CN112130907A - Session processing method and device and electronic equipment - Google Patents
Session processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN112130907A CN112130907A CN201910488383.4A CN201910488383A CN112130907A CN 112130907 A CN112130907 A CN 112130907A CN 201910488383 A CN201910488383 A CN 201910488383A CN 112130907 A CN112130907 A CN 112130907A
- Authority
- CN
- China
- Prior art keywords
- session
- message
- conversation
- user
- current
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 9
- 239000002699 waste material Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000007667 floating Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/442—Shutdown
-
- 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
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides a session processing method, a session processing device and electronic equipment, wherein the method comprises the following steps: predicting the conversation state of the current conversation according to the characteristic data of the user chatting; if the prediction result is that the prediction session is ended, pushing a reminding message; and within the preset time, if no new session message is added, closing the current session. According to the embodiment of the invention, the conversation state is predicted according to the characteristic data of the user chat, the reminding message is pushed to the conversation in the predicted conversation ending state, the counter is started, the possibility of closing the conversation in advance under the condition of considering the customer experience is realized, and therefore, the occupied customer service resources are released.
Description
Technical Field
The application relates to a session processing method, a session processing device and electronic equipment, and belongs to the technical field of computers.
Background
In the existing customer service chat, in the situation of solving user problems, a user consults a customer service, the customer service sends a solution to the user, the user leaves a help-seeking page after obtaining an answer, but the situation that a session is not closed actively often occurs, resources of the customer service are occupied by the user all the time, and the waste of the customer service and session resources is caused.
Disclosure of Invention
The embodiment of the invention provides a session processing method, a session processing device and electronic equipment, which are used for reducing waste of customer service and session resources.
In order to achieve the above object, an embodiment of the present invention provides a session processing method, including:
predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
if the prediction result is that the prediction session is ended, pushing a reminding message;
and within the preset time, if no new session message is added, closing the current session.
An embodiment of the present invention further provides a session processing apparatus, including:
a session state prediction module: the system is used for predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
reminding the pushing module: the system is used for pushing a reminding message under the condition that the prediction result is that the session is predicted to be ended;
a session closing module: and closing the current session if no new session message is added in the preset time.
An embodiment of the present invention further provides an electronic device, including:
a memory for storing a program;
a processor, coupled to the memory, for executing the program for:
predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
if the prediction result is that the prediction session is ended, pushing a reminding message;
and within the preset time, if no new session message is added, closing the current session.
According to the embodiment of the invention, the conversation state is predicted according to the characteristic data of the user chat, the reminding message is pushed to the conversation in the predicted conversation ending state, the counter is started, and the possibility of closing the conversation in advance under the condition of considering the customer experience is realized, so that occupied customer service and conversation resources are released, and the waste of the customer service and conversation resources is reduced.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Fig. 1 is a schematic flow chart of a session processing method according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario of a session processing method according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a session processing apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art
In the existing situation of solving the user problem by customer service chat, the situation that the session is not actively closed often occurs after the user finishes consulting the problem with the customer service, so that the customer service and the session resources are always occupied, and the waste of the customer service and the session resources is caused.
According to the embodiment of the invention, the conversation state is predicted according to the customer service and the characteristic data of the user when chatting, the prediction result is the conversation of the predicted conversation end, the reminding message is pushed to the user, and if the new conversation message does not occur within the timing time, the conversation is closed. Therefore, the possibility of closing the disconnected session in advance under the condition of considering the customer experience is realized, and occupied customer service resources are released.
The technical solution of the present invention is further illustrated by some specific examples.
Example one
As shown in fig. 1, which is a schematic flow chart of a session processing method according to an embodiment of the present invention, the method includes the following steps:
s101: and predicting the conversation state of the current conversation according to the characteristic data of the user chatting.
Specifically, the processing of predicting the session state of the current session according to the characteristic data of the user chat can be executed in response to the customer service sending a message; or after the customer service and/or the member sends out the message, if no new conversation message is added in the preset time, the conversation state of the current conversation is predicted according to the characteristic data of the user chat.
In the situation of solving the user problem by the customer service online chat, the general session termination is subject to the condition that the customer service sends the last session, so that the process of predicting the session state of the current session can be triggered after the customer service sends a message each time. In an actual scenario, after the customer service sends the message, the system may wait for a preset time, for example, 5 seconds, and after waiting, if there is no user or customer service continues to send the message, the session may be considered to be ended, and the session state prediction may be triggered.
In addition, the prediction of the session state may be triggered by that no new reply message is added within a preset time after a message is sent by any one of the customer service and the user, for example, a preset silent time may be set to 30 seconds, and the prediction of the session state may be triggered by that no new reply message is added within 30 seconds after the message is sent by the customer service or the user.
And further, for the session meeting the trigger condition, predicting the session state of the current session according to the characteristic data of the user chat. The characteristic data of the user chat can comprise a user historical behavior track and/or session data of a current session and/or user heartbeat data.
Specifically, the historical behavior track of the user may be recorded in a behavior manner of the user in the past chat process, for example, the user enters the conversation several times in 24 hours in the past online activity, the duration of each chat, whether the user actively closes the conversation after the conversation ends or closes the conversation after the user leaves the conversation in an offline manner, and the like. The feature data may include session data between the user and the customer service, for example, content data of a chat between the user and the customer service, a resolution of a question, and a reply content of a solution to the customer service by the user. In addition, the characteristic data can also comprise user heartbeat data, namely custom data which is used for regularly informing the opposite side of the own state at the client side and the server side, the custom data is sent according to a certain time interval to tell the opposite side whether the opposite side is online, and meanwhile, the opposite side is judged whether the opposite side is in conversation or not by obtaining returned data.
S102: and if the prediction result is that the session is predicted to be ended, pushing a reminding message.
Specifically, the prediction result may include two aspects, that is, whether the current session is the predicted session end and the corresponding confidence, and thus, the condition for pushing the alert message may be: and if the current conversation is predicted to be the end of the predicted conversation and the corresponding confidence coefficient is larger than a preset threshold value, pushing a reminding message.
The session state prediction is to analyze the feature data of the chat through a machine learning model so as to predict the session state, wherein the prediction result includes whether the current session state is the predicted session end and a corresponding confidence, and the session with the predicted session end includes session disconnection caused by user leaving or session actively closing by the user in an actual scene, so that the prediction result can be session disconnection with a confidence of 80%. When the prediction result is a line break and the confidence level is greater than a preset threshold, for example, when the prediction result is a line break and the confidence level is greater than 80% (it can be considered that the session has a high probability of being a line break), a reminder message is pushed, where the reminder message may start a timer while pushing the reminder in a countdown reminding manner.
In addition, in order to record the state of the session, two session state identifiers, namely normal and offline, can be set for the current session, wherein the session state identifier is set to be in a normal state by default. When the session state prediction result is a disconnection and the confidence is greater than a preset threshold, the session state identifier may be determined, and the following two processes are performed on the session state identifier which is a disconnection and a normal session respectively: if the session state identifier is normal, the session state identifier is set to be disconnected and then a reminding message is pushed; and if the session state identifier is disconnected, directly pushing a reminding message. In addition, when the prediction result is a broken line and the confidence coefficient is less than or equal to the preset threshold or the prediction result is normal, when the session state identifier is a broken line, the session state identifier is set to be normal and then the processing flow is ended, and when the session state identifier is normal, the processing flow is directly ended.
It should be further noted that the above-mentioned reminding message may be pushed to a page where the customer service and the user chat, or may be pushed to the user and the customer service in a manner of popping up a floating widget or a widget, so as to prompt whether the session is in progress or not under the conditions of network signal disconnection, opening other pages, etc., thereby avoiding the occupation of customer service resources by the session that has been ended, and also avoiding the influence on the customer experience caused by the false closing of the session in progress.
S103: and within the preset time, if the session message is not newly added, closing the current session.
Specifically, after the reminding message is pushed and the timer is started, if no new session message is added in the preset timing time, the session is closed so as to release the customer service resource, and if a new session message appears, the timer is closed and the countdown is terminated. In addition, in an actual scene, when the user sees the reminding message and then if there is a problem and wants to continue the conversation, the countdown reminding can be actively closed, so that the timer is closed and the conversation is continued.
The steps of the session processing method according to the embodiment of the present invention are introduced above, and a corresponding specific scenario is described below with reference to fig. 2, where fig. 2 is a schematic view of an application scenario of the session processing method according to the embodiment of the present invention.
As shown in fig. 2, in a specific scenario of a user chat, when a customer service sends a last session or when the customer service or the user sends a message, no new reply message is added within a preset time, a session state prediction is triggered, the session state prediction analyzes feature data of the chat through a machine learning model (a "session state prediction intelligent algorithm" in a corresponding diagram), and thereafter, the following processes may be performed for different prediction results:
1) when the result of the session state prediction is a disconnection and the confidence is greater than a preset threshold (for example, the result of the prediction is a disconnection and the confidence is greater than 80%), the session state identifier is judged, and if the session state identifier is normal, the session state identifier is firstly set to be a disconnection, then a reminding message is pushed, and a timer is started. It should be noted that the processing logic of the timer may be executed independently after the timer is started, that is, within a preset time (for example, 30 seconds) of the timer, if there is no new session message, the session is closed, and if there is a new session message, the timer is closed. In addition, in an actual scenario, the user may also actively close the reminder message when seeing the reminder message and still want to continue the session, thereby terminating the timer.
2) When the result of the session state prediction is a disconnection and the confidence is greater than or equal to a preset threshold (for example, the result of the prediction is a disconnection and the confidence is greater than 80%), the session state identification is judged, and if the session state identification at the moment is a disconnection, a reminding message can be directly pushed and a timer can be started.
3) When the result of the session state prediction is a disconnection but the confidence coefficient is less than or equal to a preset threshold (for example, the result of the prediction is a disconnection and the confidence coefficient is less than or equal to 80%) or the result of the session state prediction is normal, the session state identifier is determined, and if the session state identifier is normal at the moment, the determination process is ended.
4) And when the result of the session state prediction is disconnected but the confidence coefficient is less than or equal to a preset threshold (for example, the result of the prediction is disconnected and the confidence coefficient is less than or equal to 80%) or the result of the session state prediction is normal, judging the session state identifier, if the session state identifier is disconnected, setting the session state identifier to be normal, and then ending the process.
The main flow (flow except for the timer processing logic) shown in fig. 2 may be executed at preset time intervals after being triggered, and in practical applications, the time interval of the main flow execution may be set to be the same as the time interval of the countdown. That is, if no new session message occurs within the countdown interval, the session will be closed, and the main flow need not be executed again. If new conversation messages occur, the characteristic data of the user chat correspondingly changes, and therefore judgment of the conversation disconnection state is triggered again.
According to the embodiment of the invention, the conversation state is predicted according to the customer service and the characteristic data of the user when chatting, the prediction result is the conversation of the predicted conversation end, the reminding message is pushed to the user, and if the new conversation message does not occur within the timing time, the conversation is closed. Therefore, the possibility of closing the disconnected session in advance under the condition of considering the customer experience is realized, and occupied customer service and session resources are released, so that the waste of the customer service and the session resources is reduced.
Example two
As shown in fig. 3, which is a schematic structural diagram of a session processing apparatus according to an embodiment of the present invention, the apparatus includes: the system comprises a session state prediction module 21, a disconnection prompting push module 22 and a disconnection processing module 23.
The session state prediction module 21: and the system is used for predicting the session state of the current session according to the characteristic data of the user chat.
Specifically, the processing of predicting the session state of the current session according to the characteristic data of the user chat can be executed in response to the customer service sending a message; or after the customer service and/or the member sends out the message, if no new conversation message is added in the preset time, the conversation state of the current conversation is predicted according to the characteristic data of the user chat.
In the situation of solving the user problem by the customer service online chat, the general session termination is subject to the condition that the customer service sends the last session, so that the process of predicting the session state of the current session can be triggered after the customer service sends a message each time. In an actual scenario, after the customer service sends the message, the system may wait for a preset time, for example, 5 seconds, and after waiting, if there is no user or customer service continues to send the message, the session may be considered to be ended, and the session state prediction may be triggered.
In addition, the prediction of the session state may be triggered by that no new reply message is added within a preset time after a message is sent by any one of the customer service and the user, for example, a preset silent time may be set to 30 seconds, and the prediction of the session state may be triggered by that no new reply message is added within 30 seconds after the message is sent by the customer service or the user.
And further, for the session meeting the trigger condition, predicting the session state of the current session according to the characteristic data of the user chat. The characteristic data of the user chat can comprise a user historical behavior track and/or session data of a current session and/or user heartbeat data.
The historical behavior track of the user can be recorded for the behavior mode of the user in the past chatting process, for example, the user enters the phone several times in 24 hours in the past online activity, the time length of each chatting, whether the off-line mode is the active closing of the conversation after the conversation of the user is finished or the system closes the conversation after the conversation is left, and the like. The feature data may include session data between the user and the customer service, for example, content data of a chat between the user and the customer service, a resolution of a question, and a reply content of a solution to the customer service by the user. In addition, the characteristic data can also comprise user heartbeat data, namely custom data which is used for regularly informing the opposite side of the own state at the client side and the server side, the custom data is sent according to a certain time interval to tell the opposite side whether the opposite side is online, and meanwhile, the opposite side is judged whether the opposite side is in conversation or not by obtaining returned data.
The reminding pushing module 22: and the reminding message is pushed when the prediction result is that the prediction session is ended.
Specifically, the prediction result may include two aspects, that is, whether the current session is the predicted session end and the corresponding confidence, and thus, the condition for pushing the alert message may be: and if the current conversation is predicted to be the end of the predicted conversation and the corresponding confidence coefficient is larger than a preset threshold value, pushing a reminding message.
The session state prediction is to analyze the feature data of the chat through a machine learning model so as to predict the session state, wherein the prediction result includes whether the current session state is the predicted session end and a corresponding confidence, and the session with the predicted session end includes session disconnection caused by user leaving or session actively closing by the user in an actual scene, so that the prediction result can be session disconnection with a confidence of 80%. When the prediction result is a line break and the confidence level is greater than a preset threshold, for example, when the prediction result is a line break and the confidence level is greater than 80% (it can be considered that the session has a high probability of being a line break), a reminder message is pushed, where the reminder message may start a timer while pushing the reminder in a countdown reminding manner.
In addition, in order to record the state of the session, two session state identifiers, namely normal and offline, can be set for the current session, wherein the session state identifier is set to be in a normal state by default. When the session state prediction result is a disconnection and the confidence coefficient is greater than a preset threshold value, the session state identification can be judged, the following two processes are respectively carried out on the session state identification which is a disconnection and a normal session, and if the session state identification is normal, the session state identification is set to be a disconnection and then a reminding message is pushed; and if the session state identification is offline, pushing a reminding message. In addition, when the prediction result is a broken line and the confidence coefficient is less than or equal to the preset threshold or the prediction result is normal, when the session state identifier is a broken line, the session state identifier is set to be normal and then the processing flow is ended, and when the session state identifier is normal, the processing flow is directly ended.
It should be further noted that the above-mentioned reminding message may be pushed to a page where the customer service and the user chat, or may be pushed to the user and the customer service in a manner of popping up a floating widget or a widget, so as to prompt whether the session is in progress or not under the conditions of network signal disconnection, opening other pages, etc., thereby avoiding the occupation of customer service resources by the session that has been ended, and also avoiding the influence on the customer experience caused by the false closing of the session in progress.
The session closing module 23: and closing the current session if the session message is not added within the preset time.
Specifically, after the reminding message is pushed and the timer is started, if no new session message is added in the preset timing time, the session is closed so as to release the customer service resource, and if a new session message appears, the timer is closed and the countdown is terminated. In addition, in an actual scene, when the user sees the reminding message and then if there is a problem and wants to continue the conversation, the countdown reminding can be actively closed, so that the timer is closed and the conversation is continued.
According to the embodiment of the invention, the conversation state is predicted according to the customer service and the characteristic data of the user when chatting, the prediction result is the conversation of the predicted conversation end, the reminding message is pushed to the user, and if the new conversation message does not occur within the timing time, the conversation is closed. Therefore, the possibility of closing the disconnected session in advance under the condition of considering the customer experience is realized, occupied customer service and session resources are released, and the waste of the customer service and session resources is reduced.
EXAMPLE III
The foregoing embodiment describes a flow process and a device structure according to an embodiment of the present invention, and the functions of the method and the device can be implemented by an electronic device, as shown in fig. 4, which is a schematic structural diagram of the electronic device according to an embodiment of the present invention, and specifically includes: a memory 110 and a processor 120.
And a memory 110 for storing a program.
In addition to the programs described above, the memory 110 may also be configured to store other various data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phonebook data, messages, pictures, videos, and so forth.
The memory 110 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
A processor 120, coupled to the memory 110, for executing the program in the memory 110, for performing the following:
predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
if the prediction result is that the prediction session is ended, pushing a reminding message;
and within the preset time, if no new session message is added, closing the current session.
The characteristic data of the user chat may include:
historical behavior traces of the user and/or session data of the current session and/or heartbeat data of the user.
The predicting the session state of the current session according to the feature data of the user chat may include:
responding to the message sent by the customer service, executing the process of predicting the conversation state of the current conversation according to the characteristic data of the user chat;
or,
after the customer service and/or the member sends out the message, if no new conversation message is added in the preset time, the process of predicting the conversation state of the current conversation according to the characteristic data of the user chat is executed.
The prediction result may include whether the current session predicts the end of the session and a corresponding confidence, and if the prediction result is that the session is predicted to be ended, pushing the reminder message may include:
and if the current conversation is predicted to be the end of the predicted conversation and the corresponding confidence coefficient is larger than a preset threshold value, pushing a reminding message.
Wherein, the current conversation is provided with a conversation state identification which is set as a normal state by default,
pushing the reminder message may include:
judging the session state identifier, if the session state identifier is normal, setting the session state identifier as a push reminding message after the prediction session is ended;
and if the session state identification is the predicted session end, pushing a reminding message.
The above detailed descriptions of the processing procedure, the technical principle, and the technical effect are described in detail in the foregoing embodiments, and are not repeated herein.
Further, as shown, the electronic device may further include: communication components 130, power components 140, audio components 150, display 160, and other components. Only some of the components are schematically shown in the figure and it is not meant that the electronic device comprises only the components shown in the figure.
The communication component 130 is configured to facilitate wired or wireless communication between the electronic device and other devices. The electronic device may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 130 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 130 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
The power supply component 140 provides power to the various components of the electronic device. The power components 140 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for an electronic device.
The audio component 150 is configured to output and/or input audio signals. For example, the audio component 150 includes a Microphone (MIC) configured to receive external audio signals when the electronic device is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 110 or transmitted via the communication component 130. In some embodiments, audio assembly 150 also includes a speaker for outputting audio signals.
The display 160 includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (11)
1. A session processing method, comprising:
predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
if the prediction result is that the prediction session is ended, pushing a reminding message;
and within the preset time, if no new session message is added, closing the current session.
2. The method of claim 1, wherein the characteristic data of the user chat includes:
historical behavior traces of the user and/or session data of the current session and/or heartbeat data of the user.
3. The method of claim 1, wherein the predicting the session state of the current session according to the characteristic data of the user chat comprises:
responding to the message sent by the customer service, executing the process of predicting the conversation state of the current conversation according to the characteristic data of the user chat;
or,
and after the customer service and/or the member sends out the message, if no new session message is added in the preset time, executing the process of predicting the session state of the current session according to the characteristic data of the user chat.
4. The method of claim 1, wherein the prediction result comprises whether the current session predicts the end of the session and a corresponding confidence level, and if the prediction result is the predicted end of the session, pushing the reminder message comprises:
and if the current conversation is predicted to be the end of the predicted conversation and the corresponding confidence coefficient is larger than a preset threshold value, pushing a reminding message.
5. The method of claim 1, wherein the current session is provided with a session state identification that is set to a normal state by default,
the pushing of the reminding message comprises:
judging the session state identifier, if the session state identifier is normal, setting the session state identifier as a reminding message after the prediction session is ended;
and if the session state identification is the predicted session end, pushing a reminding message.
6. A session processing apparatus comprising:
a session state prediction module: the system is used for predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
reminding the pushing module: the system is used for pushing a reminding message under the condition that the prediction result is that the session is predicted to be ended;
a session closing module: and closing the current session if no new session message is added in the preset time.
7. The apparatus of claim 6, wherein the characteristic data of the user chat comprises:
historical behavior traces of the user and/or session data of the current session and/or heartbeat data of the user.
8. The apparatus of claim 6, wherein the predicting the session state of the current session according to the feature data of the user chat comprises:
responding to the message sent by the customer service, executing the process of predicting the conversation state of the current conversation according to the characteristic data of the user chat;
or,
and after the customer service and/or the member sends out the message, if no new session message is added in the preset time, executing the process of predicting the session state of the current session according to the characteristic data of the user chat.
9. The apparatus of claim 6, wherein the prediction result comprises whether the current session predicts the end of the session and a corresponding confidence level, and if the prediction result is the predicted end of the session, pushing the reminder message comprises:
and if the current conversation is predicted to be the end of the predicted conversation and the corresponding confidence coefficient is larger than a preset threshold value, pushing a reminding message.
10. The apparatus of claim 6, wherein the current session is provided with a session state identification that is set to a normal state by default,
the pushing of the reminding message comprises:
judging the session state identifier, if the session state identifier is normal, setting the session state identifier as a reminding message after the prediction session is ended;
and if the session state identification is the predicted session end, pushing a reminding message.
11. An electronic device, comprising:
a memory for storing a program;
a processor, coupled to the memory, for executing the program for:
predicting the conversation state of the current conversation according to the characteristic data of the user chatting;
if the prediction result is that the prediction session is ended, pushing a reminding message;
and within the preset time, if no new session message is added, closing the current session.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910488383.4A CN112130907A (en) | 2019-06-05 | 2019-06-05 | Session processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910488383.4A CN112130907A (en) | 2019-06-05 | 2019-06-05 | Session processing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112130907A true CN112130907A (en) | 2020-12-25 |
Family
ID=73849041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910488383.4A Pending CN112130907A (en) | 2019-06-05 | 2019-06-05 | Session processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112130907A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114064319A (en) * | 2021-11-18 | 2022-02-18 | 中国银行股份有限公司 | Method and device for processing event data, electronic equipment and storage medium |
| CN115102915A (en) * | 2022-06-21 | 2022-09-23 | 元心信息科技集团有限公司 | Information interaction method and device, electronic equipment and computer readable storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1629870A (en) * | 2003-06-30 | 2005-06-22 | 微软公司 | Methods and architecture for providing status and forecasts of a user's preference and availability |
| CN106096059A (en) * | 2016-07-11 | 2016-11-09 | 上海亿保健康管理有限公司 | A kind of method based on scene pushed information |
| US20170195486A1 (en) * | 2015-12-30 | 2017-07-06 | Shanghai Xiaoi Robot Technology Co., Ltd. | Intelligent customer service systems, customer service robots, and methods for providing customer service |
| CN107634992A (en) * | 2017-09-05 | 2018-01-26 | 成都知道创宇信息技术有限公司 | A kind of method for carrying out auto-destruct resource using websocket linking status |
| CN107995377A (en) * | 2017-11-03 | 2018-05-04 | 平安科技（深圳）有限公司 | Customer service management method, electronic device and computer-readable recording medium |
| CN108833588A (en) * | 2018-07-09 | 2018-11-16 | 北京华沁智联科技有限公司 | Conversation processing method and device |
| CN109150701A (en) * | 2015-12-30 | 2019-01-04 | 上海智臻智能网络科技股份有限公司 | Customer service system method of servicing |
| CN109215642A (en) * | 2017-07-04 | 2019-01-15 | 阿里巴巴集团控股有限公司 | Processing method, device and the electronic equipment of man-machine conversation |
| CN109543005A (en) * | 2018-10-12 | 2019-03-29 | 平安科技（深圳）有限公司 | The dialogue state recognition methods of customer service robot and device, equipment, storage medium |
| CN109804602A (en) * | 2016-10-03 | 2019-05-24 | 微软技术许可有限责任公司 | Contact availability prediction |
-
2019
- 2019-06-05 CN CN201910488383.4A patent/CN112130907A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1629870A (en) * | 2003-06-30 | 2005-06-22 | 微软公司 | Methods and architecture for providing status and forecasts of a user's preference and availability |
| US20170195486A1 (en) * | 2015-12-30 | 2017-07-06 | Shanghai Xiaoi Robot Technology Co., Ltd. | Intelligent customer service systems, customer service robots, and methods for providing customer service |
| CN109150701A (en) * | 2015-12-30 | 2019-01-04 | 上海智臻智能网络科技股份有限公司 | Customer service system method of servicing |
| CN106096059A (en) * | 2016-07-11 | 2016-11-09 | 上海亿保健康管理有限公司 | A kind of method based on scene pushed information |
| CN109804602A (en) * | 2016-10-03 | 2019-05-24 | 微软技术许可有限责任公司 | Contact availability prediction |
| CN109215642A (en) * | 2017-07-04 | 2019-01-15 | 阿里巴巴集团控股有限公司 | Processing method, device and the electronic equipment of man-machine conversation |
| CN107634992A (en) * | 2017-09-05 | 2018-01-26 | 成都知道创宇信息技术有限公司 | A kind of method for carrying out auto-destruct resource using websocket linking status |
| CN107995377A (en) * | 2017-11-03 | 2018-05-04 | 平安科技（深圳）有限公司 | Customer service management method, electronic device and computer-readable recording medium |
| CN108833588A (en) * | 2018-07-09 | 2018-11-16 | 北京华沁智联科技有限公司 | Conversation processing method and device |
| CN109543005A (en) * | 2018-10-12 | 2019-03-29 | 平安科技（深圳）有限公司 | The dialogue state recognition methods of customer service robot and device, equipment, storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114064319A (en) * | 2021-11-18 | 2022-02-18 | 中国银行股份有限公司 | Method and device for processing event data, electronic equipment and storage medium |
| CN115102915A (en) * | 2022-06-21 | 2022-09-23 | 元心信息科技集团有限公司 | Information interaction method and device, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105653323B (en) | Application management method and device | |
| CN105677460B (en) | Applied program processing method and device | |
| US10986573B2 (en) | Bluetooth mesh network gateway and device data communication | |
| CN105893129B (en) | Method and device for processing application program in terminal | |
| CN105204743A (en) | Interaction control method and device for speech and video communication | |
| CN110474980A (en) | Data control method and device, electronic equipment and storage medium | |
| CN105246135A (en) | Wireless network accessing method and device, and mobile terminal | |
| US11832240B2 (en) | Method and device for sidelink communication | |
| CN105488026A (en) | Concerned topic reminding method and apparatus | |
| CN112130907A (en) | Session processing method and device and electronic equipment | |
| CN113867927A (en) | Resource allocation method, device, electronic equipment and storage medium | |
| CN111488207B (en) | Application process keep-alive method and device, network equipment and storage medium | |
| CN105281965A (en) | Traffic acquisition method and traffic acquisition device based on IOS | |
| CN108702708B (en) | Downlink control signaling detection method, device and storage medium | |
| CN107846646B (en) | Control method and device of intelligent sound box and readable storage medium | |
| CN105227426B (en) | Application interface switching method and device and terminal equipment | |
| CN106921733B (en) | Cluster notification pushing method and device and electronic equipment | |
| CN110868347A (en) | Message prompting method, device and system | |
| CN104093199A (en) | Timer setting method and terminal | |
| CN105075189A (en) | Receiving a communication event | |
| CN112688856B (en) | Method and device for releasing friend relationship | |
| CN108933868B (en) | Call prompting method, device and system | |
| CN112395103B (en) | Method and device for sending delay message and storage medium | |
| CN108196893A (en) | Adjust the method, apparatus and terminal of terminal sleeping | |
| CN114363146A (en) | Network detection method, system, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |