CN108228950A - A kind of information processing method and device - Google Patents
A kind of information processing method and device Download PDFInfo
- Publication number
- CN108228950A CN108228950A CN201611198308.7A CN201611198308A CN108228950A CN 108228950 A CN108228950 A CN 108228950A CN 201611198308 A CN201611198308 A CN 201611198308A CN 108228950 A CN108228950 A CN 108228950A
- Authority
- CN
- China
- Prior art keywords
- information
- marketing personnel
- recommended models
- current
- personnel
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of information processing method and device, is related to data service technical field, to improve the accuracy of the prediction result provided to marketing personnel, so as to cut operating costs.The information processing method of the present invention, including：Obtain the information of current marketing personnel；According to the information of the current marketing personnel, the recommended models with the information matches of the current marketing personnel are obtained；Wherein, the recommended models are trained using the information of default marketing personnel and the information of the corresponding historic customer of the default marketing personnel；Obtain the information of pending client；It is that the current marketing personnel determine target customer from the pending client according to the information of the current marketing personnel, the information of the pending client and the recommended models.Present invention is mainly used in business marketing technology.
Description
Technical field
The present invention relates to data service technical field more particularly to a kind of information processing methods and device.
Background technology
The modeling mining of precision marketing model and using process, including three basic processes：For the history of training pattern
Data collection and feature selecting stage；The model training stage；Use model prediction recommendation stage etc..
For example, telecom operators are marketed particular terminal or during flow package by voice contact staff to client, customer service people
Member sees the customers of the recommendation marketing of system output, is exactly the recommendation results that backstage has precision marketing model.
But it is used existing for modeling trained history data collection stage, modelling phase and following model
Stage is all concerned only with the historical data of customer group, the feature of customer group, the marketing objectives visitor recommended to different marketing personnel
Family group is also same recommended models as a result, the prediction result so as to cause recommendation is inaccurate.
Invention content
In view of this, the present invention provides a kind of information processing method and device, to improve provided to marketing personnel it is pre-
The accuracy of result is surveyed, so as to cut operating costs.
In order to solve the above technical problems, the present invention provides a kind of information processing method, including：
Obtain the information of current marketing personnel；
According to the information of the current marketing personnel, the recommendation mould with the information matches of the current marketing personnel is obtained
Type；Wherein, the recommended models are to utilize the default information of marketing personnel and the corresponding historic customer of the default marketing personnel
Information train；
Obtain the information of pending client；
According to the information of the current marketing personnel, the information of the pending client and the recommended models, from described
It is that the current marketing personnel determine target customer in pending client.
Wherein, the information according to the current marketing personnel obtains the information matches with the current marketing personnel
Recommended models the step of, including：
The information of marketing personnel in the information of the current marketing personnel, with each alternative recommended models of storage is carried out
Matching；
If the matching degree of the information of the current marketing personnel and the information of the marketing personnel in the first alternative recommended models
More than predetermined threshold value, then using the described first alternative recommended models as the recommendation mould of the information matches with the current marketing personnel
Type.
Wherein, it is described according to the information of the current marketing personnel, the information of the pending client and the recommendation mould
Type is the step of current marketing personnel determine target customer from the pending client, including：
Using the information of the current marketing personnel, the information of the pending client as the recommended models input,
Run the recommended models；
The target customer is determined according to the operation result of the recommended models.
Wherein, the step of information of the current marketing personnel of acquisition before, the method further includes：
The training recommended models.
Wherein, the step of training recommended models, including：
Obtain the information of the default marketing personnel；
The information of the corresponding historic customer of the default marketing personnel is obtained, wherein the information of the historic customer includes institute
State the mark of historic customer, the client characteristics of the historic customer, the marketing result of the historic customer；
Using the information of the information of the default marketing personnel and the historic customer as the input of default proposed algorithm, instruction
Practice the corresponding recommended models of the default marketing personnel.
Wherein, after the step of information of the pending client of acquisition, the method further includes：
Obtain the real-time emotion status information of the current marketing personnel；
It is described according to the information of the current marketing personnel, the information of the pending client and the recommended models, from
It is the step of current marketing personnel determine target customer in the pending client, specially：
The information of the current marketing personnel, the information of the pending client, the real-time emotion status information are made
For the input of the recommended models, the recommended models are run；
The target customer is determined according to the operation result of the recommended models.
Second aspect, the present invention provide a kind of information processing unit, including：
First information acquisition module, for obtaining the information of current marketing personnel；
Recommended models acquisition module for the information according to the current marketing personnel, obtains and the current marketing people
The recommended models of the information matches of member；Wherein, the recommended models be using default marketing personnel information and described pre- anchor a tent
What the information of the corresponding historic customer of pin personnel was trained；
Second data obtaining module, for obtaining the information of pending client；
Determining module, for according to the current marketing personnel information, the information of the pending client and described push away
Model is recommended, is that the current marketing personnel determine target customer from the pending client.
Wherein, the recommended models acquisition module includes：
Matched sub-block, for by the battalion in the information of the current marketing personnel, with each alternative recommended models of storage
The information of pin personnel is matched；
Acquisition submodule, if the information for the current marketing personnel and the marketing personnel in the first alternative recommended models
Information matching degree be more than predetermined threshold value, then using the described first alternative recommended models as the letter with the current marketing personnel
Cease matched recommended models.
Wherein, the determining module includes：
First operation submodule, for using the information of the information of the current marketing personnel, the pending client as
The input of the recommended models runs the recommended models；
First determination sub-module, for determining the target customer according to the operation result of the recommended models.
Wherein, described device further includes：
Training module, for training the recommended models.
Wherein, the training module includes：
First information acquisition submodule, for obtaining the information of the default marketing personnel；
Second acquisition of information submodule, for obtaining the information of the corresponding historic customer of the default marketing personnel, wherein
The information of the historic customer includes the mark of the historic customer, the client characteristics of the historic customer, the historic customer
Marketing result；
Training submodule, for the information of the information of the default marketing personnel and the historic customer to be pushed away as default
The input of algorithm is recommended, trains the corresponding recommended models of the default marketing personnel.
Wherein, described device further includes：
Third data obtaining module, for obtaining the real-time emotion status information of the current marketing personnel；
The determining module includes：
Second operation submodule, for by the information of the information of the current marketing personnel, the pending client, described
Input of the real-time emotion status information as the recommended models, runs the recommended models；
Second determination sub-module, for determining the target customer according to the operation result of the recommended models.
The above-mentioned technical proposal of the present invention has the beneficial effect that：
In embodiments of the present invention, when recommending client to current marketing personnel, using corresponding with current marketing personnel
Recommended models and the current information of marketing personnel, the information of pending client are recommended, also, the recommended models are profits
It is trained with the information of default marketing personnel and the information of the corresponding historic customer of the default marketing personnel.Namely
It says, in the scheme of the embodiment of the present invention, when recommending target customer to marketing personnel, the information for not only allowing for client is also examined
The information of marketing personnel is considered, therefore, compared with prior art, can have been carried using the scheme of the embodiment of the present invention to marketing personnel
For more accurate prediction result, so as to cut operating costs.
Description of the drawings
Fig. 1 is the flow chart of the information processing method of the embodiment of the present invention one；
Fig. 2 is the flow chart of the information processing method of the embodiment of the present invention two；
Fig. 3 is the schematic diagram of training recommended models in the embodiment of the present invention two；
Fig. 4 is the schematic diagram for recommending target customer in the embodiment of the present invention two using recommended models；
Fig. 5 is the schematic diagram of the information processing unit of the embodiment of the present invention three；
Fig. 6 is the structure chart of the information processing unit of the embodiment of the present invention three.
Specific embodiment
Below in conjunction with drawings and examples, the specific embodiment of the present invention is described in further detail.Following reality
Example is applied for illustrating the present invention, but be not limited to the scope of the present invention.
In the prior art, when recommending target customer to marketing personnel, procedure below is generally included：
First, the directly related history data set of user is collected as training set, these user data usually cover user
Essential attribute (gender, age, in net length of surfing the Net, terminal models etc.), history consumer behavior (which voice set meal, flow ordered
Which dats services with increment set meal orders, whether participated in marketing activity) and the characteristics such as historical bills, it further includes and is directed to
Whether the product to be marketed, these users receive the marketing Suggestions of contact staff, i.e., the history marketing result of each user；So
Afterwards, training set is done with the historical data of user and marketing result, selects specific machine learning or mining algorithm, be trained,
Generation is for the marketing prediction of result model of this marketing product；Finally, for fresh target user group, it is used as language using the model
Whether sound contact staff is worth new user the recommendation foundation of marketing (whether marketing can succeed).
Due to being concerned only with the historical data of customer group, the feature of customer group in said program, to different marketing people
The marketing objectives customers that member recommends also all are same recommended models as a result, the prediction result so as to cause recommendation is not allowed
Really.For this purpose, the scheme of the embodiment of the present invention using the information of marketing personnel and the information of client simultaneously as Consideration, so as to
It is enough accurately to recommend client for marketing personnel, it cuts operating costs.
Embodiment one
As shown in Figure 1, the information processing method of the embodiment of the present invention one, including：
Step 101, the information for obtaining current marketing personnel.
Wherein, the information of the current marketing personnel includes but is not limited to：Gender, audio, tone, average word speed, language
Speech feature likes color (character trait), culture background (education background, cultural preference etc.), emotional state etc..
Step 102, the information according to the current marketing personnel obtain and the information matches of the current marketing personnel
Recommended models.
Wherein, the recommended models are to utilize the default information of marketing personnel and the corresponding history of the default marketing personnel
What the information of client was trained.
In practical applications, different marketing personnel can be directed to and trains different recommended models.In training recommended models,
By information (being also possible to the information for including current marketing personnel), the corresponding history of marketing personnel of some preset marketing personnel
Client namely the marketing personnel once carried out the information of the client of marketing as Consideration, by proposed algorithm, such as determined
Plan tree, Bayes etc., the corresponding recommended models of the training marketing personnel.
So, in this step, by the battalion in the information of the current marketing personnel, with each alternative recommended models of storage
The information of pin personnel is matched.If the information of the current marketing personnel is with the marketing personnel's in the first alternative recommended models
The matching degree of information is more than predetermined threshold value, then using the described first alternative recommended models as the information with the current marketing personnel
Matched recommended models.Wherein, which can arbitrarily be set.
For example, matched, the information of current marketing personnel A and the information of the marketing personnel in recommended models B relatively match.That
Here, using recommended models B as the corresponding recommended models of current marketing personnel A.
Step 103, the information for obtaining pending client.
Wherein, the information of the pending client refers to treating that the information of the client of sales service is unfolded to it, including but
It is not limited to：Gender, age, in net length of surfing the Net, terminal models etc..
Step 104, according to the information of the current marketing personnel, the information of the pending client and the recommendation mould
Type is that the current marketing personnel determine target customer from the pending client.
Specifically, in this step, using the information of the current marketing personnel, the information of the pending client as institute
The input of recommended models is stated, runs the recommended models, the target is then determined according to the operation result of the recommended models
Client.That is, the output result of the recommended models can be used as target customer.
It can thus be seen that in the scheme of the embodiment of the present invention, when recommending target customer to marketing personnel, not only examine
The information for having considered client also contemplates the information of marketing personnel, therefore, compared with prior art, utilizes the side of the embodiment of the present invention
Case can provide more accurate prediction result to marketing personnel, so as to cut operating costs.
Embodiment two
As shown in Fig. 2, the information processing method of the embodiment of the present invention two, including：
Step 201, training recommended models.
In this step, the information of default marketing personnel is obtained, obtains the corresponding historic customer of the default marketing personnel
Information, wherein the information of the historic customer includes the mark of the historic customer, the client characteristics of the historic customer, institute
State the marketing result of historic customer.Then, using the information of the information of the default marketing personnel and the historic customer as pre-
If the input of proposed algorithm, the corresponding recommended models of the default marketing personnel are trained.
Wherein, the default marketing personnel can be any one or multiple marketing personnel, which can
To be decision tree, Bayes's scheduling algorithm.
As shown in Figure 3, it is assumed that recommended models are trained to marketing personnel A and marketing personnel B at this.
Wherein, the information of marketing personnel A includes：Gender, tone, average word speed, language feature, likes color (property at audio
Lattice feature), culture background (education background, cultural preference etc.), emotional state etc..The information of marketing personnel B includes：Gender, sound
Frequently, tone, average word speed, language feature, like color (character trait), culture background (education background, cultural preference etc.), feelings
Not-ready status etc..
To marketing personnel A, can be marketed and undergone according to its history, obtain the information of corresponding historic customer, as towards this
The training set of the marketing recommended models of marketing personnel.Equally, to marketing personnel B, it can be marketed and undergone according to its history, obtained and correspond to
Historic customer information, the training set as the marketing recommended models towards the marketing personnel.
Selected proposed algorithm, such as decision tree, Bayes, are believed with the information of each marketing personnel and corresponding historic customer
It ceases for input, prediction model is recommended in the marketing that training is directed to the marketing personnel.As shown in figure 3, it is directed to marketing personnel A and battalion respectively
Pin personnel B generates two different recommended models.The characteristic attribute of historic customer is not only included in the decision attribute of recommended models
(gender, age etc.) has also merged the characteristic attribute (audio, emotional state etc.) of marketing personnel.Meanwhile for different marketing
Personnel generation prediction model in, including marketing personnel's characteristic attribute also differ.
Only only include historic customer group (P1 ... from by the angle of marketing client, the training set collected with existing method
Pn characteristic) is different, and the solution of the present invention is on the basis of the feature for considering historic customer group, different marketing personnel
The training data that the characteristic of (A, B ...) also serves as no less important is collected.In this way, for each being marketed
Client, need collect training sample record by<Historic customer ID：History feature：History marketing result>, it is turned into<Battalion
Pin person ID：Salesman's history feature：Historic customer ID：Customer historical feature：History marketing result>.
Therefore, in embodiments of the present invention, training set used in modeling combines the characteristic of marketing personnel, more meets battalion
It is the process of marketing personnel and client both sides and the requirement of behavior to sell interactive process, is mutually tied with client characteristics by marketing personnel's feature
The data set of conjunction can obtain more accurately recommended models.Thus, the prediction carried out using this model more targetedly, is more met
Actual effect, prediction accuracy are by higher.
Step 202, the information for obtaining current marketing personnel.
Assuming that current marketing personnel C, the information of the marketing personnel C of acquisition include：Gender, audio, tone, average word speed,
Language feature likes color (character trait), culture background (education background, cultural preference etc.), emotional state etc..
Step 203, the information according to the current marketing personnel obtain and the information matches of the current marketing personnel
Recommended models.
It is assumed that matched, the corresponding recommended models of marketing personnel A can be as the recommended models of marketing personnel C.
Step 204, the information for obtaining pending client.
It is assumed that pending client in this includes (P1 ... Pn), the information respectively included is：Gender, age, in net net
Age, terminal models etc..
Step 205, the real-time emotion status information for obtaining the current marketing personnel.
In this step, the real-time voice segment of acquisition marketing personnel C, and it is uploaded to emotional state identification device.Then
The device analyzes the real-time emotion state of marketing personnel C using intelligent sound sentiment analysis algorithm, and returns to analysis knot
Fruit.Wherein, the real-time emotion status information of marketing personnel C can be happy, dejected, normal, excited etc..The real-time emotion state
Information is input in recommended models together as the real-time emotion state characteristic attribute of marketing personnel C and the information of pending client
Carry out marketing prediction of result.In this way, the real-time status by marketing personnel can be realized, it is dynamically generated different recommendation results.I.e.
, can be according to marketing personnel in the different emotional states of different time for the same pending customers of a batch, generation is not exactly the same
Prediction recommendation results.
Step 206, by the information of the current marketing personnel, the information of the pending client, the real-time emotion shape
Input of the state information as the recommended models, runs the recommended models.
Step 207 determines the target customer according to the operation result of the recommended models.
As shown in figure 4, by the information of marketing personnel C, the real-time emotion status information of marketing personnel C, pending client
Input of the information as the recommended models, runs the recommended models, and the target of marketing personnel C is determined from pending client
Client.
It can thus be seen that in the scheme of the embodiment of the present invention, when recommending target customer to marketing personnel, not only examine
The information for having considered client also contemplates the information of marketing personnel, therefore, compared with prior art, utilizes the side of the embodiment of the present invention
Case can provide more accurate prediction result to marketing personnel, and so as to cut operating costs, marketing has higher success rate.
Embodiment three
As shown in figure 5, the information processing unit of the embodiment of the present invention three, including：
First information acquisition module 501, for obtaining the information of current marketing personnel；Recommended models acquisition module 502 is used
In the information according to the current marketing personnel, the recommended models with the information matches of the current marketing personnel are obtained；Wherein,
The recommended models are instructed using the information of default marketing personnel and the information of the corresponding historic customer of the default marketing personnel
It gets；Second data obtaining module 503, for obtaining the information of pending client；Determining module 504, for according to institute
The information of current marketing personnel, the information of the pending client and the recommended models are stated, are from the pending client
The current marketing personnel determine target customer.
Wherein, the recommended models acquisition module 502 includes：
Matched sub-block, for by the battalion in the information of the current marketing personnel, with each alternative recommended models of storage
The information of pin personnel is matched；Acquisition submodule, if information and the first alternative recommendation mould for the current marketing personnel
The matching degree of the information of marketing personnel in type is more than predetermined threshold value, then works as using the described first alternative recommended models as with described
The recommended models of the information matches of preceding marketing personnel.
Wherein, the determining module 504 includes：First operation submodule, for by the information of the current marketing personnel,
Input of the information of the pending client as the recommended models, runs the recommended models；First determination sub-module is used
In determining the target customer according to the operation result of the recommended models.
In order to improve marketing efficiency, as shown in fig. 6, described device further includes：
Training module 505, for training the recommended models.
Wherein, the training module 505 includes：First information acquisition submodule, for obtaining the default marketing personnel
Information；Second acquisition of information submodule, for obtaining the information of the corresponding historic customer of the default marketing personnel, wherein institute
The information for stating historic customer includes the mark of the historic customer, the client characteristics of the historic customer, the historic customer
Marketing result；Training submodule, for using the information of the information of the default marketing personnel and the historic customer as default
The corresponding recommended models of the default marketing personnel are trained in the input of proposed algorithm.
Again as shown in fig. 6, in order to further improve the accuracy rate of recommendation, described device further includes：
Third data obtaining module 506, for obtaining the real-time emotion status information of the current marketing personnel.
At this point, the determining module 504 includes：Second operation submodule, for by the information of the current marketing personnel,
The input of the information of the pending client, the real-time emotion status information as the recommended models, runs the recommendation
Model；Second determination sub-module, for determining the target customer according to the operation result of the recommended models.
The operation principle of device of the present invention can refer to the description of preceding method embodiment.
It can thus be seen that in the scheme of the embodiment of the present invention, when recommending target customer to marketing personnel, not only examine
The information for having considered client also contemplates the information of marketing personnel, therefore, compared with prior art, utilizes the side of the embodiment of the present invention
Case can provide more accurate prediction result to marketing personnel, and so as to cut operating costs, marketing has higher success rate.
In several embodiments provided herein, it should be understood that disclosed method and apparatus, it can be by other
Mode realize.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
For a kind of division of logic function, there can be other dividing mode in actual implementation, such as multiple units or component can combine
Or it is desirably integrated into another system or some features can be ignored or does not perform.Another point, shown or discussed phase
Coupling, direct-coupling or communication connection between mutually can be by some interfaces, the INDIRECT COUPLING or communication of device or unit
Connection can be electrical, machinery or other forms.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
That the independent physics of each unit includes, can also two or more units integrate in a unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can be stored in one and computer-readable deposit
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, is used including some instructions so that a computer
Equipment (can be personal computer, server or the network equipment etc.) performs receiving/transmission method described in each embodiment of the present invention
Part steps.And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, abbreviation
ROM), random access memory (Random Access Memory, abbreviation RAM), magnetic disc or CD etc. are various to store
The medium of program code.
The above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, several improvements and modifications can also be made, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (12)
1. a kind of information processing method, which is characterized in that including：
Obtain the information of current marketing personnel；
According to the information of the current marketing personnel, the recommended models with the information matches of the current marketing personnel are obtained；Its
In, the recommended models are the information of the information and the corresponding historic customer of the default marketing personnel using default marketing personnel
What training obtained；
Obtain the information of pending client；
According to the information of the current marketing personnel, the information of the pending client and the recommended models, from described treat
It is that the current marketing personnel determine target customer to manage in client.
2. according to the method described in claim 1, it is characterized in that, the information according to the current marketing personnel, obtains
The step of with the recommended models of the information matches of the current marketing personnel, including：
By the information progress of the marketing personnel in the information of the current marketing personnel, with each alternative recommended models of storage
Match；
If the information of the current marketing personnel and the matching degree of the information of the marketing personnel in the first alternative recommended models are more than
Predetermined threshold value, then using the described first alternative recommended models as the recommended models of the information matches with the current marketing personnel.
It is 3. according to the method described in claim 1, it is characterized in that, the information according to the current marketing personnel, described
The information of pending client and the recommended models are that the current marketing personnel determine target visitor from the pending client
The step of family, including：
Using the information of the current marketing personnel, the information of the pending client as the input of the recommended models, operation
The recommended models；
The target customer is determined according to the operation result of the recommended models.
4. according to the method described in claim 1, it is characterized in that, obtain current marketing personnel described information the step of
Before, the method further includes：
The training recommended models.
5. according to the method described in claim 4, it is characterized in that, the step of the training recommended models, including：
Obtain the information of the default marketing personnel；
The information of the corresponding historic customer of the default marketing personnel is obtained, wherein the information of the historic customer includes described go through
The mark of history client, the client characteristics of the historic customer, the marketing result of the historic customer；
Using the information of the information of the default marketing personnel and the historic customer as the input of default proposed algorithm, training institute
State the corresponding recommended models of default marketing personnel.
6. according to the method described in claim 1, it is characterized in that, obtain pending client described information the step of it
Afterwards, the method further includes：
Obtain the real-time emotion status information of the current marketing personnel；
It is described according to the information of the current marketing personnel, the information of the pending client and the recommended models, from described
It is the step of current marketing personnel determine target customer in pending client, specially：
Using the information of the current marketing personnel, the information of the pending client, the real-time emotion status information as institute
The input of recommended models is stated, runs the recommended models；
The target customer is determined according to the operation result of the recommended models.
7. a kind of information processing unit, which is characterized in that including：
First information acquisition module, for obtaining the information of current marketing personnel；
Recommended models acquisition module for the information according to the current marketing personnel, is obtained with the current marketing personnel's
The recommended models of information matches；Wherein, the recommended models are the information using default marketing personnel and the default marketing people
What the information of the corresponding historic customer of member was trained；
Second data obtaining module, for obtaining the information of pending client；
Determining module, for information, the information of the pending client and the recommendation mould according to the current marketing personnel
Type is that the current marketing personnel determine target customer from the pending client.
8. device according to claim 7, which is characterized in that the recommended models acquisition module includes：
Matched sub-block, for by the marketing people in the information of the current marketing personnel, with each alternative recommended models of storage
The information of member is matched；
Acquisition submodule, if for the information of the current marketing personnel and the letter of the marketing personnel in the first alternative recommended models
The matching degree of breath is more than predetermined threshold value, then using the described first alternative recommended models as the information with the current marketing personnel
The recommended models matched.
9. device according to claim 7, which is characterized in that the determining module includes：
First operation submodule, for using the information of the information of the current marketing personnel, the pending client as described in
The input of recommended models runs the recommended models；
First determination sub-module, for determining the target customer according to the operation result of the recommended models.
10. device according to claim 7, which is characterized in that described device further includes：
Training module, for training the recommended models.
11. device according to claim 10, which is characterized in that the training module includes：
First information acquisition submodule, for obtaining the information of the default marketing personnel；
Second acquisition of information submodule, for obtaining the information of the corresponding historic customer of the default marketing personnel, wherein described
The information of historic customer includes the mark of the historic customer, the client characteristics of the historic customer, the battalion of the historic customer
Sell result；
Training submodule, for recommending to calculate the information of the information of the default marketing personnel and the historic customer as default
The corresponding recommended models of the default marketing personnel are trained in the input of method.
12. device according to claim 7, which is characterized in that described device further includes：
Third data obtaining module, for obtaining the real-time emotion status information of the current marketing personnel；
The determining module includes：
Second operation submodule, for by the information of the information of the current marketing personnel, the pending client, it is described in real time
Input of the emotional state information as the recommended models, runs the recommended models；
Second determination sub-module, for determining the target customer according to the operation result of the recommended models.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611198308.7A CN108228950A (en) | 2016-12-22 | 2016-12-22 | A kind of information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611198308.7A CN108228950A (en) | 2016-12-22 | 2016-12-22 | A kind of information processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108228950A true CN108228950A (en) | 2018-06-29 |
Family
ID=62656966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611198308.7A Pending CN108228950A (en) | 2016-12-22 | 2016-12-22 | A kind of information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108228950A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493133A (en) * | 2018-10-31 | 2019-03-19 | 深圳市轱辘汽车维修技术有限公司 | A kind of determining method, apparatus and electronic equipment for promoting product |
| CN110009397A (en) * | 2019-03-11 | 2019-07-12 | 深圳前海微众银行股份有限公司 | A kind of method and device of precision marketing |
| CN110533453A (en) * | 2019-07-22 | 2019-12-03 | 平安科技（深圳）有限公司 | Based on the matched Products Show method, apparatus of user, computer equipment |
| CN113641904A (en) * | 2021-08-16 | 2021-11-12 | 上海花千树信息科技有限公司 | Method and device for recommending target customers for stores under Internet marriage line |
| CN115081501A (en) * | 2021-03-15 | 2022-09-20 | 中国电信股份有限公司 | User classification method and device, cascaded user classification model and equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462468A (en) * | 2014-12-17 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Information supply method and device |
| CN105868298A (en) * | 2016-03-23 | 2016-08-17 | 华南理工大学 | Mobile phone game recommendation method based on binary decision tree |
-
2016
- 2016-12-22 CN CN201611198308.7A patent/CN108228950A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462468A (en) * | 2014-12-17 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Information supply method and device |
| CN105868298A (en) * | 2016-03-23 | 2016-08-17 | 华南理工大学 | Mobile phone game recommendation method based on binary decision tree |
Non-Patent Citations (1)
| Title |
|---|
| 周涛: "基于用户情境的协同推荐算法研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493133A (en) * | 2018-10-31 | 2019-03-19 | 深圳市轱辘汽车维修技术有限公司 | A kind of determining method, apparatus and electronic equipment for promoting product |
| CN110009397A (en) * | 2019-03-11 | 2019-07-12 | 深圳前海微众银行股份有限公司 | A kind of method and device of precision marketing |
| CN110533453A (en) * | 2019-07-22 | 2019-12-03 | 平安科技（深圳）有限公司 | Based on the matched Products Show method, apparatus of user, computer equipment |
| CN115081501A (en) * | 2021-03-15 | 2022-09-20 | 中国电信股份有限公司 | User classification method and device, cascaded user classification model and equipment |
| CN113641904A (en) * | 2021-08-16 | 2021-11-12 | 上海花千树信息科技有限公司 | Method and device for recommending target customers for stores under Internet marriage line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6799574B2 (en) | Method and device for determining satisfaction with voice dialogue | |
| CN108228950A (en) | A kind of information processing method and device | |
| US20190272553A1 (en) | Predictive Modeling with Entity Representations Computed from Neural Network Models Simultaneously Trained on Multiple Tasks | |
| CN108509465A (en) | A kind of the recommendation method, apparatus and server of video data | |
| CN110582762A (en) | Automatic response server device, terminal device, response system, response method, and program | |
| CN108399169A (en) | Dialog process methods, devices and systems based on question answering system and mobile device | |
| CN107609960A (en) | Rationale for the recommendation generation method and device | |
| CN111182162B (en) | Telephone quality inspection method, device, equipment and storage medium based on artificial intelligence | |
| CN109658923A (en) | Voice quality detecting method, equipment, storage medium and device based on artificial intelligence | |
| CN111625632A (en) | Question-answer pair recommendation method, device, equipment and storage medium | |
| CN103534697B (en) | For providing the method and system of statistics dialog manager training | |
| CN108269125A (en) | Comment information method for evaluating quality and system, comment information processing method and system | |
| CN109615504A (en) | Products Show method, apparatus, electronic equipment and computer readable storage medium | |
| CN110309114A (en) | Processing method, device, storage medium and the electronic device of media information | |
| CN107071193A (en) | The method and apparatus of interactive answering system accessing user | |
| US20180218432A1 (en) | Recommendation integrated online digital sales service chat system | |
| CN109299245A (en) | The method and apparatus that knowledge point is recalled | |
| CN108804526A (en) | Interest determines that system, interest determine method and storage medium | |
| CA3114298C (en) | Recommendation method and system and method and system for improving a machine learning system | |
| CN109992781A (en) | Processing, device, storage medium and the processor of text feature | |
| CN114218488A (en) | Information recommendation method and device based on multi-modal feature fusion and processor | |
| CN111736940A (en) | Business interface display method and device for intelligent counter | |
| WO2019237354A1 (en) | Method and apparatus for computerized matching based on emotional profile | |
| CN112053205A (en) | Product recommendation method and device through robot emotion recognition | |
| CN113486166B (en) | Construction method, device and equipment of intelligent customer service robot and storage medium |
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: 20180629 |
|
| RJ01 | Rejection of invention patent application after publication |