CN105553833B - Customer service system and its method of servicing, robot customer service - Google Patents

Customer service system and its method of servicing, robot customer service Download PDF

Info

Publication number
CN105553833B
CN105553833B CN201511025278.5A CN201511025278A CN105553833B CN 105553833 B CN105553833 B CN 105553833B CN 201511025278 A CN201511025278 A CN 201511025278A CN 105553833 B CN105553833 B CN 105553833B
Authority
CN
China
Prior art keywords
customer service
session
message
conversation message
robot
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201511025278.5A
Other languages
Chinese (zh)
Other versions
CN105553833A (en
Inventor
李思远
朱频频
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guizhou little love robot technology Co., Ltd.
Shanghai Zhizhen Intelligent Network Technology Co Ltd
Original Assignee
Guizhou Little Love Robot Technology Co Ltd
Shanghai Zhizhen Intelligent Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guizhou Little Love Robot Technology Co Ltd, Shanghai Zhizhen Intelligent Network Technology Co Ltd filed Critical Guizhou Little Love Robot Technology Co Ltd
Priority to CN201811074976.8A priority Critical patent/CN109245995B/en
Priority to CN201511025278.5A priority patent/CN105553833B/en
Priority to CN201811075502.5A priority patent/CN109150701B/en
Publication of CN105553833A publication Critical patent/CN105553833A/en
Priority to US15/390,172 priority patent/US10063702B2/en
Priority to US16/043,415 priority patent/US11032419B2/en
Application granted granted Critical
Publication of CN105553833B publication Critical patent/CN105553833B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/02User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/14Session management
    • H04L67/148Migration or transfer of sessions

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Manipulator (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

A kind of customer service system and its method of servicing, robot customer service, the customer service system method of servicing include: to detect whether itself is in session suspended state when robot customer service is received from the conversation message at consumer user end;When the robot customer service detects that itself is in session suspended state, the transmission operation of conversation message between the consumer user end and customer service client is executed;When the robot customer service, which detects, itself is not in session suspended state, as the robot customer service from conversation message described in main process task;In autonomous treatment process, when meeting preset session suspension condition, the process that the robot customer service is switched to session suspended state is executed.Above scheme can be realized artificial customer service and robot customer service cooperates, and so as to enhance the validity of customer service system service, improve the user experience of customer.

Description

Customer service system and its method of servicing, robot customer service
Technical field
The present invention relates to instant messaging field more particularly to a kind of customer service system and its method of servicing, robot visitor Clothes.
Background technique
With the rapid development of Internet, the raising of people's service awareness, network customer service has spread to all trades and professions, deep Enter the links to everyday commerce service.
Current customer service system is usually made of machine customer service and artificial customer service, and wherein machine customer service is generally based on net The immediate communication tool of page, artificial customer service be usually the immediate communication tool being embedded in webpage, each artificial customer service client There is manual maintenance at end.In customer service processes, when receiving the conversation message from customer, first carried out by machine customer service Service.When customer thinks that machine customer service can not solve the problems, such as its proposition, then click artificial customer service manually, Xiang Rengong customer service into Row consulting.
Above-mentioned customer service system, can quick response client to a certain extent demand.However, in actual application, Machine customer service identifies the content of the conversation message of customer's input, searches and the conversation message from the resource database stored Content matching data, and the obtained data of matching are sent to user client and carry out response, for same problem, usually Repeated answer can be mechanically carried out, is easy to enrage client, influences customer experience.And artificial customer service then can not Always Online", and Multiple customers are usually faced simultaneously, thus there is the case where cannot replying in time.Thus current customer service system is difficult to effectively The demand for services for meeting customer influences the user experience of customer.
Summary of the invention
Present invention solves the technical problem that being how to enhance the validity of customer service system service, the user's body of customer is improved It tests.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of customer service system method of servicing, which comprises
When robot customer service is received from the conversation message at consumer user end, detects and itself whether be in session hang-up State;
When the robot customer service detects that itself is in session suspended state, the consumer user end and customer service are executed The transmission operation of conversation message between client;
When the robot customer service, which detects, itself is not in session suspended state, independently by the robot customer service Manage the conversation message;In autonomous treatment process, when meeting preset session suspension condition, execute the robot visitor Clothes switch to the process of session suspended state.
Optionally, described when the robot customer service detects and itself is not in session suspended state, by the machine People's customer service is from conversation message described in main process task, comprising:
Identify the content of the conversation message;
According to the content of the conversation message, determine whether itself can be from conversation message described in main process task;
When determining that itself can be from conversation message described in main process task, extracted and the meeting from the Service Source stored The matched response message of content institute of message is talked about, and is sent to the consumer user end.
Optionally, described in autonomous treatment process, when meeting preset session suspension condition, execute the machine People's customer service switches to the process of session suspended state, comprising:
When determine itself can not from main process task or when can not identify the conversation message, will from the consumer user State in the subsequent session business at end is set as session suspended state, and extraction is pacified with the content matching of the conversation message Property response message and be sent to the consumer user end, and will it is described itself can not be from main process task or unrecognized conversation message It is sent to customer service client.
Optionally, the method also includes: the robot customer service will described in can not be from main process task or unrecognized meeting Pacifying property response message corresponding to words message can not be sent to described from together with main process task or unrecognized conversation message The customer service client.
Optionally, after the robot customer service detects that itself is in session suspended state, further includes: when the machine When people's customer service is not received from the conversation message of the customer service client, the robot customer service identifies the conversation message Content extracts the pacifying property response message with the content matching of the conversation message and is sent to the consumer user end.
Optionally, the method also includes: when in the session service at the robot customer service and the consumer user end In session status, and when receiving from the conversation message that the customer service client is sent to the consumer user end, by itself It is being switched to session suspended state with the session status in the session service at the consumer user end, and is executing the customer service client The transmitting of conversation message operates between end and the consumer user end.
Optionally, the method also includes: when determining the session between the customer service client and the consumer user end At the end of, restore from the state in the session service between the consumer user end to be session status.
Optionally, the conversation end between the determination customer service client and the consumer user end, including it is following It is at least one:
Determine that the transmission of sessionless message reaches preset duration between the customer service client and the consumer user end;
Detect that signal is completed in the session of the customer service client.
Optionally, the customer service client when detecting that session window is closed or detects that the customer service client is sent Conversation message in complete comprising display session content when issue the session and complete signal.
Optionally, the pacifying property response message is suitable for characterizing the state that customer service is in searching problem answers.
Optionally, the Service Source includes: language empirical data and customer service resource data.
Optionally, the conversation message between consumer user end is subjected to classification fractionation according to scene and obtains different scenes class Other customer service resource data.
Optionally, the method also includes: carry out big data machine training, to identify scene class belonging to conversation message Not.
Optionally, the content according to the conversation message, it is determined whether can be wrapped from conversation message described in main process task It includes:
Determine whether the robot customer service can independently answer the conversation message according to the language empirical data Content;
When determining that the robot customer service can not answer according to the language empirical data, the conversation message is determined Scene type belonging to content;
When determining that the robot customer service can independently answer according to the language empirical data, or there are the sessions When scene type belonging to the content of message, determine that the robot customer service can be from conversation message described in main process task.
Optionally, described when being determined to from conversation message described in main process task, it is extracted from the Service Source stored With the matched response message of content institute of the conversation message, comprising:
When determining that the robot customer service can independently answer according to the language empirical data, from the language stored It is extracted in empirical data and the matched response message of the content of conversation message institute;
When determination can not independently answer according to the language empirical data, extracted from the customer service resource data stored Under affiliated scene with the matched response message of the content of conversation message institute.
Optionally, the form of the conversation message comprises at least one of the following: the sentence of natural language text composition, data Link, voice, image and video.
Optionally, described image includes following at least one of: the either statically or dynamically picture with semantic information, or For the targeted product of customer's session or the photo or screenshotss information of service object.
To solve the above problems, the embodiment of the invention also provides a kind of robot customer service, the robot customer service includes:
First message interactive unit suitable for receiving the conversation message from consumer user end, and returns and disappears with the session The matched response message of content institute of breath;
State detection unit, suitable for receiving the conversation message from consumer user end when the first message interactive unit When, detect the robot customer service with the state in the session service at the consumer user end;
From Main Processor Unit, suitable for detecting that the robot customer service is not in session and hangs up when the state detection unit When state, returned from conversation message described in main process task, and by response message obtained by the first message interactive unit To the consumer user end;
Status control unit is suitable for described from the autonomous treatment process of Main Processor Unit, when meeting preset hang-up item When part, controlling the robot customer service is being that shape is hung up in session with the state in the subsequent session business at the consumer user end State;
Second message interactive unit, suitable for detecting that the robot customer service is in session and hangs when the state detection unit When the state of rising, the conversation message that the first message interactive unit receives is transmitted to customer service client;And it will be from described The conversation message of customer service client is sent to corresponding consumer user end by the first message interactive unit.
Optionally, described to include: from Main Processor Unit
Recognition unit, suitable for detecting that the robot customer service is not in session suspended state when the state detection unit When, identify the content of conversation message received by the first message interactive unit;
Ability judging unit determines institute suitable for the content of the conversation message identified according to the recognition unit Whether state robot customer service can be from conversation message described in main process task;
Storage unit is suitable for storage service resource;
First response message generation unit, suitable for determining that the robot customer service can be autonomous when the ability judging unit When handling the conversation message, the content institute with the conversation message is extracted from the Service Source that the storing sub-units store Matched response message.
Optionally, the status control unit, suitable for determining that the robot customer service can not when the ability judging unit When from main process task or can not identify the conversation message, the robot customer service is controlled in the rear extended meeting with the consumer user end State in call business is session suspended state;
It is described from Main Processor Unit further include: the second response message generation unit, be suitable in the status control unit control The robot customer service is made when being session suspended state with the state in the subsequent session business at the consumer user end, from institute State the pacifying property response message extracted in the Service Source of storage unit storage with the content matching of the conversation message;
The first message interactive unit is further adapted for the pacifying property response with the content matching of the conversation message Message is back to the consumer user end.
Optionally, the second message interactive unit is further adapted for not disappearing described from main process task or unrecognized session Corresponding the pacifying property response message of breath with it is described can not be sent to from together with main process task or unrecognized conversation message it is described Customer service client.
Optionally, described from Main Processor Unit, it is further adapted for detecting the robot customer service when the state detection unit It is being session suspended state with the state in the session service at the consumer user end, and the second message interactive unit does not connect When receiving from the conversation message of the customer service client, the content of the conversation message is identified, extract and the conversation message Content matching pacifying property response message and be sent to the consumer user end.
Optionally, the status control unit is further adapted for the session in the robot customer service and the consumer user end Session status is in business, and the second message interactive unit receives the conversation message from the customer service client When, the robot customer service is being switched to session hang-up shape with the state in the subsequent session business at the consumer user end State, and control the second message interactive unit and execute message exchange operations.
Optionally, the robot customer service further include: conversation end detection unit, be suitable for judge the customer service client and Whether the session between the consumer user end terminates;
The status control unit is further adapted for when the session between the determining customer service client and the consumer user end At the end of, restoring state of the robot customer service between the consumer user end in subsequent session business is session shape State.
Optionally, the conversation end detection unit comprises at least one of the following:
First detection sub-unit, is adapted to detect for whether the second message interactive unit free time reaches preset duration, and is reaching When preset duration, the conversation end between the customer service client and the consumer user end is determined;
Second detection sub-unit is adapted to detect for the session from the customer service client and completes signal, and comes detecting When completing signal from the session of the customer service client, the session between the customer service client and the consumer user end is determined Terminate.
Optionally, the Service Source that the storage unit is stored includes: language empirical data and customer service resource data.
Optionally, the robot customer service further include: machine training unit is suitable for carrying out big data machine to the robot Device training, to identify scene type belonging to conversation message, the scene type is will be between consumer user end according to scene Conversation message carry out classification split obtain.
Optionally, the ability judging unit, comprising:
First judgment sub-unit is adapted to determine that whether the robot customer service can be independently according to the language empirical data It answers the content of the conversation message;
Second judgment sub-unit, suitable for determining that the robot customer service can not autonomous basis when first judgment sub-unit When the language empirical data is answered, scene type belonging to the content of the conversation message is determined.
Optionally, the first response message generation unit, comprising:
First generates subelement, is suitable for independently being made according to the language empirical data when the determining robot customer service When answering, extracted from the language empirical data that the storage unit is stored and the matched response of the content of conversation message institute Message;
Second generates subelement, suitable for that can not be answered according to the language empirical data when the determining robot customer service When, from the content institute extracted in the customer service resource data that the storage unit is stored under affiliated scene with the conversation message The response message matched.
Optionally, the pacifying property response message is suitable for characterizing the state that customer service is in searching problem answers.
Optionally, the form of the conversation message comprises at least one of the following: the sentence of natural language text composition, data Link, voice, image and video.
Optionally, described image includes following at least one of: the either statically or dynamically picture with semantic information, or For the targeted product of customer's session or the photo or screenshotss information of service object.
To solve the above problems, the customer service system includes: customer the embodiment of the invention also provides a kind of customer service system Client, customer service client and any of the above-described kind of robot customer service suitable for conversating with the consumer user end, the visitor It takes client and the consumer user end passes through the robot customer service session.
Optionally, the robot customer service is suitable for when the consumer user end and customer service client that are in session status being more It is a, and determine that itself can not be from main process task or when can not identify the conversation message, according to the customer service client for being in session status The conversation message from consumer user end and corresponding pacifying property response message are sent to task amount most by the task amount at end Few customer service client.
Optionally, the robot customer service is suitable for when the consumer user end and customer service client that are in session status being more It is a, and determination can not be recorded from main process task or when can not identify the conversation message according to conversation message itself, will it is described itself The customer service of consumer user end conversation message is processed before can not being sent to from main process task or unrecognized conversation message Client.
Compared with prior art, the technical solution of the embodiment of the present invention has the advantages that
When robot customer service is received from the conversation message at consumer user end, session extension itself whether is in by detecting The state of rising, and when determining that itself is in session suspended state, execute session between the consumer user end and customer service client The transmission of message operates, i.e., is directly customer service by the artificial customer service for being located at customer service client, and itself is not in determining When session suspended state, as robot customer service itself from conversation message described in main process task, and in autonomous treatment process, work as satisfaction When preset session suspension condition, the process that the robot customer service is switched to session suspended state is executed, i.e., mainly by machine Device people customer service is independently the customer service positioned at the consumer user end, and when meeting certain condition, is automatically switched to by people Work is customer service, to realize that artificial customer service and robot customer service cooperate.On the one hand, session is in robot customer service When suspended state, it is only necessary to the transmission for the message that conversates and need not carry out it is any from main process task, robot customer service can be saved Service Source;On the other hand, robot customer service only when itself being not in session suspended state could utonomous working, Gu Rengong The priority of customer service is higher, can seize session to avoid robot customer service midway, customer is enabled to obtain consistent formula service body It tests, so as to improve the validity of customer service system service, improves the user experience of customer.
Further, robot customer service is receiving the conversation message from consumer user end and itself is being not in session extension , itself whether can be from conversation message described in main process task by the content and determination that identify the conversation message when state of rising.When When determining that itself can be from conversation message described in main process task, from extracted in the Service Source stored in the conversation message Hold matched response message, and sent to the consumer user end, customer is timely and effectively replied.
Further, when determine itself can not be from main process task or when can not identify the conversation message, on the one hand, by itself It is being set as session suspended state with the state in the subsequent session business at the consumer user end, process resource can be saved; On the other hand, it by sending the pacifying property response message with the content matching of the conversation message in time, can be obtained to avoid customer Impatience is generated less than reasonable response, and itself can not be sent to described from main process task or unrecognized conversation message Customer service client, manually selects without customer, when the robot customer service can not be effectively treated, may be implemented artificial customer service and When intervention and effectively solve the problems, such as the customer.In short, above scheme passes through the robot customer service association with artificial customer service automatically With work, customer can be timely and effectively solved the problems, such as, and customer is the area for being not felt by robot customer service Yu artificial customer service Not, during waiting to be answered, mood is available effectively to be pacified, and obtains better Interactive Experience.
Further, by by it is described can not be from pacifying property response corresponding to main process task or unrecognized conversation message Message can not be sent to the customer service client with described from together with main process task or unrecognized conversation message, so that artificial visitor Clothes it can be seen that robot customer service to the content of the response message of customer replies, convenient for the continuity and consistency of hold acknowledge, So as to optimize consistent formula service experience, the user experience of customer is improved.
Further, when robot customer service is in session suspended state, if not receiving the meeting from customer service client Words message identifies the content of conversation message when that is, artificial customer service does not intervene processing also, can recognize that conversation message Content when, corresponding pacifying property response message is extracted from the Service Source stored, and interact with customer in artificial customer service In the process, the robot customer service does not make any identification, from main process task or response to conversation message, but only carries out customer service client The transmission at end and the both sides' session of consumer user end, can be further improved the collaborative e-commerce of robot customer service Yu artificial customer service, into one Step alleviates the impatience in customer's waiting process.
Further, when being in session shape with robot customer service described in the session service at the consumer user end itself State, and when receiving from the conversation message of the customer service client, by robot customer service in the meeting with the consumer user end Session status in call business is switched to session suspended state, and executes between the customer service client and the consumer user end The transmission of conversation message operates, and in artificial and robot customer service cooperative working process, the priority of artificial customer service is higher, manually Customer service is as needed, can actively intervene at any time, therefore better service can be provided for customer.
Further, when robot customer service determines the conversation end between the customer service client and the consumer user end When, restore from the state in the subsequent session business between the consumer user end to be session status, i.e., in artificial visitor When clothes intervention is completed, the state of robot customer service is automatically switched back into, realizes the seamless rank of artificial customer service Yu robot customer service It connects, so as to advanced optimize the service experience of customer.
Further, by sessionless message transmission between the determination customer service client and the consumer user end up in advance If duration, or when detecting that session window is closed or detect in conversation message that the customer service client is sent comprising aobvious When showing the content that session is completed, signal is completed in the session that the customer service client is sent automatically, can automatically identify artificial visitor Clothes intervention is completed, and so as to reduce the operation of artificial customer service, reduces the workload of artificial customer service, is artificial customer service provider Just.
Further, by carrying out big data training to the robot customer service, the robot customer service is known Whether scene type belonging to other conversation message is capable of handling the conversation message and carries out subsequent so as to quickly determine Processing, can be improved customer service response speed, further enhances the Interactive Experience of customer.
Further, when the robot customer service is determined to independently be answered according to language empirical data, from being stored Language empirical data in extract with the matched response message of the content of conversation message institute, and when determination can not autonomous basis When language empirical data is answered, the matched response message of content institute under affiliated scene with the conversation message is chosen, thus not But it can be answered, and can be answered according to customer service resource data, and due to matched resource data according to language empirical data It is corresponding with the scene of customer service, thus the range for the response message that robot customer service can answer can be expanded and improve response Accuracy.
Further, disappeared by the pacifying property response for characterizing the state that customer service is in searching problem answers to consumer feedback Breath, finds for the content of conversation message with customer service client and provides the process of solution and be performed simultaneously, on the one hand can be with Reflect the virtual condition of customer service and be manually entered without customer service, has not only been saved the response operation time of artificial customer service, but also can be right Customer's mood plays the role of pacifying;On the other hand but also artificial customer service can will be put into and solve the problems, such as customer the more time In the middle, so as to more promptly providing the response for more enabling Customer Satisfaction.
Detailed description of the invention
Fig. 1 is a kind of customer service system structural schematic diagram in the embodiment of the present invention;
Fig. 2 is a kind of customer service system method of servicing flow chart in the embodiment of the present invention;
Fig. 3 is another customer service system method of servicing flow chart in the embodiment of the present invention;
Fig. 4 is a kind of consumer user end interactive interface schematic diagram in the embodiment of the present invention;
Fig. 5 is session status handoff procedure schematic diagram during a kind of customer service in the embodiment of the present invention;
Fig. 6 is a kind of structural schematic diagram of robot customer service in the embodiment of the present invention.
Specific embodiment
As previously mentioned, current customer service system, in customer service processes, machine customer service and artificial customer service are each independently For customer service, i.e., first serviced by machine customer service.When customer thinks that machine customer service can not solve the problems, such as its proposition, then Artificial customer service is clicked manually, and Xiang Rengong customer service is seeked advice from.Above scheme there are robot customer service mechanicalness repeat answer it is easy Enrage customer, and artificial customer service can not Always Online" and usual customer it is numerous, it is difficult to reply in time, therefore current customer service system It is difficult to effectively meet the demand for services of customer.
In view of the above-mentioned problems, the embodiment of the present invention provides a kind of customer service system, referring to Fig.1 shown in customer service system structure show It is intended to, comprising: consumer user end 11, customer service client 12 and the robot visitor suitable for conversating with the consumer user end 11 13 are taken, the customer service client and the consumer user end are conversated by the robot customer service.
In the customer service system of the embodiment of the present invention, cooperated by robot customer service and artificial customer service, by robot Customer service is unified to receive the conversation message from consumer user end, by detecting whether itself is in session suspended state, and true When determining itself to be in session suspended state, the transmission behaviour of conversation message between the consumer user end and customer service client is executed Make, i.e., be directly customer service by the artificial customer service for being located at customer service client, and itself is not in session suspended state determining When, as robot customer service itself from conversation message described in main process task, and in autonomous treatment process, hung when meeting preset session When the condition of rising, execute the process that the robot customer service is switched to session suspended state, i.e., it is mainly autonomous by robot customer service For positioned at the customer service at the consumer user end, and when meeting certain condition, automatically switch to by being manually customer service, To realize that artificial customer service and robot customer service cooperate.
It is understandable to enable above-mentioned purpose of the invention, feature and beneficial effect to become apparent, with reference to the accompanying drawing to this The specific embodiment of invention is described in detail.
Referring to FIG. 1 and FIG. 2, a kind of customer service system method of servicing in the embodiment of the present invention is carried out below by way of specific steps Detailed description.
S21, robot customer service receive the conversation message from consumer user end.
In specific implementation, the form of the conversation message can there are many.For example, it may be natural language text forms Any of them form such as sentence, data link, voice, image or video or diversified forms combination.
S22, robot customer service detect itself whether in session suspended state, itself be in session hang-up when detecting When state, step S23 is executed;When detect itself be in be not in session suspended state when, execute step S24.
In specific implementation, in order to save the process resource of robot customer service, robot customer service and artificial customer service are realized Cooperate, can the state of conversation message by robot customer service from main process task from consumer user end be set as " session shape State ", or " non-suspended state ", and can not state from main process task or when can not identify the content of conversation message by robot customer service It is set as " session suspended state ".
S23 executes the transmission operation of conversation message between the consumer user end and customer service client.
S24, the robot customer service is from conversation message described in main process task.
In an embodiment of the present invention, the process of robot customer service from the conversation message described in main process task is as follows: firstly, It identifies the content of the conversation message, later, according to the content of the conversation message, determines whether itself can be from main process task institute State conversation message, and when determining that itself can be from conversation message described in main process task, from the Service Source stored extract with The matched response message of content institute of the conversation message, and sent to the consumer user end.
S25 detects whether to meet preset session suspension condition, if so, thening follow the steps S26;If it is not, then executing Step S24.
S26 executes the process that the robot customer service is switched to session suspended state.
It, can will be described when meeting preset session suspension condition in the autonomous treatment process of robot customer service Robot customer service switches to session suspended state.For example, itself from main process task or can not can not identify the session when detect When message, following operation can be executed:
By from session suspended state is set as in the state in the subsequent session business at the consumer user end, extract With the pacifying property response message of the content matching of the conversation message and be sent to the consumer user end, and will itself nothing Method is sent to customer service client from main process task or unrecognized conversation message.
Wherein, the pacifying property response message refers to the message that the uneasiness of customer and negative feeling can be made to settle out, In specific implementation, it can be presented by modes such as natural word language, picture, voice, music.
In specific implementation, can by it is described can not be from pacifying property corresponding to main process task or unrecognized conversation message Response message can not be sent to the customer service client with described from together with main process task or unrecognized conversation message, so that people Work customer service can see robot customer service to the content of the response message of customer replies, convenient for the continuity of hold acknowledge and consistent Property, so as to optimize consistent formula service experience, improve the user experience of customer.
Using above-described embodiment, on the one hand, when robot customer service is in session suspended state, it is only necessary to conversate and disappear The transmission of breath and need not carry out it is any from main process task, the Service Source of robot customer service can be saved;On the other hand, robot visitor Clothes only when itself being not in session suspended state could utonomous working, the priority of old friend's work customer service is higher, can be to avoid machine Session is seized in device people customer service midway, enables customer to obtain consistent formula service experience, so as to improve customer service system service Validity, improve the user experience of customer.
