CN113163063B - Intelligent outbound call system and method - Google Patents
Intelligent outbound call system and method Download PDFInfo
- Publication number
- CN113163063B CN113163063B CN202110481412.1A CN202110481412A CN113163063B CN 113163063 B CN113163063 B CN 113163063B CN 202110481412 A CN202110481412 A CN 202110481412A CN 113163063 B CN113163063 B CN 113163063B
- Authority
- CN
- China
- Prior art keywords
- outbound
- module
- data
- time
- submodule
- 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
Images
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
- H04M3/523—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2242/00—Special services or facilities
- H04M2242/18—Automated outdialling systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the application discloses an intelligent outbound system and a method, wherein the system comprises an outbound time calculation module, an intelligent outbound module and a version iteration module; the outbound time calculation module calculates target outbound time according to the basic data and the service requirement information, and pushes the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements; the intelligent outbound module executes outbound operation according to the target outbound time and performs voice interaction with a user, collects outbound record data and communication record data, and sends the outbound record data and the communication record data to the version iteration module; the version iteration module analyzes the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeds back and updates the optimizable parameter to the outbound time calculation module, so that the outbound time calculation module performs version iteration according to the optimizable parameter, and the outbound call completing rate of the intelligent outbound is improved.
Description
Technical Field
The application relates to the technical field of communication, in particular to an intelligent outbound system and an intelligent outbound method.
Background
Robot Process Automation (RPA), which is a business process automation technology based on software robots and artificial intelligence, can replace or assist humans to complete repetitive work and tasks in digital equipment.
The intelligent outbound belongs to one of RPA technology, which is an artificial intelligence form that the voice robot replaces the artificial seat to complete the telephone call and voice communication. The intelligent outbound technology is one of important realization and landing forms of the RPA, is gradually mature, and is widely applied to services such as intelligent marketing, intelligent return visit, intelligent collection and the like in multiple industries such as finance, insurance, education, internet and the like. How to improve the call completing rate of the outbound call has become one of the important research topics of the intelligent outbound call.
Disclosure of Invention
The embodiment of the application provides an intelligent outbound system and method, which can analyze the optimal outbound time of different users in different service requirements by combining abundant basic data and service requirement information so as to improve the outbound call completing rate of intelligent outbound.
In a first aspect, an intelligent outbound system is provided, which comprises an outbound time calculation module, an intelligent outbound module and a version iteration module;
the outbound time calculation module is used for calculating target outbound time according to basic data and service requirement information and pushing the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements;
the intelligent outbound module is used for executing outbound operation according to the target outbound time and carrying out voice interaction with a user, collecting outbound record data and communication record data, and sending the outbound record data and the communication record data to the version iteration module;
and the version iteration module is used for analyzing the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so as to enable the outbound time calculation module to carry out version iteration according to the optimizable parameter.
In a second aspect, an intelligent outbound method is provided, which is applied to the intelligent outbound system according to the first aspect, and the method includes:
the control outbound time calculation module calculates target outbound time according to basic data and service requirement information and pushes the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements;
controlling the intelligent outbound module to execute outbound operation and perform voice interaction with a user according to the target outbound time, collecting outbound record data and communication record data, and sending the outbound record data and the communication record data to the version iteration module;
and controlling the version iteration module to analyze the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter.
In a third aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program adapted to be loaded by a processor for performing the steps of the intelligent call-out method according to the second aspect.
In a fourth aspect, a computer device is provided, the computer device comprising a processor and a memory, the memory having stored therein a computer program, the processor being configured to perform the steps of the intelligent callout method according to the second aspect by calling the computer program stored in the memory.
The embodiment of the application provides an intelligent outbound system and a method, wherein the intelligent outbound system comprises an outbound time calculation module, an intelligent outbound module and a version iteration module; the outbound time calculation module calculates target outbound time according to the basic data and the service requirement information and pushes the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements; the intelligent outbound module executes outbound operation and voice interaction with the user according to the target outbound time, collects outbound record data and communication record data, and sends the outbound record data and the communication record data to the version iteration module; and the version iteration module analyzes the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeds back and updates the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter. According to the method and the device, the optimal outbound time of different users in different service requirements is analyzed by combining abundant basic data and service requirement information, and the outbound record data and communication record data obtained after outbound operation is performed on the system based on the historical version are used for self-learning and iteration of the intelligent outbound system so as to improve the outbound call completing rate of the intelligent outbound.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent outbound call system according to an embodiment of the present application.
Fig. 2 is a schematic flow chart of an intelligent outbound method according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides an intelligent outbound system and method. Specifically, the intelligent outbound method according to the embodiment of the present application may be executed by a computer device, where the computer device may be a terminal or a server. The terminal can be a terminal device such as a smart phone, a tablet Computer, a notebook Computer, a touch screen, a game machine, a Personal Computer (PC), a Personal Digital Assistant (PDA), and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content distribution network service, and a big data and artificial intelligence platform, but is not limited thereto.
The intelligent outbound technology is one of important realization and landing forms of the RPA, is gradually mature, and is widely applied to services such as intelligent marketing, intelligent return visit, intelligent collection and the like in multiple industries such as finance, insurance, education, internet and the like. At present, the intelligent outbound technology related to the outbound time is basically realized by the following two schemes: the first is intelligent selection of outbound line in time dimension; the second is fine control of outbound time, such as being able to control outbound to the minute level. Both schemes can improve the call-out call completing rate and the user experience to a certain extent.
The two schemes are mainly optimized in the realization of the inside of the intelligent outbound system, the first scheme only concerns the connection condition and the call quality of different lines in different time periods, and the second scheme is the accurate outbound according to the preset time point. The two schemes do not integrate the service characteristics of the product and the two aspects of the target user to deeply explore and realize the intelligent selection of the optimal outbound time; the situation that the time period with the highest outbound call connection probability of each user is different under different products, different services and different user attributes is not considered. How to accurately and individually find the different points, select the optimal outbound time period, and form a dynamic closed-loop scheme by using the different searching mechanisms, which cannot be realized only in the intelligent outbound system, and needs to be completed by combining the big data analysis of the user and the whole self-iteration mechanism together in a cooperative manner.
The intelligent outbound system is based on abundant user big data, combines a data analysis model and strategies, comprehensively considers service benefits and user experience, achieves a set of intelligent outbound system capable of finely analyzing, individually analyzing, excavating, selecting and recommending the optimal intelligent outbound time of different users in different service requirements, can achieve on-line effect self-learning and iteration upgrading core strategy configuration based on historical versions, achieves scheme closed loop, is suitable for being uniformly achieved on various platforms, and finally improves outbound call completion rate of intelligent outbound, and further improves service indexes and user experience of intelligent outbound.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating an architecture of an intelligent outbound call system according to an embodiment of the present application. The intelligent outbound system 100 comprises an outbound time calculation module 110, an intelligent outbound module 120 and a version iteration module 130, wherein the three modules form a closed loop.
The outbound time calculation module 110 is a core module of the intelligent outbound system 100, and mainly undertakes processing and calculation of user big data and adaptation processing of result forms meeting different service requirements.
The outbound time calculation module 110 is configured to calculate a target outbound time according to the basic data and the service requirement information, and push the target outbound time to the intelligent outbound module 120, where the target outbound time includes optimal outbound time of different users in different service requirements.
The outbound time calculation module 110 includes a preposed data sub-module 111, a core calculation sub-module 112, a post-adapter sub-module 113, and a unified configuration management sub-module 114.
The pre-data sub-module 111 is used for providing basic data and a data processing mode.
As shown in fig. 1, the basic data may include business crowd attribute data, historical behavior data, historical communication data, and outbound line data. The data processing mode may include processing modes such as a data update mechanism for maintaining each big data source, data preprocessing, data quality evaluation, and data fusion. The service population attribute data refers to basic attribute data of the user, and mainly comprises gender, age, native place, occupation, geographical position and the like of the user. The historical behavior data refers to operation behavior data or financial behavior data generated when a user uses a target client (such as a browser, an application app, an applet and other software terminals) in a historical time period; the historical communication data refers to outgoing call record data and communication record data generated by the intelligent outgoing call module 120 calling the user and communicating in a historical time period, such as a calling state, a call duration, a communication intention and the like. The outbound line data refers to data related to each call line, such as call quality of the line, which is actually outbound in the intelligent outbound module 120.
The core calculation submodule 112 is configured to calculate a target parameter according to the basic data and the data processing manner.
For example, the core computation submodule 112 performs computation of various policies and models mainly based on the basic data and data processing manner of the prepositive data submodule 111. The core computation submodule 112 may be formed by factors such as empirical weighting, linear regression, ranking strategies and behavioral models.
The core computation submodule 112 may also have a plurality of implementation and access forms, for example, the core computation submodule 112 may also be packaged as an online real-time query service, which not only can satisfy the requirements of authorizing different services to query as required, but also can support flexible access of more services.
The calculation of the core calculation sub-module 112 has various forms, and different calculation modes can be selected according to different service crowd attribute data (namely user attribute data), historical behavior data, historical communication data and outbound line data.
Optionally, the basic data includes business crowd attribute data and historical behavior data.
Optionally, the target parameter at least includes an experience weighted value corresponding to different outbound periods, and activeness and active time of different users.
The core computation sub-module 112 is configured to set experience weighted values corresponding to different outbound time periods according to the service crowd attribute data. For example, the morning, evening and evening work and rest rules of users in different geographic locations are different due to the time zone crossing, and for the users in the east region, the middle region and the west region, there is a systematic difference in the turn-on probability in different time periods, and it can be considered that different experience weights are assigned to different outbound time periods according to the geographic location of each user for the difference.
The core calculation sub-module 112 is configured to calculate activity levels and activity times of different users according to the historical behavior data of the different users.
Optionally, the core computation submodule 112 is configured to compute activity levels and activity times of different users according to the historical behavior data of the different users, and specifically includes:
acquiring record types and record times corresponding to the record types in different types of historical behavior data of different users within a specific time period according to the historical behavior data of the different users, and taking the record types and the record times as characteristic values of a clustering algorithm;
recalculating the characteristic value of the clustering algorithm according to a preset time period, wherein the preset time period is less than the specific time period;
performing weight reduction processing on each characteristic value according to the preset time period;
and clustering the characteristic values subjected to the weight reduction processing to calculate the activity degrees and the activity time of different users.
For example, for different types of historical behavior data of users, a clustering algorithm is adopted, and the record type and the corresponding times in the latest specific time period are taken as characteristic values of the clustering algorithm. The record types corresponding to the different types of historical behavior data may include recorded behavior types such as login behavior, browsing behavior, clicking behavior, screenshot behavior, query behavior, input behavior, and the like. For example, the feature value may be the number of times the user logged into the app the last month (or week, or three days). Or the characteristic value may be the frequency with which the user clicks a button in the last week (or month), or the characteristic value may be the total number of active weeks (or days), etc.
For example, the eigenvalues are spread and calculated according to a smaller preset time period. When the preset time period is set, the business is generally divided according to business characteristics, for example, the collection of the business is generally divided into overdue stages according to months, and the preset time period can be set to be each month; for example, if the telemarketing service is concerned about the user in the recent period of time, the telemarketing service may be divided into weeks, and the preset time period is set to each week.
For example, each feature value is weighted down according to a preset time period. When each eigenvalue is subjected to weight reduction treatment according to a preset time period, a common weight reduction treatment method can be adopted, for example, the weight reduction treatment is performed by selecting and using Newton's cooling law, and a weight calculation formula is defined as follows:
the weight of the current cycle is the weight of the last cycle × e (the number of cycles of the cooling coefficient x interval) to the power, where e is a natural constant.
For example, clustering is performed by using a clustering algorithm (such as a K-means algorithm), a final classification scheme is determined, and finally, the activity and the activity time of different users are calculated by using the clustering model.
For example, taking a K-means clustering algorithm as an example, calculating the activity of the user according to the historical behavior data of the user, specifically:
(1) first, the K value (number of categories of liveness clusters) is selected according to the elbow rule: drawing loss functions corresponding to different K values into a broken line, wherein the horizontal axis is the value of K, the vertical axis is the loss function defined by the sum of squares of distances, and the K value corresponding to an obvious inflection point is searched on the broken line as a selected result;
(2) traversing all the processed data such as processing and weight reduction, finding the central point of the data closest to the data, and dividing the data into the category, so that all the data are divided into K categories;
(3) calculating the average value of all data in each category as a new central point;
(4) repeating the above process until the K central points are not changed any more, and achieving the result of convergence;
(5) and finally, marking different liveness degrees according to actual conditions for the K types which are already converged.
For example, taking a K-means clustering algorithm as an example, the active time of the user is calculated according to the historical behavior data of the user, and specifically:
(1) first, the K value (number of classes of active time clusters) is selected according to the elbow rule: drawing loss functions corresponding to different K values into a broken line, wherein the horizontal axis is the value of K, the vertical axis is the loss function defined by the sum of squares of distances, and the K value corresponding to an obvious inflection point is searched on the broken line as a selected result;
(2) traversing all the processed data such as processing and weight reduction, finding the central point of the data closest to the data, and dividing the data into the category, so that all the data are divided into K categories;
(3) calculating the average value of all data in each category as a new central point;
(4) repeating the above process until the K central points are not changed any more, and achieving the result of convergence;
(5) and finally, marking different active time according to actual conditions for the K types which are converged.
Optionally, the basic data further includes historical communication data. The target parameters also include a preferred time period for the target user.
The core computation submodule 112 is further configured to extract an actual outbound time period of the target user according to the call text information in the historical communication data, and use the extracted actual outbound time period as a preferred time period of the target user.
For example, the call text information in the historical communication data may include information about time intervals (such as morning, evening, etc.) during which the user is suitable for answering the call, which are fed back by the user per call, and the call text information in the historical communication data may be analyzed by a text analysis model to extract the time interval information and convert the time interval information into an actual outbound time interval (such as 9 o 'clock or 19 o' clock, etc.), which is used as a dimension of a preferred time interval of the user.
Optionally, the basic data further includes outbound line data.
The core calculation sub-module 112 is further configured to calculate a call completing rate and a call quality of each call out time period in the overall line according to the data of the call out line, so as to adjust the empirical weighted value corresponding to each call out time period in the overall line according to the call completing rate and the call quality.
For example, the call completing rate and the call quality ratio of the whole line in which call out time intervals are relatively high are calculated according to the call out line data, and then the calculation result is taken as a dimension to adjust the experience weighted value of each call out time interval in a targeted manner. For example, the empirical weighted value is large for a line with good call completing rate and call quality; otherwise, the empirical weighted value is low for the line with poor call completing rate and call quality.
The post-adaptation submodule 113 is configured to determine the target outbound time according to the target parameter and the service requirement information, and push the target outbound time to the intelligent outbound module 120 according to a form specified by a service.
Optionally, the post-adaptor module 113 is configured to determine, according to the target parameter and the service requirement information, a preferred time period relationship, a preferred time period distribution, and a preferred time period number corresponding to different services, determine the target outbound time according to a service personalized adjustment condition, and push the target outbound time to the intelligent outbound module 120 according to a service-specified form.
For example, the post-adaptation submodule 113 is configured to filter an outbound time meeting a condition according to a calculation result (target parameter) of the core calculation submodule 111 and a service requirement, where the outbound time meeting the condition may be an optimal outbound time of each service or an optimal outbound time of different users in different service requirements, and push the optimal outbound time to the intelligent outbound module 120 in a service-specific manner. For example, the post-adaptation submodule 113 is configured to determine, according to the calculation result (target parameter) of the core calculation submodule 112 and the specified service requirement, a preferred time period relationship, preferred time period distribution, and a preferred time period number corresponding to different services, further screen out outbound time meeting the condition according to the service personalized adjustment condition, and push the outbound time meeting the condition (optimal outbound time of each service, or optimal outbound time of different users in different service requirements) to the intelligent outbound module 120 according to a preset push form corresponding to the specified service requirement. The back adapter sub-module 113 mainly performs adaptation processing according to different service requirement information, for example, for telemarketing service, it is specified that each user can only dial twice each day, and the two times are in the morning and afternoon respectively, then the back adapter sub-module 113 selects the best time interval in the morning and afternoon respectively as outbound time; for the call collection service, each user is specified to dial three times a day, and the post-adapter module 113 can select the top 3 period for recommendation.
The service requirement information may include a service type and a service requirement. For example, the service types may include an intelligent marketing service (telemarketing service), an intelligent return visit service, an intelligent collection service (telecollection service), and the like. For example, the service requirement may be an outbound frequency of the target service, an outbound target user, an outbound communication purpose, and the like.
The unified configuration management sub-module 114 is configured to uniformly manage the pre-data sub-module 111, the core computation sub-module 112, and the post-adapter sub-module 113, and is configured to interact with the version iteration module 130, so as to control the outbound time computation module 110 to perform version iteration according to the optimizable parameter sent by the version iteration module 130.
The preposed data submodule 111, the core calculation submodule 112 and the post-adapter submodule 113 in the outbound time calculation module 110 are three interdependent submodules. The configuration and abstraction related to the three interdependent sub-modules are uniformly managed by a uniform configuration management sub-module 114, which is convenient for interaction with the version iteration module 130 and can ensure self-iteration of calculation. When the unified configuration management sub-module 114 performs unified management, all configurations are uniformly stored according to a key value pair (key) format, and a unified query and modification interface is provided, and each self-iteration only needs to call the modification interface to modify the value of the specified key, and each calculation only needs to call the query interface to query the value of the specified key.
The intelligent outbound module 120 is configured to execute an outbound operation according to the target outbound time, perform voice interaction with the user, collect outbound recording data and communication recording data, and send the outbound recording data and the communication recording data to the version iteration module 130.
Optionally, the intelligent outbound module 120 further includes a robot submodule 121, where the robot submodule 121 includes a plurality of robots 1211 for different services;
the intelligent outbound module 120 is used for distributing the optimal outbound time of the different users in different service requirements to outbound lines of the robots 1211 of different services in the robot submodule 121 according to service types, and the robots 1211 of different services perform outbound operation and perform voice interaction with the users; and
and the intelligent outbound module 120 is configured to control the robot submodule 121 to store outbound record data and communication record data of each outbound operation, and send the outbound record data and the communication record data to the version iteration module 130.
For example, intelligent outbound module 120 is a module that interacts with the user. The intelligent outbound module 120 further includes a robot submodule 121, where the robot submodule 121 includes a plurality of robots 1211 for different services, such as a service a robot 1211-1, a service B robot 1211-2, a service C robot 1211-3, and the like, where the robots 1211 for different services may be set according to specific service requirement information. After the intelligent outbound module 120 receives the push result of the optimal outbound time of each service pushed by the outbound time calculation module 110 or the optimal outbound time of different users in different service requirements, the intelligent outbound module distributes the pushed optimal outbound time of each service or the optimal outbound time of different users in different service requirements to the outbound line of the robot 1211 of different services in the robot submodule 121 according to the service type, and the robot 1211 is responsible for outbound and voice interaction with the user. Meanwhile, the robot submodule 121 stores outgoing call record data and communication record data of each call, where the outgoing call record data may include a call state, a call duration, call user information, and the like, and the communication data may include a communication intention, a communication frequency, and the like of a user. Wherein, the calling state can be finally calculated and reflected on the call completing rate of the outbound call; and the communication intention can select the part related to the expected called time interval fed back by the user, and finally the part is used for calculating the optimal outgoing call time of the same user at the next time.
The intelligent outbound module 120 sends outbound record data and communication record data stored and recorded by the robot submodule 121 to the version iteration module 130.
The version iteration module 130 is configured to analyze an optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feed back and update the optimizable parameter to the outbound time calculation module 110, so that the outbound time calculation module 110 performs version iteration according to the optimizable parameter.
Optionally, the version iteration module 130 is configured to, according to the outbound record data and the communication record data of different services corresponding to different users, count and analyze actual effects of the optimal outbound time in each dimension of different service requirements of the different users recommended by the outbound time calculation module 110, count user communication intentions, and count an outbound call completing rate;
analyzing the contribution degree and the correlation degree corresponding to each data source and the calculation result of the outbound time calculation module 110 according to the actual effect, the user communication intention and the outbound call completing rate, so as to determine an optimizable parameter in the outbound time calculation module 110 according to the contribution degree and the correlation degree;
feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module 110 performs version iteration according to the optimizable parameter.
Wherein, the version iteration module 130 is used for taking charge of the effect statistics and the iteration initiation of the whole intelligent outbound system 100. By acquiring the outbound record data and the communication record data of different services in the intelligent outbound module 120, counting and analyzing the actual effect of the optimal outbound time in each dimension of each service, which is recommended by the outbound time calculation module 110 and is not related to each service by the user in each service aspect, counting user feedback related data (such as user communication intention), counting outbound call completing rate, automatically analyzing the contribution degree and the correlation degree corresponding to each data source and the calculation result of the outbound time calculation module 110 by means of methods such as correlation and contribution degree analysis, and the like, finding an optimizable parameter in the outbound time calculation module, feeding back and updating the optimizable parameter to the uniform configuration management sub-module 114, so that the uniform configuration management sub-module 114 controls the outbound time calculation module 110 to perform iterative version according to the optimizable parameter.
The correlation analysis can select different calculation modes according to different data dimensions and data types, generally speaking, the typing variables can select variance analysis, and the numerical type can select regression analysis and the like. The regression analysis refers to performing linear regression analysis on a calculation result (X) of a certain dimensionality and the actual call completing rate (serving as Y) of the final recommended outbound time, and analyzing whether a correlation exists between the calculation result (X) and the actual call completing rate. For example, the output results of the clustering model (which can be considered as typing variables) and the actual call-in rate of the final recommended outbound time are analyzed.
For example, taking the empirical weight value corresponding to the geographic location dimension as an example, analysis of variance may be selected, the actual dialing status and the dialing times of each user are aggregated in the geographic location dimension, the call completing rate of each geographic area or province (which may be a group) at different outbound time is calculated, and then the inter-group error SSA of each group is calculated to verify the systematic difference of each group, and the systematic difference is compared with the empirical weight value assignment of the core computation sub-module to verify the rationality of the current empirical weight value assignment and whether updating is required.
Wherein, the contribution degree analysis can evaluate which data or strategy dimension brings the promotion of the final effect. A common analysis modality is pareto analysis. The basic idea is to draw an accumulated contribution degree curve by taking the connection condition of each user in each time period and the calculation result of each dimension of the core calculation submodule as input; and analyzing which dimensionalities of the calculation results have high promotion contribution degrees to the actual call completing rate and which dimensionalities of the calculation results have low promotion contribution degrees to the actual call completing rate according to the accumulated contribution degree curve, thereby pertinently improving the calculation parameters of each dimensionality.
The intelligent outbound system 100 provided by the embodiment of the application includes an outbound time calculation module 110, an intelligent outbound module 120, and a version iteration module 130; the outbound time calculation module 110 calculates a target outbound time according to the basic data and the service requirement information, and pushes the target outbound time to the intelligent outbound module 120, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements; the intelligent outbound module 120 executes outbound operation and voice interaction with the user according to the target outbound time, collects outbound record data and communication record data, and sends the outbound record data and the communication record data to the version iteration module 130; the version iteration module 130 analyzes the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeds back and updates the optimizable parameter to the outbound time calculation module 110, so that the outbound time calculation module 110 performs version iteration according to the optimizable parameter. According to the method and the device, the optimal outbound time of different users in different service requirements is analyzed by combining abundant basic data and service requirement information, and the outbound record data and communication record data obtained after outbound operation is performed on the system based on the historical version are used for self-learning and iteration of the intelligent outbound system so as to improve the outbound call completing rate of the intelligent outbound.
The embodiment of the present application further provides an intelligent outbound method applied to the above intelligent outbound system, which has a principle similar to that of the above intelligent outbound system and is not described herein again.
Referring to fig. 2, fig. 2 is a schematic flowchart of an intelligent outbound method according to an embodiment of the present application. It should be noted that the intelligent outbound method according to the embodiment of the present application may be applied to the intelligent outbound system according to the embodiment of the present application, and the intelligent outbound system may be configured on a computer device. The specific process can be as follows:
Optionally, the outbound time calculation module includes a pre-data submodule, a core calculation submodule, a post-adaptation submodule, and a unified configuration management submodule. Step 201 can also be realized by the following steps:
201.1) acquiring the basic data and the data processing mode through the preposed data submodule;
controlling the core calculation submodule to calculate target parameters according to the basic data and the data processing mode;
201.2) controlling the post-adaptation submodule to determine the target outbound time according to the target parameter and the service requirement information, and pushing the target outbound time to the intelligent outbound module;
201.3) the preposed data submodule, the core calculation submodule and the post adaptation submodule are managed in a unified way through the unified configuration management submodule, and the unified configuration management submodule interacts with the version iteration module so as to control the outbound time calculation module to carry out version iteration according to the optimized parameters sent by the version iteration module.
Optionally, the basic data includes business crowd attribute data and historical behavior data;
the target parameters at least comprise experience weighted values corresponding to different outbound periods, and activeness and active time of different users;
the control of the core calculation submodule to calculate the target parameter according to the basic data and the data processing mode comprises the following steps:
controlling the core computing submodule to set experience weighted values corresponding to different outbound periods according to the business crowd attribute data;
and controlling the core calculation submodule to calculate the activity degrees and the activity time of different users according to the historical behavior data of the different users.
Optionally, the controlling the core computing sub-module to compute activity levels and activity times of different users according to the historical behavior data of the different users includes:
controlling the core computing submodule to obtain record types and record times corresponding to the record types in different types of historical behavior data of different users in a specific time period according to the historical behavior data of the different users, and taking the record types and the record times as characteristic values of a clustering algorithm;
recalculating the characteristic value of the clustering algorithm according to a preset time period, wherein the preset time period is less than the specific time period;
performing weight reduction processing on each characteristic value according to the preset time period;
and clustering the characteristic values subjected to the weight reduction processing to calculate the activity degrees and the activity time of different users.
Optionally, the basic data further includes historical communication data;
the target parameters further comprise a preferred time period of the target user;
the control of the core calculation submodule to calculate the target parameter according to the basic data and the data processing mode comprises the following steps:
and controlling the core computation submodule to extract the actual outbound time period of the target user according to the call text information in the historical communication data, and taking the extracted actual outbound time period as an optimal time period of the target user.
Optionally, the basic data further includes outbound line data;
the control of the core computation submodule to compute target parameters according to the basic data and the data processing mode comprises the following steps:
and controlling the core calculation submodule to calculate the call completing rate and the call quality of each call out time interval in the whole line according to the call out line data so as to adjust the empirical weighted value corresponding to each call out time interval in the whole line according to the call completing rate and the call quality.
Optionally, the controlling the post-adaptation sub-module to determine the target outbound time according to the target parameter and the service requirement information, and push the target outbound time to the intelligent outbound module includes:
and controlling the postposition adaptation sub-module to determine the optimal time interval relationship, optimal time interval distribution and optimal time interval number corresponding to different services according to the target parameters and the service requirement information, determining the target outbound time according to service personalized adjustment conditions, and pushing the target outbound time to the intelligent outbound module according to a service designated form.
Optionally, the intelligent outbound module further includes a robot sub-module, where the robot sub-module includes a plurality of robots with different services; the step 202 may be implemented by the following steps, specifically:
202.1) distributing the optimal outbound time of different users in different service requirements to outbound lines of robots of different services in the robot submodule according to service types;
202.2) controlling the robots with different services to carry out outbound operation and voice interaction with a user;
202.3) controlling the robot submodule to store the outbound record data and the communication record data of each outbound operation, and sending the outbound record data and the communication record data to the version iteration module.
And 203, controlling the version iteration module to analyze the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter.
Optionally, step 203 may be implemented by the following steps:
203.1) controlling the version iteration module to count and analyze the actual effect of the optimal outbound time of different users in different service requirements recommended by the outbound time calculation module in each dimension according to the outbound record data and the communication record data of different services corresponding to different users, counting the user communication intention and counting the outbound call completing rate;
203.2) controlling the version iteration module to analyze the contribution degree and the correlation degree corresponding to each data source and the calculation result of the outbound time calculation module according to the actual effect, the user communication intention and the outbound call completing rate so as to determine an optimizable parameter in the outbound time calculation module according to the contribution degree and the correlation degree;
203.3) controlling the version iteration module to feed back and update the optimizable parameter to the outbound time calculation module so as to enable the outbound time calculation module to carry out version iteration according to the optimizable parameter.
All the above technical solutions may be combined arbitrarily to form an optional embodiment of the present application, and are not described in detail herein.
According to the intelligent outbound method provided by the embodiment of the application, the target outbound time is calculated by controlling the outbound time calculation module according to basic data and service requirement information, and is pushed to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements; controlling the intelligent outbound module to execute outbound operation and perform voice interaction with a user according to the target outbound time, collecting outbound record data and communication record data, and sending the outbound record data and the communication record data to the version iteration module; and controlling the version iteration module to analyze the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter. According to the method and the device, the optimal outbound time of different users in different service requirements is analyzed by combining abundant basic data and service requirement information, and the outbound record data and communication record data obtained after outbound operation is performed on the system based on the historical version are used for self-learning and iteration of the intelligent outbound system so as to improve the outbound call completing rate of the intelligent outbound.
Correspondingly, the embodiment of the present application further provides a computer device, where the computer device can implement all steps in the intelligent outbound method in the above embodiments, the computer device may be a terminal or a server, and the terminal may be a smart phone, a tablet computer, a notebook computer, a smart television, a smart sound box, a wearable smart device, a personal computer, and so on. The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, big data and artificial intelligence platform and the like. As shown in fig. 3, fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application. The computer apparatus 300 includes a processor 301 having one or more processing cores, a memory 302 having one or more computer-readable storage media, and a computer program stored on the memory 302 and executable on the processor. The processor 301 is electrically connected to the memory 302. Those skilled in the art will appreciate that the computer device configurations illustrated in the figures are not meant to be limiting of computer devices and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
The processor 301 is a control center of the computer apparatus 300, connects various parts of the entire computer apparatus 300 by various interfaces and lines, performs various functions of the computer apparatus 300 and processes data by running or loading software programs and/or modules stored in the memory 302, and calling data stored in the memory 302, thereby monitoring the computer apparatus 300 as a whole.
In the embodiment of the present application, the processor 301 in the computer device 300 loads instructions corresponding to processes of one or more application programs into the memory 302, and the processor 301 executes the application programs stored in the memory 302 according to the following steps, so as to implement various functions:
the control outbound time calculation module calculates target outbound time according to basic data and service requirement information and pushes the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements;
controlling the intelligent outbound module to execute outbound operation and perform voice interaction with a user according to the target outbound time, collecting outbound record data and communication record data, and sending the outbound record data and the communication record data to the version iteration module;
and controlling the version iteration module to analyze the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
In some embodiments, as shown in FIG. 3, computer device 300 further comprises: a display unit 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306, and a power supply 307. The processor 301 is electrically connected to the display unit 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306, and the power source 307. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 3 does not constitute a limitation of the computer device, and may include more or fewer components than illustrated, or some components may be combined, or a different arrangement of components.
The display unit 303 may be used to display information input by or provided to a user and various graphical user interfaces of the computer device, which may be made up of graphics, text, icons, video, and any combination thereof. The display unit 303 may include a display panel and a touch panel.
The rf circuit 304 may be used for transceiving rf signals to establish wireless communication with a network device or other computer device via wireless communication, and for transceiving signals with the network device or other computer device.
The audio circuit 305 may be used to provide an audio interface between the user and the computer device through speakers, microphones. The audio circuit 305 may transmit the electrical signal converted from the received audio data to a speaker, and convert the electrical signal into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 305 and converted into audio data, and then the audio data is processed by the audio data output processor 301, and then the processed audio data is sent to another computer device through the radio frequency circuit 304, or the audio data is output to the memory 302 for further processing. The audio circuit 305 may also include an earbud jack to provide communication of a peripheral headset with the computer device.
The input unit 306 may be used to receive input numbers, character information, or user characteristic information (e.g., fingerprint, iris, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.
The power supply 307 is used to power the various components of the computer device 300. In some embodiments, the power supply 307 may be logically coupled to the processor 301 through a power management system, such that functions of managing charging, discharging, and power consumption are performed through the power management system. Power supply 307 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
Although not shown in fig. 3, the computer device 300 may further include a camera, a sensor, a wireless fidelity module, a bluetooth module, etc., which are not described in detail herein.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, where the computer programs can be loaded by a processor to execute the steps in any one of the intelligent outbound methods provided in the present application.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the computer program stored in the storage medium can execute the steps in any of the intelligent outbound methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the intelligent outbound methods provided in the embodiments of the present application can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
The above detailed description is given to an intelligent outbound system and method provided by the embodiments of the present application, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and the application scope may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (9)
1. An intelligent outbound system is characterized in that the intelligent outbound system comprises an outbound time calculation module, an intelligent outbound module and a version iteration module;
the outbound time calculation module is used for calculating target outbound time according to basic data and service requirement information and pushing the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements; the outbound time calculation module comprises a preposed data submodule, a core calculation submodule, a postposition adaptation submodule and a unified configuration management submodule; the prepositive data submodule is used for providing the basic data and a data processing mode; the core calculation submodule is used for calculating target parameters according to the basic data and the data processing mode; the post-adapter module is used for determining the target outbound time according to the target parameters and the service requirement information and pushing the target outbound time to the intelligent outbound module; the unified configuration management submodule is used for uniformly managing the preposed data submodule, the core calculation submodule and the rear adapter submodule and is used for interacting with the version iteration module so as to control the outbound time calculation module to carry out version iteration according to the optimizable parameters sent by the version iteration module;
the intelligent outbound module is used for executing outbound operation according to the target outbound time and carrying out voice interaction with a user, collecting outbound record data and communication record data, and sending the outbound record data and the communication record data to the version iteration module;
and the version iteration module is used for analyzing the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so as to enable the outbound time calculation module to carry out version iteration according to the optimizable parameter.
2. The intelligent outbound system of claim 1 wherein said base data comprises business demographic attribute data and historical behavior data;
the target parameters at least comprise experience weighted values corresponding to different outbound periods, and activeness and active time of different users;
the core calculation submodule is used for setting experience weighted values corresponding to different outbound periods according to the business crowd attribute data;
and the core calculation submodule is used for calculating the activity degrees and the activity time of different users according to the historical behavior data of the different users.
3. The intelligent outbound system of claim 2, wherein the core computation submodule is configured to compute liveness and active time of different users according to the historical behavior data of the different users, and specifically includes:
acquiring record types and record times corresponding to the record types in different types of historical behavior data of different users within a specific time period according to the historical behavior data of the different users, and taking the record types and the record times as characteristic values of a clustering algorithm;
recalculating the characteristic value of the clustering algorithm according to a preset time period, wherein the preset time period is less than the specific time period;
performing weight reduction processing on each characteristic value according to the preset time period;
and clustering the characteristic values after the weight reduction processing so as to calculate the activity degrees and the activity time of different users.
4. The intelligent outbound system of claim 2 wherein said base data further comprises historical communication data;
the target parameters further comprise a preferred time period of the target user;
the core calculation submodule is further used for extracting the actual outbound time period of the target user according to the call text information in the historical communication data, and taking the extracted actual outbound time period as a preferred time period of the target user.
5. The intelligent outbound system of claim 2 wherein said base data further comprises outbound line data;
the core calculation submodule is further used for calculating the call completing rate and the call quality of each call out time interval in the whole circuit according to the call out circuit data, and adjusting the experience weighted value corresponding to each call out time interval in the whole circuit according to the call completing rate and the call quality.
6. The intelligent outbound system of any one of claims 1 to 5, wherein the post-adaptation sub-module is configured to determine, according to the target parameter and the service requirement information, a preferred time period relationship, a preferred time period distribution, and a preferred time period number corresponding to different services, determine the target outbound time according to a service personalized adjustment condition, and push the target outbound time to the intelligent outbound module in a service-specific manner.
7. The intelligent outbound system of claim 1 wherein said intelligent outbound module further comprises a robot submodule, said robot submodule comprising a plurality of different business robots;
the intelligent outbound module is used for distributing the optimal outbound time of different users in different service requirements to outbound lines of robots of different services in the robot submodule according to service types, and the robots of different services perform outbound operation and perform voice interaction with the users; and
the intelligent outbound module is used for controlling the robot submodule to store outbound record data and communication record data of each outbound operation and sending the outbound record data and the communication record data to the version iteration module.
8. The intelligent outbound system according to claim 1, wherein the version iteration module is configured to, according to the outbound record data and the communication record data of different services corresponding to different users, count and analyze actual effects in each dimension of the optimal outbound time of the different users in different service requirements recommended by the outbound time calculation module, count user communication intentions, and count outbound call completing rates;
analyzing the contribution degree and the correlation degree corresponding to each data source and the calculation result of the outbound time calculation module according to the actual effect, the user communication intention and the outbound call completing rate, and determining an optimizable parameter in the outbound time calculation module according to the contribution degree and the correlation degree;
and feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter.
9. An intelligent outbound method applied to the intelligent outbound system according to claim 1, the method comprising:
the intelligent outbound module is used for controlling an outbound time calculation module to calculate target outbound time according to basic data and service requirement information and pushing the target outbound time to the intelligent outbound module, wherein the target outbound time comprises the optimal outbound time of different users in different service requirements, and the outbound time calculation module comprises a preposed data submodule, a core calculation submodule, a postposition adaptation submodule and a unified configuration management submodule, and specifically comprises: acquiring the basic data and a data processing mode through the preposed data submodule; controlling the core computation submodule to compute target parameters according to the basic data and the data processing mode; controlling the post-adaptation submodule to determine the target outbound time according to the target parameter and the service requirement information, and pushing the target outbound time to the intelligent outbound module; the preposed data submodule, the core calculation submodule and the post-adaptation submodule are managed in a unified mode through the unified configuration management submodule, and the unified configuration management submodule interacts with the version iteration module to control the outbound time calculation module to carry out version iteration according to the optimized parameters sent by the version iteration module;
controlling the intelligent outbound module to execute outbound operation according to the target outbound time and perform voice interaction with a user, collecting outbound record data and communication record data, and sending the outbound record data and the communication record data to the version iteration module;
and controlling the version iteration module to analyze the optimizable parameter of the outbound time calculation module according to the outbound record data and the communication record data, and feeding back and updating the optimizable parameter to the outbound time calculation module so that the outbound time calculation module performs version iteration according to the optimizable parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110481412.1A CN113163063B (en) | 2021-04-30 | 2021-04-30 | Intelligent outbound call system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110481412.1A CN113163063B (en) | 2021-04-30 | 2021-04-30 | Intelligent outbound call system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113163063A CN113163063A (en) | 2021-07-23 |
| CN113163063B true CN113163063B (en) | 2022-09-09 |
Family
ID=76872787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110481412.1A Active CN113163063B (en) | 2021-04-30 | 2021-04-30 | Intelligent outbound call system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113163063B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114040051B (en) * | 2021-11-05 | 2024-05-24 | 中国平安财产保险股份有限公司 | Multi-round outbound method and device, readable storage medium and computer equipment |
| CN114866651B (en) * | 2022-07-07 | 2022-09-20 | 南通小红帽网络科技有限公司 | Node-reusable intelligent outbound method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110166632A (en) * | 2019-04-15 | 2019-08-23 | 中国平安人寿保险股份有限公司 | Intelligent outgoing call processing method, device, computer equipment and storage medium |
| CN110312046A (en) * | 2019-05-23 | 2019-10-08 | 中国平安人寿保险股份有限公司 | Outgoing call data optimization methods, device, computer equipment and storage medium |
| CN110351443A (en) * | 2019-06-17 | 2019-10-18 | 深圳壹账通智能科技有限公司 | Intelligent outgoing call processing method, device, computer equipment and storage medium |
| CN111435482A (en) * | 2019-01-14 | 2020-07-21 | 顺丰科技有限公司 | Outbound model construction method, outbound method, device and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005125222A1 (en) * | 2004-06-22 | 2005-12-29 | Zte Corporation | Method for protecting incoming calls in personalized ring back tone service |
| CN102450039B (en) * | 2011-05-31 | 2013-12-04 | 华为技术有限公司 | Calling-out method, calling-out server and calling-out system |
| CN109636302A (en) * | 2018-10-23 | 2019-04-16 | 平安科技（深圳）有限公司 | Outgoing call rule configuration method, calling-out method, device and communication equipment |
| CN109600522A (en) * | 2018-12-10 | 2019-04-09 | 中国银行股份有限公司 | A kind of outgoing call control method and device |
| CN110381220B (en) * | 2019-08-19 | 2021-03-12 | 中国工商银行股份有限公司 | Information recommendation method and device, electronic equipment and readable storage medium |
| CN111901485B (en) * | 2020-08-12 | 2021-08-27 | 中国银行股份有限公司 | Control method and device of outbound system |
| CN112399021B (en) * | 2020-11-03 | 2021-11-12 | 中国平安人寿保险股份有限公司 | Voice call data processing method and device, computer equipment and storage medium |
| CN112333342B (en) * | 2020-11-16 | 2022-11-08 | 平安普惠企业管理有限公司 | Intelligent voice calling method, device, equipment and storage medium |
-
2021
- 2021-04-30 CN CN202110481412.1A patent/CN113163063B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111435482A (en) * | 2019-01-14 | 2020-07-21 | 顺丰科技有限公司 | Outbound model construction method, outbound method, device and storage medium |
| CN110166632A (en) * | 2019-04-15 | 2019-08-23 | 中国平安人寿保险股份有限公司 | Intelligent outgoing call processing method, device, computer equipment and storage medium |
| CN110312046A (en) * | 2019-05-23 | 2019-10-08 | 中国平安人寿保险股份有限公司 | Outgoing call data optimization methods, device, computer equipment and storage medium |
| CN110351443A (en) * | 2019-06-17 | 2019-10-18 | 深圳壹账通智能科技有限公司 | Intelligent outgoing call processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113163063A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8788439B2 (en) | Instance weighted learning machine learning model | |
| US7774349B2 (en) | Statistical models and methods to support the personalization of applications and services via consideration of preference encodings of a community of users | |
| US20100191658A1 (en) | Predictive Engine for Interactive Voice Response System | |
| CN113163063B (en) | Intelligent outbound call system and method | |
| CN109408724A (en) | Multimedia resource estimates the determination method, apparatus and server of clicking rate | |
| CN108076224A (en) | application control method, device and storage medium and mobile terminal | |
| CN108153463B (en) | Application interface display control method and device, storage medium and mobile terminal | |
| AU2016341201A1 (en) | Optimized routing of interactions to contact center agents based on machine learning | |
| WO2013042115A2 (en) | Computerized data-aware agent systems for retrieving data to serve a dialog between human user and computerized system | |
| CN111489095A (en) | Risk user management method and device, computer equipment and storage medium | |
| WO2019062405A1 (en) | Application program processing method and apparatus, storage medium, and electronic device | |
| CN107330715A (en) | The method and apparatus for selecting display advertising material | |
| CN111435482A (en) | Outbound model construction method, outbound method, device and storage medium | |
| WO2022048515A1 (en) | Method and apparatus for implementing evaluation, and storage medium | |
| CN112633962A (en) | Service recommendation method and device, computer equipment and storage medium | |
| US20180374025A1 (en) | Methods and systems for determining persona of participants by the participant use of a software product | |
| GB2517358A (en) | Recommendation creation system | |
| CN116208709A (en) | Voice outbound method, device, electronic equipment and storage medium | |
| CN104615763B (en) | Middle table updating method and device | |
| CN113934612A (en) | User portrait updating method and device, storage medium and electronic equipment | |
| CN113886674A (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| US20230297909A1 (en) | System and method for predicting service metrics using historical data | |
| CN115103321B (en) | Short message sending method and device, computer equipment and storage medium | |
| CN116911928B (en) | Training method and device of advertisement recommendation model based on creative features | |
| CN114820085B (en) | User screening method, related device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |