CN110689457A - Intelligent reception method for online clients in real estate industry, server and storage medium - Google Patents
Intelligent reception method for online clients in real estate industry, server and storage medium Download PDFInfo
- Publication number
- CN110689457A CN110689457A CN201910952094.5A CN201910952094A CN110689457A CN 110689457 A CN110689457 A CN 110689457A CN 201910952094 A CN201910952094 A CN 201910952094A CN 110689457 A CN110689457 A CN 110689457A
- Authority
- CN
- China
- Prior art keywords
- transaction
- client
- recommended
- similarity calculation
- browsing
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
Abstract
The invention provides an online customer intelligent reception method, a server and a storage medium in the production industry, which are used for acquiring attention characteristic information of a customer to be recommended based on a browsing log of the customer to be recommended to each display floor; acquiring transaction characteristic information of each business consultant in the platform, wherein the transaction characteristic information is obtained by analyzing the transaction items submitted by the business consultants; carrying out similarity calculation on the concerned characteristic information of the client to be recommended and the transaction characteristic information of each business consultant; determining a target employment consultant as a recommendation object according to the similarity calculation result; and generating a recommendation message to recommend the target employment advisor to the client to be recommended. Analyzing the attention points of the clients by researching on-line browsing behaviors of the clients; by researching the transaction information of the business consultants, similarity matching is carried out between the client attention points and the transaction characteristics of the business consultants, and the business consultants with transaction information similar to the client attention points are recommended to the on-line visiting clients. Thereby achieving targeted reception.
Description
Technical Field
The invention relates to the technical field of real estate networks, in particular to an online customer intelligent reception method, a server and a storage medium in the real estate industry.
Background
Nowadays, the online house-watching platform technology is relatively mature and widely applied, but how to better serve the clients, the clients can pertinently receive the reception of a professional consultant, the communication efficiency is improved, and the visiting and transaction are further promoted to be converted into a pain point of the current online marketing.
Disclosure of Invention
The invention provides an intelligent receiving method, a server and a storage medium for online clients in the real estate industry, which mainly solve the technical problems that: how to more pertinently recommend a job-placing consultant for a client who watches rooms on line and better meet the room-watching requirements of client consultation, reception and the like.
In order to solve the technical problem, the invention provides an intelligent customer reception method in the on-line production industry, which comprises the following steps:
acquiring attention characteristic information of a client to be recommended based on a browsing log of the client to be recommended to each display floor;
acquiring transaction characteristic information of each business consultant in the platform, wherein the transaction characteristic information is obtained by analyzing the transaction items submitted by the business consultants;
carrying out similarity calculation on the attention characteristic information of the client to be recommended and the transaction characteristic information of each business consultant;
determining a target employment consultant as a recommendation object according to the similarity calculation result;
and generating a recommendation message to recommend the target employment advisor to the client to be recommended.
Optionally, the attention feature information includes at least one of an attention item position type, an attention property shape, an attention periphery matching, an attention house type area, and an attention price;
the transaction characteristic information comprises at least one of a transaction position type, a transaction property form, a transaction periphery matching, a transaction house type area and a transaction price.
Optionally, the obtaining of the attention feature information of the client to be recommended includes:
determining the position type of each browsing item in the browsing log of the client to be recommended, and calculating the number of browsing items corresponding to the same position type; selecting the position type with the largest browsing item quantity as the concerned item position type of the client to be recommended; or selecting the position type with the browsing item quantity reaching a first set threshold value as the concerned item position type of the client to be recommended;
determining the property form of each browsing item in the browsing log of the client to be recommended, and calculating the quantity of browsing items corresponding to the same property form; selecting the property form with the largest browsing item quantity as the concerned property form of the client to be recommended; or selecting the property shape of which the browsing item quantity reaches a second set threshold value as the concerned property shape of the to-be-recommended client;
determining the peripheral matching of each browsing item in the browsing log of the client to be recommended, and performing quantization and mean processing on the peripheral matching of each browsing item to serve as the concerned peripheral matching of the client to be recommended;
determining the type of each browsing item in the browsing log of the client to be recommended, and calculating the number of browsing items corresponding to the same type of the type; selecting the house type with the largest number of browsing items as the concerned house type of the client to be recommended; or selecting the house type with the browsing item quantity reaching a third set threshold value as the concerned house type of the client to be recommended;
determining the house type area of each browsing item in the browsing log of the client to be recommended, and calculating the average house type area of each browsing item as the concerned house type of the client to be recommended;
and determining the price of each browsing item in the browsing log of the client to be recommended, and calculating the average price of each browsing item as the concerned price of the client to be recommended.
Optionally, the deal feature information is obtained by analyzing based on the project dealt by the employment consultant, and includes:
acquiring information of each project submitted by the employment consultant, and determining the position type, property form, periphery matching, house type, house area and price of each project;
counting the number of transaction items under the same position type, selecting the position type with the maximum number of transaction items as the transaction position type of the business consultant, or selecting the position type with the number of transaction items reaching a fourth set threshold value as the transaction position type of the business consultant;
counting the number of transaction items under the same property form, selecting the property form with the maximum number of transaction items as the transaction property form of the service consultant, or selecting the property form with the number of transaction items reaching a fifth set threshold value as the transaction property form of the service consultant;
after carrying out quantization and mean value processing on the peripheral matching sets of various items submitted by the employment consultant, the peripheral matching sets are used as the submitting peripheral matching sets of the employment consultant;
counting the number of transaction items under the same housing type, selecting the housing type with the largest number of transaction items as the transaction housing type of the business consultant, or selecting the housing type with the number of transaction items reaching a sixth set threshold as the transaction housing type of the business consultant;
calculating the average housing area of the project submitted by the employment consultant as the submitting housing area of the employment consultant;
and calculating the average transaction price of the transaction items of the business consultant as the transaction price of the business consultant.
Optionally, the calculating the similarity between the attention characteristic information of the client to be recommended and the transaction characteristic information of each live advisor includes:
carrying out similarity calculation on the concerned position type and the deal position type to obtain a first similarity calculation result;
carrying out similarity calculation on the concerned property shape and the transaction property shape to obtain a second similarity calculation result;
carrying out similarity calculation on the concerned periphery matching and the friendship periphery matching to obtain a third similarity calculation result;
performing similarity calculation on the concerned house type and the deal house type to obtain a fourth similarity calculation result;
performing similarity calculation on the concerned house type area and the deal house type area to obtain a fifth similarity calculation result;
and carrying out similarity calculation on the concerned price and the deal price to obtain a sixth similarity calculation result.
Optionally, the determining, according to the similarity calculation result, a target employment advisor to be recommended includes:
performing mean processing on the first similarity calculation result, the second similarity calculation result, the third similarity calculation result, the fourth similarity calculation result, the fifth similarity calculation result, and the sixth similarity calculation result to obtain the similarity calculation result;
and recommending the plurality of the employment consultants with larger similarity values in the similarity calculation results to the client to be recommended as the target employment consultants.
Optionally, before generating a recommendation message to recommend the target employment advisor to the client to be recommended, the method further includes: and determining that the client to be recommended is currently in a non-floor page browsing state.
Optionally, the method further includes: and when the client to be recommended is determined to be in a floor page browsing state currently, screening out at least one corresponding employment advisor under the floor browsed by the client to be recommended from each similarity calculation result to serve as the target employment advisor.
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 steps of the method for intelligent customer reception on a property industry online.
The present invention also provides a storage medium having one or more programs stored thereon that are executable by one or more processors to perform the steps of the method for intelligent customer reception on a property industry online as described in any one of the above.
The invention has the beneficial effects that:
according to the intelligent receiving method, the server and the storage medium for the online clients in the real estate industry, provided by the invention, the attention feature information of the clients to be recommended is obtained based on the browsing logs of the clients to be recommended to each display floor; acquiring transaction characteristic information of each business consultant in the platform, wherein the transaction characteristic information is obtained by analyzing the transaction items submitted by the business consultants; carrying out similarity calculation on the concerned characteristic information of the client to be recommended and the transaction characteristic information of each business consultant; determining a target employment consultant as a recommendation object according to the similarity calculation result; and generating a recommendation message to recommend the target employment advisor to the client to be recommended. Analyzing the focus of a client and depicting the portrait of the client by researching the online browsing behavior of the client; by researching the transaction information of the business consultant, the source image of the transaction room is described; and performing similarity matching on the client attention points and the transaction characteristics of the business consultants, and recommending the business consultants with transaction information similar to the client attention points to the online visiting clients. Therefore, targeted reception is achieved, targeting is achieved, reception communication efficiency is improved, and improvement of conversion rate is expected to be promoted.
Drawings
FIG. 1 is a flow chart of a method for intelligent customer reception in a real estate industry online according to a first embodiment of the present invention;
fig. 2 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 are not intended to limit the invention.
The first embodiment is as follows:
in order to recommend a business counselor to an online house-watching client more specifically and better meet the house-watching requirements of client consultation, reception and the like, the embodiment provides an online client intelligent reception method for the local production industry, which screens a business counselor more suitable for the client requirements by analyzing the online access behavior of the client and the transaction project characteristics of the business counselor, so as to provide better service for the online house-watching client, improve the reception and communication efficiency, further improve the use experience of the client and promote the promotion of the transaction conversion rate.
Referring to fig. 1, the intelligent customer reception method for the real estate industry provided in this embodiment mainly includes the following steps:
s101, obtaining attention characteristic information of the client to be recommended based on the browsing logs of the client to be recommended to each display building.
First, the client and the consulting room acquire services from the server through the corresponding client, and the client stores the created browsing log in the server for online browsing behavior of the building, and the transaction information of the consulting room is also usually stored in the server, so that the server can acquire the transaction information. For the online browsing behavior of the client, the server can also monitor at any time.
And analyzing the browsing log of the client to be recommended to obtain the attention characteristic information of the client to be recommended.
In this embodiment, the attention feature information includes at least one of an attention location type, an attention property shape, an attention perimeter kit, an attention house type, an attention house area, and an attention price.
Analyzing the browsing log to obtain the attention feature information comprises:
determining the position type of each browsing item in the browsing log of the client to be recommended, and calculating the number of browsing items corresponding to the same position type; selecting the position type with the largest browsing item quantity as the concerned position type of the client to be recommended; or selecting the position type with the browsing item quantity reaching a first set threshold value as the concerned position type of the client to be recommended; the first set threshold value can be flexibly set according to actual conditions.
Determining the property form of each browsing item in the browsing log of the client to be recommended, and calculating the quantity of browsing items corresponding to the same property form; selecting the property form with the largest browsing item quantity as the concerned property form of the client to be recommended; or selecting the property shape of which the browsing item quantity reaches a second set threshold value as the concerned property shape of the client to be recommended; the second setting threshold value can be flexibly set according to actual conditions.
And determining the peripheral matching of each browsing item in the browsing log of the client to be recommended, and performing quantization and mean processing on the peripheral matching of each browsing item to serve as the concerned peripheral matching of the client to be recommended.
Determining the type of each browsing item in the browsing log of the client to be recommended, and calculating the number of browsing items corresponding to the same type of the type; selecting the house type with the largest number of browsing items as the concerned house type of the client to be recommended; or selecting the house type with the browsing item quantity reaching a third set threshold value as the concerned house type of the client to be recommended; the third setting threshold value can be flexibly set according to actual conditions.
Determining the house type area of each browsing item in the browsing log of the client to be recommended, and calculating the average house type area of each browsing item as the concerned house type area of the client to be recommended.
And determining the price of each browsing item in the browsing log of the client to be recommended, and calculating the average price of each browsing item as the concerned price of the client to be recommended.
In other embodiments of the present invention, the method for analyzing the browsing log of the client to be recommended to obtain the attention feature information may adopt any other existing method, which is not limited herein.
With the prolonging of the online browsing project time of the client, the data volume of the browsing log is increased, the concerned characteristic information of the client is analyzed based on the browsing log of the client to be recommended, the calculation amount is increased gradually, and the calculation efficiency of the server is affected. In order to reduce the calculation amount, the information about the items concerned by the client in the browsing log of the client to be recommended can be directly obtained, the items concerned by the user can be found, for example, the house sources collected by the client, and the concerned characteristic information of the client can be analyzed based on all the house sources collected by the client, wherein the type of the concerned characteristic information and the analysis process can adopt the way of the above example.
S102, acquiring the transaction characteristic information of each business consultant in the platform, wherein the transaction characteristic information is obtained by analyzing the project submitted by the business consultant.
In this embodiment, the transaction characteristic information includes at least one of a transaction location type, a transaction property shape, a transaction periphery matching, a transaction type area, and a transaction price.
Analyzing based on the project traded by the business consultant to obtain trading characteristic information includes:
acquiring information of each project submitted by a business consultant, and determining the position type, property form, periphery matching, house type, house area and price of each project; wherein the location types of the items include, but are not limited to, riverside, lake, business district, street, park, etc.; the property forms include but are not limited to high-rise, small high-rise, ocean houses, spliced villas, united villas, single villas and the like; the peripheral accessories comprise the number of nearby bus lines, the number of nearby schools, the number of nearby subway lines, the number of nearby hospitals, the number of nearby shopping malls, the number of nearby catering places, the number of nearby entertainment places and the number of nearby banks; types include, but are not limited to, five rooms, two halls, three toilets, four rooms, two halls, two toilets, three rooms, two halls, one toilet, one room, one hall, one toilet, etc.;
counting the number of transaction items under the same position type, selecting the position type with the maximum number of transaction items as the transaction position type of the business consultant, or selecting the position type with the number of transaction items reaching a fourth set threshold value as the transaction position type of the business consultant; for example, the business consultant has 10 sets of houses in the current transaction projects, wherein the position types are 5 for 'approaching the river', 3 for 'business circles', 1 for 'approaching the park' and 1 for 'approaching the street', the position type with the largest transaction project number is selected as the transaction position type, the 'approaching the river' position type has the largest transaction project number, and therefore the 'approaching the river' position type is used as the transaction position type of the business consultant; if the position type with the transaction item quantity reaching 3 is selected as the transaction position type of the business consultant, the transaction position type comprises 'Lingjiang' and 'Shang Pan'; it should be understood that the fourth setting threshold can be flexibly set according to actual situations;
counting the number of transaction items under the same property form, selecting the property form with the maximum number of transaction items as the transaction property form of the service consultant, or selecting the property form with the number of transaction items reaching a fifth set threshold value as the transaction property form of the service consultant; for example, if there are 10 sets of transaction sources of the business consultant, wherein 6 sets of property forms are "high level", 3 sets are "ocean room", and 1 set is "small high level", then according to the property form with the largest number of selected transaction items, as the transaction property form of the business consultant, the "high level" is used as the transaction property form, because the number of transaction items of the "high level" is the largest, the receiving advantage of the business consultant can be reflected most; if the fifth set threshold is set to 3, the high-rise building and the ocean room are required to be used as business forms of the business consultant; the fifth set threshold value can be flexibly set according to the actual situation;
