CN111754061A - Method and device for controlling man-machine distribution, server equipment and storage medium - Google Patents
Method and device for controlling man-machine distribution, server equipment and storage medium Download PDFInfo
- Publication number
- CN111754061A CN111754061A CN201911163781.5A CN201911163781A CN111754061A CN 111754061 A CN111754061 A CN 111754061A CN 201911163781 A CN201911163781 A CN 201911163781A CN 111754061 A CN111754061 A CN 111754061A
- Authority
- CN
- China
- Prior art keywords
- consultation
- customer service
- machine
- human
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and a device for controlling man-machine shunting, server equipment and a storage medium, wherein the method comprises the following steps: when a consultation event is detected, determining a consultation scene corresponding to the current consultation event; when the human-computer difference value corresponding to the consultation scene is within a preset range, distributing the current consultation event to a corresponding customer service type according to a preset flow distribution condition, wherein the customer service type is machine customer service or manual customer service; when the human-computer difference value of the consultation scene exceeds a preset range, distributing the current consultation event to artificial customer service; the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene. The problem that the processing effect of a plurality of consultation events is poor due to the existing man-machine distribution mode of the consultation events is solved, and the technical effect of carrying out man-machine distribution on the consultation events on the premise of not reducing the processing effect of the consultation events is achieved.
Description
Technical Field
The embodiment of the invention relates to the field of computer software, in particular to a method and a device for controlling man-machine shunting, server equipment and a storage medium.
Background
In order to reduce the expenditure of customer service cost, more and more merchants introduce machine customer service, but it cannot be denied that the user experience of the machine customer service in many aspects is poor at present, so that the phenomenon that the machine customer service and the manual customer service coexist occurs. When the machine customer service and the human-computer customer service coexist, the continuously-occurring consultation events need to be distributed, so that part of the consultation events are distributed to the human-computer customer service to be processed, and part of the consultation events are distributed to the machine customer service to be processed.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: the adoption of the method of shunting the consultation events according to the user grade, the label information and the percentage of the consultation events can cause poor treatment effect of a plurality of consultation events.
Disclosure of Invention
The embodiment of the invention provides a method, a device, server equipment and a storage medium for controlling man-machine shunting, which aim to solve the problem that the man-machine shunting result of a consultation event in the prior art can cause poor processing effect of a plurality of consultation events, thereby realizing man-machine shunting of the consultation event on the premise of not reducing the processing effect of the consultation event.
In a first aspect, an embodiment of the present invention provides a method for controlling human-machine offload, including:
when a consultation event is detected, determining a consultation scene corresponding to the current consultation event;
when the human-computer difference value corresponding to the consultation scene is within a preset range, distributing the current consultation event to a corresponding customer service type according to a preset flow distribution condition, wherein the customer service type is machine customer service or manual customer service;
when the human-computer difference value of the consultation scene exceeds a preset range, distributing the current consultation event to artificial customer service;
the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene.
Further, the determining the consultation scene corresponding to the current consultation event includes:
determining a consultation intention corresponding to the current consultation event based on the trained intention classification model;
and determining a consultation scene corresponding to the current consultation event according to the determined consultation intention.
Further, the preset shunting conditions include:
the corresponding relation between the comparison result of the human-computer distribution ratio and the human-computer distribution threshold of the consultation scene to which the current consultation event belongs and the customer service type;
the human-computer distribution proportion is determined according to a preset switching interval of the consultation scene and a human-computer difference value, wherein the preset switching interval is used for expressing a percentage interval of distributing the consultation events of the consultation scene to human service or machine service.
Further, the man-machine shunt ratio is determined according to the following formula:
F＝(Max+Min)/M
wherein, F is a human-computer distribution ratio, Max is an upper limit value of a preset switching interval, Min is a lower limit value of the preset switching interval, M is a human-computer difference value, and M is a ratio of the machine customer service quality score to the manual customer service quality score in a corresponding consultation scene.
Further, if the man-machine shunt ratio exceeds the range of the preset switching interval, determining the difference between the upper limit value and the lower limit value of the preset switching interval and the man-machine shunt ratio respectively, and assigning the upper limit value or the lower limit value corresponding to the minimum difference to the man-machine shunt ratio so as to update the man-machine shunt ratio.
Further, the human-computer distribution threshold is a percentage of a hash value of a preset ID, where the preset ID is a PIN value of the user, a session ID of the current consultation event, or a message ID of the current consultation event.
Further, still include:
and counting the service quality scores of the artificial customer service and the service quality scores of the machine customer service of each consultation scene based on a preset counting period, and updating the human-computer difference value of each current consultation scene based on a counting result.
In a second aspect, an embodiment of the present invention further provides a device for controlling man-machine shunting, including:
the scene module is used for determining a consultation scene corresponding to the current consultation event when the consultation event is detected;
the distribution module is used for distributing the current consultation event to a corresponding customer service type according to a preset distribution condition when the man-machine difference value corresponding to the consultation scene is within a preset range, and the customer service type is machine customer service or manual customer service;
the orientation module is used for distributing the current consultation event to the artificial customer service when the human-computer difference value of the consultation scene exceeds a preset range;
the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene.
In a third aspect, an embodiment of the present invention further provides a server device, where the server device includes:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method for controlling human-machine offload according to any embodiment.
In a fourth aspect, the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the method for controlling human-machine offload according to any of the embodiments.
According to the technical scheme of the method for controlling the man-machine flow distribution, when a consultation event is detected, a consultation scene corresponding to the current consultation event is determined; when the human-computer difference value of the consultation scene is in a preset range, the service quality of the manual customer service and the service quality of the machine customer service for processing the consultation events under the consultation scene are equivalent, so that the processing effect of the consultation events is approximately equivalent finally no matter the current consultation events are distributed to the machine customer service or the manual customer service according to a preset distribution condition, namely, the processing effect difference is not larger due to different customer service types distributed by the consultation events; when the human-computer difference value of the consultation scene exceeds the preset range, the service quality of the manual customer service for the consultation event in the consultation scene is far higher than that of the machine customer service for the consultation event in the consultation scene, and at the moment, if the current consultation event is distributed to the machine customer service, the processing effect is very poor, so that the current consultation event is distributed to the manual customer service to obtain a higher processing effect. Therefore, compared with the prior art, the scheme of the embodiment can improve the processing effect of the consultation events to a greater extent, and can distribute the consultation events to the machine customer service as much as possible, so that the technical effect of reducing the cost of the customer service is achieved under the condition of improving the event processing effect.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, 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 flowchart of a method for controlling man-machine offload according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for controlling man-machine offload according to a second embodiment of the present invention;
fig. 3 is a block diagram of a device for controlling man-machine shunting according to a third embodiment of the present invention;
fig. 4 is a block diagram of a further apparatus for controlling human-machine offload according to a third embodiment of the present invention;
fig. 5 is a block diagram of a server device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through embodiments with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
Example one
Fig. 1 is a flowchart of a method for controlling man-machine offload according to an embodiment of the present invention. The technical scheme of the embodiment is suitable for the condition that the consultation events are allocated between the manual customer service and the machine customer service on the premise of not reducing the consultation event processing effect. The method can be executed by the device for controlling the man-machine shunt, which can be implemented in a software and/or hardware manner and configured to be applied in a processor. The method specifically comprises the following steps:
s101, when the consultation event is detected, determining a consultation scene corresponding to the current consultation event.
In order to facilitate the management of the consultation event, the corresponding relationship between the consultation event and the consultation scene needs to be established first. Therefore, when a new consultation event enters, the consultation scene corresponding to the current consultation event can be determined according to the current consultation event and the corresponding relation between the consultation event and the consultation scene. Taking e-commerce platform as an example, the consultation scenario generally includes orders, logistics, price guarantees, invoices, members, distribution, warranties, and the like.
Wherein, the corresponding relation between the consultation event and the consultation scene can be established through the trained intention classification model. After the trained intention classification model is determined, inputting the current consultation event into the trained intention classification model to determine the consultation intention corresponding to the current consultation event, and then determining the consultation scene corresponding to the current consultation event according to the determined consultation intention, for example, the consultation intentions of order modification, order cancellation and order state explanation all correspond to the same order scene; the electronic invoice, the invoice refund modification and the consultation intention related to the invoice increase all correspond to the invoice scene.
The human-machine difference value is used for representing the difference between the service quality of the machine customer service corresponding to the consultation scene and the service quality of the artificial customer service, and can be represented by the ratio of the machine customer service quality score and the artificial customer service quality score corresponding to the consultation scene, and the difference value is shown in table 1. The service quality is used for measuring the satisfaction degree of the customer to the service quality of the manual customer service or the machine customer service to the consultation event, and can be reflected by service quality scores fed back by the user through various ways, such as 100 points of very satisfactory service, 20 points of satisfactory service, 60 points of general satisfaction, 40 points of unsatisfactory service, 0 point of very unsatisfactory service and the like.
It is understood that the human-machine difference value can also be represented by a ratio between the manual customer service quality score of the corresponding consultation scene and the customer service quality score thereof. It should be noted that, if no special description is given, the man-machine difference values used in this embodiment and the following embodiments are: and the ratio of the machine customer service quality score to the artificial customer service quality score of the corresponding consultation scene.
It is understood that, in the present embodiment, the qos score of each advisory scenario is an average score, which is a ratio of the sum of the qos scores of all advisory events of the target advisory scenario within a certain statistical period to the number of all advisory events.
In order to ensure the accuracy of the human-computer difference value, the embodiment preferably counts the service quality scores of the artificial customer service and the machine customer service in each consultation scene based on a preset counting period, and updates the human-computer difference value of each current consultation scene based on a counting result.
TABLE 1 Man-machine difference value table
| Name of consultation scene | Manual customer service quality scoring | Machine customer service quality of service scoring | Human-machine difference value |
| Order form | 90.3 | 91.7 | 1.01 |
| Logistics | 89.7 | 90.3 | 1.01 |
| Price protector | 86.3 | 88.9 | 1.03 |
| Receipt | 91.3 | 86.3 | 0.95 |
| Member | 92.4 | 20.1 | 0.87 |
| Delivery system | 88.5 | 78.5 | 0.89 |
| Warranty repair | 83.5 | 73.2 | 0.88 |
And S102, when the man-machine difference value corresponding to the consultation scene is within a preset range, distributing the current consultation event to a corresponding customer service type according to a preset flow distribution condition, wherein the customer service type is machine customer service or manual customer service.
If the man-machine difference value corresponding to the consultation scene to which the current consultation event belongs is in the preset range, the service quality of the current consultation event by the machine customer service and the artificial customer service is equivalent, and the current consultation event can be distributed to the machine customer service or the artificial customer service according to the preset distribution condition.
Alternatively, the preset shunting condition may be a task amount, so that the current consultation event may be allocated to the one with the smaller task amount according to the current task amounts of the machine customer service and the manual customer service, so that the current consultation event may be solved earlier.
Alternatively, the preset diversion condition may be a randomly generated value of 0 to 1, for example, when the value is 0, the current consultation event is assigned to the machine customer service, and when the value is 1, the current consultation event is assigned to the manual customer service.
S103, when the human-computer difference value of the consultation scene exceeds a preset range, distributing the current consultation event to the artificial customer service.
In this embodiment, the preset range may be a range greater than or equal to a certain preset threshold, and when the human-computer difference value is a ratio of the machine customer service quality score to the artificial customer service quality score, the preset threshold is preferably a value less than 1. Therefore, when the human-computer difference value exceeds the preset range, the human-computer difference value is smaller than the preset threshold value, the machine customer service quality score is far smaller than the manual customer service quality score, and if the current consultation event is distributed to the machine customer service, the satisfaction degree of the client is low to a great extent.
It is understood that the human-machine difference value can also be expressed as a ratio between the artificial customer service quality score and the machine customer service quality score in the corresponding consultation scenario. The preset range may be expressed as a range less than or equal to a preset threshold, and the preset threshold is preferably a value greater than 1. When the human-computer difference value exceeds the preset range, the human-computer difference value is larger than the preset threshold value, and at the moment, the machine customer service quality score is far smaller than the artificial customer service quality score, namely, for the consultation event under the corresponding consultation scene, the machine customer service quality is far lower than the artificial customer service quality.
According to the technical scheme of the method for controlling the man-machine flow distribution, when a consultation event is detected, a consultation scene corresponding to the current consultation event is determined; when the human-computer difference value of the consultation scene is in a preset range, the service quality of the manual customer service and the service quality of the machine customer service for processing the consultation events under the consultation scene are equivalent, so that the processing effect of the consultation events is approximately equivalent finally no matter the current consultation events are distributed to the machine customer service or the manual customer service according to a preset distribution condition, namely, the processing effect difference is not larger due to different customer service types distributed by the consultation events; when the human-computer difference value of the consultation scene exceeds the preset range, the service quality of the manual customer service for the consultation event in the consultation scene is far higher than that of the machine customer service for the consultation event in the consultation scene, and at the moment, if the current consultation event is distributed to the machine customer service, the processing effect is very poor, so that the current consultation event is distributed to the manual customer service to obtain a higher processing effect. Therefore, compared with the prior art, the scheme of the embodiment can improve the processing effect of the consultation events to a greater extent, and can distribute the consultation events to the machine customer service as much as possible, thereby achieving the technical effect of greatly reducing the customer service cost under the condition of improving the event processing effect.
Example two
Fig. 2 is a flowchart of a method for controlling man-machine offload according to a second embodiment of the present invention. On the basis of the above embodiments, the embodiments of the present invention further describe the allocation of the current consultation event to the machine service or the manual service according to the preset diversion condition.
Correspondingly, the method of the embodiment comprises the following steps:
s201, when the consultation event is detected, determining a consultation scene corresponding to the current consultation event.
S202, when the man-machine difference value corresponding to the consultation scene is within a preset range, distributing the current consultation event to a corresponding customer service type according to a preset distribution condition, wherein the customer service type is machine customer service or artificial customer service, and the preset distribution condition comprises a corresponding relation between a comparison result of a man-machine distribution ratio and a man-machine distribution threshold value of the consultation scene to which the current consultation event belongs and the customer service type.
For example, if the human-machine distribution ratio of the consultation scene to which the current consultation event belongs is smaller than the human-machine distribution threshold, the current consultation event is distributed to the human-machine service, otherwise, the current consultation event is distributed to the machine service, and see table 2.
TABLE 2 Man-machine offload data
The human-computer shunt proportion is determined according to a preset switching interval of a consultation scene and a human-computer difference value, and can be determined through the following formula:
F＝(Max+Min)/M
wherein, F is a human-computer distribution ratio, Max is an upper limit value of a preset switching interval, Min is a lower limit value of the preset switching interval, M is a human-computer difference value, and M is a ratio of the machine customer service quality score to the manual customer service quality score in a corresponding consultation scene.
It can be understood that, since the difference between the machine service quality and the manual service quality in different consultation scenarios is different, the ratio between the two may be equal to 1, or greater than 1 or less than 1. Therefore, when the difference between the upper limit value of the preset switching interval and the lower limit value of the preset switching interval is small, the man-machine shunt ratio may be greater than the upper limit value of the preset switching interval or smaller than the lower limit value of the preset switching interval, that is, the man-machine shunt ratio may exceed the range of the preset switching interval. And if the man-machine shunt ratio exceeds the range of the preset switching interval, respectively determining the difference value between the upper limit value and the lower limit value of the preset switching interval and the current man-machine shunt ratio, and assigning the upper limit value or the lower limit value corresponding to the minimum difference value to the current man-machine shunt ratio so as to update the current man-machine shunt ratio.
Illustratively, the human-computer difference value of a certain scene is 0.8, and the preset switching interval is [80, 60 ]]Thus the man-machine split ratio is
And if the current man-machine shunting ratio is higher than the upper limit value 80 of the preset switching interval, updating the current man-machine shunting ratio to 80.
The man-machine separation threshold value is a percentage of a hash value of a preset ID, wherein the preset ID can be a PIN value of a user, a session ID of a current consultation event or a message ID of the current consultation event.
The preset switching interval is used for expressing a percentage interval of distributing the consultation events of the consultation scene to the human service or the machine service. For example, the human-machine difference value and the human-machine diversion threshold value are both unrelated to the preset switching interval, then for the preset switching interval [ a, B ], under the condition that B is kept unchanged, the upper limit value a is changed into a-S, the human-machine diversion ratio distributed among [ a-S, a ] is changed into a-S, namely the maximum value of the human-machine diversion ratio is reduced, then the human-machine diversion threshold value distributed among the [ a-S, a ] is possibly changed from being originally smaller than the human-machine diversion ratio into being larger than the human-machine diversion ratio, namely being changed from being distributed to the human-machine customer service into being distributed to the machine customer service, and therefore the number of consultation events distributed to the machine customer service is increased. On the contrary, under the condition that a is kept unchanged, the lower limit value B is changed into B + T, the human-machine distribution ratio distributed between [ B, B + T ] is changed into B + T, and then the human-machine distribution threshold value originally distributed between [ B, B + T ] may be changed from being originally larger than the human-machine distribution ratio into being smaller than the human-machine distribution ratio, that is, from being allocated to the machine service to being allocated to the manual service. Therefore, the user can modify the number of the consultation events distributed to the human customer service and the machine customer service by modifying the preset switching interval.
And S203, when the human-computer difference value of the consultation scene exceeds a preset range, distributing the current consultation event to the artificial customer service.
The method comprises the steps of determining a man-machine shunting proportion based on an upper limit value and a lower limit value of a preset switching interval and a man-machine difference value, determining a shunting object of a current consultation event according to the size relation between the man-machine shunting proportion and a man-machine shunting threshold value, and enabling a user to modify the number of the consultation events distributed to the machine customer service and the artificial customer service by modifying the range of the preset switching interval.
EXAMPLE III
Fig. 3 is a block diagram of a device for controlling man-machine offload according to a third embodiment of the present invention. The device is used for executing the method for controlling the man-machine shunt provided by any embodiment, and the device can be implemented by software or hardware. The device includes:
the scene module 11 is configured to determine a consultation scene corresponding to a current consultation event when the consultation event is detected;
the distribution module 12 is configured to distribute the current consultation event to a corresponding customer service type according to a preset distribution condition when the human-computer difference value corresponding to the consultation scene is within a preset range, where the customer service type is machine customer service or manual customer service;
the orientation module 13 is used for distributing the current consultation event to the artificial customer service when the human-computer difference value of the consultation scene exceeds a preset range; the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene.
Optionally, the scene module determines a consultation intention corresponding to the current consultation event based on the trained intention classification model; and determining a consultation scene corresponding to the current consultation event according to the determined consultation intention.
As shown in fig. 4, the apparatus further includes an updating module 10, configured to count the quality of service scores of the artificial customer service and the quality of service scores of the machine customer service in each consultation scene based on a preset counting period, and update the human-machine difference value in each current consultation scene based on a counting result.
According to the technical scheme of the device for controlling the man-machine flow distribution, when the consultation event is detected through the scene module, the consultation scene corresponding to the current consultation event is determined; when the human-computer difference value corresponding to the consultation scene is within a preset range, the current consultation event is distributed to the corresponding customer service type according to a preset distribution condition through the distribution module, and the customer service type is machine customer service or manual customer service; when the human-computer difference value of the consultation scene exceeds a preset range, the orientation module allocates the current consultation event to the artificial customer service; the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene. When the service quality of the manual customer service and the service quality of the machine customer service are the same when processing the current consultation event, the current consultation event is distributed to the machine customer service or the manual customer service according to the preset distribution condition, and when the service quality of the manual customer service for processing the current consultation event is higher than the service quality of the machine customer service for processing the current consultation event, the current consultation event is distributed to the manual customer service, so that the consultation event distribution is realized under the condition of not reducing the service quality, and the processing effect of the consultation event is greatly improved.
The device for controlling human-computer shunt provided by the embodiment of the invention can execute the method for controlling human-computer shunt provided by any embodiment of the invention, has corresponding functional modules and beneficial effects of the execution method, and the technical details which are not detailed in the embodiment are referred to the embodiment.
Example four
Fig. 5 is a schematic structural diagram of a server apparatus according to a fourth embodiment of the present invention, as shown in fig. 5, the apparatus includes a processor 201, a memory 202, an input device 203, and an output device 204; the number of the processors 201 in the device may be one or more, and one processor 201 is taken as an example in fig. 5; the processor 201, the memory 202, the input device 203 and the output device 204 in the apparatus may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The memory 202, as a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules (e.g., the scene module 11, the diversion module 12, and the orientation module 13) corresponding to anti-corrosion for controlling human-machine diversion in embodiments of the present invention. The processor 201 executes various functional applications and data processing of the device by executing software programs, instructions and modules stored in the memory 202, that is, the method for controlling the man-machine shunt is realized.
The memory 202 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 202 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 202 may further include memory located remotely from the processor 201, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 203 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the apparatus.
The output device 204 may include a display device such as a display screen, for example, of a user terminal.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to perform a method for controlling human-machine offload, where the method includes:
when a consultation event is detected, determining a consultation scene corresponding to the current consultation event;
when the human-computer difference value corresponding to the consultation scene is within a preset range, distributing the current consultation event to a machine customer service or a manual customer service according to a preset flow distribution condition;
when the human-computer difference value of the consultation scene exceeds a preset range, distributing the current consultation event to artificial customer service;
the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the method for controlling human-machine offload provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, where the computer software product may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute the method for controlling man-machine offload according to the embodiments of the present invention.
It should be noted that, in the embodiment of the apparatus for controlling human-machine flow distribution, each unit and each module included in the apparatus are only divided according to functional logic, but are not limited to the above division, as long as the corresponding function can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method of controlling human-machine diversion, comprising:
when a consultation event is detected, determining a consultation scene corresponding to the current consultation event;
when the human-computer difference value corresponding to the consultation scene is within a preset range, distributing the current consultation event to a corresponding customer service type according to a preset flow distribution condition, wherein the customer service type is machine customer service or manual customer service;
when the human-computer difference value of the consultation scene exceeds a preset range, distributing the current consultation event to artificial customer service;
the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene.
2. The method of claim 1, wherein the determining the advisory scenario corresponding to the current advisory event comprises:
determining a consultation intention corresponding to the current consultation event based on the trained intention classification model;
and determining a consultation scene corresponding to the current consultation event according to the determined consultation intention.
3. The method of claim 1, wherein the preset splitting conditions comprise:
the corresponding relation between the comparison result of the human-computer distribution ratio and the human-computer distribution threshold of the consultation scene to which the current consultation event belongs and the customer service type;
the human-computer distribution proportion is determined according to a preset switching interval of the consultation scene and a human-computer difference value, wherein the preset switching interval is used for expressing a percentage interval of distributing the consultation events of the consultation scene to human service or machine service.
4. The method of claim 3, wherein the human-machine split ratio is determined according to the following formula:
F＝(Max+Min)/M
wherein, F is a human-computer distribution ratio, Max is an upper limit value of a preset switching interval, Min is a lower limit value of the preset switching interval, M is a human-computer difference value, and M is a ratio of the machine customer service quality score to the manual customer service quality score in a corresponding consultation scene.
5. The method according to claim 4, wherein if the man-machine split ratio exceeds the range of the preset switching interval, the difference between the upper limit value and the lower limit value of the preset switching interval and the man-machine split ratio is determined, and the upper limit value or the lower limit value corresponding to the minimum difference is assigned to the man-machine split ratio to update the man-machine split ratio.
6. The method of claim 3, wherein the man-machine offload threshold is a percentage of a hash value of a preset ID, wherein the preset ID is a PIN value of the user, a session ID of the current consultation event, or a message ID of the current consultation event.
7. The method according to any one of claims 1-6, further comprising:
and counting the service quality scores of the artificial customer service and the service quality scores of the machine customer service of each consultation scene based on a preset counting period, and updating the human-computer difference value of each current consultation scene based on a counting result.
8. A device for controlling man-machine shunting, characterized by comprising:
the scene module is used for determining a consultation scene corresponding to the current consultation event when the consultation event is detected;
the distribution module is used for distributing the current consultation event to a corresponding customer service type according to a preset distribution condition when the man-machine difference value corresponding to the consultation scene is within a preset range, and the customer service type is machine customer service or manual customer service;
the orientation module is used for distributing the current consultation event to the artificial customer service when the human-computer difference value of the consultation scene exceeds a preset range;
the human-computer difference value is used for representing the difference between the service quality of the machine customer service and the service quality of the artificial customer service corresponding to the consultation scene.
9. A server apparatus, characterized in that the apparatus comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of controlling human-machine offload according to any of claims 1-7.
10. A storage medium containing computer-executable instructions for performing the method of controlling human-machine offload according to any of claims 1-7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911163781.5A CN111754061A (en) | 2019-11-22 | 2019-11-22 | Method and device for controlling man-machine distribution, server equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911163781.5A CN111754061A (en) | 2019-11-22 | 2019-11-22 | Method and device for controlling man-machine distribution, server equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111754061A true CN111754061A (en) | 2020-10-09 |
Family
ID=72672884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911163781.5A Pending CN111754061A (en) | 2019-11-22 | 2019-11-22 | Method and device for controlling man-machine distribution, server equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754061A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379229A (en) * | 2021-06-08 | 2021-09-10 | 北京沃东天骏信息技术有限公司 | Resource scheduling method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243745A1 (en) * | 2007-03-31 | 2008-10-02 | Mitchell Kwok | Human Level Artificial Intelligence Software Application for Machine & Computer Based Program Function |
| CN105072173A (en) * | 2015-08-03 | 2015-11-18 | 谌志群 | Customer service method and system for automatically switching between automatic customer service and artificial customer service |
| CN105808652A (en) * | 2016-02-26 | 2016-07-27 | 北京京东尚科信息技术有限公司 | Realization method and device of online customer services |
| CN107590159A (en) * | 2016-07-08 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
| CN108418981A (en) * | 2018-03-16 | 2018-08-17 | 苏州思必驰信息科技有限公司 | The method and device of dialogue service is provided for client |
| CN108769440A (en) * | 2018-06-06 | 2018-11-06 | 北京京东尚科信息技术有限公司 | Preposition shunt method and device |
| CN109189898A (en) * | 2018-07-27 | 2019-01-11 | 北京新广视通科技有限公司 | A kind of intelligent response method and system |
| CN110033281A (en) * | 2018-01-11 | 2019-07-19 | 中兴通讯股份有限公司 | A kind of method and device that intelligent customer service is converted to artificial customer service |
| CN110457453A (en) * | 2019-07-12 | 2019-11-15 | 平安普惠企业管理有限公司 | Customer problem and customer service interconnection method, device, medium, electronic equipment |
-
2019
- 2019-11-22 CN CN201911163781.5A patent/CN111754061A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243745A1 (en) * | 2007-03-31 | 2008-10-02 | Mitchell Kwok | Human Level Artificial Intelligence Software Application for Machine & Computer Based Program Function |
| CN105072173A (en) * | 2015-08-03 | 2015-11-18 | 谌志群 | Customer service method and system for automatically switching between automatic customer service and artificial customer service |
| CN105808652A (en) * | 2016-02-26 | 2016-07-27 | 北京京东尚科信息技术有限公司 | Realization method and device of online customer services |
| CN107590159A (en) * | 2016-07-08 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
| CN110033281A (en) * | 2018-01-11 | 2019-07-19 | 中兴通讯股份有限公司 | A kind of method and device that intelligent customer service is converted to artificial customer service |
| CN108418981A (en) * | 2018-03-16 | 2018-08-17 | 苏州思必驰信息科技有限公司 | The method and device of dialogue service is provided for client |
| CN108769440A (en) * | 2018-06-06 | 2018-11-06 | 北京京东尚科信息技术有限公司 | Preposition shunt method and device |
| CN109189898A (en) * | 2018-07-27 | 2019-01-11 | 北京新广视通科技有限公司 | A kind of intelligent response method and system |
| CN110457453A (en) * | 2019-07-12 | 2019-11-15 | 平安普惠企业管理有限公司 | Customer problem and customer service interconnection method, device, medium, electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379229A (en) * | 2021-06-08 | 2021-09-10 | 北京沃东天骏信息技术有限公司 | Resource scheduling method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110351375B (en) | Data processing method and device, computer device and readable storage medium | |
| US20200167847A1 (en) | Material display control method, device and system | |
| CN107103009B (en) | Data processing method and device | |
| CN110012075B (en) | Data transmission method and related equipment | |
| CN109615389A (en) | Electronic-payment transaction risk control method, device, server and storage medium | |
| CN107203883A (en) | A kind of risk control method and equipment | |
| CN112769943A (en) | Service processing method and device | |
| CN115617511A (en) | Resource data processing method and device, electronic equipment and storage medium | |
| CN111754061A (en) | Method and device for controlling man-machine distribution, server equipment and storage medium | |
| CN113608751B (en) | Operation method, device and equipment of reasoning service platform and storage medium | |
| CN108632085B (en) | Gray level user management method, device, platform and storage medium | |
| CN110753323A (en) | Card resource allocation method and server | |
| CN112188295B (en) | Video recommendation method and device | |
| CN104427118A (en) | Method for recommending contents and mobile terminal | |
| CN111881304B (en) | Author identification method, device, equipment and storage medium | |
| CN115794421A (en) | Resource allocation method and device and electronic equipment | |
| CN115357179A (en) | Display screen management method, display screen management device, electronic equipment and storage medium | |
| CN110460663B (en) | Data distribution method and device among distributed nodes, server and storage medium | |
| CN113822704A (en) | Method and device for calculating discount cost, electronic equipment and readable storage medium | |
| CN114463065A (en) | Pricing method, pricing device, computer equipment and storage medium | |
| CN114048010A (en) | Method, device, equipment and storage medium for controlling service timeout time | |
| CN110083438B (en) | Transaction distribution method, device, equipment and storage medium | |
| CN114358508A (en) | Work order distribution method, device, equipment and medium | |
| CN111144771A (en) | Method and device for determining wind evaluation strategy and computer storage medium | |
| CN112241889A (en) | Account detail repairing method, device, equipment 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 |