CN111415199A - Customer prediction updating method and device based on big data and storage medium - Google Patents
Customer prediction updating method and device based on big data and storage medium Download PDFInfo
- Publication number
- CN111415199A CN111415199A CN202010199929.7A CN202010199929A CN111415199A CN 111415199 A CN111415199 A CN 111415199A CN 202010199929 A CN202010199929 A CN 202010199929A CN 111415199 A CN111415199 A CN 111415199A
- Authority
- CN
- China
- Prior art keywords
- client
- customer
- browsing
- data
- behavior
- 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.)
- Pending
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Abstract
The invention provides a customer prediction updating method, a customer prediction updating device and a storage medium based on big data, wherein the customer prediction updating method comprises the following steps: acquiring a behavior log generated by browsing building books by a client; analyzing a behavior log of a client and storing the behavior log in a behavior database as a client behavior data table; analyzing a client behavior data table, predicting client figures and transaction probability of the client, and storing the client figures and the prediction result of the transaction probability in a prediction database; and updating the client portrait and the transaction probability according to the real-time behavior data of the client on the day to obtain a real-time prediction result and the client portrait. The big data-based client prediction updating method, device and storage medium provided by the invention can acquire the online browsing condition and client transaction intention related to the client in real time and some information concerned online previously; the method and the system have the advantages that the selling can control the behaviors of the clients on the day before the visit, the selling is more targeted, the selling cost is reduced, and the transaction probability is improved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a customer prediction updating method and device based on big data and a storage medium.
Background
In the sale of the property, customers who go to the sales floor and visit the house often have certain house purchasing purposes, and after the customers go to the sales floor and go to the house after being prepared, the customers may go to the house and directly purchase or order the customers, so that the customers must be well known. Now after the client arrives, the online data of the client cannot be acquired by the APP of the live advisor in real time, and the delay of the data causes the real demand of the live advisor on the client to be unclear, which may bring unsatisfactory leaving of the client and waste of sales resources. It is important to achieve real-time updating of customer data.
Disclosure of Invention
The invention provides a customer forecast updating method, a device and a storage medium based on big data, which can acquire the on-line browsing condition, the customer willingness to deal and some information concerned on the line in real time; the method and the system have the advantages that the selling can control the behaviors of the clients on the day before the visit, the selling is more targeted, the selling cost is reduced, and the transaction probability is improved.
The invention adopts the following technical scheme:
a big data-based customer forecast updating method comprises the following steps:
acquiring a behavior log generated by browsing building books by a client;
analyzing a behavior log of a client and storing the behavior log in a behavior database as a client behavior data table;
analyzing a client behavior data table, predicting client figures and transaction probability of the client, and storing the client figures and the prediction result of the transaction probability in a prediction database;
and updating the client portrait and the transaction probability according to the real-time behavior data of the client on the day to obtain a real-time prediction result.
Further, the customer's behavioral logs include, but are not limited to, viewing floor details, viewing house type details, 720 house looks, usage of the house credit calculator.
Further, the customer behavior data table comprises a plurality of key fields, wherein the key fields comprise but are not limited to customer telephone numbers, behavior names, browsing floor names, browsing house type names, staying time, visiting time and customer positioning information, and the behavior names are called behavior logs of customers.
Further, the analyzing the customer behavior data table to perform customer portrayal on the customer specifically includes: the method comprises the following steps of obtaining the most positioning information of a client, the distance between the frequent positioning of the client and a building selling place, the house type concerned by the client in a month, the browsing times of the concerned house type, the building concerned by the client in a month, the browsing times and duration of the concerned building, the favorite area of the client in a month, the browsing times and duration of the favorite area, the favorite money amount of the client in a month and the browsing times and duration of the favorite money amount.
Furthermore, the house type concerned by the client in the last month, the browsing times of the house type concerned, the building concerned by the client in the last month, the browsing times and duration of the building concerned, the favorite area of the client in the last month, the browsing times and duration of the favorite area, the favorite money amount of the client in the last month, and the browsing times and duration of the favorite money amount are all obtained by the maximum browsing times of the client.
Further, the analyzing the customer behavior data table to predict the deal probability of the customer specifically includes:
preprocessing and characteristic engineering processing are carried out on the customer behavior data table to obtain customer input data;
selecting L ightGBM prediction models, selecting 3000 data of committed clients as positive samples and 3000 data of non-committed clients as negative samples according to a downsampling mode, and dividing the data into training data and test data according to a ratio of 7:3 to train and test the L ightGBM prediction models;
inputting the input data of a client who does not deal with the client, and outputting the result of predicting the deal probability of the client by the L lightGBM prediction model.
Further, the client input data comprises a client ID, a floor access ID, access days, total access page number, total browsing duration, total browsing times, floor access number, house type access, night access, average daily access duration, average daily click number, average daily access page number, single-day maximum click number, single-day maximum browsing duration, days visited not till now, use times of a housing loan calculator and whether to deal with.
Further, the updating the client portrait and the transaction probability according to the real-time behavior data of the client on the current day to obtain a real-time prediction result specifically comprises:
monitoring data changes in the behavior database by adopting a big data monitoring tool canal;
when monitoring that the current browsing data of the client is more than 10, acquiring the current real-time behavior data of the client, wherein the current real-time behavior data comprises client id, behavior name, browsing floor name, browsing house type name, residence time and visiting time;
flowing the current data into a real-time computing module flink through kafka, and processing and computing the current data in the flink to obtain a current day index, wherein the current day index comprises total browsing duration, whether a house loan calculator is used, the house type and the browsing duration which are the most browsed, the floor and the browsing duration which are the most browsed, and the area and the amount which are the most browsed;
updating the client transaction probability according to the calculated current day index, specifically: when the total daily browsing duration of the client is longer than the maximum daily browsing duration before the client, or a room credit calculator is used for more than two times, updating the transaction probability of the client, wherein the updating rule is as follows: if the customer transaction probability is below 60%, adding 5% on the basis of the original transaction probability, if the customer transaction probability is between 60% and 80%, adding 1% on the basis of the original transaction probability, and if the transaction probability is above 80%, not changing the transaction probability;
and updating the client portrait, and updating the corresponding house type concerned by the client when the maximum browsing time of the house type on the current day of the client is longer than the average browsing time of the corresponding house type concerned by the current client every day, wherein the house type comprises a building, a house type, an area and a money amount.
The seller obtains the forecast result and the client portrait from the forecast database, and returns the latest forecast result and the latest client portrait when the seller requests the client data.
An apparatus 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 steps of the big data based customer forecast update method.
A storage medium storing one or more programs, the one or more programs executable by one or more processors to implement the steps of a big data based customer forecast update method.
The invention has the beneficial effects that:
the scheme provides the flow of the real estate big data-based client prediction real-time synchronization method, the browsing data of the client can be updated to the sales end in real time, and the sales can preliminarily know the client before receiving the client. Aiming at a first visit client, when the client arrives, the first visit client scans the two-dimensional code, and the sales can document the client in time, acquire the online browsing condition related to the client in real time and acquire the transaction intention of the client and some information concerned online; for customers with two or more visits, the sales can also have control over the behavior on the day before the visit. More targeted sales, reduced sales cost and improved transaction probability.
Drawings
Fig. 1 is a schematic step diagram according to a first embodiment of the present invention.
Fig. 2 is a schematic diagram of a real-time update synchronization process according to a first embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a device according to a second embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example one
When a customer goes to a building selling part to see a house, aiming at a first visiting customer, when the customer arrives, scanning a two-dimensional code, the customer can be filed in time for sale, the relevant online browsing condition of the customer is obtained in real time, and the willingness of the customer to deal and some information concerned online in the past are obtained; aiming at the clients with two or more visits, the sales can control the behaviors of the day before the visits.
As shown in fig. 1, the present invention provides a big data-based customer prediction update method, which comprises the following specific steps:
and S1, acquiring a behavior log generated by browsing the building book by the client. The customer's behavioral logs include, but are not limited to, viewing floor details, viewing house type details, 720 house looks, usage of the house credit calculator.
And S2, analyzing the behavior log of the client and storing the behavior log in a behavior database as a client behavior data table. The customer behavior data table comprises a plurality of key fields, wherein the key fields comprise but are not limited to a customer telephone number, a behavior name, a browsing floor name, a browsing house type name, a staying time, visiting time and customer positioning information, and the behavior name is a behavior log of the customer.
And S3, analyzing the client behavior data table, predicting client portrait and transaction probability for the client, and storing the client portrait and transaction probability prediction result in the prediction database.
With respect to a customer representation:
the method mainly comprises the most positioning information of a client, the distance between the frequent positioning of the client and a building selling place, the house type concerned by the client in one month, the browsing times of the concerned house type, the building concerned by the client in one month, the browsing times and duration of the concerned building, the favorite area of the client in one month, the browsing times and duration of the favorite area, the favorite money of the client in one month and the browsing times and duration of the favorite money. Wherein, the preference and the attention of the client are obtained by the maximum browsing times of the client.
For example, the resident position of the client is 'Chongqing North', the number of times that the client browses two rooms and one hall in one month is the largest, the number of times that the client pays attention to the building named 'Lishiquyuan' in one month is the largest, the number of times that the client browses a house with the area of '70-80 square meters' in one month is the largest, the number of times is 45, and the number of times that the client browses a house with the area of '100 plus 120 Ten Yuan' in one month is the largest, the number of times is 60.
Then, the most positioning information of the client is the Chongqing north (which can be more specific), the distance between the client and the sales floor where the client frequently positions is the distance between the Chongqing north and the sales floor, the house type concerned by the client in one month is a two-room one-hall, the browsing frequency of the house type concerned is 30 times, the building disc concerned by the client in one month is the poetry park, the browsing frequency of the building disc concerned is 30 times, the duration is the total duration of the browsing of 30 times, the favorite area of the client in one month is 70-80 square meters, the favorite area browsing frequency is 45 times, the duration is the total duration of the browsing of 45 times, the favorite amount of the client in one month is 100 plus 120 ten thousand yuan, the favorite amount of the browsing frequency is 60 times, and the duration is the total duration of the browsing of 60 times.
The bargaining probability prediction process comprises the following steps:
t1: characteristic engineering treatment: and preprocessing the customer behavior data table and performing characteristic engineering processing to obtain customer input data. The customer input data fields include: customer ID, visit building ID, visit days, total visit page number, total browse duration, total browse times, visit building number, visit house type, visit night, average visit daily duration, average click times per day, average visit page number per day, maximum click times per day, maximum browse time per day, number of days visited before and after, use number of housing loan calculator, and whether to deal with.
T2, model construction, training and testing, wherein a L ightGBM prediction model is selected to predict the customer deal probability, 3000 data of deal customers are selected as positive samples in a downsampling mode, 3000 data of non-deal customers are selected as negative samples, the data are divided into training data and testing data according to the ratio of 7:3 to train and test the L ightGBM prediction model, the overall accuracy of a model test result is 90.2%, the accuracies of the positive samples and the negative samples are 91% and 89% respectively, and the recall rate is 89% and 92% respectively.
T3, inputting the customer input data of a non-transaction customer, and outputting the transaction probability prediction result of the customer by the L ightGBM prediction model.
And S4, updating the client portrait and the transaction probability according to the real-time behavior data of the current day of the client to obtain a real-time prediction result and the client portrait. The forecast data before the customer is stored in the forecast database and can be directly obtained by the sales end.
The whole real-time update synchronization process is shown in fig. 2, and the specific update and calculation steps are as follows:
and S41, monitoring data change in the behavior database by adopting a big data monitoring tool canal.
S42, when monitoring that the current browsing data of the client is more than 10, acquiring the current real-time behavior data of the client, including client id, behavior name, browsing floor name, browsing house type name, staying time and visiting time.
S43, flowing into a real-time calculation module flink through kafka, and processing and calculating the stream data in the flink to obtain the current day index, wherein the current day index comprises total browsing duration, whether a room credit calculator is used, the most visited house types and browsing duration, the most visited floors and browsing duration, and the most visited areas and money.
The MySQ L data monitoring is achieved, kafka completes distributed storage of the data, throughput is high, and flink is a distributable open source computing framework oriented to data stream processing and batch data processing, is mainly used for processing stream data (preprocessing data), is high in processing speed and can process a large amount of data.
S44, updating the client transaction probability according to the calculated current day index, specifically: and when the total daily browsing duration of the client is longer than the maximum daily browsing duration before the client, or more than two house loan calculators are used, updating the client transaction probability to cover the original transaction probability prediction result. Wherein, the updating rule is as follows: if the customer transaction probability is below 60%, 5% is added on the basis of the original transaction probability, if the customer transaction probability is between 60% and 80%, 1% is added on the basis of the original transaction probability, and if the transaction probability is above 80%, the transaction probability is not changed.
S45, updating the client portrait: the house types comprise building, house type, area and money, and when the maximum browsing time of a client to a certain house type on the same day is longer than the average browsing time of the corresponding house type concerned by the client on the current day, the corresponding house type concerned by the client is updated.
For example: the current concerned house type of the client is four rooms, two halls and two toilets, the total browsing time of the next month is 120 minutes, the browsing days are 10 days, and the average browsing time of each day is 12 minutes. Today, a client is online to browse the three rooms, one hall and two guards for many times, and the total time for browsing the three rooms, one hall and two guards is 15 minutes, so that the type of the client concerned house is updated to the three rooms, one hall and two guards.
S46, the seller obtains the forecast result and the customer portrait from the forecast database, and when the seller requests the customer data, the latest forecast result and the latest customer portrait are returned.
Case description:
the client has a certain registration and browsing behavior (including checking the floor and the house type) on the public number in 8/4/2019, the client has no file but has a browsing behavior on the applet by 3/9, and the transaction probability of the client is 72% according to the browsing behavior of the client. A client portrait part: the method is characterized in that a frequently-located place of a client is a Chongqing Yubei area, a building concerned by the client in one month is a Lishiquyuan, browsing times and browsing duration of the building are respectively 10 times and 32 minutes, a house concerned by the client in one month is a three-room two-toilet, the browsing times and browsing duration of the house are respectively 23 times and 45 minutes, the area concerned by the client in one month is 90-120 square meters, the browsing times and the browsing duration of the area in the range are respectively 18 times and 33 minutes, the amount concerned by the client in one month is 150 plus 170w, and the browsing times and the browsing duration of the amount in the range are respectively 17 times and 31 minutes.
The customer browses the building again in 2019, 9, 4 and 21 times, respectively browses the house type and the periphery, and uses the house credit calculator. Monitoring the change of data, feeding back the client to the flink in a streaming data form, calculating to obtain the total browsing time length of 23 minutes, using a room credit calculator, browsing the most residential three-rooms, one room, two toilets, browsing the most stories as Lishiquyuan, browsing the most areas of 90-120 square meters, and browsing the most amount of 150-. Updating the transaction probability according to an updating rule: since the use of the room credit calculator or browsing time is longer than the average past daily time, and the customer's original transaction probability is 72%, the result is 73% by adding 1% on the basis. The client portrait part can see that the house type browsed by the client on the day is changed according to the data, and the floor, the area and the amount of money are not changed, so that the house type can be updated. The following table is an updated comparison table, as shown below.
| Probability of a deal | Concerned building plate | Concerned house type | Area of interest | Preferred amount of money | |
| Before updating | 72％ | Lishi interesting garden | Three-room two-hall two-toilet | 90-120㎡ | 150-170w |
| After update | 73％ | Lishi interesting garden | Three-room one-hall two-toilet | 90-120㎡ | 150-170w |
The customer scans the code in the floor in 2019, 9, 4, 14:43, the sales establishes the file for the customer, requests the customer to deal with the forecast data and the customer image through the sales terminal message, and the obtained customer forecast data is the data updated in real time.
Example two:
in the present embodiment, on the basis of the first embodiment, a device is provided, please refer to fig. 3, which is mainly used for implementing the steps of the big data-based customer prediction update method of the first embodiment, and the device mainly includes a processor 21, a memory 22 and a communication bus 23; the communication bus 23 is used for realizing connection communication between the processor 21 and the memory 22; the processor 21 is configured to execute one or more programs stored in the memory 22 to implement the steps of the big data based customer forecast update method as in the above embodiment. For details, please refer to the description in the first embodiment, which is not repeated herein.
In addition, the present embodiment also provides a storage medium, where one or more programs are stored, and the one or more programs are executable by one or more processors to implement the steps of the big data based customer prediction update method according to 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.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; these modifications and substitutions do not cause the essence of the corresponding technical solution to depart from the scope of the technical solution of the embodiments of the present invention, and are intended to be covered by the claims and the specification of the present invention.
Claims (10)
1. A big data-based customer prediction updating method is characterized by comprising the following steps:
acquiring a behavior log generated by browsing building books by a client;
analyzing a behavior log of a client and storing the behavior log in a behavior database as a client behavior data table;
analyzing a client behavior data table, predicting client figures and transaction probability of the client, and storing the client figures and the prediction result of the transaction probability in a prediction database;
and updating the client portrait and the transaction probability according to the real-time behavior data of the client on the day to obtain a real-time prediction result and the client portrait.
2. The big data based customer forecast updating method of claim 1, wherein said customer's behavior log includes but is not limited to checking floor details, checking house type details, 720 house-watching, and usage of house credit calculator.
3. The big data based customer forecast updating method of claim 2, wherein said customer behavior data table comprises a plurality of key fields, said key fields include but are not limited to customer telephone, behavior name, browsing floor name, browsing house name, staying time, visiting time, customer location information, wherein said behavior name is customer's behavior log.
4. The big data-based client forecast updating method according to claim 1, wherein the analyzing the client behavior data table to perform client representation on the client comprises: the method comprises the following steps of obtaining the most positioning information of a client, the distance between the frequent positioning of the client and a building selling place, the house type concerned by the client in a month, the browsing times of the concerned house type, the building concerned by the client in a month, the browsing times and duration of the concerned building, the favorite area of the client in a month, the browsing times and duration of the favorite area, the favorite money amount of the client in a month and the browsing times and duration of the favorite money amount.
5. The big-data-based customer forecast updating method according to claim 4, wherein the house type concerned by the customer in the last month, the browsing times of the concerned house type, the building concerned by the customer in the last month, the browsing times and duration of the concerned building, the favorite area of the customer in the last month, the browsing times and duration of the favorite area, the favorite money amount of the customer in the last month, and the browsing times and duration of the favorite money amount are all obtained by maximizing the browsing times of the customer.
6. The big data-based customer prediction updating method according to claim 5, wherein analyzing the customer behavior data table to predict the probability of a deal for a customer specifically comprises:
preprocessing and characteristic engineering processing are carried out on the customer behavior data table to obtain customer input data;
selecting L ightGBM prediction models, selecting 3000 data of committed clients as positive samples and 3000 data of non-committed clients as negative samples according to a downsampling mode, and dividing the data into training data and test data according to a ratio of 7:3 to train and test the L ightGBM prediction models;
inputting the input data of a client who does not deal with the client, and outputting the result of predicting the deal probability of the client by the L lightGBM prediction model.
7. The big data based customer forecast updating method of claim 6, wherein said customer input data comprises customer ID, visit floor ID, visit days, total visit pages, total browse duration, total browse times, visit floor number, visit house type, visit at night, average visit daily duration, average click times per day, average number of visited pages per day, maximum click times per day, maximum browse duration per day, number of days visited until now, use of housing loan calculator, deal with or not.
8. The big data-based client forecast updating method according to claim 7, wherein the updating of the client portrait and the deal probability according to the real-time behavior data of the client on the current day to obtain the real-time forecast result specifically comprises:
monitoring data changes in the behavior database by adopting a big data monitoring tool canal;
when monitoring that the current browsing data of the client is more than 10, acquiring the current real-time behavior data of the client, wherein the current real-time behavior data comprises client id, behavior name, browsing floor name, browsing house type name, residence time and visiting time;
flowing the current data into a real-time computing module flink through kafka, and processing and computing the current data in the flink to obtain a current day index, wherein the current day index comprises total browsing duration, whether a house loan calculator is used, the house type and the browsing duration which are the most browsed, the floor and the browsing duration which are the most browsed, and the area and the amount which are the most browsed;
updating the client transaction probability according to the calculated current day index, specifically: when the total daily browsing duration of the client is longer than the maximum daily browsing duration before the client, or a room credit calculator is used for more than two times, updating the transaction probability of the client, wherein the updating rule is as follows: if the customer transaction probability is below 60%, adding 5% on the basis of the original transaction probability, if the customer transaction probability is between 60% and 80%, adding 1% on the basis of the original transaction probability, and if the transaction probability is above 80%, not changing the transaction probability;
and updating the client portrait, and updating the corresponding house type concerned by the client when the maximum browsing time of the house type on the current day of the client is longer than the average browsing time of the corresponding house type concerned by the current client every day, wherein the house type comprises a building, a house type, an area and a money amount.
The seller obtains the forecast result and the client portrait from the forecast database, and returns the latest forecast result and the latest client portrait when the seller requests the client data.
9. An apparatus 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 steps of the big data based customer forecast updating method of any of claims 1 to 8.
10. A storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the steps of the big data based customer forecast update method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010199929.7A CN111415199A (en) | 2020-03-20 | 2020-03-20 | Customer prediction updating method and device based on big data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010199929.7A CN111415199A (en) | 2020-03-20 | 2020-03-20 | Customer prediction updating method and device based on big data and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111415199A true CN111415199A (en) | 2020-07-14 |
Family
ID=71493127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010199929.7A Pending CN111415199A (en) | 2020-03-20 | 2020-03-20 | Customer prediction updating method and device based on big data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111415199A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150273A (en) * | 2020-09-24 | 2020-12-29 | 中国农业银行股份有限公司 | System, method, apparatus and storage medium for processing online credit service |
| CN112183408A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Case image-based customer portrait system and method |
| CN112561598A (en) * | 2020-12-23 | 2021-03-26 | 中国农业银行股份有限公司重庆市分行 | Customer loss prediction and retrieval method and system based on customer portrait |
| CN112561569A (en) * | 2020-12-07 | 2021-03-26 | 上海明略人工智能(集团)有限公司 | Dual-model-based arrival prediction method and system, electronic device and storage medium |
| CN112765180A (en) * | 2021-01-27 | 2021-05-07 | 上海英方软件股份有限公司 | Method and device for analyzing column names of table building logs of DB2 database |
| CN113034211A (en) * | 2021-05-25 | 2021-06-25 | 武汉卓尔数字传媒科技有限公司 | Method and device for predicting user behavior and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507042A (en) * | 2017-09-15 | 2017-12-22 | 携程计算机技术（上海）有限公司 | Marketing method and system based on user's portrait |
| CN108337316A (en) * | 2018-02-08 | 2018-07-27 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN108510321A (en) * | 2018-03-23 | 2018-09-07 | 北京焦点新干线信息技术有限公司 | A kind of construction method and device of house property user portrait |
| CN109242523A (en) * | 2018-07-06 | 2019-01-18 | 成都正合云智数据科技有限公司 | A kind of building purchasers being exclusively used in real estate's sales industry draw a portrait method and its realization device |
| CN109615432A (en) * | 2018-12-14 | 2019-04-12 | 成都德迈安科技有限公司 | Consumer behaviour portrait tool based on big data |
| 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 |
| CN109710697A (en) * | 2018-12-28 | 2019-05-03 | 厦门笨鸟电子商务有限公司 | A kind of generation method of corporate user's portrait |
| CN110196888A (en) * | 2019-05-27 | 2019-09-03 | 深圳前海微众银行股份有限公司 | Data-updating method, device, system and medium based on Hadoop |
-
2020
- 2020-03-20 CN CN202010199929.7A patent/CN111415199A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507042A (en) * | 2017-09-15 | 2017-12-22 | 携程计算机技术（上海）有限公司 | Marketing method and system based on user's portrait |
| CN108337316A (en) * | 2018-02-08 | 2018-07-27 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN108510321A (en) * | 2018-03-23 | 2018-09-07 | 北京焦点新干线信息技术有限公司 | A kind of construction method and device of house property user portrait |
| CN109242523A (en) * | 2018-07-06 | 2019-01-18 | 成都正合云智数据科技有限公司 | A kind of building purchasers being exclusively used in real estate's sales industry draw a portrait method and its realization device |
| 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 |
| CN109615432A (en) * | 2018-12-14 | 2019-04-12 | 成都德迈安科技有限公司 | Consumer behaviour portrait tool based on big data |
| CN109710697A (en) * | 2018-12-28 | 2019-05-03 | 厦门笨鸟电子商务有限公司 | A kind of generation method of corporate user's portrait |
| CN110196888A (en) * | 2019-05-27 | 2019-09-03 | 深圳前海微众银行股份有限公司 | Data-updating method, device, system and medium based on Hadoop |
Non-Patent Citations (1)
| Title |
|---|
| 李维胜 黄容: ""基于大数据技术的房地产网络社区营销模式研究"", 《技术经济与管理研究》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150273A (en) * | 2020-09-24 | 2020-12-29 | 中国农业银行股份有限公司 | System, method, apparatus and storage medium for processing online credit service |
| CN112183408A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Case image-based customer portrait system and method |
| CN112183408B (en) * | 2020-09-30 | 2023-09-29 | 重庆天智慧启科技有限公司 | Customer portrait system and method based on field image |
| CN112561569A (en) * | 2020-12-07 | 2021-03-26 | 上海明略人工智能(集团)有限公司 | Dual-model-based arrival prediction method and system, electronic device and storage medium |
| CN112561569B (en) * | 2020-12-07 | 2024-02-27 | 上海明略人工智能(集团)有限公司 | Dual-model-based store arrival prediction method, system, electronic equipment and storage medium |
| CN112561598A (en) * | 2020-12-23 | 2021-03-26 | 中国农业银行股份有限公司重庆市分行 | Customer loss prediction and retrieval method and system based on customer portrait |
| CN112765180A (en) * | 2021-01-27 | 2021-05-07 | 上海英方软件股份有限公司 | Method and device for analyzing column names of table building logs of DB2 database |
| CN112765180B (en) * | 2021-01-27 | 2023-01-17 | 上海英方软件股份有限公司 | Method and device for analyzing column names of table building logs of DB2 database |
| CN113034211A (en) * | 2021-05-25 | 2021-06-25 | 武汉卓尔数字传媒科技有限公司 | Method and device for predicting user behavior and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111415199A (en) | Customer prediction updating method and device based on big data and storage medium | |
| CN109615129B (en) | Real estate customer transaction probability prediction method, server and computer storage medium | |
| CN110689457A (en) | Intelligent reception method for online clients in real estate industry, server and storage medium | |
| US11093977B2 (en) | Ad ranking system and method utilizing bids and adjustment factors based on the causal contribution of advertisements on outcomes | |
| CN101802856A (en) | Measuring a location based advertising campaign | |
| CN110324414B (en) | Resource bit flow distribution method and device and electronic equipment | |
| CN103748605A (en) | Conversion type to conversion type funneling | |
| US7895149B2 (en) | System for opinion reconciliation | |
| CN107807997A (en) | User's portrait building method, device and computing device based on big data | |
| CN109685536B (en) | Method and apparatus for outputting information | |
| CN109903087A (en) | The method, apparatus and storage medium of Behavior-based control feature prediction user property value | |
| CN110889725B (en) | Online advertisement CTR estimation method, device, equipment and storage medium | |
| CN112348592A (en) | Advertisement recommendation method and device, electronic equipment and medium | |
| CN112163963A (en) | Service recommendation method and device, computer equipment and storage medium | |
| WO2023207411A1 (en) | Traffic determination method and apparatus based on spatio-temporal data, and device and medium | |
| Shen et al. | Enhancing stochastic kriging for queueing simulation with stylized models | |
| CN110569190B (en) | Transaction pressure testing method and device, electronic device and readable storage medium | |
| CN107798118A (en) | User's portrait building method, device and computing device based on big data | |
| US20050165596A1 (en) | Method and apparatus for determining expected values in the presence of uncertainty | |
| US20110015951A1 (en) | Evaluation of website visitor based on value grade | |
| CN110796379B (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| Altalhi et al. | Developing a framework and algorithm for scalability to evaluate the performance and throughput of CRM systems | |
| CN111182465A (en) | Method and device for determining terminal affiliation | |
| CN110544165B (en) | Credit risk score card creating method and device and electronic equipment | |
| CN113657996A (en) | Method and device for determining feature contribution degree in federated learning and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200714 |