CN117812185B - Control method and system of intelligent outbound system - Google Patents
Control method and system of intelligent outbound system Download PDFInfo
- Publication number
- CN117812185B CN117812185B CN202410225130.9A CN202410225130A CN117812185B CN 117812185 B CN117812185 B CN 117812185B CN 202410225130 A CN202410225130 A CN 202410225130A CN 117812185 B CN117812185 B CN 117812185B
- Authority
- CN
- China
- Prior art keywords
- outbound
- execution
- sub
- node
- feature
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004364 calculation method Methods 0.000 claims abstract description 94
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 230000007717 exclusion Effects 0.000 claims abstract description 16
- 238000007621 cluster analysis Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 10
- 230000006978 adaptation Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 9
- 238000007726 management method Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000013433 optimization analysis Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5141—Details of processing calls and other types of contacts in an unified manner
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5175—Call or contact centers supervision arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/523—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
- H04M3/5232—Call distribution algorithms
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Marketing (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a control method and a system of an intelligent outbound system, which relate to the technical field of data transmission, and the method comprises the following steps: acquiring a pre-execution outbound work order information set of a target outbound system, and sending the pre-execution outbound work order information set to an outbound execution unit to execute an outbound task; redundant identification is carried out on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to the real-time outbound task execution result, and a plurality of first outbound indexes are obtained; performing execution node cluster analysis based on the pre-execution outbound work order information set, and performing mutual exclusion identification on a plurality of sub outbound execution units to obtain Q mutually exclusive sub outbound execution unit sets; performing calculation force optimization on the outbound execution units based on a plurality of first outbound indexes and Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation force distribution scheme; and controlling the target outbound system based on the optimal force distribution scheme. The invention solves the technical problems of slow response and low working efficiency of the outbound system in the prior art.
Description
Technical Field
The invention relates to the technical field of data transmission, in particular to a control method and a control system of an intelligent outbound system.
Background
With the improvement of technology, the outbound task is converted into a mode of processing by a computer system by the traditional manual dispatch, so that the outbound efficiency is greatly improved. However, due to uneven distribution of computing power of the computer, insufficient adaptive adjustment of the real-time outbound task completion situation and the like, the efficiency and effect of the outbound system cannot meet the requirements, and intelligent management and control are needed. In the prior art, the technical problems of slow response and low working efficiency of an outbound system exist.
Disclosure of Invention
The application provides a control method and a control system of an intelligent outbound system, which are used for solving the technical problems of slow response and low working efficiency of the outbound system in the prior art.
In view of the above problems, the present application provides a method and a system for controlling an intelligent outbound system.
In a first aspect of the present application, there is provided a method for controlling an intelligent outbound system, the method comprising:
Acquiring a pre-execution outbound work order information set of a target outbound system, and transmitting the pre-execution outbound work order information set to an outbound execution unit to execute an outbound task;
Redundant identification is carried out on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to a real-time outbound task execution result, and a plurality of first outbound indexes are obtained;
Performing execution node cluster analysis based on the pre-execution outbound work order information set, and performing mutual exclusion identification on the plurality of sub-outbound execution units to obtain Q mutually exclusive sub-outbound execution unit sets;
Performing calculation force optimization on the outbound execution units based on the plurality of first outbound indexes and Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation force distribution scheme;
And controlling the target outbound system based on the optimal force distribution scheme.
In a second aspect of the present application, there is provided a control system for an intelligent outbound system, the system comprising:
The outbound task execution module is used for acquiring a pre-execution outbound work order information set of the target outbound system and sending the pre-execution outbound work order information set to the outbound execution unit to execute the outbound task;
the first outbound index obtaining module is used for carrying out redundancy identification on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to the real-time outbound task execution result to obtain a plurality of first outbound indexes;
the execution unit set obtaining module is used for performing node clustering analysis based on the pre-execution outbound work order information set, and performing mutual exclusion identification on the plurality of sub outbound execution units to obtain Q mutual exclusion sub outbound execution unit sets;
The calculation force distribution scheme obtaining module is used for carrying out calculation force optimization on the outbound execution units based on the plurality of first outbound indexes and the Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation force distribution scheme;
And the control module is used for controlling the target outbound system based on the optimal force distribution scheme.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the method comprises the steps of obtaining a pre-execution outbound work order information set of a target outbound system, sending the pre-execution outbound work order information set to an outbound execution unit to execute outbound tasks, performing redundancy identification on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to real-time outbound task execution results to obtain a plurality of first outbound indexes, performing execution node clustering analysis based on the pre-execution outbound work order information set, performing mutual exclusion identification on the plurality of sub outbound execution units to obtain Q mutually exclusive sub outbound execution unit sets, performing calculation optimization on the outbound execution units based on the plurality of first outbound indexes and the Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation distribution scheme, and performing management and control on the target outbound system based on the optimal calculation distribution scheme. The technical effects of optimizing the operational calculation power distribution of the outbound system and improving the management and control quality of the outbound system are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a control method of an intelligent outbound system according to an embodiment of the present application;
fig. 2 is a schematic flow chart of generating a plurality of first sub-outbound indexes in a control method of an intelligent outbound system according to an embodiment of the present application;
Fig. 3 is a schematic flow chart of a stage optimal force distribution scheme corresponding to a maximum value of resource fitness in an iterative process as an optimal force distribution scheme in a control method of an intelligent outbound system according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a management and control system of an intelligent outbound system according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an outbound task execution module 11, a first outbound index obtaining module 12, an execution unit set obtaining module 13, a calculation force distribution scheme obtaining module 14 and a management and control module 15.
Detailed Description
The application provides a control method and a control system of an intelligent outbound system, which are used for solving the technical problems of slow response and low working efficiency of the outbound system in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a method for controlling an intelligent outbound system, where the method includes:
Acquiring a pre-execution outbound work order information set of a target outbound system, and transmitting the pre-execution outbound work order information set to an outbound execution unit to execute an outbound task;
In one possible embodiment, the target outbound system is any system that needs to be managed. The pre-execution outbound work order information set is used for describing outbound task conditions which are preset by the target outbound system and need to be executed, and comprises information such as calling users, calling time, calling content and the like. The outbound execution unit is a functional unit for executing outbound tasks in the target outbound system, the pre-execution outbound work order information set is sent to the outbound execution unit, and the outbound execution unit performs outbound. The technical effect of intelligent outbound call is achieved.
Redundant identification is carried out on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to a real-time outbound task execution result, and a plurality of first outbound indexes are obtained;
Further, as shown in fig. 2, the redundancy recognition is performed on the plurality of sub outbound execution units of the pre-execution outbound worksheet information set according to the real-time outbound task execution result, and the embodiment of the application further includes:
Acquiring a work order execution tolerance threshold of the pre-execution outbound work order information set, traversing the real-time outbound task execution result to determine the punctuality of the plurality of sub outbound execution units, and generating a plurality of first sub outbound indexes;
traversing the memory occupancy rate of the plurality of sub-outbound execution units to generate a plurality of second sub-outbound indexes;
the plurality of first outbound indices is generated based on the plurality of first sub-outbound indices and a plurality of second sub-outbound indices.
In one embodiment, the real-time outbound task execution result is information describing the outbound execution condition of the pre-execution outbound work order information set by the outbound execution unit in a real-time state, and the information includes call duration, dial-out time, dial-out sub outbound execution unit and the like. And analyzing the task execution conditions of a plurality of sub outbound execution units in the pre-execution outbound work order information set based on the real-time outbound task execution result, and determining the operation redundancy of the sub outbound execution units so as to obtain a plurality of first outbound indexes. The first outbound index reflects the task execution capacity of the sub-outbound execution units, and the larger the outbound index is, the higher the outbound task execution capacity of the corresponding sub-outbound execution unit is.
In one possible embodiment, the deviation degree allowable in the execution process of the worksheet in the pre-execution outbound worksheet information set is collected, so as to obtain the worksheet execution tolerance threshold. The work order execution tolerance threshold reflects the range of deviation in the execution process of the outbound execution unit of the target outbound system. For example, the outbound call time may deviate by 1 minute. And taking the outbound time as an index, carrying out information retrieval on the real-time outbound task execution result so as to obtain a plurality of outbound times, carrying out tolerance threshold value calculation with the work order, and obtaining a plurality of outbound time deviations according to the difference calculation result. And based on the matching of the plurality of sub-outbound execution units and the plurality of outbound time deviations, a plurality of outbound time deviation sets corresponding to the plurality of sub-outbound execution units are determined, and each outbound time deviation set corresponds to one sub-outbound execution unit. And carrying out mean processing on the plurality of outbound time deviation sets to obtain a plurality of outbound time differences. And respectively comparing the outbound time differences with the median value of the worksheet execution tolerance threshold value, so as to obtain a plurality of time rates of the plurality of sub-outbound execution units, and taking the plurality of time rates as the plurality of first sub-outbound indexes.
Preferably, a plurality of real-time memory occupancy rates of a plurality of sub-outbound execution units are determined based on the real-time outbound task execution result, and average processing is performed on the plurality of real-time memory occupancy rates so as to obtain a plurality of second sub-outbound indexes. Further, the plurality of first sub-outbound indices and the plurality of second sub-outbound indices are weighted to generate a plurality of first outbound indices.
Performing execution node cluster analysis based on the pre-execution outbound work order information set, and performing mutual exclusion identification on the plurality of sub-outbound execution units to obtain Q mutually exclusive sub-outbound execution unit sets;
in one embodiment, the pre-executing outbound work order information sets are subjected to similar aggregation analysis of the execution nodes of outbound tasks, and the plurality of sub outbound execution units are subjected to mutual exclusion identification according to analysis results, so that basis is provided for subsequent calculation optimization analysis, disorder optimization is avoided, and imbalance in calculation resource use among different execution nodes is avoided. The execution node is the outbound application of outbound work order information, including return visit, recommendation, after-sales and the like. The mutual exclusion identification of the plurality of sub-outbound execution units is to keep the sub-outbound execution units of different execution nodes mutually independent. Furthermore, the sub-outbound execution units of the same execution node are grouped into one set, thereby generating Q mutually exclusive sub-outbound execution unit sets.
Further, the embodiment of the application further comprises:
collecting outbound characteristics of the pre-execution outbound work order information set to obtain a pre-execution outbound work order characteristic set;
generating a first execution node, wherein the first execution node is obtained by extracting a pre-execution outbound worksheet feature from the pre-execution outbound worksheet feature set without replacing the random as a first pre-execution outbound worksheet feature, and storing the first pre-execution outbound worksheet feature in the execution node;
Inputting the pre-execution outbound worksheet feature set into the first execution node for similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in a first sub-node of the first execution node, and if not, adding the similarity into the first sub-pre-execution outbound worksheet feature set;
Generating a second execution node, wherein the second execution node is obtained by extracting a pre-execution outbound worksheet feature from the first sub-pre-execution outbound worksheet feature set without replacing the random as a second pre-execution outbound worksheet feature, and storing the second pre-execution outbound worksheet feature in the execution node;
And inputting the first sub-pre-execution outbound work order feature set into the second execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in the second sub-node of the second execution node, and if not, adding the similarity into the second sub-pre-execution outbound work order feature set.
Further, the embodiment of the application further comprises:
generating a Q-1 executing node, wherein the Q-1 executing node is obtained by extracting a pre-executing outbound worksheet feature from a Q-2 sub pre-executing outbound worksheet feature set without replacing the pre-executing outbound worksheet feature as a Q-1 pre-executing outbound worksheet feature, and storing the Q-1 pre-executing outbound worksheet feature in the executing node;
Inputting the Q-2 sub pre-execution outbound worksheet feature set into the Q-1 execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in the Q-1 sub node of the Q-1 execution node, and if not, adding the similarity into the Q sub node of the Q execution node;
Performing feature intersection solving based on the sub-pre-execution outbound worksheet feature sets stored in the first sub-node, the second sub-node, the Q-1 sub-node and the Q sub-node respectively, and performing outbound feature identification on the first execution node, the second execution node, the Q-1 execution node and the Q execution node according to feature intersection solving results;
According to the first executing node, the second executing node, the Q-1 executing node and the Q executing node after the outbound feature identification, respectively matching a plurality of corresponding sub outbound executing units to generate Q sub outbound executing unit sets, wherein each sub outbound executing unit set corresponds to one executing node;
and performing mutual exclusion identification on the Q sub-outbound execution unit sets to generate Q mutually exclusive sub-outbound execution unit sets.
Further, the embodiment of the application further comprises:
generating a similarity calculation formula, embedding the similarity calculation formula into a first execution node, wherein the similarity calculation formula is as follows:
；
wherein, For the similarity between the first pre-execution outbound work order feature and the i-th pre-execution outbound work order feature in the pre-execution outbound work order feature set, i is an integer greater than or equal to 1,/>For the first pre-execution outbound worksheet feature,/>The method comprises the steps of setting an i-th pre-execution outbound worksheet feature in a pre-execution outbound worksheet feature set;
And traversing the pre-execution outbound work order feature set, and inputting the pre-execution outbound work order feature set and the first pre-execution outbound work order feature set into the similarity calculation formula to perform similarity recognition.
In one embodiment of the application, the pre-execution outbound work order information set is subjected to outbound feature collection to obtain a pre-execution outbound work order feature set. The outbound feature is to describe the work order condition in the pre-executing outbound work order information set, and comprises whether the user is a purchased client, outbound content keywords and the like. And generating a first execution node, wherein the first execution node is used for extracting a pre-execution outbound worksheet feature from the pre-execution outbound worksheet feature set randomly without returning to the first execution node as a first pre-execution outbound worksheet feature, storing the first pre-execution outbound worksheet feature in the execution node, and then obtaining the first pre-execution outbound worksheet feature, wherein the first execution node is used for carrying out two-class classification on the pre-execution outbound worksheet feature set, one class with the similarity greater than the preset similarity with the first pre-execution outbound worksheet feature stored in the first execution node is stored in a first sub-node of the first execution node, and one class with the similarity less than or equal to the preset similarity is added into the first sub-pre-execution outbound worksheet feature set. The similarity reflects the similarity degree of the first pre-execution outbound work order feature and the pre-execution outbound work order feature in the pre-execution outbound work order feature set. The preset similarity is a degree of similarity between pre-execution outbound worksheet features of the same execution node preset by a person skilled in the art. The similarity calculation formula embedded in the first execution node is used for carrying out quantization calculation on the similarity degree of the first pre-execution outbound work order feature and the pre-execution outbound work order feature in the pre-execution outbound work order feature set. And inputting the pre-execution outbound worksheet feature set into the first execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in a first sub-node of the first execution node, and if not, adding the similarity into the first sub-pre-execution outbound worksheet feature set.
Preferably, a pre-execution outbound worksheet feature is extracted from the first sub-pre-execution outbound worksheet feature set by not replacing the random as a second pre-execution outbound worksheet feature, and the second pre-execution outbound worksheet feature is stored in an execution node to generate a second execution node. And inputting the first sub-pre-execution outbound work order feature set into the second execution node to perform similarity recognition, judging whether the similarity is larger than the preset similarity, if so, storing the similarity in the second sub-node of the second execution node, and if not, adding the similarity into the second sub-pre-execution outbound work order feature set.
Based on the same principle, generating a Q-1 executing node, wherein the Q-1 executing node extracts a pre-execution outbound worksheet feature from a Q-2 sub-pre-execution outbound worksheet feature set without returning the pre-execution outbound worksheet feature as a Q-1 pre-execution outbound worksheet feature, stores the Q-1 pre-execution outbound worksheet feature into the executing node, inputs the Q-2 sub-pre-execution outbound worksheet feature set into the Q-1 executing node for similarity recognition, judges whether the similarity is larger than a preset similarity, if so, stores the Q-1 sub-node into the Q-1 executing node, and if not, adds the Q-1 sub-node into the Q-1 executing node. Furthermore, feature intersection is obtained based on the feature sets of the sub-pre-execution outbound worksheets stored in the first sub-node, the second sub-node, the Q-1 sub-node and the Q sub-node respectively, and outbound feature identification is carried out on the first execution node, the second execution node, the Q-1 execution node and the Q execution node according to feature intersection obtaining results, namely, outbound use executed by each execution node is identified.
Preferably, the first execution node, the second execution node, the Q-1 execution node and the Q execution node after the outbound feature identification are respectively matched with a corresponding plurality of sub outbound execution units to generate Q sub outbound execution unit sets, wherein each sub outbound execution unit set corresponds to one execution node. And then carrying out mutual exclusion identification on the Q sub-outbound execution unit sets to generate Q mutually exclusive sub-outbound execution unit sets.
