CN114117157A - Session processing method, device, computer equipment and storage medium - Google Patents
Session processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114117157A CN114117157A CN202111399976.7A CN202111399976A CN114117157A CN 114117157 A CN114117157 A CN 114117157A CN 202111399976 A CN202111399976 A CN 202111399976A CN 114117157 A CN114117157 A CN 114117157A
- Authority
- CN
- China
- Prior art keywords
- customer service
- service
- session
- content
- target
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title abstract description 13
- 230000004044 response Effects 0.000 claims abstract description 58
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000004590 computer program Methods 0.000 claims abstract description 25
- 230000000977 initiatory effect Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000008451 emotion Effects 0.000 claims description 40
- 238000004458 analytical method Methods 0.000 claims description 29
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The application relates to a session processing method, a session processing device, a computer device, a storage medium and a computer program product. The method comprises the following steps: receiving session content input in a customer service session window of a target service recipient; performing intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is larger than or equal to a preset threshold value, returning the response content to the target service receiver; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content; and after the reply content of the artificial customer service for the session content is obtained, returning the reply content to the target service receiver. By adopting the method, the efficiency of session processing can be improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a session processing method, an apparatus, a computer device, and a storage medium.
Background
With the development of artificial intelligence technology, an intelligent customer service technology appears, and the traditional intelligent customer service technology can utilize algorithms such as Natural Language Processing (NLP) and artificial intelligence machine learning (MACHINE LEARNING) and the like, and is combined with systems such as knowledge management and automatic question answering to have a conversation with a consultant, so that a quick and effective communication bridge is established between a seller and the consultant.
Although the current intelligent customer service can deal with some common and basic problems, the situation that the intelligent customer service cannot provide accurate service still exists. Under the condition that the intelligent customer service cannot provide accurate service, the consultant can perform service switching operation for switching to manual service, wait for switching to the manual customer service, and reestablish a session between the manual customer service and the consultant to provide the consultant service after switching to the manual customer service. Obviously, the method cannot avoid the problem that the reaction time of intelligent customer service to manual customer service is too long, thereby causing the reduction of conversation processing efficiency.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a session processing method, apparatus, computer device, computer readable storage medium and computer program product, which can improve efficiency.
In a first aspect, the present application provides a session processing method. The method comprises the following steps:
receiving session content input in a customer service session window of a target service recipient; a service head portrait corresponding to a service unit is displayed in the customer service session window; the service unit comprises a plurality of service providers which provide services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot;
performing intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability;
determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result;
if the intention identification probability is larger than or equal to a preset threshold value, returning the response content to the target service receiver so as to correspondingly display the response content and the service head portrait in a customer service session window;
if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content;
after the reply content of the manual customer service for the session content is acquired, the reply content is returned to the target service receiving party, so that the reply content and the service head portrait are correspondingly displayed in the customer service session window.
In one embodiment, the manual customer service account number corresponds to a manual customer service interface; the manual customer service interface contains a session list of each session provided by the service unit; the session list shows the identifier of the service provider which currently provides service for each session in the service unit; the identification comprises a target identification of a target customer service robot which provides service for the target service receiver at present;
if the intention recognition probability is smaller than a preset threshold value, initiating an early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content includes:
if the intention recognition probability is smaller than a preset threshold value, then
And triggering to determine the target identification in the session list of the artificial customer service interface, and carrying out early warning prompt based on the target identification so as to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content.
In one embodiment, the reply content of the session content is obtained by the artificial customer service through a reply content acquisition step; the reply content acquiring step includes:
responding to a session switching operation aiming at the target identification in the session list, and switching the target session corresponding to the target identification to the artificial customer service interface as a target session window; the target session is a session conducted by the target service recipient and the target customer service robot;
displaying the response content as auxiliary information in the manual customer service interface;
and acquiring reply content input by the artificial customer service in the target session window based on the reply content.
In one embodiment, the method further comprises:
correspondingly displaying the reply content and the identifier of the artificial customer service in the target session window in the artificial customer service interface;
and changing the target identifier into the identifier of the artificial customer service in the session list in the artificial customer service interface.
In one embodiment, the method further comprises:
if the intention recognition probability meets an accurate recognition condition, executing the step of determining response content corresponding to the conversation content based on the intention recognition result by the target customer service robot;
and if the intention identification probability does not meet the accurate identification condition, acquiring similar sentences of the conversation content through the target customer service robot, and returning the similar sentences to the target service receiver, so that the similar sentences and the service head portrait are correspondingly displayed in the customer service conversation window.
In one embodiment, the method further comprises:
inputting the conversation content into an emotion analysis model to obtain an emotion analysis result output by the emotion analysis model;
and if the emotion analysis result represents that the target service receiver has negative emotion, initiating early warning to the artificial customer service account.
In one embodiment, the method further comprises:
carrying out rule matching on the target session content according to an abnormal detection rule to obtain a rule matching result;
and if the rule matching result represents that the session is abnormal, initiating early warning to the artificial customer service account.
In a second aspect, the present application further provides a session processing apparatus. The device comprises:
the receiving module is used for receiving the session content input in a customer service session window of the target service receiver; a service head portrait corresponding to a service unit is displayed in the customer service session window; the service unit comprises a plurality of service providers which provide services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot;
the acquisition module is used for carrying out intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is larger than or equal to a preset threshold value, returning the response content to the target service receiver so as to correspondingly display the response content and the service head portrait in a customer service session window; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content;
and the reply module is used for returning the reply content to the target service receiver after acquiring the reply content of the artificial customer service for the session content, so that the reply content and the service avatar are correspondingly displayed in the customer service session window.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the method of the embodiments of the application when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the method according to embodiments of the present application.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, performs the steps of the method according to embodiments of the present application.
The session processing method, the session processing device, the computer equipment, the storage medium and the computer program product receive the session content input in the customer service session window of the target service receiver; a service head portrait corresponding to a service unit is displayed in a customer service session window; the service unit comprises a plurality of service providers for providing services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot; performing intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is larger than or equal to a preset threshold value, returning response content to the target service receiver so that the response content and the service head portrait are correspondingly displayed in the customer service session window; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account number to prompt the artificial customer service corresponding to the artificial customer service account number to reply to the session content; and after the reply content of the manual customer service for the session content is acquired, returning the reply content to the target service receiver so as to correspondingly display the reply content and the service head portrait in a customer service session window. In the scheme, the service is provided for the target service receiver through the service unit, the reply content of the artificial customer service and the response content of the intelligent customer service robot are displayed corresponding to the service head portrait, when the intelligent customer service cannot provide accurate service, the intervention of the artificial customer service is timely reminded, therefore, the artificial customer service in the service unit can be conveniently switched to provide service under the condition that the service receiver does not sense, the operation of service switching and the switching waiting time length are avoided, therefore, the efficiency of session processing can be improved while the accurate service is guaranteed to be provided.
Drawings
FIG. 1 is a diagram of an application environment of a session processing method in one embodiment;
FIG. 2 is a flow diagram that illustrates a method for session handling in one embodiment;
FIG. 3a is a schematic diagram of a human customer service interface in one embodiment;
FIG. 3b is a diagram of a customer service session window in one embodiment;
FIG. 4a is a timing diagram of session processing in one embodiment;
FIG. 4b is a timing diagram of anomaly detection in one embodiment;
FIG. 5 is a block diagram showing the structure of a session processing apparatus according to one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The session processing method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the first terminal 102 and the second terminal 106 communicate with the server 104 through a network, respectively. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. The first terminal 102 may present a customer service session window having a service avatar corresponding to the service unit to the target service recipient. Server 104 may receive session content entered in a customer service session window of a target service recipient; the service unit comprises a plurality of service providers for providing services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot; the server 104 may perform intent recognition on the session content to obtain an intent recognition result and a corresponding intent recognition probability; the server 104 may determine, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is greater than or equal to the preset threshold value, the server 104 can return the response content to the target service receiver through the first terminal 102, so that the response content and the service avatar are correspondingly displayed in the customer service session window; if the intention identification probability is smaller than the preset threshold, the server 104 may initiate an early warning to the artificial customer service account through the second terminal 106 to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content; the server 104 may return the reply content to the target service recipient after acquiring the reply content of the artificial customer service for the session content. The first terminal 102 may display the reply content in correspondence with the service icon in the customer service session window. The first terminal 102 and the second terminal 106 may be, but are not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
It is to be understood that the first terminal 102 may be a service receiving end and the second terminal 106 may be a service providing end.
In one embodiment, as shown in fig. 2, a session processing method is provided, which may be executed by the first terminal, the second terminal and the server in fig. 1 together, and is implemented through interaction between the terminal and the server, including the following steps:
s202, receiving the conversation content input in the customer service conversation window of the target service receiver.
The service receiver is a party that receives a service provided by a service unit. The customer service session window is a session window for providing customer service to a target service receiver. And a service head portrait corresponding to the service unit is displayed in the customer service session window. The service avatar is an avatar uniquely corresponding to a service unit. It is understood that whether any service provider in a service unit provides a service, an avatar unique to that service unit is displayed. The service unit includes a plurality of service providers that provide services for a target service recipient. The service provider comprises a manual customer service account and a bound target customer service robot.
Specifically, the target service receiver may initiate a customer service session at the service receiver, and the service receiver may present a customer service session window with a service avatar to the target service receiver. The target service recipient may enter the session content in a customer service session window, and the service recipient may send the session content to a server, which may receive the session content.
S204, performing intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result.
The intention recognition is to recognize the intention of the session content. The intention recognition probability refers to a probability of recognizing the intention of the conversation content, that is, the intention recognition accuracy. It will be appreciated that the higher the probability of intent recognition, the more accurate the intent recognition. The customer service robot is an intelligent robot for providing customer service to a service receiver. The response content refers to content that responds to the session content. It will be appreciated that interaction between the service provider and the service recipient requires the service provider to respond to the incoming session content of the service recipient.
Specifically, the server may perform intent recognition on the session content, obtaining an intent recognition result and a corresponding intent recognition probability. The server can determine response content corresponding to the session content from the intention identification result according to the intention identification probability through the target customer service robot. For example, when the intention recognition probability is very high, the server may directly use the intention recognition result as the response content corresponding to the session content.
In one embodiment, the intention recognition result may include at least one of response content corresponding to the conversation content, similar sentences similar to the conversation content, and unrecognized prompt information. It will be appreciated that the intent recognition results correspond to intent recognition probabilities, with different intent recognition probabilities corresponding to different intent recognition results. For example, when the intention recognition probability is very low, i.e., it is not recognized, the intention recognition result may be unrecognizable prompt information. When the intention recognition probability is very low, i.e., accurate recognition, the intention recognition result may be response content corresponding to the session content. When the intention recognition probability is medium, that is, accurate recognition cannot be performed, the intention recognition result may be a similar sentence similar to the session content.
In one embodiment, the server may match the conversation content with statements in the statement sample library for intent recognition of the conversation content. It will be appreciated that when the conversation content matches a statement in the sample library of statements, both are intended the same. The server may use the degree of match between the conversation content and the sentences in the sentence sample library as the intention recognition probability.
S206, if the intention identification probability is larger than or equal to the preset threshold value, returning response content to the target service receiver so as to correspondingly display the response content and the service head portrait in the customer service session window; if the intention recognition probability is smaller than a preset threshold value, an early warning is initiated to the artificial customer service account number to prompt the artificial customer service corresponding to the artificial customer service account number to reply to the session content.
The preset threshold is a threshold for judging accurate matching. It can be understood that if the intention recognition probability is greater than or equal to the preset threshold, accurate matching can be performed; if the intention recognition probability is smaller than a preset threshold, accurate matching cannot be performed.
Specifically, the server may compare the intention identification probability with a preset threshold, and send the response content to the service receiving end to return the response content to the target service receiving end if the intention identification probability is greater than or equal to the preset threshold. And the service receiving end receives the response content and correspondingly displays the response content and the service head portrait in the customer service session window. If the intention recognition probability is smaller than the preset threshold, the server can initiate early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content.
In an embodiment, the server may send the warning information to a service provider where the artificial customer service account is located, and the service provider may prompt, in an artificial customer service interface, the artificial customer service corresponding to the artificial customer service account to reply to the session content based on the warning information.
S208, after the reply content of the manual customer service for the session content is obtained, the reply content is returned to the target service receiver, so that the reply content and the service head portrait are correspondingly displayed in the customer service session window.
The reply content refers to content replied by the manual customer service for the session content.
Specifically, after acquiring the reply content of the manual customer service for the session content, the server may send the reply content to the service receiving end, so as to return the reply content to the target service receiving end. And the service receiving end receives the reply content and correspondingly displays the received reply content and the service head portrait in the customer service session window. It can be understood that both the response content and the reply content are displayed corresponding to the service icon, and the reply information of one service providing object is displayed in the customer service session window.
In the session processing method, session content input in a customer service session window of a target service receiver is received; a service head portrait corresponding to a service unit is displayed in a customer service session window; the service unit comprises a plurality of service providers for providing services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot; performing intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is larger than or equal to a preset threshold value, returning response content to the target service receiver so that the response content and the service head portrait are correspondingly displayed in the customer service session window; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account number to prompt the artificial customer service corresponding to the artificial customer service account number to reply to the session content; and after the reply content of the manual customer service for the session content is acquired, returning the reply content to the target service receiver so as to correspondingly display the reply content and the service head portrait in a customer service session window. In the scheme, the service is provided for the target service receiver through the service unit, the reply content of the artificial customer service and the response content of the intelligent customer service robot are displayed corresponding to the service head portrait, when the intelligent customer service cannot provide accurate service, the intervention of the artificial customer service is timely reminded, therefore, the artificial customer service in the service unit can be conveniently switched to provide service under the condition that the service receiver does not sense, the operation of service switching and the switching waiting time length are avoided, therefore, the efficiency of session processing can be improved while the accurate service is guaranteed to be provided.
In one embodiment, the manual customer service account number corresponds to a manual customer service interface; the manual customer service interface contains a session list of each session provided by a service unit; the session list shows the identification of the service provider which provides service for each session currently in the service unit; the identification comprises a target identification of a target customer service robot which provides service for a target service receiver at present; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content comprises the following steps: and if the intention recognition probability is smaller than a preset threshold value, triggering to determine a target identifier in the manual customer service interface session list, and carrying out early warning prompt based on the target identifier so as to prompt the manual customer service corresponding to the manual customer service account to reply to the session content.
The session list refers to a list of sessions provided by a service unit.
Specifically, if the server determines that the intention recognition probability is smaller than a preset threshold value, that is, the customer service robot cannot provide accurate service, the server triggers the service provider to determine the target identifier in the manual customer service interface session list. The service providing end can carry out early warning prompt on the artificial customer service by changing the target identification in the artificial customer service interface so as to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content. It will be appreciated that the pre-warning is used to prompt the human customer service to reply to the session content. The early warning prompt can be carried out on the artificial customer service no matter the customer service robot cannot provide the service or the current condition that the artificial customer service provides the service.
In one embodiment, the target identification may include at least one of a name of the service recipient, an avatar of the customer service robot, an avatar of a human service, and the like.
In one embodiment, the service provider may present the session list in the form of a vertically arranged cell. The identifier of the service provider currently providing service for each session in the service unit is shown in each cell. It can be understood that the service provider can show the service condition of the service provider in the service unit to the manual customer service through the session list.
In one embodiment, the service provider may prompt the human customer service by at least one of warning ways of flashing a target identifier, changing a color of the target identifier, and replacing the target identifier in the human customer service interface.
In the embodiment, if the intention recognition probability is smaller than a preset threshold, the target identification is triggered to be determined in the manual customer service interface session list, and early warning prompt is performed based on the target identification to prompt that the manual customer service corresponding to the manual customer service account replies to session contents.
In one embodiment, the reply content of the manual customer service for the session content is obtained through a reply content acquisition step; the reply content acquiring step comprises: responding to a session switching operation aiming at a target identifier in the session list, and switching a target session corresponding to the target identifier into a human customer service interface as a target session window; the target session is a session between the target service receiver and the target customer service robot; displaying the response content as auxiliary information in the manual customer service interface; and acquiring reply contents input by the artificial customer service in the target session window based on the reply contents.
The auxiliary information is information for assisting the manual customer service to reply to the session content.
Specifically, the manual customer service may perform a session switching operation for the target identifier in the session list, and the service provider may switch the target session corresponding to the target identifier to the manual customer service interface as the target session window through the session switching operation. It can be understood that the manual customer service can be switched to any session window of the service unit for providing service in the manual customer service interface. The target session is a session conducted by the target service recipient and the target customer service robot. The service provider displays the response content as auxiliary information in the manual customer service interface, and the manual customer service can directly adopt the response content as reply content or modify the response content to obtain the reply content. It can be understood that the artificial customer service may directly input the reply content in the target session window without adopting the reply content, and the service provider may obtain the reply content that the artificial customer service inputs in the target session window based on the reply content.
In one embodiment, the manual customer service may click on a target identifier in the session list, and trigger the service provider to switch a target session corresponding to the target identifier to the manual customer service interface as a target session window.
In this embodiment, each session window serviced by the service unit is included in the manual customer service interface, and the manual customer service can manage and control each session serviced by the service unit to provide accurate service for the service receiver.
In one embodiment, the method further comprises: in a target session window in the artificial customer service interface, correspondingly displaying the reply content and the identification of the artificial customer service; and in a session list in the manual customer service interface, changing the target identification into the identification of the manual customer service.
Specifically, the human customer service may disarm the hosted service of the customer service robot in the target session window. The service providing end can respond to the operation of releasing the escrow of the manual customer service, allow the manual customer service to reply to the conversation content, and after the reply content is obtained, correspondingly display the reply content and the identification of the manual customer service in a target conversation window in a manual customer service interface. The service providing end can change the target identification into the identification of the artificial customer service in the session list in the artificial customer service interface when the artificial customer service provides the service. The identification of the artificial customer service may be a head portrait of the artificial customer service.
In one embodiment, shown in FIGS. 3a and 3b, a human customer service interface and a customer service session window, respectively. The service receiving end can display the response content or the reply content corresponding to the service avatar to the service receiving end in the customer service session window, and the service receiving end perceives a service provider in the whole process, namely the service receiver perceives the service provider as artificial customer service in the whole process. The service providing end can provide service for the manual customer service display service unit in the manual customer service interface. For example, "applet- > home page- > borrowing" and "deduction three times at 8, 12 and 17 points per day" are response contents returned by the customer service robot to the service receiver; "sorry, you are going to urgency before you, i contact the background personnel now to help you inquire" and "you can receive after 4 am because of the bank system maintenance at night" is the reply content replied by the manual customer service for the conversation content. Obviously, the response content and the reply content are displayed differently in the customer service session window and the manual customer service interface, the service receiver cannot know whether the service is provided by the manual customer service or the customer service robot, and the manual customer service can intervene in time when the customer service robot cannot provide accurate service, so that the service receiver perceives the manual customer service as the whole service.
In the manual customer service interface, the left side is a session list, and the right side is a target session window. The session list is displayed in cells arranged in the longitudinal direction, and each cell has a name of a service receiver and an avatar of a service provider corresponding to each session. The target conversation window shows that the service receiver in the left conversation list is Zhang-two, the current conversation provided with the service provided by the customer service robot, and the manual customer service can click the cell to enter the target conversation window. It will be appreciated that the "unmanaged" button is used to unmanage the service of the customer service robot, and that the "unmanaged" may be converted to "managed" after the service of the customer service robot is unmanaged. The manual service can click on the "host" button, causing the service robot to provide service. When the customer service robot cannot provide accurate service, manual customer service intervention is requested, for example, a service receiver is 'Zhang Siang', a service provider can flash or shake a cell where the customer service robot is located, and the color of the cell is changed to prompt manual customer service. Such as the cell flashing and changing from white to red. For the current session of providing service by the manual customer service, the service provider will also prompt the manual customer service. For example, the service receiver is "zhangjiu", the service provider can set the color of the cell where the manual customer service is located differently, for example, the customer service robot normally provides the service in white, the customer service robot cannot provide the service in red, and the manual customer service provides the service in blue.
In the embodiment, the reply content and the identifier of the artificial customer service are correspondingly displayed in a target session window in the artificial customer service interface; in a session list in the manual customer service interface, the target identification is changed into the identification of the manual customer service, so that the manual customer service can be prompted in multiple aspects, and accurate service is provided for a service receiver.
In one embodiment, the method further comprises: if the intention recognition probability meets the accurate recognition condition, executing a step of determining response content corresponding to the conversation content based on an intention recognition result through the target customer service robot; and if the intention identification probability does not meet the accurate identification condition, acquiring similar sentences of the conversation content through the target customer service robot, and returning the similar sentences to the target service receiver, so that the similar sentences and the service head portrait are correspondingly displayed in a customer service conversation window.
The accurate recognition condition is a condition for determining accurate recognition.
In one embodiment, the precise recognition condition may include that the intended recognition probability is greater than or equal to a first recognition threshold. It is to be understood that if the intention recognition probability is greater than or equal to the first recognition threshold, it indicates that the precise recognition condition is satisfied. For example, the first recognition threshold is 90%, and if the intention recognition probability is greater than 90%, it indicates that the accurate recognition condition is satisfied. The first recognition threshold is also called a precise recognition threshold, i.e., greater than or equal to the first recognition threshold indicates precise recognition.
In another embodiment, the precise recognition condition may include that the intended recognition probability is within a preset precise recognition probability interval.
In one embodiment, if the intention recognition probability does not satisfy the accurate recognition condition but satisfies the fuzzy recognition condition, similar sentences of the conversation content are acquired by the target customer service robot.
In one embodiment, the fuzzy recognition condition may include the intended recognition probability being less than a first recognition threshold and greater than or equal to a second recognition threshold. It is understood that satisfying the fuzzy recognition condition explains that the intention can be recognized, but the recognition is not accurate enough. For example, if the first recognition threshold is 90% and the second recognition threshold is 80%, the intended recognition probability is between 80% and 90%, and it is determined that the fuzzy recognition condition is satisfied.
In one embodiment, if the intention recognition probability does not satisfy the precise recognition condition and does not satisfy the fuzzy recognition condition, the intention recognition result is that the intention cannot be recognized, and further, prompt information for prompting the service receiver to ask again can be returned.
Specifically, the server may compare the accurate identification condition with the intention identification probability, and if the intention identification probability satisfies the accurate identification condition, perform a step of determining, by the target customer service robot, response content corresponding to the conversation content based on the intention identification result; and if the intention identification probability does not meet the accurate identification condition, acquiring similar sentences of the conversation content through the target customer service robot, and returning the similar sentences to the target service receiver, so that the similar sentences and the service head portrait are correspondingly displayed in a customer service conversation window. It can be understood that if the intention recognition probability does not satisfy the accurate recognition condition, it indicates that accurate recognition cannot be performed, and indicates that the customer service robot does not understand well, several questions, i.e., similar sentences, which the service recipient may want to ask may be returned.
In one embodiment, if the intention recognition probability does not meet the accurate recognition condition for one or more times, the server may trigger an early warning prompt for the human customer service in the human customer service interface.
In this embodiment, if the intention recognition probability satisfies the accurate recognition condition, a step of determining, by the target customer service robot, response content corresponding to the session content based on the intention recognition result is performed; and if the intention identification probability does not meet the accurate identification condition, acquiring similar sentences of the conversation content through the target customer service robot, and returning the similar sentences to the target service receiver, so that the similar sentences and the service head portrait are correspondingly displayed in a customer service conversation window.
In one embodiment, the method further comprises: inputting the conversation content into an emotion analysis model to obtain an emotion analysis result output by the emotion analysis model; and if the emotion analysis result represents that the target service receiving party has negative emotion, initiating early warning to the artificial customer service account.
The emotion analysis model is a model for analyzing emotion of a service recipient.
Specifically, the server may input the session content to the emotion analysis model to obtain an emotion analysis result output by the emotion analysis model, where the emotion analysis result may be an emotion state value used for representing a current emotion state, and if the emotion analysis result represents that the target service receiver has a negative emotion, that is, the emotion state value reaches a preset emotion threshold, an early warning is initiated to the manual customer service account.
In one embodiment, session history records of the service receiver and the service provider can be stored in a session database, developers can obtain the historical session records from the session database through the terminal, perform satisfaction marking operation on the content in the historical session records, extract positive session samples, neutral session samples and negative session samples from the historical session records, and construct emotion analysis models based on the positive session samples, the neutral session samples and the negative session samples.
In the embodiment, the session content is input to the emotion analysis model to obtain an emotion analysis result output by the emotion analysis model; if the emotion analysis result represents that the target service receiver has negative emotion, early warning is initiated to the artificial customer service account, the artificial customer service can be prompted when the emotion of the service receiver is not good, timely intervention of the artificial customer service is guaranteed, accurate service is provided, and experience of the service receiver is improved.
In one embodiment, the method further comprises: carrying out rule matching on the target session content according to the abnormal detection rule to obtain a rule matching result; and if the rule matching result represents that the session is abnormal, initiating early warning to the manual customer service account.
The anomaly detection rule is a rule for detecting an anomaly of the target session.
Specifically, the developer may preset an abnormality detection rule for the abnormal situation. The server can carry out rule matching on the target session content according to the abnormality detection rule to obtain a rule matching result, and if the rule matching result represents that the session is abnormal, early warning is initiated to the artificial customer service account. For example, the anomaly detection rule may be that the customer repeats a certain question more than a few times and certain keywords, such as "complaints", "dirty words".
In the embodiment, rule matching is carried out on the target session content according to an abnormal detection rule to obtain a rule matching result; if the rule matching result represents that the session is abnormal, early warning is initiated to the artificial customer service account, abnormal conditions can be detected in multiple aspects, the artificial customer service is prompted when the abnormal conditions occur, timely intervention of the artificial customer service is guaranteed, accurate service is provided, and experience of a service receiver is improved.
In one embodiment, shown in FIGS. 4a and 4b, a timing diagram of the session processing of FIG. 4a and a timing diagram of the anomaly detection, respectively. The service receiving end can send the session content input by the service receiving end in the customer service session window to the server, and the server can perform intention identification on the session content through the intelligent interaction unit to obtain an intention identification result and intention identification probability. The server can judge the question and answer threshold value of the intention identification probability through the customer service unit. It can be understood that the customer service unit may obtain the response result from the intention recognition result or prompt intervention of the manual customer service according to the question-answer threshold, for example, the question-answer threshold may be an accurate matching condition, the intention recognition probability is 80% -90%, the manual customer service is prompted to perform early warning, or the manual customer service is early warned after 2 times of the occurrence of the intention recognition probability is 80% -90%. While the question-answer threshold value is judged, abnormal conditions occurring in the conversation can be detected. It is understood that the manner of anomaly detection may be an anomaly detection rule of the emotion analysis model. And when the abnormal condition occurs, prompting and early warning are carried out on the manual customer service so as to return the reply content of the manual customer service to the service receiver. It can be understood that when the abnormal condition is detected, the server does not return the response content even if the question-answer threshold is reached, and prompts the manual customer service to intervene to return the reply content that the manual customer service replies to the session content.
In the embodiment, the intervention of manual customer service is timely prompted by effectively judging the abnormal condition of the service receiver, the user experience of the service receiver is improved, the preposed filtering effect of the customer service robot is ensured, and the labor cost is reduced.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a session processing apparatus for implementing the above-mentioned session processing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the session processing device provided below may refer to the limitations on the session processing method in the foregoing, and details are not described here.
In one embodiment, as shown in fig. 5, there is provided a session processing apparatus 500, including: a receiving module 502, an obtaining module 504, and a replying module 506, wherein:
a receiving module 502, configured to receive session content input in a customer service session window of a target service recipient; a service head portrait corresponding to a service unit is displayed in the customer service session window; the service unit comprises a plurality of service providers which provide services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot;
an obtaining module 504, configured to perform intent recognition on the session content to obtain an intent recognition result and a corresponding intent recognition probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is larger than or equal to a preset threshold value, returning the response content to the target service receiver so as to correspondingly display the response content and the service head portrait in a customer service session window; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content;
a reply module 506, configured to, after acquiring reply content of the manual customer service for the session content, return the reply content to the target service recipient, so that the reply content and the service avatar are correspondingly displayed in the customer service session window.
In one embodiment, the manual customer service account number corresponds to a manual customer service interface; the manual customer service interface contains a session list of each session provided by the service unit; the session list shows the identifier of the service provider which currently provides service for each session in the service unit; the identification comprises a target identification of a target customer service robot which provides service for the target service receiver at present; the obtaining module 504 is further configured to trigger the determination of the target identifier in the manual customer service interface session list if the intention recognition probability is smaller than a preset threshold, and perform an early warning prompt based on the target identifier, so as to prompt the manual customer service corresponding to the manual customer service account to reply to the session content.
In one embodiment, the reply content of the session content is obtained by the artificial customer service through a reply content acquisition step; the obtaining module 504 is further configured to respond to a session switching operation for the target identifier in the session list, and switch the target session corresponding to the target identifier to the artificial customer service interface as a target session window; the target session is a session conducted by the target service recipient and the target customer service robot; displaying the response content as auxiliary information in the manual customer service interface; and acquiring reply content input by the artificial customer service in the target session window based on the reply content.
In one embodiment, the reply module 506 is further configured to correspondingly display the reply content and the identifier of the artificial customer service in the target session window in the artificial customer service interface; and changing the target identifier into the identifier of the artificial customer service in the session list in the artificial customer service interface.
In one embodiment, the obtaining module 504 is further configured to execute the step of determining, by the target customer service robot, answer content corresponding to the session content based on the intention recognition result if the intention recognition probability satisfies an accurate recognition condition; and if the intention identification probability does not meet the accurate identification condition, acquiring similar sentences of the conversation content through the target customer service robot, and returning the similar sentences to the target service receiver, so that the similar sentences and the service head portrait are correspondingly displayed in the customer service conversation window.
In one embodiment, the obtaining module 504 is further configured to input the session content to an emotion analysis model to obtain an emotion analysis result output by the emotion analysis model; and if the emotion analysis result represents that the target service receiver has negative emotion, initiating early warning to the artificial customer service account.
In an embodiment, the obtaining module 504 is further configured to perform rule matching on the target session content according to an anomaly detection rule, so as to obtain a rule matching result; and if the rule matching result represents that the session is abnormal, initiating early warning to the artificial customer service account.
The modules in the session processing device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing session handling related data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a session handling method.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a session handling method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the configurations shown in fig. 6 and 7 are merely block diagrams of portions of configurations related to aspects of the present application, and do not constitute limitations on the computing devices to which aspects of the present application may be applied, as particular computing devices may include more or less components than shown, or combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above-described method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method for session processing, the method comprising:
receiving session content input in a customer service session window of a target service recipient; a service head portrait corresponding to a service unit is displayed in the customer service session window; the service unit comprises a plurality of service providers which provide services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot;
performing intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability;
determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result;
if the intention identification probability is larger than or equal to a preset threshold value, returning the response content to the target service receiver so as to correspondingly display the response content and the service head portrait in a customer service session window;
if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content;
after the reply content of the manual customer service for the session content is acquired, the reply content is returned to the target service receiving party, so that the reply content and the service head portrait are correspondingly displayed in the customer service session window.
2. The method of claim 1, wherein the manual customer service account number corresponds to a manual customer service interface; the manual customer service interface contains a session list of each session provided by the service unit; the session list shows the identifier of the service provider which currently provides service for each session in the service unit; the identification comprises a target identification of a target customer service robot which provides service for the target service receiver at present;
if the intention recognition probability is smaller than a preset threshold value, initiating an early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content includes:
if the intention recognition probability is smaller than a preset threshold value, then
And triggering to determine the target identification in the session list of the artificial customer service interface, and carrying out early warning prompt based on the target identification so as to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content.
3. The method according to claim 2, wherein the artificial customer service obtains the reply content of the session content through a reply content obtaining step; the reply content acquiring step includes:
responding to a session switching operation aiming at the target identification in the session list, and switching the target session corresponding to the target identification to the artificial customer service interface as a target session window; the target session is a session conducted by the target service recipient and the target customer service robot;
displaying the response content as auxiliary information in the manual customer service interface;
and acquiring reply content input by the artificial customer service in the target session window based on the reply content.
4. The method of claim 3, further comprising:
correspondingly displaying the reply content and the identifier of the artificial customer service in the target session window in the artificial customer service interface;
and changing the target identifier into the identifier of the artificial customer service in the session list in the artificial customer service interface.
5. The method of claim 1, further comprising:
if the intention recognition probability meets an accurate recognition condition, executing the step of determining response content corresponding to the conversation content based on the intention recognition result by the target customer service robot;
and if the intention identification probability does not meet the accurate identification condition, acquiring similar sentences of the conversation content through the target customer service robot, and returning the similar sentences to the target service receiver, so that the similar sentences and the service head portrait are correspondingly displayed in the customer service conversation window.
6. The method of claim 1, further comprising:
inputting the conversation content into an emotion analysis model to obtain an emotion analysis result output by the emotion analysis model;
and if the emotion analysis result represents that the target service receiver has negative emotion, initiating early warning to the artificial customer service account.
7. The method according to any one of claims 1 to 5, further comprising:
carrying out rule matching on the target session content according to an abnormal detection rule to obtain a rule matching result;
and if the rule matching result represents that the session is abnormal, initiating early warning to the artificial customer service account.
8. A session processing apparatus, characterized in that the apparatus comprises:
the receiving module is used for receiving the session content input in a customer service session window of the target service receiver; a service head portrait corresponding to a service unit is displayed in the customer service session window; the service unit comprises a plurality of service providers which provide services for the target service receiver; the service provider comprises an artificial customer service account and a bound target customer service robot;
the acquisition module is used for carrying out intention identification on the conversation content to obtain an intention identification result and corresponding intention identification probability; determining, by the target customer service robot, response content corresponding to the conversation content based on the intention recognition result; if the intention identification probability is larger than or equal to a preset threshold value, returning the response content to the target service receiver so as to correspondingly display the response content and the service head portrait in a customer service session window; if the intention recognition probability is smaller than a preset threshold value, initiating early warning to the artificial customer service account to prompt the artificial customer service corresponding to the artificial customer service account to reply to the session content;
and the reply module is used for returning the reply content to the target service receiver after acquiring the reply content of the artificial customer service for the session content, so that the reply content and the service avatar are correspondingly displayed in the customer service session window.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111399976.7A CN114117157B (en) | 2021-11-19 | 2021-11-19 | Session processing method, apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111399976.7A CN114117157B (en) | 2021-11-19 | 2021-11-19 | Session processing method, apparatus, computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114117157A true CN114117157A (en) | 2022-03-01 |
| CN114117157B CN114117157B (en) | 2024-04-09 |
Family
ID=80440711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111399976.7A Active CN114117157B (en) | 2021-11-19 | 2021-11-19 | Session processing method, apparatus, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114117157B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506372A (en) * | 2017-07-11 | 2017-12-22 | 哈尔滨工业大学深圳研究生院 | A kind of automatic conversation switching method of robot customer service under mixed type session |
| WO2018006727A1 (en) * | 2016-07-08 | 2018-01-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for transferring from robot customer service to human customer service |
| CN109245994A (en) * | 2015-12-30 | 2019-01-18 | 上海智臻智能网络科技股份有限公司 | A kind of robot client service method |
| CN111061831A (en) * | 2019-10-29 | 2020-04-24 | 深圳绿米联创科技有限公司 | Method and device for switching machine customer service to manual customer service and electronic equipment |
| CN111917878A (en) * | 2020-08-03 | 2020-11-10 | 腾讯科技（深圳）有限公司 | Message processing method, device, equipment and storage medium |
| CN112750186A (en) * | 2021-01-19 | 2021-05-04 | 深圳追一科技有限公司 | Virtual image switching method and device, electronic equipment and storage medium |
| CN113079263A (en) * | 2021-03-16 | 2021-07-06 | 京东数字科技控股股份有限公司 | Method, device, system and medium for intelligent customer service switching |
| WO2021175007A1 (en) * | 2020-03-02 | 2021-09-10 | 深圳壹账通智能科技有限公司 | Online customer service consultation method and apparatus, medium, and electronic device |
-
2021
- 2021-11-19 CN CN202111399976.7A patent/CN114117157B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109245994A (en) * | 2015-12-30 | 2019-01-18 | 上海智臻智能网络科技股份有限公司 | A kind of robot client service method |
| WO2018006727A1 (en) * | 2016-07-08 | 2018-01-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for transferring from robot customer service to human customer service |
| CN107506372A (en) * | 2017-07-11 | 2017-12-22 | 哈尔滨工业大学深圳研究生院 | A kind of automatic conversation switching method of robot customer service under mixed type session |
| CN111061831A (en) * | 2019-10-29 | 2020-04-24 | 深圳绿米联创科技有限公司 | Method and device for switching machine customer service to manual customer service and electronic equipment |
| WO2021175007A1 (en) * | 2020-03-02 | 2021-09-10 | 深圳壹账通智能科技有限公司 | Online customer service consultation method and apparatus, medium, and electronic device |
| CN111917878A (en) * | 2020-08-03 | 2020-11-10 | 腾讯科技（深圳）有限公司 | Message processing method, device, equipment and storage medium |
| CN112750186A (en) * | 2021-01-19 | 2021-05-04 | 深圳追一科技有限公司 | Virtual image switching method and device, electronic equipment and storage medium |
| CN113079263A (en) * | 2021-03-16 | 2021-07-06 | 京东数字科技控股股份有限公司 | Method, device, system and medium for intelligent customer service switching |
Non-Patent Citations (1)
| Title |
|---|
| 张瑞;潘鑫;杨艳妮;黄正伟;: "情感介入式智能客户服务系统", 情报理论与实践, no. 08, 30 August 2016 (2016-08-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114117157B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11164091B1 (en) | Natural language troubleshooting engine | |
| CN111917878B (en) | Message processing method, device, equipment and storage medium | |
| CN109684047A (en) | Event-handling method, device, equipment and computer storage medium | |
| US20160104094A1 (en) | Future meeting evaluation using implicit device feedback | |
| CN110245714B (en) | Image recognition method and device and electronic equipment | |
| CN112135325A (en) | Network switching method, device, storage medium and terminal | |
| CN113435912A (en) | Data analysis method, device, equipment and medium based on client portrait | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN117474091A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN112801145A (en) | Safety monitoring method and device, computer equipment and storage medium | |
| CN116703598A (en) | Transaction behavior detection method, device, computer equipment and storage medium | |
| CN114117157A (en) | Session processing method, device, computer equipment and storage medium | |
| CN111143608A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN114598844A (en) | Doorbell reminding method and device, intelligent doorbell equipment and storage medium | |
| CN114329128A (en) | Method and device for acquiring marking data, computer equipment and storage medium | |
| CN114373122A (en) | Device identification method and device, computer device and storage medium | |
| AU2021276239A1 (en) | Identifying claim complexity by integrating supervised and unsupervised learning | |
| CN111049988A (en) | Intimacy prediction method, system, equipment and storage medium for mobile equipment | |
| CN116415237B (en) | Risk device identification method, apparatus, computer device and storage medium | |
| CN114265757A (en) | Equipment anomaly detection method and device, storage medium and equipment | |
| CN114358328A (en) | Method and device for detecting on-off state of transformer substation equipment and computer equipment | |
| CN116962335A (en) | Prompt message sending method and device, computer equipment and storage medium | |
| CN117151873A (en) | Abnormality prompting method, abnormality prompting device, computer equipment and storage medium | |
| CN115330514A (en) | Loan behavior risk management method and device, computer equipment and storage medium | |
| CN117649303A (en) | Security service acceptance method, device, computer 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant after: Zhaolian Consumer Finance Co.,Ltd. Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: MERCHANTS UNION CONSUMER FINANCE Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |