preprocessing unit determines to preprocess the client data;
if Wm > Wm0, the data preprocessing unit determines that client data is not preprocessed.
In the embodiment of the invention, the preset maximum completion rate Wm0 is 90%, and a person skilled in the art can adjust the preset maximum completion rate Wm0 according to specific conditions.
Specifically, the method and the device for displaying the video content by the client have the advantages that the maximum completion rate of watching the video by the client is compared with the preset maximum completion rate so as to accurately judge the interest degree and the watching behavior of the video content by the client, and the requirements and the favorites of the client are better known, so that a targeted basis is provided for subsequent personalized recommendation.
Specifically, the data preprocessing unit calculates a first relative difference delta Wm between a maximum completion rate Wm of a video watched by a client and a preset maximum completion rate Wm0 under the condition of determining to preprocess the client data, and determines a preprocessing mode for preprocessing the client data according to a comparison result of the first relative difference delta Wm and the first preset relative difference delta Wm0, and sets delta wm= (Wm 0-Wm)/Wm 0;
if delta Wm > -delta Wm0, the data preprocessing unit determines to preprocess the client data in a first preprocessing mode;
if delta Wm is less than or equal to delta Wm0, the data preprocessing unit determines to preprocess the client data in a second preprocessing mode.
The first preprocessing mode is a second preprocessing mode in which the data preprocessing unit filters video watching times data in client data, the second preprocessing mode is a mode in which the data preprocessing unit calculates completion rate dispersion Wa of video watching by clients, whether the maximum completion rate Wm is adjusted or not is determined according to the completion rate dispersion Wa, and if the maximum completion rate Wm is not adjusted, the client data is preprocessed in the first preprocessing mode.
In the embodiment of the present invention, the value of the first preset relative difference Δwm0 is 0.33, where the first preset relative difference Δwm0 is obtained when the maximum completion rate Wm is 60%, and a person skilled in the art can adjust the first preset relative difference Δwm0 according to specific situations.
Specifically, the method and the device for preprocessing the client data in the invention calculate the first relative difference between the maximum completion rate of the client watching the video and the preset maximum completion rate, and determine the preprocessing mode for preprocessing the client data according to the comparison result so as to more accurately perform personalized data preprocessing aiming at the watching behaviors of different clients, thereby improving the accuracy and the efficiency of data analysis.
Specifically, the data preprocessing unit calculates the completion rate dispersion Wa of the video watched by the client as
,
Where Wi represents the completion rate of the i-th viewing of the video, μ represents the average of the completion rates of viewing the video, and C represents the number of times the client views the video.
Specifically, the data preprocessing unit determines whether to adjust the maximum completion rate Wm according to a comparison result of the completion rate dispersion Wa and a preset completion rate dispersion Wb under the condition that the client data is preprocessed in a second preprocessing mode;
if Wa is less than or equal to Wb, the data preprocessing unit determines to adjust the maximum completion rate Wm;
if Wa > Wb, the data preprocessing unit determines that the maximum completion ratio Wm is not adjusted.
In the embodiment of the present invention, the value of the preset completion rate dispersion Wb is 100, and a person skilled in the art can adjust the preset completion rate dispersion Wb according to specific situations.
Specifically, the completion rate dispersion is compared with the preset completion rate dispersion to more accurately judge the completion rate distribution condition of the video watched by the client, so that the watching behavior and preference of the client are better known, and a targeted basis is provided for subsequent personalized recommendation.
Specifically, the data preprocessing unit calculates a second relative difference Δwa between the completion rate dispersion Wa and a preset completion rate dispersion Wb under the condition of determining the maximum completion rate Wm adjustment, determines an adjustment coefficient ki for adjusting the maximum completion rate Wm according to the comparison result of the second relative difference Δwa and the second preset relative difference Δwb, and sets Δwa= -Wa-Wb;
if DeltaWa is less than or equal to DeltaWb, the data preprocessing unit determines to adjust the maximum completion rate Wm by a first adjustment coefficient k 1;
if ΔWa > - ΔWb, the data preprocessing unit determines to adjust the maximum completion rate Wm by the second adjustment coefficient k 2.
The adjusted maximum completion rate Wm is set to wm1=wm0×ki, i=1, 2.
Wherein the first adjustment coefficientThe second adjustment coefficient->。
In the embodiment of the present invention, the second preset relative difference Δwb is obtained when the completion rate dispersion Wa is 80, and the second preset relative difference Δwb can be adjusted according to specific situations by a person skilled in the art.
Specifically, the invention determines the adjustment coefficient for adjusting the maximum completion rate according to the comparison result so as to more accurately adjust the personalized completion rate aiming at the watching behaviors of different clients, thereby improving the accuracy and the efficiency of data analysis.
Specifically, the data analysis module further comprises a client identity marking unit, the data analysis unit calculates the interest degree D of the client after the client data analysis is completed in a first analysis mode, the client identity marking unit determines the marking type of the client according to the comparison result of the interest degree D and the preset interest degree D0, and the setting is carried out
;
If D is less than or equal to D0, the client identity marking unit determines that the marking type of the client is a first marking type;
if D > D0, the client identity marking unit determines that the marking type of the client is a second marking type.
Wherein the first tag type is a low-interest potential user and the second tag type is a high-interest potential user.
In the embodiment of the present invention, the preset interestingness D0 takes a value of 0.87, and the preset interestingness D0 is obtained when the number of times the client watches the video is 1 and the maximum completion rate Wm of watching the video is 90%.
Specifically, the method and the system for classifying the customers into the low-interest potential users and the high-interest potential users by setting the interestingness, enterprises provide differentiated services according to different user types, and the demands and interests of the users are better known, so that products and services which are more in line with the demands of the users are provided, and the user experience is improved.
Specifically, the data analysis unit calculates the activity attenuation rate L of the client when determining that the analysis mode for analyzing the client data is a second analysis mode, the client identity marking unit determines the marking category of the client according to the comparison result of the activity attenuation rate L of the client and the preset activity attenuation rate, and the data analysis module is provided with a first preset activity attenuation rate L1 and a second preset activity attenuation rate L2, wherein L1 is smaller than L2, and the setting is performed;
If L is less than or equal to L1, the client identity marking unit determines that the marking category of the client is a first marking category;
if L1 is more than L and less than or equal to L2, the client identity marking unit determines that the marking category of the client is a second marking category;
if L > L2, the client identity marking unit determines that the marking category of the client is a third marking category.
The first marking category is a high-value customer, the second marking category is a potential customer, and the third marking category is a general customer.
In the embodiment of the present invention, the first preset liveness attenuation rate L1 is set to 2.1, where the first preset liveness attenuation rate L1 is obtained when the historical consumption number of customers is 3 and the time interval from the last purchase is 10 days, the second preset liveness attenuation rate L2 is set to 4.2, and the second preset liveness attenuation rate L2 is obtained when the historical consumption number of customers is 3 and the time interval from the last purchase is 100 days, and those skilled in the art can adjust the first preset liveness attenuation rate L1 and the second preset liveness attenuation rate L2 according to specific situations.
Specifically, the method determines the marking category of the client according to the activity attenuation rate to more accurately distinguish the value degree of the client, and classifies the client into three categories of high-value client, potential client and general client by setting two preset activity attenuation rates so as to more accurately classify the client, thereby adopting different marketing strategies for different types of clients, improving marketing efficiency, providing targeted basis for subsequent personalized recommendation, providing more personalized service, meeting the requirements of different types of clients and further improving the satisfaction degree of the client.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A big data based potential customer identity marking system comprising:
the data acquisition module is used for acquiring historical consumption times of clients, time intervals from the last purchase, the times of watching the video by the clients and the maximum completion rate of watching the video;
the data analysis module is connected with the data acquisition module and comprises a data analysis unit and a data preprocessing unit, wherein the data analysis unit is used for determining an analysis mode for analyzing the client data according to the evaluation value of the client consumption data, and the data preprocessing unit is used for determining whether to preprocess the client data according to the maximum completion rate of the client watching the video and determining a preprocessing mode for preprocessing the client data according to the first relative difference;
the analysis methods comprise a first analysis method for determining whether to preprocess client data according to the maximum completion rate of the client watching the video and a second analysis method for determining the mark category of the client according to the activity attenuation rate of the client.
2. The big data-based potential customer identity marking system according to claim 1, wherein the data analysis unit determines a plurality of analysis modes for analyzing the customer data according to a comparison result of the customer consumption data evaluation value and a preset customer consumption data evaluation value, the analysis modes including a first analysis mode determined when the customer consumption data evaluation value is equal to or less than the preset customer consumption data evaluation value and a second analysis mode determined when the customer consumption data evaluation value is greater than the preset customer consumption data evaluation value.
3. The big data based potential customer identity marking system according to claim 2, wherein the data analysis unit determines a maximum completion rate of the customer viewing the video to determine to pre-process the customer data on the condition that the maximum completion rate is equal to or less than a preset maximum completion rate, in the case that the analysis mode of the customer data analysis is determined to be the first analysis mode.
4. A big data based potential customer identity marking system according to claim 3, wherein the data preprocessing unit determines a plurality of preprocessing modes for preprocessing the customer data according to a first relative difference under the condition of determining to preprocess the customer data, the plurality of preprocessing modes including a first preprocessing mode in which the data preprocessing unit filters video watching times data in the customer data and a second preprocessing mode in which the data preprocessing unit calculates a completion rate dispersion of the video watched by the customer, determines whether to adjust a maximum completion rate according to the completion rate dispersion, and if it is determined not to adjust the maximum completion rate, preprocesses the customer data in the first preprocessing mode.
5. The big data based latent client identity marking system according to claim 4, wherein the data preprocessing unit calculates a completion rate dispersion of viewing the video by the client according to the following formula under the condition that the client data is preprocessed in the second preprocessing mode is determined, and sets up
,
Where Wa represents the completion rate dispersion, wi represents the completion rate of the i-th viewing of the video, μ represents the average of the completion rates of viewing the video, and C represents the number of times the video is viewed by the client;
and determining to adjust the maximum completion rate under the condition that the completion rate dispersion is smaller than or equal to a preset completion rate dispersion, and determining not to adjust the maximum completion rate under the condition that the completion rate dispersion is larger than the preset completion rate dispersion.
6. The big data based latent subscriber identity marking system according to claim 5, wherein said data preprocessing unit determines a number of adjustment coefficients for adjusting the maximum completion rate based on the second relative difference, said number of adjustment coefficients including a first adjustment coefficient, under the condition of determining the adjustment for the maximum completion rateSecond adjustment coefficientWherein Δwa represents the second relative difference, wherein the second relative difference is determined from the completion rate dispersion and a preset completion rate dispersion.
7. The big data based potential customer identity marking system according to claim 6, wherein the data analysis unit determines the customer's interest level based on the maximum completion rate and the number of times the customer views the video after the customer data analysis is completed in the first analysis mode.
8. The big data based potential customer identity marking system according to claim 7, wherein the data analysis module further comprises a customer identity marking unit, the data analysis unit determines a plurality of marking types of the customer according to a comparison result of the interestingness and a preset interestingness after the customer data is analyzed in a first analysis manner, and the plurality of marking types comprises a first marking type determined under a condition that the interestingness is less than or equal to a preset interestingness and a second marking type determined under a condition that the interestingness is greater than the preset interestingness.
9. The big data based potential customer identity marking system as claimed in claim 8, wherein the data analysis unit calculates an activity decay rate of the customer according to the following formula in determining that an analysis mode of analyzing the customer data is a second analysis mode, sets up
,
Where T represents the time interval from the last purchase and A represents the historical number of consumer consumption.
10. The big data based potential customer identity marking system according to claim 9, wherein the data analysis unit determines a number of marking categories of the customer according to the activity decay rate of the customer, the number of marking categories including a first marking category of the high value customer, a second marking category of the potential customer, and a third marking category of the general customer, in case that the analysis mode of analyzing the customer data is determined to be the second analysis mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311297063.3A CN117035853B (en) | 2023-10-09 | 2023-10-09 | Potential customer identity marking system based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311297063.3A CN117035853B (en) | 2023-10-09 | 2023-10-09 | Potential customer identity marking system based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117035853A true CN117035853A (en) | 2023-11-10 |
CN117035853B CN117035853B (en) | 2024-02-02 |
Family
ID=88641628
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311297063.3A Active CN117035853B (en) | 2023-10-09 | 2023-10-09 | Potential customer identity marking system based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117035853B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140279208A1 (en) * | 2013-03-14 | 2014-09-18 | Rosie | Electronic shopping system and service |
CN108269331A (en) * | 2017-12-12 | 2018-07-10 | 国政通科技股份有限公司 | A kind of intelligent video big data processing system |
CN108985816A (en) * | 2018-06-07 | 2018-12-11 | 佛山市业鹏机械有限公司 | A kind of mattress purchasing psychology analysis system and method based on big data |
CN109903098A (en) * | 2019-03-12 | 2019-06-18 | 安徽赛迪信息技术有限公司 | A kind of identification of client identity and automatic clustering system |
CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
CN115115232A (en) * | 2022-07-01 | 2022-09-27 | 鑫洋互联网科技(广州)有限公司 | Business information analysis and pushing method embedded into campus life |
CN116402539A (en) * | 2023-06-08 | 2023-07-07 | 北京吉欣科技有限公司 | Method, system, equipment and storage medium for guest development based on big data |
-
2023
- 2023-10-09 CN CN202311297063.3A patent/CN117035853B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140279208A1 (en) * | 2013-03-14 | 2014-09-18 | Rosie | Electronic shopping system and service |
CN108269331A (en) * | 2017-12-12 | 2018-07-10 | 国政通科技股份有限公司 | A kind of intelligent video big data processing system |
CN108985816A (en) * | 2018-06-07 | 2018-12-11 | 佛山市业鹏机械有限公司 | A kind of mattress purchasing psychology analysis system and method based on big data |
CN109903098A (en) * | 2019-03-12 | 2019-06-18 | 安徽赛迪信息技术有限公司 | A kind of identification of client identity and automatic clustering system |
CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
CN115115232A (en) * | 2022-07-01 | 2022-09-27 | 鑫洋互联网科技(广州)有限公司 | Business information analysis and pushing method embedded into campus life |
CN116402539A (en) * | 2023-06-08 | 2023-07-07 | 北京吉欣科技有限公司 | Method, system, equipment and storage medium for guest development based on big data |
Also Published As
Publication number | Publication date |
---|---|
CN117035853B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8706544B1 (en) | Method and system for automatically measuring and forecasting the demographic characterization of customers to help customize programming contents in a media network | |
US6714917B1 (en) | Subscriber identification based on electronic program guide data | |
AU761730B2 (en) | Subscriber identification system | |
US20130247083A1 (en) | Systems and methods for matching an advertisement to a video | |
Spangler et al. | Using data mining to profile TV viewers | |
US20130211880A1 (en) | Chat categorization and agent performance modeling | |
US20130254787A1 (en) | Method and apparatus to perform real-time audience estimation and commercial selection suitable for targeted advertising | |
US20100274666A1 (en) | System and method for selecting a message to play from a playlist | |
CN116862592B (en) | Automatic push method for SOP private marketing information based on user behavior | |
US20240251118A1 (en) | Systems and methods for predicting television viewership patterns for advanced consumer segments | |
CN111612519B (en) | Method, device and storage medium for identifying potential customers of financial products | |
US11704540B1 (en) | Systems and methods for responding to predicted events in time-series data using synthetic profiles created by artificial intelligence models trained on non-homogenous time series-data | |
US20230410020A1 (en) | Systems and methods for real-time lead grading | |
CN110544131A (en) | Data-driven E-commerce user purchasing behavior prediction method | |
CN115147152A (en) | Advertisement putting effect data acquisition and statistical analysis system | |
CN117035853B (en) | Potential customer identity marking system based on big data | |
US20180276694A1 (en) | Consumer response intelligent spend prediction system | |
US11868860B1 (en) | Systems and methods for cohort-based predictions in clustered time-series data in order to detect significant rate-of-change events | |
WO2020162833A1 (en) | Method and system for generating content data | |
CN109145207B (en) | Information personalized recommendation method and device based on classification index prediction | |
CN115713389A (en) | Financial product recommendation method and device | |
Sun et al. | The power of fear: Facial emotion analysis of CEOs to forecast firm performance | |
US10997613B2 (en) | Cross-channel recommendation processing | |
ŁabanowsNi et al. | APPLICATION OF THE NONLINEAR AUTOREGRESSIVE MODEL WITH EXOGENOUS INPUTS FOR PREDICTING THE GROSS OPERATING PRODUCT BASED ON USALI DATA | |
CN113435983A (en) | Personalized commodity recommendation method based on machine vision and improved neural network |
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 |