Performing calculation force optimization on the outbound execution units based on the plurality of first outbound indexes and Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation force distribution scheme;
Further, the embodiment of the application further comprises:
the first outbound indexes and the Q mutually exclusive sub outbound execution unit sets are sent to an algorithm distribution unit to be subjected to distribution scheme identification, so that a plurality of to-be-selected algorithm distribution schemes are obtained;
Performing computing power resource utilization analysis on the plurality of computing power distribution schemes to be selected to obtain a plurality of resource fitness;
Respectively comparing the plurality of resource fitness to the reciprocal of the sum of the plurality of resource fitness, and multiplying the calculation result with a preset adjustment step length to obtain a plurality of adaptation adjustment step lengths;
Fine tuning the multiple to-be-selected computing power distribution schemes according to a preset adjustment mode based on the multiple adaptation adjustment step sizes, and summarizing fine tuning results to generate an extended computing power distribution scheme set, wherein the preset adjustment mode is to respectively call in and call out preset quantity of pre-execution outbound worksheet information to multiple mutually exclusive sub outbound execution units in multiple mutually exclusive sub outbound execution unit sets in the multiple to-be-selected computing power distribution schemes;
and performing calculation force optimization based on the extended calculation force distribution scheme set to generate an optimal calculation force distribution scheme.
Further, as shown in fig. 3, the embodiment of the present application further includes:
Randomly selecting an extended computing power distribution scheme from the extended computing power distribution scheme set as a first extended computing power distribution scheme, and calculating corresponding first resource fitness;
Randomly selecting an extended computing power distribution scheme from the extended computing power distribution scheme set again to serve as a second extended computing power distribution scheme, and calculating corresponding second resource fitness;
Judging whether the first resource fitness is larger than the second resource fitness, if so, taking the second extended computing power distribution scheme as a stage optimal computing power distribution scheme according to a certain probability;
If not, the second expansion calculation force distribution scheme is used as a stage optimal calculation force distribution scheme;
After the preset iteration times are met through multiple iteration optimization, the phase optimal calculation force distribution scheme corresponding to the maximum value of the resource fitness in the iteration process is used as an optimal calculation force distribution scheme.
In one possible embodiment, according to the plurality of first outbound indexes and the Q mutually exclusive sub outbound execution unit sets, performing calculation optimization on the outbound execution units, thereby realizing optimal calculation resource allocation and obtaining an optimal calculation allocation scheme. The optimal force distribution scheme is a target outbound system optimal force distribution scheme determined according to actual task execution conditions.
In one embodiment, the plurality of first outbound indexes and the Q mutually exclusive sub outbound execution units are sent to a computing power distribution unit to identify a distribution scheme, so as to obtain a plurality of candidate computing power distribution schemes. The power distribution unit is a functional unit for intelligently acquiring a power distribution scheme. Preferably, the first outbound index of a plurality of samples, the mutually exclusive sub outbound execution unit set of a plurality of samples and the to-be-selected calculation power distribution scheme set of a plurality of samples are obtained to serve as construction data, and the construction data is utilized to conduct supervision training on a framework constructed based on the convolutional neural network until convergence, so that a calculation power distribution unit with complete training is obtained. And respectively carrying out average value calculation on the memory occupancy rate of the Q sub outbound execution unit sets in the multiple candidate calculation force distribution schemes to obtain multiple first sub-resource fitness. And respectively calculating the variances of the memory occupancy rates in the Q sub outbound execution units in the multiple candidate calculation force distribution schemes to obtain multiple second sub-resource fitness. And carrying out weighted calculation on the plurality of first sub-resource fitness and the plurality of second sub-resource fitness so as to obtain a plurality of resource fitness.
And further, the inverse of the sum of the plurality of resource fitness ratios is multiplied by the calculation result and the preset adjustment step length to obtain a plurality of adaptation adjustment step lengths. And fine tuning the multiple to-be-selected computing power distribution schemes according to a preset adjustment mode based on the multiple adaptation adjustment step sizes, and summarizing fine tuning results to generate an extended computing power distribution scheme set, wherein the preset adjustment mode is to respectively call in and call out preset quantity of pre-execution outbound worksheet information to multiple mutually exclusive sub outbound execution units in multiple mutually exclusive sub outbound execution unit sets in the multiple to-be-selected computing power distribution schemes. The preset adjustment step length is the number of calling-in or calling-out of the pre-execution outbound worksheet information in the mutex outbound execution unit, which is set by a person skilled in the art. By performing fine tuning, an extended set of computing force distribution schemes is obtained. And further, performing calculation force optimization based on the extended calculation force distribution scheme set to generate an optimal calculation force distribution scheme. The technical effects of expanding the optimizing range and improving the accuracy and quality of calculation force optimization are achieved.
Preferably, an extended computing power distribution scheme is randomly selected from the extended computing power distribution scheme set as a first extended computing power distribution scheme, and the corresponding first resource fitness is calculated, and an extended computing power distribution scheme is randomly selected from the extended computing power distribution scheme set as a second extended computing power distribution scheme, and the corresponding second resource fitness is calculated. Judging whether the first resource fitness is larger than the second resource fitness, if so, taking the second extended calculation force distribution scheme as a stage optimal calculation force distribution scheme according to a certain probability, and avoiding sinking into a local optimal solution. And if not, taking the second extended calculation force distribution scheme as a stage optimal calculation force distribution scheme, and taking the stage optimal calculation force distribution scheme corresponding to the maximum value of the resource fitness in the iteration process as an optimal calculation force distribution scheme after the preset iteration times are met through multiple iteration optimization.
And controlling the target outbound system based on the optimal force distribution scheme.
In the embodiment of the application, the calculation force distribution is carried out on the target outbound system according to the obtained optimal calculation force distribution scheme, so that the calculation force balance is realized, the actual task execution condition is considered, the calculation force distribution effect of the outbound system is improved, and the technical effects of improving the operation and response efficiency of the outbound system are achieved.
In summary, the embodiment of the application has at least the following technical effects:
According to the application, through the execution condition of the outbound task of the target outbound system, the calculation force optimization is carried out on a plurality of sub outbound execution units, so that an optimal calculation force distribution scheme is obtained, and the target outbound system is controlled according to the optimal calculation force distribution scheme. The technical effects of system control based on calculation force balance and actual task execution conditions and improvement of service quality of outbound systems are achieved.
Example two
Based on the same inventive concept as the control method of an intelligent outbound system in the foregoing embodiments, as shown in fig. 4, the present application provides a control system of an intelligent outbound system, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
The outbound task execution module 11 is used for acquiring a pre-execution outbound work order information set of a target outbound system and sending the pre-execution outbound work order information set to an outbound execution unit to execute an outbound task;
The first outbound index obtaining module 12 is configured to perform redundancy identification on a plurality of sub outbound execution units of the pre-execution outbound worksheet information set according to a real-time outbound task execution result, so as to obtain a plurality of first outbound indexes;
The execution unit set obtaining module 13 is configured to perform node cluster analysis based on the pre-execution outbound worksheet information set, and perform mutual exclusion identification on the plurality of sub-outbound execution units, so as to obtain Q mutually exclusive sub-outbound execution unit sets;
a calculation force distribution scheme obtaining module 14, configured to perform calculation force optimization on the outbound execution units based on the plurality of first outbound indexes and Q mutually exclusive sets of sub outbound execution units, to obtain an optimal calculation force distribution scheme;
And the control module 15 is used for controlling the target outbound system based on the optimal force distribution scheme.
Further, the first outbound index obtaining module 12 is configured to perform the following steps:
Acquiring a work order execution tolerance threshold of the pre-execution outbound work order information set, traversing the real-time outbound task execution result to determine the punctuality of the plurality of sub outbound execution units, and generating a plurality of first sub outbound indexes;
traversing the memory occupancy rate of the plurality of sub-outbound execution units to generate a plurality of second sub-outbound indexes;
the plurality of first outbound indices is generated based on the plurality of first sub-outbound indices and a plurality of second sub-outbound indices.
Further, the execution unit set obtaining module 13 is configured to perform the following steps:
collecting outbound characteristics of the pre-execution outbound work order information set to obtain a pre-execution outbound work order characteristic set;
generating a first execution node, wherein the first execution node is obtained by extracting a pre-execution outbound worksheet feature from the pre-execution outbound worksheet feature set without replacing the random as a first pre-execution outbound worksheet feature, and storing the first pre-execution outbound worksheet feature in the execution node;
Inputting the pre-execution outbound worksheet feature set into the first execution node for similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in a first sub-node of the first execution node, and if not, adding the similarity into the first sub-pre-execution outbound worksheet feature set;
Generating a second execution node, wherein the second execution node is obtained by extracting a pre-execution outbound worksheet feature from the first sub-pre-execution outbound worksheet feature set without replacing the random as a second pre-execution outbound worksheet feature, and storing the second pre-execution outbound worksheet feature in the execution node;
And inputting the first sub-pre-execution outbound work order feature set into the second execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in the second sub-node of the second execution node, and if not, adding the similarity into the second sub-pre-execution outbound work order feature set.
Further, the execution unit set obtaining module 13 is configured to perform the following steps:
generating a Q-1 executing node, wherein the Q-1 executing node is obtained by extracting a pre-executing outbound worksheet feature from a Q-2 sub pre-executing outbound worksheet feature set without replacing the pre-executing outbound worksheet feature as a Q-1 pre-executing outbound worksheet feature, and storing the Q-1 pre-executing outbound worksheet feature in the executing node;
Inputting the Q-2 sub pre-execution outbound worksheet feature set into the Q-1 execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in the Q-1 sub node of the Q-1 execution node, and if not, adding the similarity into the Q sub node of the Q execution node;
Performing feature intersection solving based on the sub-pre-execution outbound worksheet feature sets stored in the first sub-node, the second sub-node, the Q-1 sub-node and the Q sub-node respectively, and performing outbound feature identification on the first execution node, the second execution node, the Q-1 execution node and the Q execution node according to feature intersection solving results;
According to the first executing node, the second executing node, the Q-1 executing node and the Q executing node after the outbound feature identification, respectively matching a plurality of corresponding sub outbound executing units to generate Q sub outbound executing unit sets, wherein each sub outbound executing unit set corresponds to one executing node;
and performing mutual exclusion identification on the Q sub-outbound execution unit sets to generate Q mutually exclusive sub-outbound execution unit sets.
Further, the execution unit set obtaining module 13 is configured to perform the following steps:
generating a similarity calculation formula, embedding the similarity calculation formula into a first execution node, wherein the similarity calculation formula is as follows:
；
wherein, For the similarity between the first pre-execution outbound work order feature and the i-th pre-execution outbound work order feature in the pre-execution outbound work order feature set, i is an integer greater than or equal to 1,/>For the first pre-execution outbound worksheet feature,/>The method comprises the steps of setting an i-th pre-execution outbound worksheet feature in a pre-execution outbound worksheet feature set;
And traversing the pre-execution outbound work order feature set, and inputting the pre-execution outbound work order feature set and the first pre-execution outbound work order feature set into the similarity calculation formula to perform similarity recognition.
