CN113099046A - Man-machine coupling type calling method and device - Google Patents
Man-machine coupling type calling method and device Download PDFInfo
- Publication number
- CN113099046A CN113099046A CN202110331266.4A CN202110331266A CN113099046A CN 113099046 A CN113099046 A CN 113099046A CN 202110331266 A CN202110331266 A CN 202110331266A CN 113099046 A CN113099046 A CN 113099046A
- Authority
- CN
- China
- Prior art keywords
- conversation
- robot
- artificial
- conversation robot
- seat
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000008878 coupling Effects 0.000 title abstract description 13
- 238000010168 coupling process Methods 0.000 title abstract description 13
- 238000005859 coupling reaction Methods 0.000 title abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 26
- 230000004044 response Effects 0.000 claims abstract description 21
- 238000013473 artificial intelligence Methods 0.000 claims description 393
- 238000004590 computer program Methods 0.000 claims description 13
- 239000003795 chemical substances by application Substances 0.000 description 85
- 230000008569 process Effects 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- 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
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
-
- 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
- H04M3/5233—Operator skill based call distribution
-
- 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
- H04M3/5235—Dependent on call type or called number [DNIS]
Abstract
The invention discloses a man-machine coupling type calling method, which is characterized in that step 101, whether a plurality of calls which are simultaneously called are connected is judged, and step 102 is executed if the calls are connected; 102, distributing the one or more connected calls to an artificial intelligent AI conversation robot, and carrying out initial response by the AI conversation robot, wherein the AI has a binding relationship with the telephone robot and the artificial seat; 103, monitoring the response of the AI conversation robot, and judging whether manual intervention is needed; if human intervention is required, go to step 104; and 104, pushing a notification message to a manual agent to prompt the manual agent that the AI conversation robot needs conversation intervention. By the method, the coupling between the robot customer service and the manual seat can be coordinated, the number of simultaneous dialing of the control center is increased, the customer touch speed in unit time is higher, and the outbound efficiency is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of information processing, in particular to a man-machine coupling type calling method, a man-machine coupling type calling device, terminal equipment and a computer readable storage medium.
Background
With the development of science and technology, the internet industry flourishes, in order to provide business support and service optimization and maintain communication with customers, a call center is an important means for connecting customers generally adopted by internet enterprises, the traditional call center mainly comprises customer service personnel, and in the information era, the number of online customers is very large, so that the requirement for online customer service is very high, the customers need to be connected in time, and the response speed is high. To meet this demand, more lines and extended customer service personnel can be purchased from the operator in a conventional manner, but this requires a lot of resources and labor costs. Along with the development of artificial intelligence technology, artificial intelligence is applied to the customer service field of a call center, intelligent customer service tools such as robot customer service and the like appear, a lot of simple and repeated services of artificial seats can be replaced by intelligent voice customer service, and labor cost is saved. However, how to coordinate the coupling and scheduling between the robot customer service and the manual agents, increase the number of simultaneous dialing by the control center, increase the customer reaching speed in unit time, reduce call loss, increase the intervention working time of the manual agents, and realize high-efficiency outbound service is a problem to be solved in the field.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a man-machine coupled calling method, a man-machine coupled calling device, a terminal device and a computer readable storage medium.
The invention provides a man-machine coupling type calling method, which is characterized in that,
step 101, judging whether a plurality of calls initiated at the same time are connected, if yes, executing step 102;
102, distributing the one or more connected calls to an artificial intelligent AI conversation robot, and carrying out initial response by the AI conversation robot, wherein the AI has a binding relationship with the telephone robot and the artificial seat;
103, monitoring the response of the AI conversation robot, and judging whether manual intervention is needed; if human intervention is required, go to step 104;
and 104, pushing a notification message to a manual agent to prompt the manual agent that the AI conversation robot needs conversation intervention.
Preferably, in step 102, distributing said completed one or more calls to an artificial intelligence AI dialog robot comprises in particular
Step 1021, inquiring an AI conversation robot resource pool;
step 1022, selecting one or more AI conversation robots from the AI conversation robot resource pool based on a predetermined rule,
and 1023, distributing the connected one or more calls to the selected AI conversation robot.
Preferably, the monitoring the response of the AI dialogue robot in step 103, and the determining whether human intervention is required further includes:
monitoring the dialogue information of the AI dialogue robot through an artificial seat correspondingly bound to the AI dialogue robot, and selecting whether to intervene;
the monitoring mode is to monitor the real-time dialogue text of the AI and the client or the voice information, wherein the state of the client can be obtained through the voice information.
Preferably, in step 104, pushing the notification message to the human agent further comprises
Pushing a notification message to an artificial agent having a binding relationship with the AI conversation robot;
wherein, the manual seat is informed through the screen flipping; and controlling the pop-up screen to be displayed on display equipment corresponding to the artificial seat, wherein the display equipment synchronously displays one or more conversation interfaces corresponding to the AI conversation robot of the artificial seat, and the pop-up screen is displayed on the uppermost layer of the display area.
The invention also provides a man-machine coupling type calling device which is characterized in that,
a first judging module for judging whether a plurality of calls originating simultaneously are connected,
the distribution control module distributes the communicated one or more calls to an artificial intelligent AI conversation robot, the AI conversation robot carries out initial response, and the AI has a binding relationship between the telephone robot and the artificial seat;
the dialogue monitoring module monitors the response of the AI dialogue robot and judges whether manual intervention is needed; if manual intervention is needed, sending a first trigger message to a message pushing module;
and the message pushing module is used for pushing a notification message to the artificial seat to prompt the artificial seat that the AI conversation robot needs conversation intervention.
Preferably, the device further comprises
The query module is used for querying the AI conversation robot resource pool;
an AI conversation robot selection module selecting one or more AI conversation robots from the AI conversation robot resource pool based on a predetermined rule,
and the distribution control module is used for distributing the communicated one or more calls to the selected AI conversation robot.
Preferably, the device further comprises
The second judgment module monitors the dialogue information of the AI dialogue robot through the artificial seat correspondingly bound by the AI dialogue robot and selects whether to intervene;
the monitoring mode is to monitor the real-time dialogue text of the AI and the client or the voice information, wherein the state of the client can be obtained through the voice information.
Preferably, the message pushing module is used for
Pushing a notification message to an artificial agent having a binding relationship with the AI conversation robot;
wherein, the manual seat is informed through the screen flipping; and controlling the pop-up screen to be displayed on display equipment corresponding to the artificial seat, wherein the display equipment synchronously displays one or more conversation interfaces corresponding to the AI conversation robot of the artificial seat, and the pop-up screen is displayed on the uppermost layer of the display area.
The invention also provides a terminal device, characterized in that it comprises a processor and a memory, in which a computer program is stored that is executable on the processor, said computer program implementing the method as described above when executed by the processor.
The invention also provides a computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program is executable on a processor, and when executed implements the method as described above.
By the method, the coupling between the robot customer service and the manual seat can be effectively coordinated, the number of simultaneous dialing of the control center is increased, the customer reaching speed in unit time is increased, high-efficiency outbound service is realized, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 shows a call method of ergonomic type in an embodiment of the present invention.
Fig. 2 is a system architecture of the hmp call in an embodiment of the present invention.
FIG. 3 is a dialog interface display illustration in an embodiment of the invention.
Fig. 4 is a screen popup information display in one embodiment of the present invention.
Fig. 5 is a method for dispatch of a manmachine-coupled outbound call in an embodiment of the present invention.
Fig. 6 is a method for controlling an artificial agent AI workbench according to an embodiment of the present invention.
FIG. 7 is a functional illustration of an artificial agent AI workbench in one embodiment of the invention.
Fig. 8 shows a call apparatus coupled to a human machine according to an embodiment of the present invention.
Figure 9 is a device for ergonomic outbound calling in one embodiment of the present invention.
Fig. 10 is an artificial agent AI table apparatus in one embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The embodiments and specific features of the embodiments of the present invention are detailed descriptions of technical solutions of the embodiments of the present invention, and are not limited to technical solutions of the present invention, and the technical features of the embodiments and the embodiments of the present invention may be combined with each other without conflict.
Example one
Referring to fig. 1, an embodiment of the present invention provides a method for a call with man-machine coupling,
step 101, judging whether a plurality of calls initiated at the same time are connected, if yes, executing step 102;
102, distributing the one or more connected calls to an artificial intelligent AI conversation robot, and carrying out initial response by the AI conversation robot, wherein the AI has a binding relationship with the telephone robot and the artificial seat;
103, monitoring the response of the AI conversation robot, and judging whether manual intervention is needed; if human intervention is required, go to step 104;
and 104, pushing a notification message to a manual agent to prompt the manual agent that the AI conversation robot needs conversation intervention.
Referring to the system architecture of fig. 2, the control center may control to dial a plurality of client phones simultaneously, and when there is a phone connected, the control center distributes the phone to the agents, where the system includes M agents, such as agent A, B, C, D shown in fig. 2, etc., each agent corresponds to an AI workstation, and each agent is configured with N AI conversation robots, for example, AI conversation robots such as AI 1, AI 2, AI 3, AI 4, etc. are bound to agent a, that is, AI workstations of agent a corresponding to AI conversation robots such as AI 1, AI 2, AI 3, AI 4, etc.
In particular, in step 102, distributing the connected one or more calls to an artificial intelligence AI dialog robot comprises in particular
Step 1021, inquiring an AI conversation robot resource pool;
step 1022, selecting one or more AI conversation robots from the AI conversation robot resource pool based on a predetermined rule,
and 1023, distributing the connected one or more calls to the selected AI conversation robot.
The AI conversation robot resource pool can be pre-constructed, and the pre-construction of the AI conversation robot resource pool comprises the following steps:
polling N AI conversation robots respectively corresponding to the M personnel seats,
and judging the busy/idle state of the artificial seat, namely that the artificial seat is idle or in conversation, if the artificial seat is idle, marking N AI conversation robots respectively corresponding to the artificial seat, for example, setting an AI conversation robot flag, wherein the AI conversation robot flag corresponding to the idle state of the artificial seat is '0', and the AI conversation robot flag corresponding to the busy state of the artificial seat is '1'.
Judging whether the AI conversation robot is idle or not, if so,
the idle AI conversation robot is added to the AI conversation robot resource pool.
And updating the AI conversation robot resource pool in real time.
Further, the updating the AI conversation robot resource pool in real time specifically includes:
monitoring the state of the AI conversation robot in real time, and adding the AI conversation robot entering the idle state into the AI conversation robot resource pool when the AI conversation robot releases the session and enters the idle state;
and when the AI conversation robot in the resource pool is selected and enters a conversation state, deleting the selected AI conversation robot from the resource pool.
Further, an AI conversation robot state array may be constructed, which contains parameter values such as an AI conversation robot ID, a bound agent ID, an AI conversation robot current state, and a bound agent current state. As shown in table 1 below:
table 1: AI dialogue robot state array
Further, the AI conversation robot state array may further include AI conversation robot and/or human agent conversation party data; the data of the party may further include account number of the party, attribute of the party, level of the party, category of the current conversation, etc.
For example, the current AI conversation robot AIA2 is in a conversation with a dialogues account number 137xxxxxx, dialogues attributes are registered clients, dialogues are ranked in the middle, and the current conversation category is a service promotion category.
The current states of the AI conversation robot and the current state of the bound artificial seat in the AI conversation robot state array can be further detailed as follows: current conversation state, and conversation trend information.
For example, for the current state of the AI conversation robot, the current conversation state may be in conversation or idle, and the conversation trend may be a human intervention requirement, for example, a ranking of the human intervention requirement. For the current state of the human seat, the current conversation state can be specifically in conversation or idle, and the conversation trend information is the tendency of continuous communication, on-hook and the like.
Further, an AI dialog robot status attribute field may be constructed, which stores a parameter value related to the AI dialog robot status attribute, for example, in1 or 2 bits for indicating the current status of the AI dialog robot, with an AI dialog robot ID as an index, for example, "0" for idle, i.e., idle status, "1" for in-dialog, i.e., busy status; or further representing an idle state by '00', a busy state by '11', an impending release by '01', and a waiting intervention by '10'; setting 3-4 bits for indicating binding of the agent ID; and 1, or 2 bits for indicating the current status of the agent.
Monitoring the response of the AI dialogue robot in step 103, and determining whether human intervention is required further includes:
monitoring the dialogue information of the AI dialogue robot through an artificial seat correspondingly bound to the AI dialogue robot, and selecting whether to intervene;
the monitoring mode is to monitor the real-time dialogue text of the AI and the client or the voice information, wherein the state of the client can be obtained through the voice information.
Specifically, referring to fig. 3, the dialog process of each AI dialog robot can be seen or heard in real time through the AI workstation corresponding to the human agent, and the AI workstation corresponding to the human agent can selectively intervene in the dialog of the AI dialog robot at any time based on monitoring the dialog process of the AI dialog robot.
For example, the dialog process of the AI dialog robot is recorded in real time, and the dialog process can directly store and play voice information or be presented in real time on a corresponding dialog interface of the AI dialog robot through text conversion.
The AI workbench of the artificial seat extracts corresponding keyword data and/or user state information based on multiple rounds of conversations of the AI conversation robot, and analyzes the intervention requirement of the current conversation.
For example, based on multiple rounds of conversations of the AI conversation robot, it is recognized that client 1 has business subscription intention, further communication details are needed, the AI conversation robot cannot provide further services, and client 1 has an intervention requirement.
Furthermore, the intervention demands can be graded according to the urgency degree of the intervention demands. Wherein the urgency level can be determined according to one or more of conversation duration, conversation content, conversation party attribute, conversation party level and current conversation category.
Specifically, in step 104, pushing the notification message to the human agent further comprises
Pushing a notification message to an artificial agent having a binding relationship with the AI conversation robot;
specifically, referring to fig. 4, the AI workbench can preset a pop-screen rule, and when the AI dialog enters a certain stage and requires manual intervention, the AI workbench notifies the manual intervention through the pop-screen rule.
Further, the control pop-up screen is displayed on a display device corresponding to the artificial seat, wherein the display device synchronously displays one or more dialog interfaces corresponding to the AI dialog robot corresponding to the artificial seat.
Further, controlling a conversation interface corresponding to the AI conversation robot needing manual intervention to be displayed in a key mode; the key display comprises shaking of a conversation interface, deepening of colors of a frame of the conversation interface, amplification display of the conversation interface and the like.
The method further comprises a step 105 of determining whether a first human seat bound to the AI dialog robot is free; if idle, executing step 106, otherwise executing step 107;
wherein the determining whether the first human seat bound to the AI conversation robot is idle comprises:
inquiring an AI conversation robot state array, and determining a first artificial seat bound with the AI conversation robot;
and acquiring the current state of the first artificial seat bound with the AI conversation robot.
Judging whether a first manual seat bound with the AI conversation robot is idle or not;
and 106, replacing the AI conversation robot by the first manual seat to complete the customer service conversation.
Specifically, for example, if human agent a performs human intervention, a new human agent dialog interface is created, and the history of the current dialog of the AI dialog robot that is manually intervened is pushed to the human agent dialog interface. Releasing the AI conversation robot resource, and updating the AI conversation robot state array and the AI conversation robot resource pool.
Further, step 107, determining whether other human agents that do not have a binding relationship with the AI conversation robot have a second idle human agent, if so, notifying the second idle human agent, and taking over the AI conversation robot by the second idle human agent to complete the customer service conversation.
Specifically, a notification message is pushed to a second idle human agent, the notification message is a screen flicking message, when the second idle human agent takes over the AI conversation robot, a second human agent conversation interface is created, and a history of a current conversation of the manually-intervened AI conversation robot is pushed to the second human agent conversation interface.
Based on the scheme, the coupling between the robot customer service and the manual seats can be coordinated, the number of simultaneous dialing of the control center is increased, the customer touch speed in unit time is higher, and the yield is high.
Example two
On the basis of the first embodiment, a dispatch method of man-machine coupled outbound is provided, referring to fig. 5, which is characterized in that,
step 201, determining condition parameters of an AI conversation robot, where the condition parameters of the AI conversation robot include a first condition parameter, a second condition parameter, and a third condition parameter, where the first condition parameter indicates an artificial seat state corresponding to the AI conversation robot, the second condition parameter indicates the AI conversation robot state, and the third condition parameter indicates whether the AI conversation robot is in a key conversation link;
step 202, determining candidate priority of the AI dialogue robot according to the first conditional parameter, the second conditional parameter and the third conditional parameter;
step 203, selecting N AI dialog robots meeting the distribution condition according to the candidate priority of the AI dialog robots;
and step 204, generating a distribution instruction, and distributing the connected line to the N AI conversation robots meeting the distribution condition.
The state of the artificial seat and the state of the AI dialog robot corresponding to the artificial seat in step 201 can be obtained through an AI dialog robot state array;
or acquiring an AI conversation robot state corresponding to the artificial seat through an AI conversation robot resource pool; and determining the artificial seat state through an AI conversation robot flag in the AI conversation robot resource pool or polling the artificial seat.
Preferably, the step 201 specifically further includes:
step 2012, judging whether the artificial seat meets a first preset condition, if the artificial seat meeting the first preset condition exists, executing step 2013,
step 2013, the AI conversation robots corresponding to the artificial seats meeting the first preset condition form a first candidate cluster; the AI conversation robots corresponding to the artificial agents which do not meet the first preset condition form a second candidate cluster;
step 2014, judging whether the AI conversation robots in the first candidate cluster and the second candidate cluster meet a second preset condition;
step 2015, performing secondary clustering on the first candidate cluster and the second candidate cluster according to whether the AI conversation robot meets a second preset condition, and performing first grouping marking on the AI conversation robot;
step 2016, determining whether the AI conversation robot which does not satisfy the second preset condition satisfies a third preset condition; and performing first sub-grouping marking on the AI conversation robot based on the third preset condition.
Specifically, the first preset condition is that the manual seat is idle, the second preset condition is that the AI conversation robot is idle, and the third preset condition is that the AI conversation robot is in a key conversation link.
Specifically, the step 2013 further includes constructing AI dialogue robot candidate mark information according to the clustering.
Wherein the AI conversation robot candidate mark information includes an AI conversation robot ID, and a primary clustering value. For example, the AI dialog robots AIN 1-Ni corresponding to the artificial agents satisfying the first preset condition form a first candidate cluster; AI conversation robots AI P1-Pj corresponding to the artificial agents which do not meet the first preset condition form a second candidate cluster; generating and storing corresponding AI dialogue robot candidate mark information: { AI conversation robot ID, primary clustering value }, e.g., { AIN2, 0}, { AI P1, 1}, where a primary clustering value of "0" represents that a first preset condition is satisfied, i.e., that the artificial seat corresponding to the AI conversation robot is idle, and a primary clustering value of "1" represents that a first preset condition is not satisfied, i.e., that the artificial seat corresponding to the AI conversation robot is busy.
And if the AI dialog robot meeting/not meeting the first preset condition is 0, the corresponding member in the candidate cluster is empty.
Specifically, in the step 2015, performing secondary clustering on the first candidate cluster and the second candidate cluster according to whether the AI conversation robot meets a second preset condition, and performing the first grouping marking on the AI conversation robot further includes
Dividing the first candidate cluster into a first candidate group and a second candidate group according to a second preset condition; and dividing the second candidate cluster into a third candidate group and a fourth candidate group.
And if the AI conversation robot meeting/not meeting the second preset condition is 0, the corresponding member in the candidate packet is null.
Preferably, the corresponding AI conversation robot candidate mark information is updated and stored according to the first packet mark;
specifically, after the second preset condition is determined, for example, AI dialog robots AI N1 to Ni corresponding to the artificial seats satisfying the first preset condition; AI conversation robots AI P1-Pj corresponding to the artificial agents which do not meet the first preset condition; and further dividing the information into a plurality of groups, updating and storing corresponding AI conversation robot candidate mark information: { AI dialog robot ID, primary clustering value, secondary grouping value }, e.g., { AI N2, 0, 1}, { AI P1, 1, 0}, where a secondary grouping value of "0" indicates that a second preset condition is met, i.e., that the AI dialog robot is currently idle, and a secondary grouping value of "1" indicates that a second preset condition is not met, i.e., that the AI dialog robot is busy.
Specifically, step 2016, determine whether the AI conversation robot that does not satisfy the second preset condition satisfies a third preset condition; based on the third preset condition, the marking the AI conversation robot by the first subgroup specifically includes:
acquiring the current conversation record of the AI conversation robots which do not meet the second preset condition in real time, specifically, watching or listening to the conversation process of each AI conversation robot in real time through the AI workbench corresponding to the human agent,
for example, the dialog process of the AI dialog robot is recorded in real time, and the dialog process can directly store and play voice information or be presented in real time on a corresponding dialog interface of the AI dialog robot through text conversion.
The AI workbench of the artificial seat extracts corresponding keyword data and/or user state information based on multiple rounds of conversations of the AI conversation robot, and analyzes the intervention requirement of the current conversation.
For example, the actual intention of the user is determined by extracting corresponding keyword data in the dialog, or the current state information of the user is determined by analyzing the tone and tone in the voice information of the user. For example, if the user has further willingness to communicate and tends to subscribe, but is in a machine conversation fidgetiness state, it is determined that the current AI conversation robot is in a key conversation link, that is, the client has an intervention requirement.
Furthermore, the intervention demands can be graded according to the urgency degree of the intervention demands. Wherein the urgency level can be determined according to one or more of conversation duration, conversation content, conversation party attribute, conversation party level and current conversation category.
And when the current AI conversation robot is determined to be in the key conversation link, carrying out first sub-grouping marking on the AI conversation robot in the key conversation link.
For example, for a first candidate group, a second candidate group, a third candidate group, and a fourth candidate group that are further determined after the second preset condition is performed, a first sub-group marking is performed on the AI conversation robot in the key conversation link in the group, and corresponding AI conversation robot candidate marking information is updated and stored: { AI conversation robot ID, primary clustering value, secondary clustering value, tertiary sub-clustering value }, e.g., { AI N2, 0, 1}, preferably, AI conversation robot candidate flag information of other AI conversation robots not subject to the first sub-clustering flag, e.g., { AI P1, 1, 0}, or { AI N1, 0, 1, 0 }; the third-level sub-grouping value "1" represents that the third preset condition is met, that is, the AI conversation robot is currently in the key conversation link, the third-level sub-grouping value "0" represents that the third preset condition is not met, that is, the AI conversation robot is busy, but is not in the key conversation link, and in addition, when the second-level grouping value "0" represents that the second preset condition is met, that is, the AI conversation robot is currently idle, the third-level sub-grouping value is updated to "0" based on default.
Specifically, the step 202 of determining the candidate priority of the AI conversation robot according to the first condition parameter, the second condition parameter, and the third condition parameter further includes:
obtaining candidate marking information of the AI conversation robot, and determining the priority of the alternative AI conversation robot based on a first-level clustering value, a second-level grouping value and a third-level sub-grouping value in the candidate marking information of the AI conversation robot.
The first conditional parameter, the second conditional parameter and the third conditional parameter respectively have a mapping relation with a first-level clustering value, a second-level grouping value and a third-level sub-grouping value.
For example for { AI N2, 0, 1}, { AI P1, 1, 0}, { AI N1, 0, 1, 0 };
determining 3-bit information according to the first-level clustering value, the second-level grouping value and the third-level sub-grouping: 000, 010, 011, 100, 110, 111; for example, three levels of priority are set, with 000 as the first priority level, 100 as the second priority level, 011 as the third priority level, and 110 and 111 as the fourth priority level.
Preferably, the step 202 of determining the candidate priority of the AI conversation robot according to the first condition parameter, the second condition parameter, and the third condition parameter further includes:
determining the candidate priority of the AI conversation robot according to the first, second, third, and fourth condition parameters further includes:
further, three-level sub-grouping values of other AI conversation robots in the corresponding artificial agents of the AI conversation robots are counted, calculation is performed on the three-level sub-grouping values of the other AI conversation robots, and four-level correlation values are determined. Wherein the fourth condition parameter indicates an artificial agent status prediction, which has a mapping relationship with the four-level correlation value.
For example, for AI a2, if it belongs to the artificial agent a, traversing the tertiary subgroup values of the AI dialog robot corresponding to the artificial agent a, and if the tertiary subgroup value is 1, determining the quaternary association value to be 1, and if the tertiary subgroup values of the AI dialog robot corresponding to the artificial agent a are all 0, determining the quaternary association value to be 0.
Specifically, in this scenario, the AI conversation robot candidate flag information includes the AI conversation robot ID, and 4-bit flag information: for example, 0000, 0001, 0101, 0100, 0111, 1000, 1001, 1100, 1101, 1111 are arranged in plural priority levels, where 0000 is the first priority level, 1000, 0001 is the second priority level, 0100 is the third priority level, and 0111, 1100, 1101, 1111 is the fourth priority level.
Specifically, in step 204, generating a distribution instruction, and distributing the connected line to the N AI conversation robots meeting the distribution condition includes:
distributing the connected lines based on the candidate priorities;
when the number of the AI dialogue robots with the first priority level is larger than or equal to the number of the lines to be communicated, selecting the AI dialogue robots with the first priority level;
when the number of the AI conversation robots of the first priority level is less than that of the lines to be switched on, distributing the redundant lines to the AI conversation robots of the lower priority levels.
Further comprising after said step 204:
step 205, monitoring the response of the AI session robot, and judging whether manual intervention is needed; if human intervention is required, go to step 206;
and step 206, pushing a notification message to a manual agent to prompt the manual agent that the AI conversation robot needs conversation intervention.
The steps 205-206 are similar to the steps 103-104 in the first embodiment.
The method may further include a step 207 of determining whether the first human seat bound to the AI conversation robot is idle.
Specifically, determining candidate marking information of an AI (artificial intelligence) conversation robot, and determining a first artificial seat bound with the AI conversation robot;
and acquiring the current state of the first artificial seat bound with the AI conversation robot.
Judging whether a first manual seat bound with the AI conversation robot is idle or not;
and step 208, replacing the AI conversation robot by the first manual seat to complete the customer service conversation.
Specifically, for example, if human agent a performs human intervention, a new human agent dialog interface is created, and the history of the current dialog of the AI dialog robot that is manually intervened is pushed to the human agent dialog interface. Releasing the AI conversation robot resource, and updating the AI conversation robot state array and the AI conversation robot resource pool.
Further, step 209, determining whether there is a second idle human agent in other human agents that do not have a binding relationship with the AI conversation robot, if there is a second idle human agent, notifying the second idle human agent, and taking over the AI conversation robot by the second idle human agent to complete the customer service conversation.
Preferably, the step 206 of pushing a notification message to a human agent to prompt the human agent that the AI conversation robot needs conversation intervention further may include:
determining said AI dialog robot candidate tag information, e.g., { AI dialog robot ID, first-level clustering value, second-level grouping value, third-level sub-grouping value, fourth-level association value },
and if the first-level clustering value and the fourth-level correlation value corresponding to the AI conversation robot are both '0', determining a first manual seat corresponding to the AI conversation robot, and initiating screen flicking reminding to the first manual seat.
And when the primary clustering value or the four-level correlation value corresponding to the AI conversation robot is 1, inquiring the ID of the AI conversation robot of which the primary clustering value and the four-level correlation value are both '0' in the candidate marking information of the AI conversation robot, determining a third artificial seat corresponding to the ID of the AI conversation robot, and initiating a screen popup prompt to the third artificial seat.
Furthermore, a first manual agent corresponding to the AI conversation robot can be directly determined, a screen popup prompt is initiated to the first manual agent, the screen popup prompt can be configured to be provided with a first control, and the first manual agent can operate the first control to trigger screen popup scheduling when the first manual agent cannot intervene.
After screen popup scheduling is triggered, an AI conversation robot ID with a first-level clustering value and a fourth-level correlation value both being 0 in the AI conversation robot candidate marking information can be queried, a third artificial seat corresponding to the AI conversation robot ID is determined, and screen popup prompting is initiated to the third artificial seat.
The above-mentioned manual intervention manner can also be applied to the first embodiment, and similar manual intervention is realized.
By the man-machine coupling type outbound scheduling method of the second embodiment, the state of the agent is predicted, and according to the dialing condition of the AI conversation robot of each agent, the state of the AI conversation robot, whether the AI conversation robot is in a key conversation link or not, and the connected line is distributed in a prediction mode, so that the working time of the artificial agent can be prolonged, and call loss is reduced.
EXAMPLE III
On the basis of the foregoing embodiment, referring to fig. 6, a third embodiment provides an artificial seat AI workbench control method, which is characterized in that,
step 301, monitoring the working state of the AI conversation robot; the working state of the AI conversation robot comprises information of a busy/idle state of the AI conversation robot and a conversation record of the AI conversation robot when the AI conversation robot is in the busy state;
step 302, receiving a display instruction, and displaying label information of the AI conversation robot, a working state of the AI conversation robot and a conversation record on a display device of an artificial agent AI workbench based on the display instruction;
step 303, judging whether a preset popup screen triggering condition is met, and triggering popup screen scheduling if the preset popup screen triggering condition is met;
and 304, selecting an artificial seat based on the screen popup scheduling, and displaying screen popup information on a display device of an AI workbench of the artificial seat.
Referring to fig. 7, the AI workbench of the human agent can monitor the working state of each AI conversation robot, and display key information such as the working state, conversation record, label and the like of each AI in a card mode, and when the AI requires the intervention of the human agent, the AI workbench notifies the human agent through a pop-up screen, and the human agent can also find important customers and then intervene in advance through the card.
In particular, the amount of the solvent to be used,
step 301, monitoring the working state of the AI conversation robot includes:
storing conversation records of the conversation process of the AI conversation robot in real time, wherein the conversation records can be used for directly storing voice information and/or storing corresponding text information through text conversion;
indexing a conversation record of the AI conversation robot based on the AI conversation robot ID;
the dialogue information of the AI dialogue robot comprises recorded voice information and character information converted in real time based on the voice confidence, and the voice information and the character information are both marked with time records.
Acquiring an AI conversation robot state array and/or AI conversation robot candidate mark information,
the AI conversation robot state array and/or AI conversation robot candidate tag information may be determined in the manner of the previous embodiment.
Determining busy-idle state information of the AI conversation robot based on the AI conversation robot state array and/or the AI conversation robot candidate tag information,
and when the AI conversation robot is in a busy state, searching the conversation record of the AI conversation robot through the ID of the AI conversation robot.
Specifically, the step 302 of receiving a display instruction, displaying the tag information of the AI dialog robot on a display device of an artificial agent AI workbench based on the display instruction, and the working state and the dialog record of the AI dialog robot specifically include:
when the AI conversation robot is in a busy state, triggering a conversation display instruction;
and displaying a dialog interface corresponding to the AI dialog robot in a card form based on the display instruction, wherein the dialog interface corresponding to the AI dialog robot shows that the tag information of the AI dialog robot, the working state of the AI dialog robot and a dialog record are contained.
Specifically, classifying the AI conversation robots in a plurality of busy states based on tag information of the AI conversation robots;
extracting key information of a conversation record of the AI conversation robot in a busy state, constructing a conversation information map based on the key information, and performing optimization training on the AI conversation robot based on the conversation information map of the conversation record of the AI conversation robot with the same label information, thereby enriching the intelligent processing capacity of the AI conversation robot under the label information.
Furthermore, according to the conversation record displayed by the display device of the artificial seat AI workbench, the artificial seat can actively intervene in the conversation;
for example, when a human agent is attending a dialog record displayed on a display device of the human agent AI workstation and finds that supplementation is required for the dialog, a temporary insertion may be triggered.
Specifically, a second control is arranged on a dialog interface corresponding to the AI dialog robot, and the second control is used for triggering third-party dialog insertion;
triggering temporary dialog insertion by operating the second control;
specifically, a first temporary conversation is input through an input control of a conversation interface, and the first temporary conversation can be voice information or text information.
And further, carrying out voice conversion on the voice information and the character information to generate a first temporary voice response, and transmitting the converted first temporary voice response to the calling party.
Preferably, in step 303, it is determined whether a preset pop-up screen triggering condition is met, and if the preset pop-up screen triggering condition is met, the triggering of the pop-up screen scheduling further includes:
based on multiple rounds of dialogues of the AI dialog robot, corresponding keyword data and/or user state information are extracted, and intervention requirements of the current dialogues are analyzed.
And the preset screen popup triggering condition is that the client has an intervention requirement.
And determining the actual intention of the user by extracting corresponding keyword data in the conversation, or determining the current state information of the user by analyzing tone and tone in the voice information of the user. For example, if the user has further willingness to communicate and tends to subscribe, but is in a machine conversation fidgetiness state, it is determined that the current AI conversation robot is in a key conversation link, that is, the client has an intervention requirement. At this point, screen popup scheduling is triggered.
Specifically, the step 304 further comprises
Step 305, receiving a first input aiming at the screen flipping information, wherein the first input is first operation information based on the screen flipping information.
The screen popup reminding device can be configured with a first control, and when the first manual agent cannot intervene, screen popup scheduling can be triggered by operating the first control.
For example, when the human agent a is in a conversation, and at this time, there is a need for human intervention in a plurality of AI conversation robots corresponding to the human agent a, the pop-screen information is displayed on the display device of the AI workbench of the human agent a, and the pop-screen information may include a first control, such as a transfer pop-screen. At the moment, the manual agent A can transfer the screen flicking information to other idle manual agents by clicking the first control.
Based on the embodiment, the working state of each AI robot is monitored visually through the control method of the artificial seat AI workbench, the client touch speed in unit time is increased through third-party conversation intervention and screen popup scheduling, call loss is reduced, and call efficiency is improved.
Example four
Referring to fig. 8, this embodiment provides a call device coupled to a man machine, corresponding to the method of the first embodiment, wherein,
a first judging module for judging whether a plurality of calls originating simultaneously are connected,
the distribution control module distributes the communicated one or more calls to an artificial intelligent AI conversation robot, the AI conversation robot carries out initial response, and the AI has a binding relationship between the telephone robot and the artificial seat;
the dialogue monitoring module monitors the response of the AI dialogue robot and judges whether manual intervention is needed; if manual intervention is needed, sending a first trigger message to a message pushing module;
and the message pushing module is used for pushing a notification message to the artificial seat to prompt the artificial seat that the AI conversation robot needs conversation intervention.
Preferably, the device further comprises
The query module is used for querying the AI conversation robot resource pool;
an AI conversation robot selection module selecting one or more AI conversation robots from the AI conversation robot resource pool based on a predetermined rule,
and the distribution control module is used for distributing the communicated one or more calls to the selected AI conversation robot.
Preferably, the device further comprises
The second judgment module monitors the dialogue information of the AI dialogue robot through the artificial seat correspondingly bound by the AI dialogue robot and selects whether to intervene;
the monitoring mode is to monitor the real-time dialogue text of the AI and the client or the voice information, wherein the state of the client can be obtained through the voice information.
Preferably, the message pushing module is used for
Pushing a notification message to an artificial agent having a binding relationship with the AI conversation robot;
wherein, the manual seat is informed through the screen flipping; and controlling the pop-up screen to be displayed on display equipment corresponding to the artificial seat, wherein the display equipment synchronously displays one or more conversation interfaces corresponding to the AI conversation robot of the artificial seat, and the pop-up screen is displayed on the uppermost layer of the display area.
EXAMPLE five
Referring to fig. 9, this embodiment provides a dispatch device for man-machine coupled outbound corresponding to the method of the second embodiment, characterized in that the device comprises
The parameter acquisition module is used for determining condition parameters of an AI (artificial intelligence) conversation robot, wherein the condition parameters of the AI conversation robot comprise a first condition parameter, a second condition parameter and a third condition parameter, the first condition parameter indicates an artificial seat state corresponding to the AI conversation robot, the second condition parameter indicates the state of the AI conversation robot, and the third condition parameter indicates whether the AI conversation robot is in a key conversation link;
the priority determining module is used for determining candidate priorities of the AI conversation robots according to the first conditional parameter, the second conditional parameter and the third conditional parameter;
the selection control module selects N AI conversation robots meeting the distribution conditions according to the candidate priorities of the AI conversation robots;
and the distribution control module generates a distribution instruction and distributes the connected line to the N AI conversation robots meeting the distribution condition.
The parameter obtaining module specifically further includes:
the condition judging module is used for judging whether the artificial seat meets a first preset condition or not, if the artificial seat meeting the first preset condition exists, a notification message is sent to the classification control module,
the classification control module is used for forming a first candidate cluster by the AI conversation robots corresponding to the artificial agents meeting the first preset condition; forming a second candidate cluster by the AI conversation robots corresponding to the artificial seats which do not meet the first preset condition;
the condition judgment module is further used for judging whether the AI conversation robots in the first candidate cluster and the second candidate cluster meet a second preset condition or not;
the classification control module is used for performing secondary clustering on the first candidate cluster and the second candidate cluster according to whether the AI conversation robot meets a second preset condition, and performing first grouping marking on the AI conversation robot;
the condition judgment module is further used for determining whether the AI conversation robot which does not meet the second preset condition meets a third preset condition; and performing first sub-grouping marking on the AI conversation robot based on the third preset condition.
The priority determination module is further configured to:
obtaining candidate marking information of the AI conversation robot, and determining the priority of the alternative AI conversation robot based on a first-level clustering value, a second-level grouping value and a third-level sub-grouping value in the candidate marking information of the AI conversation robot.
The distribution control module is further configured to:
distributing the connected lines based on the candidate priorities;
when the number of the AI dialogue robots with the first priority level is larger than or equal to the number of the lines to be communicated, selecting the AI dialogue robots with the first priority level;
when the number of the AI conversation robots of the first priority level is less than that of the lines to be switched on, distributing the redundant lines to the AI conversation robots of the lower priority levels.
EXAMPLE six
Referring to fig. 10, this embodiment provides an artificial seat AI table control apparatus, corresponding to the method of the third embodiment, characterized in that,
the real-time conversation monitoring module monitors the working state of the AI conversation robot; the working state of the AI conversation robot comprises information of a busy/idle state of the AI conversation robot and a conversation record of the AI conversation robot when the AI conversation robot is in the busy state;
the display control module receives a display instruction, and displays the label information of the AI conversation robot, the working state of the AI conversation robot and the conversation record on a display device of an artificial seat AI workbench based on the display instruction;
the screen popping triggering judgment module is used for judging whether preset screen popping triggering conditions are met or not, and triggering screen popping scheduling if the preset screen popping triggering conditions are met;
and the screen popup scheduling module selects an artificial seat based on the screen popup scheduling, and displays screen popup information on a display device of an AI workbench of the artificial seat.
The real-time conversation monitoring module further comprises a conversation storage module which is used for storing conversation
Storing conversation records of the conversation process of the AI conversation robot in real time, wherein the conversation records can be used for directly storing voice information and/or storing corresponding text information through text conversion;
wherein the session record of the AI session robot is indexed based on the AI session robot ID;
the dialogue information of the AI dialogue robot comprises recorded voice information and character information converted in real time based on the voice confidence, and the voice information and the character information are both marked with time records.
The display control module is further used for
When the AI conversation robot is in a busy state, triggering a conversation display instruction;
and displaying a dialog interface corresponding to the AI dialog robot in a card form based on the display instruction, wherein the dialog interface corresponding to the AI dialog robot shows that the tag information of the AI dialog robot, the working state of the AI dialog robot and a dialog record are contained.
The device also comprises
An input module that receives a first input for the popup information, the first input being first operation information based on the popup information;
the screen popup reminding device can be configured with a first control, and when the first manual agent cannot intervene, screen popup scheduling can be triggered by operating the first control.
The invention also provides a terminal device, characterized in that it comprises a processor and a memory, in which a computer program is stored that is executable on the processor, said computer program implementing the method as described above when executed by the processor.
The invention provides a computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program is executable on a processor, and when executed implements a method as described above.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. The computer-readable storage medium may include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, or a combination thereof.
The above description is only an example for the convenience of understanding the present invention, and is not intended to limit the scope of the present invention. In the specific implementation, a person skilled in the art may change, add, or reduce the components of the apparatus according to the actual situation, and may change, add, reduce, or change the order of the steps of the method according to the actual situation without affecting the functions implemented by the method.
While embodiments of the invention have been shown and described, it will be understood by those skilled in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents, and all changes that come within the meaning and range of equivalency of the claims are to be embraced within their scope.
Claims (10)
1. A man-machine coupled calling method is characterized in that,
step 101, judging whether a plurality of calls initiated at the same time are connected, if yes, executing step 102;
102, distributing the one or more connected calls to an artificial intelligent AI conversation robot, and carrying out initial response by the AI conversation robot, wherein the AI has a binding relationship with the telephone robot and the artificial seat;
103, monitoring the response of the AI conversation robot, and judging whether manual intervention is needed; if human intervention is required, go to step 104;
and 104, pushing a notification message to a manual agent to prompt the manual agent that the AI conversation robot needs conversation intervention.
2. The method according to claim 1, wherein in step 102, distributing the connected one or more calls to an Artificial Intelligence (AI) dialog robot specifically comprises
Step 1021, inquiring an AI conversation robot resource pool;
step 1022, selecting one or more AI conversation robots from the AI conversation robot resource pool based on a predetermined rule,
and 1023, distributing the connected one or more calls to the selected AI conversation robot.
3. The method of claim 1, wherein the step 103 of monitoring the AI dialog robot for responses further comprises:
monitoring the dialogue information of the AI dialogue robot through an artificial seat correspondingly bound to the AI dialogue robot, and selecting whether to intervene;
the monitoring mode is to monitor the real-time dialogue text of the AI and the client or the voice information, wherein the state of the client can be obtained through the voice information.
4. The method of claim 1, wherein pushing a notification message to a human agent in step 104 further comprises
Pushing a notification message to an artificial agent having a binding relationship with the AI conversation robot;
wherein, the manual seat is informed through the screen flipping; and controlling the pop-up screen to be displayed on display equipment corresponding to the artificial seat, wherein the display equipment synchronously displays one or more conversation interfaces corresponding to the AI conversation robot of the artificial seat, and the pop-up screen is displayed on the uppermost layer of the display area.
5. A man-machine coupled calling device is characterized in that,
a first judging module for judging whether a plurality of calls originating simultaneously are connected,
the distribution control module distributes the communicated one or more calls to an artificial intelligent AI conversation robot, the AI conversation robot carries out initial response, and the AI has a binding relationship between the telephone robot and the artificial seat;
the dialogue monitoring module monitors the response of the AI dialogue robot and judges whether manual intervention is needed; if manual intervention is needed, sending a first trigger message to a message pushing module;
and the message pushing module is used for pushing a notification message to the artificial seat to prompt the artificial seat that the AI conversation robot needs conversation intervention.
6. The apparatus of claim 5, further comprising
The query module is used for querying the AI conversation robot resource pool;
an AI conversation robot selection module selecting one or more AI conversation robots from the AI conversation robot resource pool based on a predetermined rule,
and the distribution control module is used for distributing the communicated one or more calls to the selected AI conversation robot.
7. The apparatus of claim 5, further comprising
The second judgment module monitors the dialogue information of the AI dialogue robot through the artificial seat correspondingly bound by the AI dialogue robot and selects whether to intervene;
the monitoring mode is to monitor the real-time dialogue text of the AI and the client or the voice information, wherein the state of the client can be obtained through the voice information.
8. The apparatus of claim 5, wherein the message pushing module is configured to push the message
Pushing a notification message to an artificial agent having a binding relationship with the AI conversation robot;
wherein, the manual seat is informed through the screen flipping; and controlling the pop-up screen to be displayed on display equipment corresponding to the artificial seat, wherein the display equipment synchronously displays one or more conversation interfaces corresponding to the AI conversation robot of the artificial seat, and the pop-up screen is displayed on the uppermost layer of the display area.
9. A terminal device, characterized in that the terminal device comprises a processor and a memory, in which a computer program is stored which is executable on the processor, which computer program, when being executed by the processor, carries out the method according to any one of claims 1 to 4.
10. A computer-readable storage medium, in which a computer program that is executable on a processor is stored, which computer program, when being executed, carries out the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110331266.4A CN113099046A (en) | 2021-03-26 | 2021-03-26 | Man-machine coupling type calling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110331266.4A CN113099046A (en) | 2021-03-26 | 2021-03-26 | Man-machine coupling type calling method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113099046A true CN113099046A (en) | 2021-07-09 |
Family
ID=76670716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110331266.4A Pending CN113099046A (en) | 2021-03-26 | 2021-03-26 | Man-machine coupling type calling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113099046A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113596267A (en) * | 2021-07-14 | 2021-11-02 | 成都人工智能呼叫产业园管理有限公司 | Artificial intelligence calling method, system, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110035187A (en) * | 2019-04-16 | 2019-07-19 | 浙江百应科技有限公司 | A method of realizing AI and operator attendance seamless switching in the phone |
| US10381006B1 (en) * | 2018-11-26 | 2019-08-13 | Accenture Global Solutions Limited | Dialog management system for using multiple artificial intelligence service providers |
| CN110956472A (en) * | 2019-11-06 | 2020-04-03 | 深圳市一号互联科技有限公司 | Application method of man-machine coupling intelligent customer service platform |
| CN112073588A (en) * | 2020-09-21 | 2020-12-11 | 浙江百应科技有限公司 | Call switching method for voice robot and manual seat |
-
2021
- 2021-03-26 CN CN202110331266.4A patent/CN113099046A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10381006B1 (en) * | 2018-11-26 | 2019-08-13 | Accenture Global Solutions Limited | Dialog management system for using multiple artificial intelligence service providers |
| CN110035187A (en) * | 2019-04-16 | 2019-07-19 | 浙江百应科技有限公司 | A method of realizing AI and operator attendance seamless switching in the phone |
| CN110956472A (en) * | 2019-11-06 | 2020-04-03 | 深圳市一号互联科技有限公司 | Application method of man-machine coupling intelligent customer service platform |
| CN112073588A (en) * | 2020-09-21 | 2020-12-11 | 浙江百应科技有限公司 | Call switching method for voice robot and manual seat |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113596267A (en) * | 2021-07-14 | 2021-11-02 | 成都人工智能呼叫产业园管理有限公司 | Artificial intelligence calling method, system, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3314873B1 (en) | System and method for intelligent task management and routing | |
| US10162685B2 (en) | System and method for intelligent task management and routing | |
| US7046789B1 (en) | TracM-task and resource automation for call center management | |
| CN108683818A (en) | Call center distributes method, system, equipment and the storage medium attended a banquet | |
| CN108989588A (en) | Calling allocation method, call center, electronic equipment and storage medium | |
| EP0802664A2 (en) | System and method for controlling and monitoring communication between customers and customer service representatives | |
| US20090136009A1 (en) | Knowledge Management, Capture and Modeling Tool for Multi-Modal Communications | |
| CN101888452A (en) | Multi-access customer service system and method thereof | |
| CN101645988B (en) | Next-generation call center system and queuing method thereof | |
| JP2022515483A (en) | Systems and methods for hybrid chat automation | |
| CN102546986A (en) | Call center, method of calling, client side and agent service side | |
| CN109669835A (en) | MySQL database monitoring method, device, equipment and readable storage medium storing program for executing | |
| US20220407958A1 (en) | System and Method of Capturing, Tracking, Composing, Analyzing and Automating Analog and Digital Interactions | |
| US7936868B2 (en) | Method and system for automatically generating flow charts of call flow programs | |
| CN113050509B (en) | Scheduling method and device for man-machine coupling type outbound call | |
| CN110070298A (en) | Call center's method for allocating tasks, system, equipment and storage medium | |
| CN107786759A (en) | Call queuing method and device based on Session Initiation Protocol | |
| Ahghari et al. | Benefits of cross-training in a skill-based routing contact center with priority queues and impatient customers | |
| CN109862197A (en) | A kind of New Call Center and its calling-out method | |
| CN109089001A (en) | A kind of intelligent customer service method of calling and its calling system | |
| CN113099046A (en) | Man-machine coupling type calling method and device | |
| CN104052883A (en) | Method, device and system for obtaining menu information | |
| CN104468764A (en) | Method, device and system for strategy scheduling | |
| CN102326376A (en) | Method, call centre and system for seat terminal to receive call | |
| CN101621591A (en) | Seat monitoring method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220110 Address after: 310024 floor 5, zone 2, building 3, Hangzhou cloud computing Industrial Park, Zhuantang street, Xihu District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou suddenly Cognitive Technology Co.,Ltd. Address before: 100083 gate 3, block a, 768 Creative Industry Park, Zhongguancun, No.5 Xueyuan Road, Haidian District, Beijing Applicant before: BEIJING MORAN COGNITIVE TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210709 |