after the peripheral matching of each item which is submitted by the business consultant is quantified and processed with an average value, the business consultant is used as the matching of the business consultant; optionally, the number of the bus routes near each deal of the business consultant is subjected to mean processing to be used as the number of the bus routes near the business periphery; carrying out mean value processing on the number of schools near each project which are submitted by the business consultant to serve as the number of schools near the periphery of the deal; carrying out mean value processing on the number of subway lines near each project of the business consultant as the number of nearby subway lines matched with the business periphery; carrying out mean value processing on the number of hospitals nearby each project of the transaction of the business consultant to be used as the number of hospitals nearby for matching with the transaction periphery; carrying out mean value processing on the number of shopping malls nearby each item of the deal by the business consultant to serve as the number of nearby shopping malls matched with the deal periphery; carrying out mean value processing on the number of the catering places near each item of the business consultant as the number of the catering places near the business periphery; carrying out mean value processing on the number of the entertainment places nearby each project of the business consultant as the number of the nearby entertainment places matched with the business periphery; carrying out mean value processing on the number of banks near each project of the transaction consultant to be used as the number of banks near the periphery of the transaction;
counting the number of transaction items under the same housing type, selecting the housing type with the largest number of transaction items as the transaction housing type of the business consultant, or selecting the housing type with the number of transaction items reaching a sixth set threshold as the transaction housing type of the business consultant; for example, in the 10 sets of business consultant, 4 sets of house type are "three rooms, two halls and two toilets", 3 sets are "two rooms, two halls and two toilets", and 3 sets are "four rooms, two halls and two toilets", then according to the house type selected as the business consultant with the largest number of business items, the house type is the business type using "three rooms, two halls and two toilets", because the number of business items of "three rooms, two halls and two toilets" is the largest; if the sixth set threshold is set to 4, the "three rooms, two toilets" is also used as the business type of the business consultant; the sixth setting threshold value can be flexibly set according to the actual situation;
calculating the average housing area of the project submitted by the business consultant as the submitting housing area of the business consultant; for example, if the housing area of the 10 sets of business consultants is s1, s2, s3, s4, s5, s6, s7, s8, s9 and s10, respectively, the business consultant's business housing area is s ═ (s1+ s2+ s3+ s4+ s5+ s6+ s7+ s8+ s9+ s 10)/10;
calculating the average transaction price of the transaction items of the business consultant as the transaction price of the business consultant; for example, if the prices of the 10 sets of transaction sources of the business consultant are p1, p2, p3, p4, p5, p6, p7, p8, p9 and p10, respectively, the transaction price of the business consultant is p ═ (p1+ p2+ p3+ p4+ p5+ p6+ p7+ p8+ p9+ p 10)/10.
It should be understood that other methods may be used to analyze the transaction characteristics information of the business consultant based on the business consultant transaction source, and will not be described herein.
It should be understood that there is no specific order of execution between step S101 and step S102, and the processing can be flexible.
S103, similarity calculation is carried out on the attention characteristic information of the client to be recommended and the transaction characteristic information of each business consultant.
Optionally, similarity calculation is performed on the concerned position type and the deal position type to obtain a first similarity calculation result; including but not limited to calculating similarity using the following rules:
when Instr (C, S) is more than or equal to 1, the similarity is 1; otherwise, the similarity is 0; wherein C represents a client care location type and S represents a employment advisor deal location type. Instr indicates whether or not a mutual inclusion relationship exists in the parameters. If Instr (Linjiang ', ' Linhu ') is 0 < 1, taking similarity as 0; also, for example, Instr (linjiang, businessman') is 0 < 1, which also indicates that the positions are not similar in type and the similarity is 0.
Similarity calculation is carried out on the concerned property morphology and the transaction property morphology to obtain a second similarity calculation result; if Instr (small high layer ', ' high layer ') -2 is not less than 1, the similarity is 1; if Instr ('small high-rise', 'villa') is 0, it indicates that the property shapes are dissimilar, and the similarity is 0.
Carrying out similarity calculation on the concerned periphery matching and the friendship periphery matching to obtain a third similarity calculation result; the peripheral matching and the house type are generally a string of digital characters, and the similarity is calculated by applying the following calculation rules:
wherein V (C)i) The ith bit value, V (S), representing a characteristic of interest to the customeri) Value of ith bit, w, indicating transaction characteristics of the business advisoriRepresenting the ith bit feature weight.
Carrying out similarity calculation on the concerned house type and the deal house type to obtain a fourth similarity calculation result;
similarity calculation is carried out on the concerned house type area and the deal house type area to obtain a fifth similarity calculation result;
and carrying out similarity calculation on the concerned price and the transaction price to obtain a sixth similarity calculation result.
The house area and the price are usually single numbers, and the similarity is calculated by applying the following calculation rules:
And S104, determining the target employment consultant as the recommendation object according to the similarity calculation result.
Optionally, performing mean processing on the first similarity calculation result, the second similarity calculation result, the third similarity calculation result, the fourth similarity calculation result, the fifth similarity calculation result, and the sixth similarity calculation result to obtain the similarity calculation result; and recommending the plurality of the professional consultants with larger similarity values in the similarity calculation results to the clients to be recommended as target professional consultants. For example, the first 3 business consultants with a higher similarity score are selected as the target business consultants.
And S105, generating a recommendation message to recommend the target employment advisor to the client to be recommended.
For example, a popup message is generated and sent to a client of a client to be recommended, and when the client needs online consultation and watching a house, one of the target business consultants is selected for communication, so that problems can be solved for the client conveniently and timely, and the use experience of the client is improved.
Optionally, before generating the recommendation message to recommend the target employment advisor to the client to be recommended, the method further includes: and determining that the client to be recommended is currently in a non-floor page browsing state. It should be understood that online house-viewing APP browsing pages, including login page, home page, floor list page, guide page, customer personal information page, message page, etc., all belong to non-floor pages; when a customer clicks on a specific building or house source, the customer belongs to the building page.
Optionally, when it is detected that the client to be recommended is currently in a browsing state of a building page, screening out at least one corresponding employment advisor belonging to the currently browsed building of the client to be recommended from each similarity calculation result, and using the screened at least one corresponding employment advisor as a target employment advisor.
Optionally, if 3 employment consultants are selected as target employment consultants; then, firstly, according to the similarity calculation result, determining whether the prior 3 business consultants exist business consultants under the floor currently browsed by the client to be recommended, if so, then using the 3 business consultants as the target business consultants; further, a live advisor belonging to the floor browsed by the client to be recommended may be placed in the first place for presentation; if it is determined that there are no live consultants under the floor browsed by the client to be recommended among the top 3 live consultants, the live consultant belonging to the floor currently browsed by the client to be recommended and having the highest similarity is selected as the target live consultant from the similarity calculation results of the live consultants, and the top 2 live consultants having a high similarity are also selected as the target live consultants.
In other embodiments of the present invention, the area of interest of the client to be recommended may be extracted, and in the similarity calculation result, the employment advisor in the area of interest is preferentially selected as the target employment advisor. For example, at least one of the highly similar people in the area of interest is selected as the target people consultant.
For a better understanding of the present invention, reference is made to the following detailed description taken in conjunction with specific examples:
the attention feature information of the client to be recommended is shown in the following table 1:
TABLE 1
The transaction characteristics information of each professional consultant is shown in table 2 below:
TABLE 2
| Employment consultant | Item location | Form of property | Peripheral matching | Type of house | Area of house | Price |
| Seller01 | Linjiang river | Small high-rise building | 63025479 | 221 | 80 | 12118 |
| Seller02 | In the street | Union villa | 44139889 | 523 | 212 | 16712 |
| Seller03 | Linjiang river | High-rise building | 44352610 | 321 | 112 | 12943 |
| Seller04 | Trade circle | Shop | 13313317 | 0 | 23 | 7978 |
| Seller05 | Trade circle | Small high-rise building | 32221853 | 111 | 59 | 8838 |
| Seller06 | Linjiang river | Single villa | 42411854 | 422 | 198 | 23555 |
| Seller07 | In the street | High-rise building | 22531855 | 321 | 110 | 12411 |
The feature similarity of customer01 and seller01 is calculated by the following detailed process:
(1) item location: instr (Lingjiang 'and Lingjiang') is more than or equal to 1, and the similarity is 1;
(2) the property form is as follows: instr (small high-level ', high-level') is more than or equal to 1, and the similarity is 1;
(3) the periphery is matched:
the Customer01 to be recommended pays attention to the peripheral matching 32133562, and represents 3 bus lines, 2 schools, 1 subway line, 3 hospitals, 3 shopping malls, 5 catering places, 6 entertainment places and 2 banks; the employment consultant, Seller01, was matched with the perimeter 63025479, representing 6 bus lines, 3 schools, 0 subway line, 2 hospitals, 5 malls, 4 dining places, 7 entertainment places, and 9 banks;
the peripheral matching similarity calculation process is shown in table 3 below:
TABLE 3
(4) The house type is as follows: the weights are respectively [ Chamber 0.5, Living room 0.3, toilet 0.2]
A weight selection principle, namely weakening rooms, halls and guards in sequence according to the important level meeting the living and the industrial arrangement standard, wherein in order to reflect relativity and reduce the calculation complexity, the calculation is carried out according to the ratio of 5:3: 2;
the house type is as follows: 211, room 2, hall 1, toilet;
the house type similarity calculation process is shown in the following table 4:
TABLE 4
| Feature(s) | Process for producing a metal oxide |
| Chamber | 1-abs(2-2)/(2+2)＝1 |
| Hall | 1-abs(1-2)/(1+2)＝0.6667 |
| Toilet | 1-abs(1-1)/(1+1)＝1 |
| Feature integrated similarity | [1*0.5+0.6667*0.3+1*0.2]＝0.9000 |
(5) Area of house
1-abs(78-80)/(78+80)＝0.9873；
(6) Price
1-abs(10111-12118)/(10111+12118)＝0.9097；
(7) Integrated similarity
[(1)+(2)+(3)+(4)+(5)+(6)]/6＝(1+1+0.649+0.9+0.9873+0.9097)/6＝0.9077。
Through the above processes, feature similarities of the Customer01 to be recommended and other people consultants (Seller02, Seller03, Seller04, Seller05, Seller06, and Seller07) are respectively calculated, and are specifically shown in table 5 below:
TABLE 5
| C01-S | Item location | Form of property | Type of house | Area of house | Peripheral matching | Price | Integrated similarity |
| Seller01 | 1 | 1 | 0.9000 | 0.9873 | 0.6490 | 0.9097 | 0.9077 |
| Seller02 | 0 | 0 | 0.5857 | 0.5379 | 0.7517 | 0.7539 | 0.4382 |
| Seller03 | 1 | 1 | 0.8000 | 0.8211 | 0.5961 | 0.8772 | 0.8490 |
| Seller04 | 0 | 0 | 0.0000 | 0.4554 | 0.5975 | 0.8821 | 0.3225 |
| Seller05 | 0 | 1 | 0.8333 | 0.8613 | 0.8056 | 0.9328 | 0.7388 |
| Seller06 | 1 | 0 | 0.6667 | 0.5652 | 0.7003 | 0.6007 | 0.5888 |
| Seller07 | 0 | 1 | 0.8000 | 0.8298 | 0.7354 | 0.8979 | 0.7105 |
Through the calculation, an online recommendation is performed on the client Customer01 to be recommended by a public consultant with comprehensive similarity of top 3 (here, Seller01, Seller03 and Seller 05).
The invention provides an intelligent receiving method for online clients in the real estate industry, which comprises the steps of obtaining attention characteristic information of clients to be recommended based on browsing logs of the clients to be recommended to each display floor; acquiring transaction characteristic information of each business consultant in the platform, wherein the transaction characteristic information is obtained by analyzing the transaction items submitted by the business consultants; carrying out similarity calculation on the concerned characteristic information of the client to be recommended and the transaction characteristic information of each business consultant; determining a target employment consultant as a recommendation object according to the similarity calculation result; and generating a recommendation message to recommend the target employment advisor to the client to be recommended. Analyzing the focus of a client and depicting the portrait of the client by researching the online browsing behavior of the client; by researching the transaction information of the business consultant, the source image of the transaction room is described; and performing similarity matching on the client attention points and the transaction characteristics of the business consultants, and recommending the business consultants with transaction information similar to the client attention points to the online visiting clients. Therefore, targeted reception is achieved, targeting is achieved, reception communication efficiency is improved, and improvement of conversion rate is expected to be promoted.
Example two:
in this embodiment, on the basis of the first embodiment, a server is provided for implementing the steps of the intelligent customer reception method for the real estate industry described in the first embodiment, please refer to fig. 2, and the server includes a processor 21, a memory 22 and a communication bus 23;
wherein, 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 method for intelligent customer reception on a property industry online as described in embodiment one. 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 executable by one or more processors to perform the steps of the intelligent customer reception method for a property industry as described in embodiment one. 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 (10)
1. An intelligent customer reception method on the production industry line is characterized by comprising the following steps:
acquiring attention characteristic information of a client to be recommended based on a browsing log of the client to be recommended to each display floor;
acquiring transaction characteristic information of each business consultant in the platform, wherein the transaction characteristic information is obtained by analyzing the transaction items submitted by the business consultants;
carrying out similarity calculation on the attention characteristic information of the client to be recommended and the transaction characteristic information of each business consultant;
determining a target employment consultant as a recommendation object according to the similarity calculation result;
and generating a recommendation message to recommend the target employment advisor to the client to be recommended.
2. The property industry online customer intelligent reception method of claim 1, wherein the attention feature information comprises at least one of an attention location type, an attention property shape, an attention perimeter complement, an attention house type, an attention house area, and an attention price;
the transaction characteristic information comprises at least one of a transaction position type, a transaction property form, a transaction periphery matching, a transaction house type area and a transaction price.
3. The method as claimed in claim 2, wherein the obtaining the attention feature information of the customer to be recommended comprises:
determining the position type of each browsing item in the browsing log of the client to be recommended, and calculating the number of browsing items corresponding to the same position type; selecting the position type with the largest browsing item quantity as the concerned position type of the client to be recommended; or selecting the position type with the browsing item quantity reaching a first set threshold value as the concerned position type of the client to be recommended;
determining the property form of each browsing item in the browsing log of the client to be recommended, and calculating the quantity of browsing items corresponding to the same property form; selecting the property form with the largest browsing item quantity as the concerned property form of the client to be recommended; or selecting the property shape of which the browsing item quantity reaches a second set threshold value as the concerned property shape of the to-be-recommended client;
determining the peripheral matching of each browsing item in the browsing log of the client to be recommended, and performing quantization and mean processing on the peripheral matching of each browsing item to serve as the concerned peripheral matching of the client to be recommended;
determining the type of each browsing item in the browsing log of the client to be recommended, and calculating the number of browsing items corresponding to the same type of the type; selecting the house type with the largest number of browsing items as the concerned house type of the client to be recommended; or selecting the house type with the browsing item quantity reaching a third set threshold value as the concerned house type of the client to be recommended;
determining the house type area of each browsing item in the browsing log of the client to be recommended, and calculating the average house type area of each browsing item as the concerned house type of the client to be recommended;
and determining the price of each browsing item in the browsing log of the client to be recommended, and calculating the average price of each browsing item as the concerned price of the client to be recommended.
4. The method of claim 3, wherein the transaction characteristics information is analyzed based on the terms of the transaction by a posting advisor, comprising:
acquiring information of each project submitted by the employment consultant, and determining the position type, property form, periphery matching, house type, house area and price of each project;
counting the number of transaction items under the same position type, selecting the position type with the maximum number of transaction items as the transaction position type of the business consultant, or selecting the position type with the number of transaction items reaching a fourth set threshold value as the transaction position type of the business consultant;
counting the number of transaction items under the same property form, selecting the property form with the maximum number of transaction items as the transaction property form of the service consultant, or selecting the property form with the number of transaction items reaching a fifth set threshold value as the transaction property form of the service consultant;
after carrying out quantization and mean value processing on the peripheral matching sets of various items submitted by the employment consultant, the peripheral matching sets are used as the submitting peripheral matching sets of the employment consultant;
counting the number of transaction items under the same housing type, selecting the housing type with the largest number of transaction items as the transaction housing type of the business consultant, or selecting the housing type with the number of transaction items reaching a sixth set threshold as the transaction housing type of the business consultant;
calculating the average housing area of the project submitted by the employment consultant as the submitting housing area of the employment consultant;
and calculating the average transaction price of the transaction items of the business consultant as the transaction price of the business consultant.
5. The method as claimed in claim 4, wherein the calculating the similarity between the attention feature information of the recommended client and the transaction feature information of the professional consultants comprises:
carrying out similarity calculation on the concerned position type and the deal position type to obtain a first similarity calculation result;
carrying out similarity calculation on the concerned property shape and the transaction property shape to obtain a second similarity calculation result;
carrying out similarity calculation on the concerned periphery matching and the friendship periphery matching to obtain a third similarity calculation result;
performing similarity calculation on the concerned house type and the deal house type to obtain a fourth similarity calculation result;
performing similarity calculation on the concerned house type area and the deal house type area to obtain a fifth similarity calculation result;
and carrying out similarity calculation on the concerned price and the deal price to obtain a sixth similarity calculation result.
6. The method of claim 5, wherein the determining a target job consultant to recommend based on the similarity calculation comprises:
performing mean processing on the first similarity calculation result, the second similarity calculation result, the third similarity calculation result, the fourth similarity calculation result, the fifth similarity calculation result, and the sixth similarity calculation result to obtain the similarity calculation result;
and recommending the plurality of the employment consultants with larger similarity values in the similarity calculation results to the client to be recommended as the target employment consultants.
7. The method of any of claims 1-6, wherein prior to generating a recommendation message to recommend the target marketing advisor to the customer to be recommended, further comprising: and determining that the client to be recommended is currently in a non-floor page browsing state.
8. The property industry online customer intelligent pick-up method of claim 7, the method further comprising: and when the client to be recommended is determined to be in a floor page browsing state currently, screening out at least one corresponding employment advisor under the floor browsed by the client to be recommended from each similarity calculation result to serve as the target employment advisor.
9. 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 steps of the method for intelligent customer reception on a property industry online as claimed in any one of claims 1 to 8.
10. A storage medium storing one or more programs executable by one or more processors to perform the steps of the method for intelligent customer reception on a property industry online as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910952094.5A CN110689457A (en) | 2019-10-09 | 2019-10-09 | Intelligent reception method for online clients in real estate industry, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910952094.5A CN110689457A (en) | 2019-10-09 | 2019-10-09 | Intelligent reception method for online clients in real estate industry, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110689457A true CN110689457A (en) | 2020-01-14 |
Family
ID=69111644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910952094.5A Pending CN110689457A (en) | 2019-10-09 | 2019-10-09 | Intelligent reception method for online clients in real estate industry, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110689457A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292170A (en) * | 2020-02-18 | 2020-06-16 | 重庆锐云科技有限公司 | Method, device and storage medium for recommending intention customers for appointed building |
| CN111292140A (en) * | 2020-03-19 | 2020-06-16 | 重庆锐云科技有限公司 | Online customer intelligent distribution method |
| CN111401958A (en) * | 2020-03-17 | 2020-07-10 | 重庆锐云科技有限公司 | Method and system for automatically recommending employment consultant to real estate client |
| CN111612474A (en) * | 2020-03-30 | 2020-09-01 | 北京瑞卓喜创科技发展有限公司 | Method, device, terminal and computer-readable storage medium for developing and managing house-purchasing clients |
| CN112132657A (en) * | 2020-09-21 | 2020-12-25 | 深圳思为科技有限公司 | Message reminding method and related equipment |
| CN112330387A (en) * | 2020-09-29 | 2021-02-05 | 重庆锐云科技有限公司 | Virtual broker applied to house-watching software |
| CN112348531A (en) * | 2020-10-19 | 2021-02-09 | 前海飞算科技(深圳)有限公司 | Customer relationship management system and recommendation information generation method |
| CN112561269A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | Advisor recommendation method and device |
| CN112561571A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | House purchasing intention evaluation method and related equipment |
| CN112613838A (en) * | 2020-12-18 | 2021-04-06 | 深圳市思为软件技术有限公司 | Customer management method and related device |
| CN112633901A (en) * | 2020-12-18 | 2021-04-09 | 深圳市思为软件技术有限公司 | Guest judging method and related equipment |
| CN113554532A (en) * | 2021-06-16 | 2021-10-26 | 北京房江湖科技有限公司 | Broker list page sorting method, storage medium, and program product |
| CN113763029A (en) * | 2021-07-20 | 2021-12-07 | 北京房江湖科技有限公司 | Client information recommendation method and device |
| CN117114295A (en) * | 2023-08-08 | 2023-11-24 | 深圳先锋居善科技有限公司 | Customer reception allocation method, apparatus, device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8468143B1 (en) * | 2010-04-07 | 2013-06-18 | Google Inc. | System and method for directing questions to consultants through profile matching |
| CN106776716A (en) * | 2016-11-21 | 2017-05-31 | 北京齐尔布莱特科技有限公司 | A kind of intelligent Matching marketing consultant and the method and apparatus of user |
| CN109636258A (en) * | 2019-02-12 | 2019-04-16 | 重庆锐云科技有限公司 | A kind of real estate client visiting management system |
| CN109657952A (en) * | 2018-12-07 | 2019-04-19 | 万翼科技有限公司 | Distribution method, device and the storage medium of client |
| CN109872258A (en) * | 2019-01-17 | 2019-06-11 | 平安城市建设科技(深圳)有限公司 | The matching process of building house type and nominator, device, equipment and storage medium |
-
2019
- 2019-10-09 CN CN201910952094.5A patent/CN110689457A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8468143B1 (en) * | 2010-04-07 | 2013-06-18 | Google Inc. | System and method for directing questions to consultants through profile matching |
| CN106776716A (en) * | 2016-11-21 | 2017-05-31 | 北京齐尔布莱特科技有限公司 | A kind of intelligent Matching marketing consultant and the method and apparatus of user |
| CN109657952A (en) * | 2018-12-07 | 2019-04-19 | 万翼科技有限公司 | Distribution method, device and the storage medium of client |
| CN109872258A (en) * | 2019-01-17 | 2019-06-11 | 平安城市建设科技(深圳)有限公司 | The matching process of building house type and nominator, device, equipment and storage medium |
| CN109636258A (en) * | 2019-02-12 | 2019-04-16 | 重庆锐云科技有限公司 | A kind of real estate client visiting management system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292170A (en) * | 2020-02-18 | 2020-06-16 | 重庆锐云科技有限公司 | Method, device and storage medium for recommending intention customers for appointed building |
| CN111401958A (en) * | 2020-03-17 | 2020-07-10 | 重庆锐云科技有限公司 | Method and system for automatically recommending employment consultant to real estate client |
| CN111292140A (en) * | 2020-03-19 | 2020-06-16 | 重庆锐云科技有限公司 | Online customer intelligent distribution method |
| CN111612474A (en) * | 2020-03-30 | 2020-09-01 | 北京瑞卓喜创科技发展有限公司 | Method, device, terminal and computer-readable storage medium for developing and managing house-purchasing clients |
| CN112132657A (en) * | 2020-09-21 | 2020-12-25 | 深圳思为科技有限公司 | Message reminding method and related equipment |
| CN112330387B (en) * | 2020-09-29 | 2023-07-18 | 重庆锐云科技有限公司 | Virtual broker applied to house watching software |
| CN112330387A (en) * | 2020-09-29 | 2021-02-05 | 重庆锐云科技有限公司 | Virtual broker applied to house-watching software |
| CN112348531A (en) * | 2020-10-19 | 2021-02-09 | 前海飞算科技(深圳)有限公司 | Customer relationship management system and recommendation information generation method |
| CN112561571A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | House purchasing intention evaluation method and related equipment |
| CN112561269A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | Advisor recommendation method and device |
| CN112613838A (en) * | 2020-12-18 | 2021-04-06 | 深圳市思为软件技术有限公司 | Customer management method and related device |
| CN112633901A (en) * | 2020-12-18 | 2021-04-09 | 深圳市思为软件技术有限公司 | Guest judging method and related equipment |
| CN113554532A (en) * | 2021-06-16 | 2021-10-26 | 北京房江湖科技有限公司 | Broker list page sorting method, storage medium, and program product |
| CN113763029A (en) * | 2021-07-20 | 2021-12-07 | 北京房江湖科技有限公司 | Client information recommendation method and device |
| CN117114295A (en) * | 2023-08-08 | 2023-11-24 | 深圳先锋居善科技有限公司 | Customer reception allocation method, apparatus, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110689457A (en) | Intelligent reception method for online clients in real estate industry, server and storage medium | |
| US20220114623A1 (en) | Automatically determining a current value for a home | |
| Tang et al. | Factors affecting effectiveness and efficiency of analyzing stakeholders' needs at the briefing stage of public private partnership projects | |
| WO2021174944A1 (en) | Message push method based on target activity, and related device | |
| US20210035126A1 (en) | Data processing method, system and computer device based on electronic payment behaviors | |
| CN110910282B (en) | System, method and storage medium for earning commission of multi-role customer service for real estate electronic commerce | |
| CN110716979A (en) | House buying intention client mining method, device and server | |
| CN104657133B (en) | A kind of motivational techniques for single-time-window task in mobile intelligent perception | |
| Yin et al. | Does e-commerce narrow the urban–rural income gap? Evidence from Chinese provinces | |
| US20030033195A1 (en) | Retail site location void analysis system and method | |
| KR102099562B1 (en) | System for providing art sale service with amateur art dealing market | |
| US9411860B2 (en) | Capturing intentions within online text | |
| CN108416630A (en) | A kind of determination method and device of target audience | |
| CN111723292A (en) | Recommendation method and system based on graph neural network, electronic device and storage medium | |
| CN111415199A (en) | Customer prediction updating method and device based on big data and storage medium | |
| WO2021175302A1 (en) | Data collection method and system | |
| CN111027838A (en) | Crowdsourcing task pushing method, device, equipment and storage medium thereof | |
| O’Brien et al. | Effects of economic incentives in the American film industry: An ecological approach | |
| White et al. | Influence of natural amenities on residential property values in a rural setting | |
| US20140222700A1 (en) | Predictive pairing and/or matching systems, apparatus, and methods | |
| Xia et al. | Leveraging employee online reviews for improving hotel competitiveness in the great resignation | |
| CN113706173B (en) | Information management method and device, electronic equipment and storage medium | |
| CN113032694B (en) | Scene-based query method and device, storage medium and computer equipment | |
| JPWO2005020115A1 (en) | Real estate trading system | |
| CN112434140B (en) | Reply information processing method and system |
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 |
Application publication date: 20200114 |
|
| RJ01 | Rejection of invention patent application after publication |