Further, the calculation force distribution scheme obtaining module 14 is configured to perform the following steps:
the first outbound indexes and the Q mutually exclusive sub outbound execution unit sets are sent to an algorithm distribution unit to be subjected to distribution scheme identification, so that a plurality of to-be-selected algorithm distribution schemes are obtained;
Performing computing power resource utilization analysis on the plurality of computing power distribution schemes to be selected to obtain a plurality of resource fitness;
Respectively comparing the plurality of resource fitness to the reciprocal of the sum of the plurality of resource fitness, and multiplying the calculation result with a preset adjustment step length to obtain a plurality of adaptation adjustment step lengths;
Fine tuning the multiple to-be-selected computing power distribution schemes according to a preset adjustment mode based on the multiple adaptation adjustment step sizes, and summarizing fine tuning results to generate an extended computing power distribution scheme set, wherein the preset adjustment mode is to respectively call in and call out preset quantity of pre-execution outbound worksheet information to multiple mutually exclusive sub outbound execution units in multiple mutually exclusive sub outbound execution unit sets in the multiple to-be-selected computing power distribution schemes;
and performing calculation force optimization based on the extended calculation force distribution scheme set to generate an optimal calculation force distribution scheme.
Further, the calculation force distribution scheme obtaining module 14 is configured to perform the following steps:
Randomly selecting an extended computing power distribution scheme from the extended computing power distribution scheme set as a first extended computing power distribution scheme, and calculating corresponding first resource fitness;
Randomly selecting an extended computing power distribution scheme from the extended computing power distribution scheme set again to serve as a second extended computing power distribution scheme, and calculating corresponding second resource fitness;
Judging whether the first resource fitness is larger than the second resource fitness, if so, taking the second extended computing power distribution scheme as a stage optimal computing power distribution scheme according to a certain probability;
If not, the second expansion calculation force distribution scheme is used as a stage optimal calculation force distribution scheme;
After the preset iteration times are met through multiple iteration optimization, the phase optimal calculation force distribution scheme corresponding to the maximum value of the resource fitness in the iteration process is used as an optimal calculation force distribution scheme.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (7)
1. A method for controlling an intelligent outbound system, the method comprising:
Acquiring a pre-execution outbound work order information set of a target outbound system, and transmitting the pre-execution outbound work order information set to an outbound execution unit to execute an outbound task;
Redundant identification is carried out on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to a real-time outbound task execution result, and a plurality of first outbound indexes are obtained;
Performing execution node cluster analysis based on the pre-execution outbound work order information set, and performing mutual exclusion identification on the plurality of sub-outbound execution units to obtain Q mutually exclusive sub-outbound execution unit sets;
Performing calculation force optimization on the outbound execution units based on the plurality of first outbound indexes and Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation force distribution scheme;
controlling the target outbound system based on the optimal force distribution scheme;
The redundant identification of the plurality of sub outbound execution units of the pre-execution outbound work order information set according to the real-time outbound task execution result comprises the following steps:
Acquiring a work order execution tolerance threshold of the pre-execution outbound work order information set, traversing the real-time outbound task execution result to determine the punctuality of the plurality of sub outbound execution units, and generating a plurality of first sub outbound indexes;
traversing the memory occupancy rate of the plurality of sub-outbound execution units to generate a plurality of second sub-outbound indexes;
the plurality of first outbound indices is generated based on the plurality of first sub-outbound indices and a plurality of second sub-outbound indices.
2. The method of claim 1, wherein the method further comprises:
collecting outbound characteristics of the pre-execution outbound work order information set to obtain a pre-execution outbound work order characteristic set;
generating a first execution node, wherein the first execution node is obtained by extracting a pre-execution outbound worksheet feature from the pre-execution outbound worksheet feature set without replacing the random as a first pre-execution outbound worksheet feature, and storing the first pre-execution outbound worksheet feature in the execution node;
Inputting the pre-execution outbound worksheet feature set into the first execution node for similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in a first sub-node of the first execution node, and if not, adding the similarity into the first sub-pre-execution outbound worksheet feature set;
Generating a second execution node, wherein the second execution node is obtained by extracting a pre-execution outbound worksheet feature from the first sub-pre-execution outbound worksheet feature set without replacing the random as a second pre-execution outbound worksheet feature, and storing the second pre-execution outbound worksheet feature in the execution node;
And inputting the first sub-pre-execution outbound work order feature set into the second execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in the second sub-node of the second execution node, and if not, adding the similarity into the second sub-pre-execution outbound work order feature set.
3. The method of claim 2, wherein the method further comprises:
generating a Q-1 executing node, wherein the Q-1 executing node is obtained by extracting a pre-executing outbound worksheet feature from a Q-2 sub pre-executing outbound worksheet feature set without replacing the pre-executing outbound worksheet feature as a Q-1 pre-executing outbound worksheet feature, and storing the Q-1 pre-executing outbound worksheet feature in the executing node;
Inputting the Q-2 sub pre-execution outbound worksheet feature set into the Q-1 execution node to perform similarity recognition, judging whether the similarity is larger than a preset similarity, if so, storing the similarity in the Q-1 sub node of the Q-1 execution node, and if not, adding the similarity into the Q sub node of the Q execution node;
Performing feature intersection solving based on the sub-pre-execution outbound worksheet feature sets stored in the first sub-node, the second sub-node, the Q-1 sub-node and the Q sub-node respectively, and performing outbound feature identification on the first execution node, the second execution node, the Q-1 execution node and the Q execution node according to feature intersection solving results;
According to the first executing node, the second executing node, the Q-1 executing node and the Q executing node after the outbound feature identification, respectively matching a plurality of corresponding sub outbound executing units to generate Q sub outbound executing unit sets, wherein each sub outbound executing unit set corresponds to one executing node;
and performing mutual exclusion identification on the Q sub-outbound execution unit sets to generate Q mutually exclusive sub-outbound execution unit sets.
4. A method as claimed in claim 3, wherein the method further comprises:
generating a similarity calculation formula, embedding the similarity calculation formula into a first execution node, wherein the similarity calculation formula is as follows:
；
wherein, For the similarity between the first pre-execution outbound work order feature and the i-th pre-execution outbound work order feature in the pre-execution outbound work order feature set, i is an integer greater than or equal to 1,/>For the first pre-execution outbound worksheet feature,/>The method comprises the steps of setting an i-th pre-execution outbound worksheet feature in a pre-execution outbound worksheet feature set;
And traversing the pre-execution outbound work order feature set, and inputting the pre-execution outbound work order feature set and the first pre-execution outbound work order feature set into the similarity calculation formula to perform similarity recognition.
5. The method of claim 1, wherein the method further comprises:
the first outbound indexes and the Q mutually exclusive sub outbound execution unit sets are sent to an algorithm distribution unit to be subjected to distribution scheme identification, so that a plurality of to-be-selected algorithm distribution schemes are obtained;
Performing computing power resource utilization analysis on the plurality of computing power distribution schemes to be selected to obtain a plurality of resource fitness;
Respectively comparing the plurality of resource fitness to the reciprocal of the sum of the plurality of resource fitness, and multiplying the calculation result with a preset adjustment step length to obtain a plurality of adaptation adjustment step lengths;
Fine tuning the multiple to-be-selected computing power distribution schemes according to a preset adjustment mode based on the multiple adaptation adjustment step sizes, and summarizing fine tuning results to generate an extended computing power distribution scheme set, wherein the preset adjustment mode is to respectively call in and call out preset quantity of pre-execution outbound worksheet information to multiple mutually exclusive sub outbound execution units in multiple mutually exclusive sub outbound execution unit sets in the multiple to-be-selected computing power distribution schemes;
and performing calculation force optimization based on the extended calculation force distribution scheme set to generate an optimal calculation force distribution scheme.
6. The method of claim 5, wherein the method further comprises:
Randomly selecting an extended computing power distribution scheme from the extended computing power distribution scheme set as a first extended computing power distribution scheme, and calculating corresponding first resource fitness;
Randomly selecting an extended computing power distribution scheme from the extended computing power distribution scheme set again to serve as a second extended computing power distribution scheme, and calculating corresponding second resource fitness;
Judging whether the first resource fitness is larger than the second resource fitness, if so, taking the second extended computing power distribution scheme as a stage optimal computing power distribution scheme according to a certain probability;
If not, the second expansion calculation force distribution scheme is used as a stage optimal calculation force distribution scheme;
After the preset iteration times are met through multiple iteration optimization, the phase optimal calculation force distribution scheme corresponding to the maximum value of the resource fitness in the iteration process is used as an optimal calculation force distribution scheme.
7. A system for controlling an intelligent outbound call system, the system comprising:
The outbound task execution module is used for acquiring a pre-execution outbound work order information set of the target outbound system and sending the pre-execution outbound work order information set to the outbound execution unit to execute the outbound task;
the first outbound index obtaining module is used for carrying out redundancy identification on a plurality of sub outbound execution units of the pre-execution outbound work order information set according to the real-time outbound task execution result to obtain a plurality of first outbound indexes;
the execution unit set obtaining module is used for performing node clustering analysis based on the pre-execution outbound work order information set, and performing mutual exclusion identification on the plurality of sub outbound execution units to obtain Q mutual exclusion sub outbound execution unit sets;
The calculation force distribution scheme obtaining module is used for carrying out calculation force optimization on the outbound execution units based on the plurality of first outbound indexes and the Q mutually exclusive sub outbound execution unit sets to obtain an optimal calculation force distribution scheme;
the control module is used for controlling the target outbound system based on the optimal force distribution scheme;
the first outbound index obtaining module is further configured to perform the following steps:
Acquiring a work order execution tolerance threshold of the pre-execution outbound work order information set, traversing the real-time outbound task execution result to determine the punctuality of the plurality of sub outbound execution units, and generating a plurality of first sub outbound indexes;
traversing the memory occupancy rate of the plurality of sub-outbound execution units to generate a plurality of second sub-outbound indexes;
the plurality of first outbound indices is generated based on the plurality of first sub-outbound indices and a plurality of second sub-outbound indices.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410225130.9A CN117812185B (en) | 2024-02-29 | 2024-02-29 | Control method and system of intelligent outbound system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410225130.9A CN117812185B (en) | 2024-02-29 | 2024-02-29 | Control method and system of intelligent outbound system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117812185A CN117812185A (en) | 2024-04-02 |
| CN117812185B true CN117812185B (en) | 2024-05-24 |
Family
ID=90425844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410225130.9A Active CN117812185B (en) | 2024-02-29 | 2024-02-29 | Control method and system of intelligent outbound system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117812185B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20050010099A (en) * | 2003-07-18 | 2005-01-27 | 강호석 | Call recommender system for outbound call center |
| WO2008077301A1 (en) * | 2006-12-27 | 2008-07-03 | Huawei Technologies Co., Ltd. | System for customizing calling-out service and method thereof |
| CN109472452A (en) * | 2018-10-11 | 2019-03-15 | 平安科技（深圳）有限公司 | Intelligent worker assigning method, apparatus, computer equipment and storage medium |
| CN109995950A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团贵州有限公司 | Method, system, equipment and the medium of telephone outbound call |
| CN110166641A (en) * | 2019-05-21 | 2019-08-23 | 深圳市中讯网联科技有限公司 | Dynamic prediction type intelligence automatic outer call system algorithm |
| CN111669466A (en) * | 2020-04-27 | 2020-09-15 | 平安普惠企业管理有限公司 | Intelligent outbound system configuration method, device and computer readable storage medium |
| CN113452852A (en) * | 2021-06-28 | 2021-09-28 | 中国平安财产保险股份有限公司 | Method and device for regulating and controlling number of outbound calls of machine, electronic equipment and storage medium |
| CN113890948A (en) * | 2021-09-17 | 2022-01-04 | 中国平安财产保险股份有限公司 | Resource allocation method based on voice outbound robot dialogue data and related equipment |
| CN114205467A (en) * | 2021-12-09 | 2022-03-18 | 广西电网有限责任公司 | Intelligent outbound system for power grid customer service work order and use method |
| CN115562886A (en) * | 2022-09-23 | 2023-01-03 | 浙江吉利控股集团有限公司 | Intelligent outbound system and method |
| CN117278313A (en) * | 2023-10-22 | 2023-12-22 | 滁州职业技术学院 | Security detection method and system for computer network structure optimization |
-
2024
- 2024-02-29 CN CN202410225130.9A patent/CN117812185B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20050010099A (en) * | 2003-07-18 | 2005-01-27 | 강호석 | Call recommender system for outbound call center |
| WO2008077301A1 (en) * | 2006-12-27 | 2008-07-03 | Huawei Technologies Co., Ltd. | System for customizing calling-out service and method thereof |
| CN109995950A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团贵州有限公司 | Method, system, equipment and the medium of telephone outbound call |
| CN109472452A (en) * | 2018-10-11 | 2019-03-15 | 平安科技（深圳）有限公司 | Intelligent worker assigning method, apparatus, computer equipment and storage medium |
| CN110166641A (en) * | 2019-05-21 | 2019-08-23 | 深圳市中讯网联科技有限公司 | Dynamic prediction type intelligence automatic outer call system algorithm |
| CN111669466A (en) * | 2020-04-27 | 2020-09-15 | 平安普惠企业管理有限公司 | Intelligent outbound system configuration method, device and computer readable storage medium |
| CN113452852A (en) * | 2021-06-28 | 2021-09-28 | 中国平安财产保险股份有限公司 | Method and device for regulating and controlling number of outbound calls of machine, electronic equipment and storage medium |
| CN113890948A (en) * | 2021-09-17 | 2022-01-04 | 中国平安财产保险股份有限公司 | Resource allocation method based on voice outbound robot dialogue data and related equipment |
| CN114205467A (en) * | 2021-12-09 | 2022-03-18 | 广西电网有限责任公司 | Intelligent outbound system for power grid customer service work order and use method |
| CN115562886A (en) * | 2022-09-23 | 2023-01-03 | 浙江吉利控股集团有限公司 | Intelligent outbound system and method |
| CN117278313A (en) * | 2023-10-22 | 2023-12-22 | 滁州职业技术学院 | Security detection method and system for computer network structure optimization |
Non-Patent Citations (1)
| Title |
|---|
| 客户外呼集中管理系统的设计与实现;王丽菊;蒋;;信息与电脑(理论版);20120715(07);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117812185A (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109445935B (en) | Self-adaptive configuration method of high-performance big data analysis system in cloud computing environment | |
| CN112565378A (en) | Cloud native resource dynamic prediction method and device, computer equipment and storage medium | |
| EP1903479B1 (en) | Method and system for data classification using a self-organizing map | |
| CN110674636B (en) | Power consumption behavior analysis method | |
| CN110188919A (en) | A kind of load forecasting method based on shot and long term memory network | |
| CN110162390B (en) | Task allocation method and system for fog computing system | |
| CN113051130B (en) | Mobile cloud load prediction method and system of LSTM network combined with attention mechanism | |
| Li et al. | Research on QoS service composition based on coevolutionary genetic algorithm | |
| CN113902116A (en) | Deep learning model-oriented reasoning batch processing optimization method and system | |
| CN117395253A (en) | Load balancing method, device, equipment and storage medium thereof | |
| CN118484313A (en) | Intelligent calculation power call management system and method based on data characteristics | |
| Yang et al. | Optimizing aggregation frequency for hierarchical model training in heterogeneous edge computing | |
| CN114781717A (en) | Network point equipment recommendation method, device, equipment and storage medium | |
| CN117056089B (en) | Service dynamic allocation system and method | |
| CN117707747A (en) | Resource utilization rate prediction-based job excessive allocation scheduling method and system | |
| CN117495512A (en) | Order data management method, device, equipment and storage medium | |
| CN117812185B (en) | Control method and system of intelligent outbound system | |
| CN112508363A (en) | Deep learning-based power information system state analysis method and device | |
| CN116957304A (en) | Unmanned aerial vehicle group collaborative task allocation method and system | |
| CN114268625B (en) | Feature selection method, device, equipment and storage medium | |
| CN115081609A (en) | Acceleration method in intelligent decision, terminal equipment and storage medium | |
| CN115099875A (en) | Data classification method based on decision tree model and related equipment | |
| CN114565791A (en) | Figure file identification method, device, equipment and medium | |
| CN113177613A (en) | System resource data distribution method and device | |
| CN113159957B (en) | Transaction 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |