CN115795331A - Outbound method, system, device and storage medium based on intelligent lottery - Google Patents
Outbound method, system, device and storage medium based on intelligent lottery Download PDFInfo
- Publication number
- CN115795331A CN115795331A CN202211474484.4A CN202211474484A CN115795331A CN 115795331 A CN115795331 A CN 115795331A CN 202211474484 A CN202211474484 A CN 202211474484A CN 115795331 A CN115795331 A CN 115795331A
- Authority
- CN
- China
- Prior art keywords
- decimation
- data set
- target data
- cluster
- outbound
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an outbound method, a system, a device and a storage medium based on intelligent lottery, wherein the method comprises the steps of acquiring an original data set to be lottery; setting a decimation constraint; based on the set decimation constraint, carrying out decimation on the original data set according to a pre-constructed decimation algorithm to generate a decimation data set; calling and saving the calling record according to the selected data set; the invention combines the decimation and the outbound together, can carry out target decimation efficiently and fairly based on the decimation constraint and the decimation algorithm, and simultaneously ensures the distribution balance of the decimation data.
Description
Technical Field
The invention relates to an outbound method, a system, a device and a storage medium based on intelligent decimation, belonging to the technical field of intelligent outbound.
Background
The existing spot check outbound (such as the police system performs outbound spot check on the 'entrance propaganda work of a piece police' and the 'security evaluation of residents to a community' every month) has the situation that the lottery and the outbound are separated, and the lottery needs to be performed on a target manually and then the target is led into the intelligent outbound system to perform outbound. The method has the following advantages that the method has several practical problems that firstly, the comprehensiveness of data selection is realized, the selection type outbound call is often related to wide crowds and distributed in different scenes, the whole data volume is large, but required scenes are often distributed in one area, and the real useful data randomly selected possibly only accounts for one part due to the fact that time, code number states, call completing rate and other variable factors; secondly, the drawing process is manually intervened, and unfair suspicion is easily caused; thirdly, the multiple times of decimation are independent, and the decimation algorithm is incomplete, so that the decimation target is possibly unscientific; fourth, efficiency is lower, and manual screening needs meticulous patience, needs to consume more operating time, and the comparison is like big sea fishing needle moreover, especially needs the periodic scene of carrying out big batch decimation outbound, and the inefficiency.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides an outbound method, a system, a device and a storage medium based on intelligent lottery, which combine lottery and outbound together, can efficiently and fairly perform target lottery based on lottery constraint and a lottery algorithm and simultaneously ensure the distribution balance of lottery data.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the invention provides an outbound method based on intelligent lottery, which comprises the following steps:
acquiring an original data set to be decimated;
setting a decimation constraint;
based on the set decimation constraint, carrying out decimation on the original data set according to a pre-constructed decimation algorithm to generate a decimation data set;
and carrying out outbound call according to the decimation data set and storing an outbound call record.
Optionally, the decimation constraint comprises:
a decimation mode: quantitative drawing and fixed ratio drawing; the quantitative decimation is that the number of the target data decimated in each period is a preset constant; the number of the target data which are decimated for each period by the fixed-ratio decimation is a preset ratio of an original data set;
checking modes: non-repetitive decimation and repeatable decimation; the non-repeated selection is that if target data which are not called through exist in the original data set, the target data which are called through are not selected; the repeated lottery is that any target data can be lottery;
periodic mode: day-by-day, week-by-week, month-by-month, quarter-by-quarter, year-by-year.
Optionally, the decimation algorithm includes:
clustering the original data set based on a K-Means clustering algorithm to generate a cluster;
for each cluster, counting the quantity of each type of target data in the cluster;
defining the target data with the quantity of the target data larger than the quantity threshold as a majority sample, and defining the target data with the quantity of the target data smaller than or equal to the quantity threshold as a minority sample;
calculating the decimation number of the majority class samples and the minority class samples in the clustering cluster:
in the formula (I), the compound is shown in the specification,
for the number of samples in the majority class and the minority class in the jth cluster,
is the number of majority class samples and minority class samples in the jth cluster, X + 、X - Is the number of majority class samples and minority class samples in J clustering clusters, and k is
To pair
Multiples of (d);
calculating the number of the decimations in the cluster based on the number of the majority type samples and the number of the decimations of the minority type samples in the cluster:
in the formula, SX j The number of decimations in the jth cluster;
target data is randomly extracted from the cluster based on the number of decimations in the cluster.
Optionally, the clustering the original data set based on the K-Means clustering algorithm to generate a cluster includes:
randomly extracting J target data from the original data set as initial clustering centers, and recording the J target data as { c } 1 ,c 2 ,…,c J },1<J is less than or equal to I, and I is the number of target data selected in each period;
sequentially calculating the Euclidean distance d from each target data in the original data set to the initial clustering center:
in the formula: x is the number of i ,c j I =1,2, …, I, for the ith target data and the jth initial cluster center, respectively; j =1,2, …, J, x it ,c jt The ith target data and the jth attribute value of the jth initial clustering center are respectively, and q is the number of the attribute values;
according to the Euclidean distance minimum principle, dividing each target data into initial clusters with the minimum Euclidean distance d to obtain clusters, and marking as { S 1 ,S 2 ,…,S J }；
Calculating the clustering center of each clustering cluster according to a mean method, taking the clustering center as an initial clustering center, bringing the Euclidean distance d from each target data in the original data set to the initial clustering center in turn, performing iteration until the clustering center does not move, and outputting the final clustering center and the clustering clusters.
Optionally, before outbound according to the lottery data set, format verification and repeated verification are performed on target data in the lottery data set, the target data which does not pass the format verification or the repeated verification is removed, and the target data is randomly extracted again from a cluster where the target data does not pass the format verification or the repeated verification and is supplemented into the lottery data set.
Optionally, before outbound according to the decimation data set, the method further includes performing a quantity check on the target data in the decimation data set, and if the quantity of the target data in the decimation data set is greater than the quantity determined by the decimation mode, randomly deleting an excessive quantity of the target data from the decimation data set; if the number of target data in the decimation data set is less than the number determined by the decimation pattern, a missing number of target data is randomly decimated from the original data set to complement the decimation data set.
In a second aspect, the present invention provides a outbound system based on smart decimation, the system comprising:
the data acquisition module is used for acquiring an original data set to be decimated;
a constraint setting module for setting a decimation constraint;
the data decimation module is used for performing decimation on the original data set according to a pre-constructed decimation algorithm based on the set decimation constraint to generate a decimation data set;
and the outbound record module is used for outbound and storing the outbound record according to the decimation data set.
In a third aspect, the invention provides an outbound device based on intelligent lottery, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps according to the above-described method.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above-described method.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides an outbound method, a system, a device and a storage medium based on intelligent lottery, 1) the lottery process is automatically completed without manual intervention and is fair and fair; 2) The intelligent decimation algorithm considers the problem of unbalanced class distribution of the target data set, and performs undersampling decimation on the target data set based on the clustering principle in machine learning, so that the probability of multiple decimation approaches to be equal, and the target decimation is developed more scientifically; 3) After the full amount of target crowd data is imported, the system is fully automatically executed, the efficiency is high, and particularly for scenes needing to periodically develop the decimation type intelligent outbound call.
Drawings
Fig. 1 is a flowchart of an outbound method based on smart decimation according to an embodiment of the present invention;
fig. 2 is a flowchart of an outbound method for implementing smart decimation according to an embodiment of the present invention;
figure 3 is a flow chart of a decimation algorithm provided by an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
as shown in fig. 1, an embodiment of the present invention provides an outbound method based on an intelligent lottery, including the following steps:
1. an original data set to be decimated is acquired.
2. Setting a decimation constraint; the decimation constraints include:
2.1, decimation mode: quantitative and ratiometric decimation; the quantitative decimation is that the number of the target data decimated in each period is a preset constant; the ratiometric decimation is such that the amount of target data decimated for each period is a preset proportion of the original data set.
2.2, check mode: non-repetitive decimation and repeatable decimation; the non-repeated selection is that if target data which are not called through exist in the original data set, the target data which are called through are not selected; the repeated lottery can be used for lottery any target data; namely:
when the decimation is not repeated, the data in the original data set in each period can be changed, and the changed data is the target data which is called through and is hidden or deleted;
the data in the original data set does not change for each cycle when the decimation is repeated.
2.3, periodic mode: day-by-day, week-by-week, month-by-month, quarter-by-quarter, year-by-year.
3. Based on the set decimation constraint, carrying out decimation on the original data set according to a pre-constructed decimation algorithm to generate a decimation data set;
as shown in fig. 2, the set-based decimation constraint includes: determining the number of the target data decimated per cycle according to the decimation pattern; updating the original data set based on the set check pattern; determining a cycle duration based on the cycle pattern; performing decimation on the updated original data set based on a decimation algorithm to generate a decimation data set; checking the selected data set to update the selected data set; decimation into the next cycle based on the cycle duration.
(1) The decimation algorithm includes:
clustering the original data set based on a K-Means clustering algorithm to generate a cluster;
for each cluster, counting the quantity of each type of target data in the cluster;
defining the target data with the quantity of the target data larger than the quantity threshold as a majority sample, and defining the target data with the quantity of the target data smaller than or equal to the quantity threshold as a minority sample;
calculating the decimation number of the majority class samples and the minority class samples in the clustering cluster:
in the formula (I), the compound is shown in the specification,
for the number of samples in the majority class and the minority class in the jth cluster,
is the number of majority class samples and minority class samples in the jth cluster, X + 、X - Is the number of majority class samples and minority class samples in J clustering clusters, and k is
To pair
Multiples of (d);
calculating the number of the decimations in the cluster based on the number of the majority type samples and the number of the decimations of the minority type samples in the cluster:
in the formula, SX j Is the decimation number in the jth cluster;
target data is randomly extracted from the cluster based on the number of decimations in the cluster.
(2) Clustering the original data set based on a K-Means clustering algorithm to generate a cluster comprises the following steps:
randomly extracting J target data from the original data set as initial clustering centers, and recording the J target data as { c } 1 ,c 2 ,…,c J },1<J is less than or equal to I, and I is the number of target data selected in each period;
sequentially calculating the Euclidean distance d from each target data in the original data set to the initial clustering center:
in the formula: x is a radical of a fluorine atom i ,c j I =1,2, …, I, for the ith target data and the jth initial cluster center, respectively; j =1,2, …, J, x it ,c jt The ith target data and the jth attribute value of the jth initial clustering center are respectively, and q is the number of the attribute values;
according to the Euclidean distance minimum principle, dividing each target data into initial cluster centers with the minimum Euclidean distance d to obtain cluster clusters, and marking as { S 1 ,S 2 ,…,S J }；
And calculating the clustering center of each clustering cluster according to a mean method, taking the clustering center as an initial clustering center, bringing the Euclidean distance d from each target data in the original data set to the initial clustering center in turn, performing iteration until the clustering center does not move, and outputting the final clustering center and the final clustering clusters.
4. And carrying out outbound call according to the decimation data set and storing an outbound call record.
Before outbound according to the selected data set, format check and repeated check are carried out on target data in the selected data set, the target data which do not pass the format check or the repeated check are removed, and the target data are randomly extracted from a cluster where the target data are located again to be supplemented into the selected data set.
Before outbound according to the lottery data set, the method also comprises the steps of carrying out quantity check on target data in the lottery data set, and randomly deleting redundant target data from the lottery data set if the quantity of the target data in the lottery data set is larger than the quantity determined by the lottery mode; if the number of target data in the decimation data set is less than the number determined by the decimation pattern, a missing number of target data is randomly decimated from the original data set to complement the decimation data set.
The second embodiment:
the embodiment of the invention provides an outbound system based on intelligent lottery, which comprises:
the data acquisition module is used for acquiring an original data set to be decimated;
a constraint setting module for setting a decimation constraint;
the data decimation module is used for performing decimation on the original data set according to a pre-constructed decimation algorithm based on the set decimation constraint to generate a decimation data set;
and the outbound record module is used for outbound according to the decimation data set and storing the outbound record.
Example three:
the embodiment of the invention provides an outbound device based on intelligent lottery, which comprises a processor and a storage medium;
a storage medium to store instructions;
the processor is configured to operate in accordance with instructions to perform steps in accordance with the above-described method.
Example four:
embodiments of the present invention provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (9)
1. An outbound method based on intelligent decimation, comprising:
acquiring an original data set to be decimated;
setting a decimation constraint;
based on the set decimation constraint, carrying out decimation on the original data set according to a pre-constructed decimation algorithm to generate a decimation data set;
and carrying out outbound call according to the decimation data set and storing an outbound call record.
2. The outbound method based on smart decimation according to claim 1, wherein said decimation constraints comprise:
a decimation mode: quantitative and ratiometric decimation; the quantitative decimation is that the number of the target data decimated in each period is a preset constant; the number of the target data which are decimated for each period by the fixed-ratio decimation is a preset ratio of an original data set;
checking modes: non-repetitive decimation and repeatable decimation; the non-repeated selection is that if target data which are not called through exist in the original data set, the target data which are called through are not selected; the repeated lottery is that any target data can be lottery;
periodic mode: day-by-day, week-by-week, month-by-month, quarter-by-quarter, year-by-year.
3. The outbound method based on smart decimation according to claim 1, wherein said decimation algorithm comprises:
clustering the original data set based on a K-Means clustering algorithm to generate a cluster;
for each cluster, counting the quantity of each type of target data in the cluster;
defining the target data with the quantity of the target data larger than the quantity threshold as a majority sample, and defining the target data with the quantity of the target data smaller than or equal to the quantity threshold as a minority sample;
calculating the decimation number of the majority class samples and the minority class samples in the clustering cluster:
in the formula (I), the compound is shown in the specification,
for the number of samples in the majority class and the minority class in the jth cluster,
is the number of majority class samples and minority class samples in the jth cluster, X + 、X - Is the number of majority class samples and minority class samples in J clustering clusters, and k is
To pair
Multiples of (d);
calculating the number of the decimations in the cluster based on the number of the majority type samples and the number of the decimations of the minority type samples in the cluster:
in the formula, SX j The number of decimations in the jth cluster;
target data is randomly extracted from the cluster based on the number of decimations in the cluster.
4. The outbound method based on intelligent lottery according to claim 3, wherein the clustering the original data set based on the K-Means clustering algorithm to generate the cluster comprises:
randomly extracting J target data from an original data set as an initial clustering centerIs denoted as { c 1 ,c 2 ,…,c J },1<J is less than or equal to I, and I is the number of target data selected in each period;
sequentially calculating the Euclidean distance d from each target data in the original data set to the initial clustering center:
in the formula: x is the number of i ,c j I =1,2, …, I, for the ith target data and the jth initial cluster center, respectively; j =1,2, …, J, x it ,c jt The ith target data and the jth attribute value of the jth initial clustering center are respectively, and q is the number of the attribute values;
according to the Euclidean distance minimum principle, dividing each target data into initial cluster centers with the minimum Euclidean distance d to obtain cluster clusters, and marking as { S 1 ,S 2 ,…,S J }；
Calculating the clustering center of each clustering cluster according to a mean method, taking the clustering center as an initial clustering center, bringing the Euclidean distance d from each target data in the original data set to the initial clustering center in turn, performing iteration until the clustering center does not move, and outputting the final clustering center and the clustering clusters.
5. The outbound method based on intelligent lottery according to claim 3, characterized in that before outbound according to the lottery data set, format check and repeated check are carried out on the target data in the lottery data set, the target data which does not pass the format check or repeated check are removed, and the target data is randomly extracted again from the cluster where the target data is located to be supplemented into the lottery data set.
6. The outbound method based on intelligent lottery according to claim 3, characterized in that before outbound according to the lottery data set, the method further comprises the steps of performing quantity check on the target data in the lottery data set, and if the quantity of the target data in the lottery data set is larger than the quantity determined by the lottery mode, randomly deleting the redundant quantity of the target data from the lottery data set; if the number of target data in the decimation data set is less than the number determined by the decimation pattern, a missing number of target data is randomly decimated from the original data set to complement the decimation data set.
7. An outbound system based on smart decimation, the system comprising:
the data acquisition module is used for acquiring an original data set to be decimated;
a constraint setting module for setting a decimation constraint;
the data decimation module is used for performing decimation on the original data set according to a pre-constructed decimation algorithm based on the set decimation constraint to generate a decimation data set;
and the outbound record module is used for outbound and storing the outbound record according to the decimation data set.
8. An outbound device based on intelligent lottery is characterized by comprising a processor and a storage medium;
the storage medium is to store instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 6.
9. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211474484.4A CN115795331A (en) | 2022-11-23 | 2022-11-23 | Outbound method, system, device and storage medium based on intelligent lottery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211474484.4A CN115795331A (en) | 2022-11-23 | 2022-11-23 | Outbound method, system, device and storage medium based on intelligent lottery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115795331A true CN115795331A (en) | 2023-03-14 |
Family
ID=85440548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211474484.4A Pending CN115795331A (en) | 2022-11-23 | 2022-11-23 | Outbound method, system, device and storage medium based on intelligent lottery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115795331A (en) |
-
2022
- 2022-11-23 CN CN202211474484.4A patent/CN115795331A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807545B (en) | Task duration prediction method and device, electronic equipment and storage medium | |
| CN109376596A (en) | Face matching process, device, equipment and storage medium | |
| CN102231216B (en) | Cash management method and system for self-service equipment | |
| CN108345958A (en) | Order meal delivery time prediction model construction method, prediction method, model and device | |
| CN110750567A (en) | Wearing and matching data generation method and system based on intelligent wardrobe | |
| CN109598430A (en) | Distribution range generation method, distribution range generation device, electronic equipment and storage medium | |
| CN109815631A (en) | A kind for the treatment of method and apparatus of game data | |
| CN112445690B (en) | Information acquisition method and device and electronic equipment | |
| CN112084269A (en) | Data quality calculation method and device, storage medium and server | |
| CN112418545A (en) | Load characteristic and model fusion based electricity sales amount prediction method and system | |
| CN115795331A (en) | Outbound method, system, device and storage medium based on intelligent lottery | |
| CN116972811A (en) | Unmanned aerial vehicle-based investigation method for small-scale vegetation biodiversity | |
| CN110245985A (en) | A kind of information processing method and device | |
| CN103793714A (en) | Multi-class discriminating device, data discrimination device, multi-class discriminating method and data discriminating method | |
| CN117423001A (en) | Rock lithology recognition method and system based on improved SSD, storage medium and equipment | |
| CN109902352A (en) | A kind of transient rotor angle stability analysis of key Characteristic Extraction method and system | |
| CN111583010A (en) | Data processing method, device, equipment and storage medium | |
| CN116416055A (en) | Agricultural loan assessment method and device, storage medium and electronic equipment | |
| CN116150483A (en) | Electronic license recommendation method, device and storage medium based on Bayesian network model | |
| CN109165238B (en) | Data processing method and device for generating period index data | |
| CN110727918A (en) | Logistics business trend evaluation method, computer storage medium and electronic equipment | |
| CN111680111B (en) | Billing method and device, computer equipment and computer readable storage medium | |
| CN117408787B (en) | Root cause mining analysis method and system based on decision tree | |
| CN114004492B (en) | Enterprise environment management method, device, medium and equipment based on artificial intelligence | |
| CN112396513B (en) | Data processing method and device |
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 |