CN110956479A - Product recommendation method based on sales lead interaction records - Google Patents
Product recommendation method based on sales lead interaction records Download PDFInfo
- Publication number
- CN110956479A CN110956479A CN201811122836.3A CN201811122836A CN110956479A CN 110956479 A CN110956479 A CN 110956479A CN 201811122836 A CN201811122836 A CN 201811122836A CN 110956479 A CN110956479 A CN 110956479A
- Authority
- CN
- China
- Prior art keywords
- sales
- lead
- sales lead
- data
- information
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0257—User requested
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a product recommendation method based on sales lead interaction records, which comprises the following steps: s1, collecting sales clue information of a product, wherein the sales clue is a client who is not verified and filtered; s2, establishing a sales lead prediction model, and evaluating a purchase intention index of the sales lead; s3, collecting communication information between sales leads and salesmen; s4, constructing a tactical database, obtaining the recommended tactics in the tactical database by a salesman according to a target sales lead, recommending a target product to the sales lead by adopting the obtained recommended tactics, and by the method, accurately judging the purchase intention of the sales lead according to the information of the sales lead and the communication information between the sales lead and the salesman, effectively improving the conversion rate of the sales lead to an actual buyer, thereby improving the sales performance of an enterprise and reducing the sales cost of the enterprise.
Description
Technical Field
The invention relates to a product recommendation method, in particular to a product recommendation method based on sales lead interaction records.
Background
With the continuous development of information technology and the internet, intelligent recommendation systems have gradually penetrated into every industry in our lives. By collecting and analyzing the basic attributes and behavior data of the users, the enterprise can be helped to make more effective decision and prediction in various fields.
Many existing intelligent recommendation systems establish data acquisition index dimensions with a user as a main line: purchase history, ethnic attributes, shopping events, etc. However, the data can only guide the user for the first time, and the guidance is not strong for low-frequency high-rate products. For example, in the automotive industry, a user's purchase of a car typically involves 3 links rather than an immediate purchase. The first step is the dealer telephone invitation, the second step is the sales lead to the store for consultation or test driving, and the last step is the real car purchase. The common intelligent recommendation system can only carry out one-time recommendation through basic information of a user, so that call records in the three links, various sales clue interaction records such as sales clues to store behaviors and the like are completely ignored, and a lot of guide opportunities are not well utilized, so that the sales performance of an enterprise is poor, the sales cost is high, and the user cannot buy a self-appetizing product.
Therefore, in order to solve the above technical problems, it is necessary to provide a new product recommendation method.
Disclosure of Invention
In view of this, the present invention provides a product recommendation method based on sales lead interaction records, which can effectively improve the conversion rate of sales leads, improve the sales performance of enterprises, and reduce the sales cost of enterprises.
The invention provides a product recommendation method based on sales lead interaction records, which comprises the following steps:
s1, collecting sales clue information of a product, wherein the sales clue is a client who is not verified and filtered;
s2, establishing a sales lead prediction model, and evaluating a purchase intention index of the sales lead;
s3, collecting communication information between sales leads and salesmen;
and S4, constructing a tactical database, and obtaining the recommended tactics in the tactical database by a salesman according to the target sales clue and recommending the target product to the sales clue by adopting the obtained recommended tactics.
Further, in step S2, the sales lead prediction model is as follows:
f(i)＝β0+β1x1,1+β2x2,1+…+βm-1xm-1,1+βmxm,1wherein β0，β1，β2，…，βm-1，βmRespectively the influence of the target variableCoefficient, x1,1，x2,1，…，xm-1,1，xm,1Respectively representing different target variables;
the purchase intention index of the sales lead is stored into the lead pool, and the purchase intention indexes of all the sales leads in the lead pool are ranked, and the higher the purchase intention index is, the higher the possibility of purchase is.
Further, step S1 includes performing enhancement processing on the sales lead information: and matching the sales lead data with a plurality of external data sources, acquiring sales lead behavior data, interest data and literary data, and adding the behavior data, the interest data and the literary data into the data of the original sales lead to form reinforced sales lead data.
Further, the communication information between the sales clue and the salesperson is collected by the following method:
for the character exchange records, a natural language analysis method is adopted to interpret the semantics;
for voice communication records, an AI voice recognition technology is adopted to convert voice into character information, and then a natural language analysis method is used to read semantics;
and mining related topics of the product through semantic interpretation of the communication records.
Further, the method also includes step S5:
and (3) optimizing the sales lead prediction model according to the communication information: and performing machine learning on the communication information of the sales lead and the salesperson by adopting an artificial intelligence module, finding out a new target variable related to the purchase intention of the sales lead, and then adding the target variable into a sales lead prediction model or correcting the target variable in the original model.
The invention has the beneficial effects that: according to the invention, the purchase intention of the sales clue can be accurately judged according to the information of the sales clue and the communication information between the sales clue and the salesperson, and the conversion rate of the sales clue to the actual buyer is effectively improved, so that the sales achievement of an enterprise is improved, and the sales cost of the enterprise is reduced.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings, in which:
the invention provides a product recommendation method based on sales lead interaction records, which comprises the following steps:
s1, collecting sales clue information of a product, wherein the sales clue is a client who is not verified and filtered;
s2, establishing a sales lead prediction model, and evaluating a purchase intention index of the sales lead;
s3, collecting communication information between sales leads and salesmen;
s4, constructing an tactical database, and obtaining a recommended tactic in the tactical database by a salesman according to a target sales lead and recommending a target product to the sales lead by adopting the obtained recommended tactic, wherein the tactical database is a database adopting different recommendation strategies aiming at different sales leads, for example, for vehicle sales, if the sales lead is a person with single body and low income, the salesman guides the sales lead to buy a small vehicle by adopting the corresponding tactic according to the state of the current sales lead, so that resonance can be generated between the salesman and the sales lead, and the sales lead is easy to receive recommendation and buy the product;
by the method, the purchase intention of the sales clue can be accurately judged according to the information of the sales clue and the communication information between the sales clue and the salesperson, and the conversion rate of the sales clue to the actual buyer is effectively improved, so that the sales achievement of an enterprise is improved, and the sales cost of the enterprise is reduced.
In this embodiment, in step S2, the sales lead prediction model is as follows:
f(i)＝β0+β1x1,1+β2x2,1+…+βm-1xm-1,1+βmxm,1wherein β0，β1，β2，…，βm-1，βmRespectively, the influence coefficient, x, of the target variable1,1，x2,1，…，xm-1,1，xm,1Respectively representing different target variables;
the purchase intention indexes of the sales leads are stored in a lead pool, and the purchase intention indexes of all the sales leads in the lead pool are ranked, and the higher the purchase intention index is, the higher the possibility of purchase is, wherein target variables comprise income, age, marital state, child existence, parent age and the like of the sales leads, and all the target variables influence the purchase intention of the sales leads on the products.
In this embodiment, in step S1, the method further includes performing enhancement processing on the sales lead information: and matching the sales lead data with a plurality of external data sources, acquiring sales lead behavior data, interest data and literary data, and adding the behavior data, the interest data and the literary data into the data of the original sales lead to form reinforced sales lead data. The process of matching the sales thread with the external data source is as follows:
collecting characteristic data of sales leads; the characteristic data is a using equipment number of a sales clue, a mobile phone number of the sales clue is preferentially adopted, in order to ensure the confidentiality of information of the sales clue, the mobile phone number needs to be encrypted, the encrypted mobile phone numbers are adopted for matching in the matching process, for example, the mobile phone number is converted into a serial number expressed by 0 and 1, and then the matching is carried out through the binary serial number;
matching and checking the characteristic information with an external data source, wherein the external data source is generally a communication operator data source or other third-party data sources, comparing the mobile phone number of the sales clue with the mobile phone number in the external data source, searching whether the mobile phone number has the same mobile phone number, and if not, searching from other external data sources; the behavior data comprises the activity range of the sales lead and mobile phone information (such as the mobile phone model), and the humanistic information comprises marital state, gender, whether children, age, occupation type and the like, and by the method, the state of the current sales lead can be accurately mastered, and accurate product recommendation can be provided for the sales lead;
in this embodiment, the communication information between the sales thread and the salesperson is collected by the following method:
for the character exchange records, a natural language analysis method is adopted to interpret the semantics;
for voice communication records, an AI voice recognition technology is adopted to convert voice into character information, and then a natural language analysis method is used to read semantics;
through semantic interpretation of the communication records, the topics related to the products are mined, wherein the topics related to the products comprise brands, styles, performances and the like of the products, for the character communication records, character chatting records between the salesman and the sales leads are obtained through social software of the salesman or mobile phone short messages and other modes, the voice communication records comprise call records between the salesman and the sales leads, field communication records and the like, and in addition, through the voice communication records, effective conversation indexes such as call duration, conversation interactivity, conversation frequency and emotion of the sales leads can be obtained, through the mode, the sales prediction model is optimized through various indexes, so that the results of the sales prediction model are more accurate, for example: if the call duration between the salesperson and the sales lead is longer, the probability of the sales lead arriving at the store is higher, and the weighting coefficient of the target variable of the call duration is increased; the topic mining of the product is carried out according to the communication records between the salesman and the sales thread, for example, the communication records of the sales thread refer to key words such as safety belts, air bags and the like, the communication records can be classified into safety topics, and at the moment, the prediction model of the sales thread is adjusted according to the times, attitudes, tones and volume of the sales thread refer to the key words such as safety and the like, so that the prediction result can be more accurate.
In this embodiment, the method further includes step S5:
and (3) optimizing the sales lead prediction model according to the communication information: the method comprises the steps of performing machine learning on communication information of sales leads and salesmen by adopting an artificial intelligence module, finding out a new target variable related to purchase intention of the sales leads, adding the target variable into a sales lead prediction model or correcting the target variable in an original model, and dynamically correcting the sales lead prediction model in real time by the method so as to make more accurate sales intention assessment, wherein the machine learning and artificial intelligence module is the prior art, and specific principles of the machine learning and artificial intelligence module are not described in detail herein. When the sales lead prediction model is optimized, the artificial intelligence module learns the communication information, finds out a theme related to the product, judges whether the occurrence frequency of keywords related to the theme reaches a set threshold value, if the occurrence frequency of the keywords related to the theme reaches the set threshold value, if the theme does not appear in the sales lead prediction model, the theme is used as a target variable and added into the sales prediction model, and a weight coefficient, namely an influence coefficient of the target variable, is given to the target variable, and if the target variable is already in the sales prediction model, the influence coefficient of the target variable is adjusted according to the occurrence frequency of the keywords related to the theme, so that the sales prediction model is updated, and the accuracy of the sales prediction model is more accurate.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (5)
1. A product recommendation method based on sales lead interaction records is characterized in that: the method comprises the following steps:
s1, collecting sales clue information of a product, wherein the sales clue is a client who is not verified and filtered;
s2, establishing a sales lead prediction model, and evaluating a purchase intention index of the sales lead;
s3, collecting communication information between sales leads and salesmen;
and S4, constructing a tactical database, and obtaining the recommended tactics in the tactical database by a salesman according to the target sales clue and recommending the target product to the sales clue by adopting the obtained recommended tactics.
2. The method of claim 1, wherein the method comprises: in step S2, the sales lead prediction model is as follows:
f(i)＝β0+β1x1,1+β2x2,1+…+βm-1xm-1,1+βmxm,1wherein β0，β1，β2，…，βm-1，βmRespectively, the influence coefficient, x, of the target variable1,1，x2,1，…，xm-1,1，xm,1Respectively representing different target variables;
the purchase intention index of the sales lead is stored into the lead pool, and the purchase intention indexes of all the sales leads in the lead pool are ranked, and the higher the purchase intention index is, the higher the possibility of purchase is.
3. The method of claim 1, wherein the method comprises: in step S1, the method further includes performing enhancement processing on the sales lead information: and matching the sales lead data with a plurality of external data sources, acquiring sales lead behavior data, interest data and literary data, and adding the behavior data, the interest data and the literary data into the data of the original sales lead to form reinforced sales lead data.
4. The method of claim 1, wherein the method comprises: collecting communication information between sales clues and salespeople by the following method:
for the character exchange records, a natural language analysis method is adopted to interpret the semantics;
for voice communication records, an AI voice recognition technology is adopted to convert voice into character information, and then a natural language analysis method is used to read semantics;
and mining related topics of the product through semantic interpretation of the communication records.
5. The method of claim 1, wherein the method comprises: further comprising step S5:
and (3) optimizing the sales lead prediction model according to the communication information: and performing machine learning on the communication information of the sales lead and the salesperson by adopting an artificial intelligence module, finding out a new target variable related to the purchase intention of the sales lead, and then adding the target variable into a sales lead prediction model or correcting the target variable in the original model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811122836.3A CN110956479A (en) | 2018-09-26 | 2018-09-26 | Product recommendation method based on sales lead interaction records |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811122836.3A CN110956479A (en) | 2018-09-26 | 2018-09-26 | Product recommendation method based on sales lead interaction records |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110956479A true CN110956479A (en) | 2020-04-03 |
Family
ID=69964363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811122836.3A Pending CN110956479A (en) | 2018-09-26 | 2018-09-26 | Product recommendation method based on sales lead interaction records |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110956479A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539221A (en) * | 2020-05-13 | 2020-08-14 | 北京焦点新干线信息技术有限公司 | Data processing method and system |
| CN112185355A (en) * | 2020-09-18 | 2021-01-05 | 马上消费金融股份有限公司 | Information processing method, device, equipment and readable storage medium |
| CN112711711A (en) * | 2021-01-07 | 2021-04-27 | 泰康保险集团股份有限公司 | Knowledge base-based client marketing cue recommendation method and device |
| CN113362108A (en) * | 2021-06-02 | 2021-09-07 | 北京国联视讯信息技术股份有限公司 | Accurate operation method and system based on artificial intelligence |
| CN114266488A (en) * | 2021-12-24 | 2022-04-01 | 适享智能科技(苏州)有限公司 | Salesman incentive method based on questionnaire interaction |
| CN117291655A (en) * | 2023-11-27 | 2023-12-26 | 广州欧派创意家居设计有限公司 | Consumer life cycle operation analysis method based on entity and network collaborative mapping |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105162977A (en) * | 2015-08-26 | 2015-12-16 | 上海银天下科技有限公司 | Excuse recommendation method and device |
| CN106056241A (en) * | 2016-05-26 | 2016-10-26 | 中国太平洋保险（集团）股份有限公司 | Control method and device for predicting user behavior based on large data |
| CN107194715A (en) * | 2017-04-07 | 2017-09-22 | 广东精点数据科技股份有限公司 | The construction method of social action data model |
| CN107688967A (en) * | 2017-08-24 | 2018-02-13 | 平安科技（深圳）有限公司 | The Forecasting Methodology and terminal device of client's purchase intention |
-
2018
- 2018-09-26 CN CN201811122836.3A patent/CN110956479A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105162977A (en) * | 2015-08-26 | 2015-12-16 | 上海银天下科技有限公司 | Excuse recommendation method and device |
| CN106056241A (en) * | 2016-05-26 | 2016-10-26 | 中国太平洋保险（集团）股份有限公司 | Control method and device for predicting user behavior based on large data |
| CN107194715A (en) * | 2017-04-07 | 2017-09-22 | 广东精点数据科技股份有限公司 | The construction method of social action data model |
| CN107688967A (en) * | 2017-08-24 | 2018-02-13 | 平安科技（深圳）有限公司 | The Forecasting Methodology and terminal device of client's purchase intention |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539221A (en) * | 2020-05-13 | 2020-08-14 | 北京焦点新干线信息技术有限公司 | Data processing method and system |
| CN111539221B (en) * | 2020-05-13 | 2023-09-12 | 北京焦点新干线信息技术有限公司 | Data processing method and system |
| CN112185355A (en) * | 2020-09-18 | 2021-01-05 | 马上消费金融股份有限公司 | Information processing method, device, equipment and readable storage medium |
| CN112711711A (en) * | 2021-01-07 | 2021-04-27 | 泰康保险集团股份有限公司 | Knowledge base-based client marketing cue recommendation method and device |
| CN113362108A (en) * | 2021-06-02 | 2021-09-07 | 北京国联视讯信息技术股份有限公司 | Accurate operation method and system based on artificial intelligence |
| CN113362108B (en) * | 2021-06-02 | 2023-12-29 | 北京国联视讯信息技术股份有限公司 | Accurate operation method and system based on artificial intelligence |
| CN114266488A (en) * | 2021-12-24 | 2022-04-01 | 适享智能科技(苏州)有限公司 | Salesman incentive method based on questionnaire interaction |
| CN117291655A (en) * | 2023-11-27 | 2023-12-26 | 广州欧派创意家居设计有限公司 | Consumer life cycle operation analysis method based on entity and network collaborative mapping |
| CN117291655B (en) * | 2023-11-27 | 2024-01-23 | 广州欧派创意家居设计有限公司 | Consumer life cycle operation analysis method based on entity and network collaborative mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956479A (en) | Product recommendation method based on sales lead interaction records | |
| US20210357378A1 (en) | Multi-service business platform system having entity resolution systems and methods | |
| US20180082184A1 (en) | Context-aware chatbot system and method | |
| US20180115645A1 (en) | System, method and marketplace for real-time interactive video/voice services using artificial intelligence | |
| US9460155B2 (en) | Method and system of continuous contextual user engagement | |
| US20200143115A1 (en) | Systems and methods for improved automated conversations | |
| US20160239865A1 (en) | Method and device for advertisement classification | |
| US20220172260A1 (en) | Method, apparatus, storage medium, and device for generating user profile | |
| CN110019753B (en) | Method and device for outputting back question aiming at user question | |
| US10019670B2 (en) | Systems and methods for creating and implementing an artificially intelligent agent or system | |
| CN112507139B (en) | Knowledge graph-based question and answer method, system, equipment and storage medium | |
| CN108287848B (en) | Method and system for semantic parsing | |
| US10600017B2 (en) | Co-opetition index based on rival behavior in social networks | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| US20230316186A1 (en) | Multi-service business platform system having entity resolution systems and methods | |
| CN110750633B (en) | Method and device for determining answer of question | |
| KR102156249B1 (en) | Indexing system and method using variational recurrent autoencoding | |
| CN111382265B (en) | Searching method, device, equipment and medium | |
| CN111949777A (en) | Intelligent voice conversation method and device based on crowd classification and electronic equipment | |
| CN116881730A (en) | Chat scene matching system, method, equipment and storage medium based on context | |
| CN114492310B (en) | Text labeling method, text labeling device, electronic equipment and storage medium | |
| CN114186048A (en) | Question-answer replying method and device based on artificial intelligence, computer equipment and medium | |
| KR102637614B1 (en) | Assessing applications for delivery via an application delivery server | |
| CN111127040A (en) | Data processing method, intelligent customer service system, electronic equipment and medium | |
| CN116911314B (en) | Training method of intention recognition model, conversation intention recognition 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 |