Illustrate machine in the embodiment of the present invention below by way of the client service method of customer service system another in the embodiment of the present invention The principle that device people customer service and artificial customer service cooperate, referring to Fig. 3, the specific steps are as follows:
S31 receives the conversation message from consumer user end.
In specific implementation, as previously mentioned, the form of the conversation message can there are many.For example, it may be natural language Say the knot of any of them forms such as sentence, data link, voice, image or the video of text composition or diversified forms It closes.
In an embodiment of the present invention, the form of the conversation message includes the sentence of natural language text composition.Customer Description object can be described by the sentence that the natural language forms.For example, if description object is product, the meeting Words message then can be the consulting of the product related informations such as the size to product, shape, color, quality, date of manufacture, shelf-life Message is also possible to the advisory message to after services of product.If description object is service, the conversation message can be clothes Business content, service duration, points for attention provide the consultation information for servicing related content such as attendant of service.
In specific implementation, above-mentioned conversation message, can also be with voice, image or video other than being presented with written form Form present.For example, customer is conversated by way of audio or instant audio session or video conversation with customer service.
In specific implementation, customer can also be conversated in the form of picture with customer service consumer user end.It is described Picture can be static images with semantic information, dynamic picture or it is combined or customer's session is targeted product Or the photo or screenshotss information of service object.
In specific implementation, customer can also be sent out the link comprising product or service object by way of conversation message It sees off.
It is understood that in specific implementation, the conversation message can also be natural language text composition sentence, Two or more the form such as data link, voice, image or video is implemented in combination with.For example, customer passes through voice on one side Or video and customer service session, corresponding data link is sent to customer service by consumer user end on one side.
S32 is determined from the state in session service and is thened follow the steps S37 if session suspended state;Such as non-meeting Suspended state is talked about, S33 is thened follow the steps.
If robot customer service determine from the state in the session service at the consumer user end be non-session hang up State thens follow the steps S33.If robot customer service determines the state itself being in the session service at the consumer user end and is Session suspended state then no longer will independently return the subsequent Customer Problems from the consumer user end under current sessions It is multiple, but be sent to customer service client and artificial customer service is transferred to handle, i.e. execution step S37.
Following steps S33~S36 is the autonomous treatment process of robot customer service, and step S37 is triggering manpower intervention Process.
S33 identifies the content of the conversation message, if it is possible to identify, then follow the steps S34;It is no to then follow the steps S36。
In specific implementation, the content that the conversation message can be identified by robot customer service, disappears according to different sessions Breath form can carry out identifying processing using different recognition methods.For example, can identify nature by participle and semantics recognition The sentence of spoken and written languages composition.For another example, participle and semanteme can be further carried out by the way that the voice received is switched to text Identification.If in the conversation message include image, can in image text or pattern row extract and make further The operation such as identification.If can identify, S34 is thened follow the steps.
It should be noted that some conversation messages possibly can not identify, for example, the information content such as video or image it is very big or At this moment the form of message of person's complexity may can execute step S36 beyond the recognition capability of robot customer service.
S34, it is determined whether can be from main process task, if so, thening follow the steps S35;If not, thening follow the steps S36.
Robot customer service can be according to the content of the conversation message identified, it is determined whether can be from main process task.
In specific implementation, can be confirmed whether according to the Service Source stored can be from main process task for robot.It is deposited The Service Source of storage may include stored language empirical data and customer service resource data.
Specifically, can determine whether the content of the conversation message can be independently according to the language experience number first According to answering, when being determined to independently be answered according to the language empirical data, it is determined whether can be from main process task;When determining nothing When method is independently answered according to the language empirical data, then scene belonging to the content of the conversation message may further be determined Classification, when there are when scene type belonging to the content of the conversation message, determine that the robot customer service can be autonomous for determination Handle the conversation message.
Wherein, it is the ability for improving robot autonomous processing, the training of big data machine can be carried out to robot customer service, with Identify scene type belonging to conversation message.It in specific implementation, can in advance will be between consumer user end according to scene Conversation message carries out classification fractionation and obtains the customer service resource data of different scenes classification.
In an embodiment of the present invention, in scene category classification and machine learning process, the conversation message is not only wrapped Conversation message between robot customer service and consumer user end is included, further includes the conversation message of artificial customer service Yu consumer user end, All conversation messages are subjected to classification fractionation according to scene, do not take artificial customer service as independent individual here, but conduct The element of some specific scene in entirely service link, to entire customer service operating mode be reconstructed, in the feelings of a large amount of customers Under condition, the working efficiency of artificial customer service, optimization customer service experience can effectively improve.Wherein, the element of scene may include Customer and customer service and the two are directed to the conversation message content of different service scenarios.
S35 extracts the matched response message of institute from the Service Source stored and is sent to the consumer user end.
As previously mentioned, it may include stored language empirical data that Service Source, which may include stored Service Source, With customer service resource data.Correspondingly, in specific implementation, when being determined to independently be answered according to the language empirical data, It is extracted from the language empirical data stored and the matched response message of the content of conversation message institute;When determination can not be certainly When main root is answered according to the language empirical data, belonging to extracted in the customer service resource data stored under scene with the session The matched response message of content institute of message.
For example, when the content for identifying the conversation message is " hello ", by the language empirical data stored Middle extraction obtains matched response message are as follows: " you are good,.There is anything that can service for you? ".For another example, work as identification The content of the conversation message out are as follows: " one-piece dress that may I ask that part blue that I buys is delivered? " when, then it can be according to language It says empirical data and customer service resource data, therefrom extracts the corresponding order information of the customer, obtain response message are as follows: " you are good! The one-piece dress that you buy is shipped ".The logistics information of the order can be also enclosed in the response message.
S36, by from be set as suspended state in the subsequent session business at the consumer user end, and to the Gu Objective client replys pacifying property response message corresponding with the conversation message, and the conversation message and the pacifying property are answered It answers message and is sent to customer service client.
The process of session suspended state can be completed to switch to by the customer service of step S36 robot, realize robot customer service With the collaborative work of artificial customer service.It is illustrated below by way of a concrete application scene:
Can not be from main process task or when can not identify conversation message in robot, machine customer service is extracted to disappear with the session Cease the pacifying property response message of content matching.In specific implementation, in order to avoid the conversation message of customer cannot answer for a long time It answers and generates mood restless, the pacifying property response message is suitable for characterizing customer service and is in the shape for finding problem answers State.For example, when the content for identifying conversation message are as follows: " I wants to buy double Men's Leather Shoes ", robot customer service determination can not independently be located When reason, on the one hand by from be set as session suspended state in the subsequent session business at the consumer user end;Another party Face, matching obtain pacifying property response message are as follows: " uh, it is good.Waiting, I goes to look to be suitble to your shoes.", by the pacifying property Response message is sent to consumer user end, so that customer is replied in time and patiently waited, and by " I wants to buy double men This conversation message of leather shoes " is sent to customer service customer side, so that artificial customer service is handled.It also can be set in advance some in machine Device people customer service can not identify corresponding pacifying property response message when the content of specific conversation message, such as receiving Picture, when can not identify, corresponding pacifying property response message can be set to " just a moment,please, I first has a look ".
In specific implementation, can by it is described can not be from pacifying property corresponding to main process task or unrecognized conversation message Response message can not be sent to the customer service client with described from together with main process task or unrecognized conversation message, so that people Work customer service can see robot customer service to the content of the response message of customer replies, convenient for the continuity of hold acknowledge and consistent Property, so as to optimize consistent formula service experience, improve the user experience of customer.
The conversation message is transmitted to corresponding customer service client by S37.
When robot customer service is in session suspended state, it is only necessary to the transmission for the message that conversates and need not carry out it is any From main process task, the conversation message from customer's client and customer service client is transmitted to other side respectively, is intervened by artificial customer service Processing, robot customer service only conversate the forwarding of message, without doing any identification, processing or response, so as to save The Service Source of robot customer service.
As can be seen from the above embodiments, when receiving from the conversation message at consumer user end, robot customer service itself is first First detect and itself whether be in session suspended state, and determine itself be not in session suspended state when, just by the machine People's customer service executes the operation for identifying the content of the conversation message, and when determining that itself is in session suspended state, then by people Work customer service is conversated interaction by customer service client and customer, to realize that artificial and robot customer service preferably cooperates with work Make, on the one hand, when robot customer service is in session suspended state, it is only necessary to the transmission for the message that conversates and need not be appointed What can save the Service Source of robot customer service from main process task, and on the other hand, robot customer service only itself is being not in session It could work when suspended state, the priority of old friend's work customer service is higher, session can be seized to avoid robot customer service midway, so that Customer can obtain consistent formula service experience, improve the user experience of customer.
In specific implementation, it in order to further alleviate the impatience in customer's waiting process, is in robot customer service It, i.e., can when artificial customer service does not intervene processing also if not receiving the conversation message from customer service client when session suspended state It is identified with the content to conversation message, in the content that can recognize that conversation message, from the Service Source stored Extract corresponding pacifying property response message;And receiving the conversation message from customer service client, i.e., after manpower intervention processing, In artificial customer service and customer's interactive process, the robot customer service will not make any identification to conversation message, from main process task or Response, but only carry out the transmission of customer service client and the both sides' session of consumer user end.
In specific implementation, when determining the conversation end between the customer service client and the consumer user end, machine Device people customer service can independently restore from the state in the session service between the consumer user end to be session status, i.e., Non-session suspended state.
When artificial customer service intervenes completion, by automatically switching back into the state of robot customer service, artificial customer service is realized With the seamless connection of robot customer service, so as to advanced optimize the service experience of customer.In specific implementation, can have more Kind mode determines the conversation end between the customer service client and the consumer user end.For example, determining the customer service client Whether the transmission of sessionless message reaches preset duration between end and the consumer user end, when reaching preset duration, it is determined that institute State the conversation end between customer service client and the consumer user end.For another example, if detect from the customer service client Session complete signal, when detecting that session from the customer service client completes signal, it is determined that the customer service client With the conversation end between the consumer user end.In an embodiment of the present invention, the customer service client can detect The customer service client issues the session when session window is closed and completes signal.In an alternative embodiment of the invention, work as inspection Measure when the content completed in the conversation message that the customer service client is sent comprising display session that the consumer user end can also Signal is completed to issue the session.
It is understood that in specific implementation, as needed, the method in above-mentioned difference embodiment, which can combine, to be made With.
Preset duration is reached by sessionless message transmission between the determination customer service client and the consumer user end, or Person is when detecting that session window is closed or detects complete comprising display session in conversation message that the customer service client is sent At content when, signal is completed in session that the customer service client is sent automatically, can be automatically identified artificial customer service and intervened At, so as to reduce the operation of artificial customer service, reduce the workload of artificial customer service, for artificial customer service provide conveniently.
In specific implementation, when with itself be in session status in the session service at the consumer user end, and receive When to conversation message from the customer service client, by from the session shape in the session service at the consumer user end State is switched to session suspended state, and executes the transmission behaviour of conversation message between the customer service client and the consumer user end Make, i.e., in artificial and robot customer service cooperative working process, the priority of artificial customer service is higher, and artificial customer service is as needed, It can actively intervene at any time, so as to provide better service for customer.
It is understood that being to receive a conversation message from consumer user end described in above-described embodiment When process flow, each conversation message received can be handled according to the above process.
To more fully understand those skilled in the art and realizing the present invention, below by way of a specific session context into Row is described in detail.
Referring to consumer user end interactive interface schematic diagram shown in Fig. 4.The interactive interface is the meeting of customer A and customer service B Interactive interface is talked about, is shown by the consumer user end of customer A.Wherein, in customer service system, no matter robot customer service or people Work customer service, the vivid customer service B unified as one show that active service person may be robot customer service to customer A, or It is some the subsequent artificial customer service of customer service client.The box A and B respectively indicates the identification information of customer A and customer service B, In specific implementation, it can be shown with the customer A and the information such as the customized head portrait of customer service B and the pet name in the box A and B Show.Temporal information " 5:44 in afternoon ", " 5:50 in afternoon " in dotted line frame 48,49 indicate the consumer user end interface display of customer A Session occur at the time of.The conversation message content that right side conversation message is issued by customer A, left side conversation message are customer service B Response message content.Below to this session interaction during, treatment process performed by customer service system describes in detail:
Customer A sends conversation message " hello " by consumer user end, and robot customer service, which confirms, itself is not in session extension When the state of rising, the conversation message is identified, whether after identification obtains, first confiring that can be according to language empirical data Answer, when determination can answer according to language data, extract the matched response message of institute " you are good,.What has can Think what you serviced? " and it is sent to the consumer user end of customer A.Customer A then passes through consumer user end and sends conversation message " I want buy double leather shoes ", robot customer service confirms itself be not in session suspended state and identified after, confirmation can not be autonomous Processing, then extract with conversation message " I want buy double leather shoes " institute matched pacifying property response message " uh, it is good.Waiting, I goes to see See the shoes for being suitble to you.", meanwhile, the robot customer service can will be from subsequent with the consumer user end of the customer A Session state setting in session service is session suspended state, while the conversation message " I wants to buy double leather shoes " being sent to Customer service client is handled by artificial customer service.Customer A replys conversation message " good, to thanks ".
It should be noted that artificial customer service may not in position or since artificial customer service needs the customer serviced too many, For the moment can not intervention in time processing, it is such crossed a period of time, customer A further through consumer user end issue conversation message " may I ask Get well? ", robot customer service receive the conversation message " please say hello? " afterwards, detect that itself being in session hangs up shape State then identifies the content of the message, extracts and replys corresponding pacifying property response message " waiting, I is also seeing ", concurrently It send to the consumer user end of the customer A.
Later, artificial customer service intervention, sending conversation message by customer service client, " you are good, I feels this following shoes very It is suitble to you.Http//www.tmall.com/ ", the message that robot customer service sends the artificial customer service with no treatment, It is transferred directly to the consumer user end of the customer A, after customer A sees the conversation message, reply conversation message " uh, it is good, I consider look at ", artificial customer service after customer service client receives this conversation message, successively reply response conversation message " uh, it is good 's.You are good can to contact me at any time ", and " thank to your presence, 88 ".
According to above-mentioned process flow, conversation message 41,42 is the message of robot autonomous processing and response, conversation message 43 It is robot customer service pacifying property response message generated with 44, conversation message 45,46 and 47 is the session of artificial customer service response Message.
It is understood that in specific implementation, conversation message 46 and 47 may be what robot customer service automatically generated Response message.If for example, the conversation message robot customer service of customer service response receive conversation message " uh, it is good, I consider see See " after, it does not receive the response message from customer service client in preset duration, can be confirmed that manpower intervention terminates, then may be used To identify the content of the conversation message.It, in an embodiment of the present invention, can be with after the content for identifying the conversation message According to the language empirical data stored, directly answer " uh, it is good.You are good can to contact me at any time " and " thank you Presence, 88 ".In an alternative embodiment of the invention, true according to language empirical data after the content for identifying the conversation message Surely it can not independently answer, then match the corresponding scene type of the conversation message, and the extraction from the Service Source stored Match response message " uh, it is good.You are good can to contact me at any time " and " thank to your presence, 88 ", and be successively sent to The consumer user end of the customer A.
To more fully understand those skilled in the art and realizing the present invention, implement referring to the present invention shown in fig. 5 Session status handoff procedure schematic diagram during a kind of customer service in example, to robot customer service in service process in session service Stateful switchover process is described in detail.For example, robot customer service original state is session status 51 (non-session suspended state), When the unidentified conversation message received of robot customer service or robot customer service can not from conversation message described in main process task, or When the artificial customer service of person intervenes session, then session suspended state 52 is switched to.And when robot customer service is in session suspended state, If detect the signal that artificial customer service intervention is completed, the robot customer service can conversate recovery 53, pass through meeting Words restore 53, and robot customer service can continue independently to service, that is, be switched to session status 51, can independently be customer service.? Robot customer service is in after the completion of session suspended state or manpower intervention, if not receiving the new meeting from consumer user end Message is talked about, then entire conversation procedure terminates, that is, is in conversation end state 54.
To more fully understand those skilled in the art and realizing the present invention, the embodiment of the invention also provides one kind can Realize the robot customer service of above-mentioned client service method, referring to Fig. 6, robot customer service 60 may include: first message interactive unit 61, State detection unit 62, from Main Processor Unit 63, status control unit 64 and second message interactive unit 65, in which:
First message interactive unit 61 suitable for receiving the conversation message from consumer user end, and returns and the session The matched response message of content institute of message.
State detection unit 62, suitable for receiving the session from consumer user end when the first message interactive unit 61 When message, detect the robot customer service with the state in the session service at the consumer user end.
From Main Processor Unit 63, suitable for detecting that the robot customer service is not in session when the state detection unit 62 When suspended state, pass through the first message interactive unit from conversation message described in main process task, and by response message obtained It is back to the consumer user end.
Status control unit 64 is suitable for described from the autonomous treatment process of Main Processor Unit 63, when meeting preset extension When the condition of rising, controlling the robot customer service is being session hang-up with the state in the subsequent session business at the consumer user end State.
Second message interactive unit 65, suitable for detecting that the robot customer service is in meeting when the state detection unit 62 When talking about suspended state, the conversation message that the first message interactive unit 61 receives is transmitted to customer service client;And in the future Corresponding consumer user end is sent to by the first message interactive unit 61 from the conversation message of the customer service client.
In specific implementation, the form of the conversation message may include following at least one: natural language text composition Sentence, data link, voice, image and video.
Wherein, described image includes following at least one of: the either statically or dynamically picture with semantic information, Huo Zhewei The targeted product of customer's session or the photo or screenshotss information of service object.
Using above-mentioned robot customer service, on the one hand, when robot customer service is in session suspended state, it is only necessary to be understood Talk about message transmission and need not carry out it is any from main process task, the Service Source of robot customer service can be saved;On the other hand, machine People's customer service only when itself being not in session suspended state could utonomous working, the priority of old friend's work customer service is higher, can keep away Exempt from robot customer service midway and seize session, customer is enabled to obtain consistent formula service experience, realizes robot customer service and artificial Customer service cooperates, and so as to improve the validity of customer service system service, improves the user experience of customer.
In specific implementation, as shown in fig. 6, described from Main Processor Unit 63 may include: that recognition unit 631, ability are sentenced Disconnected unit 632, storage unit 633 and the first response message generation unit 632, in which:
Recognition unit 631, suitable for detecting that the robot customer service is not in session and hangs when the state detection unit 62 When the state of rising, the content of conversation message received by the first message interactive unit 61 is identified.
Ability judging unit 632, suitable for identifying the content of the obtained conversation message according to the recognition unit 631, Determine whether the robot customer service can be from conversation message described in main process task.
Storage unit 633 is suitable for storage service resource.Wherein, Service Source may include: language empirical data and customer service Resource data etc..
First response message generation unit 634 is suitable for determining the robot customer service energy when the ability judging unit 632 It is enough from conversation message described in main process task when, extract from the Service Source that the storing sub-units 633 store and disappear with the session The matched response message of content institute of breath.
Using above-mentioned robot customer service, hung receiving the conversation message from consumer user end and itself being not in session , itself whether can be from conversation message described in main process task by the content and determination that identify the conversation message when state of rising.When When determining that itself can be from conversation message described in main process task, from extracted in the Service Source stored in the conversation message Hold matched response message, and sent to the consumer user end, customer is timely and effectively replied.
In an embodiment of the present invention, the robot customer service further includes machine training unit 66, is suitable for the machine People carries out the training of big data machine, and to identify scene type belonging to conversation message, the scene type is will be with according to scene Conversation message between consumer user end carries out classification fractionation and obtains.
By carrying out big data training to the robot customer service, the robot customer service is enabled to identify conversation message Whether affiliated scene type is capable of handling the conversation message and carries out subsequent processing so as to quickly determine, can be with Customer service response speed is improved, the Interactive Experience of customer is further enhanced.
In specific implementation, the ability judging unit 632 may include:
First judgment sub-unit (not shown) is adapted to determine that whether the robot customer service can be autonomous according to Language empirical data is answered the content of the conversation message;
Second judgment sub-unit (not shown), suitable for determining the robot customer service when first judgment sub-unit When can not independently answer according to the language empirical data, scene type belonging to the content of the conversation message is determined.
In specific implementation, the first response message generation unit 634 may include:
First generates subelement (not shown), is suitable for independently being passed through according to the language when the determining robot customer service When testing data and answering, the content with the conversation message is extracted from the language empirical data that the storage unit 633 is stored The matched response message of institute;
Second generates subelement (not shown), is suitable for when the determining robot customer service can not be according to the language experience number When according to answering, belonging to extracted in the customer service resource data that the storage unit 633 is stored under scene with the conversation message The matched response message of content institute.
Using the robot customer service in above-described embodiment, when the robot customer service is determined to independently according to language experience When data are answered, the matched response message of content institute of extraction and the conversation message from the language empirical data stored, And when determination can not independently answer according to language empirical data, choose the content institute under affiliated scene with the conversation message The response message matched can not only answer according to language empirical data, and can be answered according to customer service resource data, and due to Matched resource data is corresponding with the scene of customer service, thus can expand the response message that robot customer service can answer Range and the accuracy for improving response.
In specific implementation, as shown in fig. 6, the status control unit 64, is suitable for determining when the ability judging unit The robot customer service can not from main process task or when can not identify the conversation message, control the robot customer service with it is described State in the subsequent session business at consumer user end is session suspended state.
Correspondingly, described to may also include that the second response message generation unit 635 from Main Processor Unit 63, it is suitable for described It is being meeting with the state in the subsequent session business at the consumer user end that status control unit 64, which controls the robot customer service, When talking about suspended state, extracted from the Service Source that the storage unit 633 stores and the content matching of the conversation message Pacifying property response message.The first message interactive unit 634 is further adapted for described and the conversation message the content matching Pacifying property response message is back to the consumer user end.
The pacifying property response message refers to the message that the uneasiness of customer and negative feeling can be made to settle out, specific In implementation, it can be presented by modes such as natural word language, picture, voice, music.In an embodiment of the present invention, described Pacifying property response message is suitable for characterizing customer service and is in the state for finding problem answers.
By characterizing the pacifying property response message that customer service is in the state of searching problem answers to consumer feedback, with customer service Client is found for the content of conversation message and provides the process of solution and is performed simultaneously, and on the one hand can reflect customer service Virtual condition and be manually entered without customer service, not only saved the response operation time of artificial customer service, but can to customer's mood rise To the effect of pacifying;On the other hand but also artificial customer service can will be put into and solve the problems, such as in customer the more time, thus The response for more enabling Customer Satisfaction can more promptly be provided.
Robot customer service in above-described embodiment itself from main process task or can not can not identify the conversation message when determining When, on the one hand, it will be set as session suspended state in the state in the subsequent session business at the consumer user end certainly, it can To save process resource;On the other hand, by sending the pacifying property response message with the content matching of the conversation message in time, Can cannot get reasonable response to avoid customer and generate impatience, and will it is described itself can not be from main process task or unrecognized Conversation message is sent to customer service client, manually selects without customer, can be with when the robot customer service can not be effectively treated Realize that artificial customer service intervenes in time and effectively solves the problems, such as the customer.In short, above scheme is automatic by robot customer service With the collaborative work of artificial customer service, customer can be timely and effectively solved the problems, such as, and customer is to be not felt by robot customer service With the difference of artificial customer service, during waiting to be answered, mood is available effectively to be pacified, and obtains better Interactive Experience.
In specific implementation, the second message interactive unit 65 is further adapted for from main process task or can not identifying described Conversation message corresponding to pacifying property response message and it is described can not be from one starting of main process task or unrecognized conversation message It send to the customer service client, so that artificial customer service can see robot customer service to the content of the response message of customer replies, The user experience of customer is improved convenient for the continuity and consistency of hold acknowledge so as to optimize consistent formula service experience.
It is described from Main Processor Unit 63, be further adapted for when the state detection unit 62 detect the robot customer service with State in the session service at the consumer user end is session suspended state, and the second message interactive unit 65 does not receive When to conversation message from the customer service client, identifies the content of the conversation message, extract and the conversation message The pacifying property response message of content matching is simultaneously sent to the consumer user end.
Using above-mentioned robot customer service, when robot customer service is in session suspended state, if not receiving from customer service The conversation message of client identifies the content of conversation message when that is, artificial customer service does not intervene processing also, can identify Out when the content of conversation message, corresponding pacifying property response message is extracted from the Service Source stored, and in artificial customer service In customer's interactive process, the robot customer service not to conversation message make it is any identification, from main process task or response, but only into The transmission of row customer service client and the both sides' session of consumer user end, can be further improved the association of robot customer service Yu artificial customer service It is unison, further alleviate the impatience in customer's waiting process.
In specific implementation, the status control unit 64 is further adapted in the robot customer service and the consumer user Session status is in the session service at end, and the second message interactive unit 65 is received from the customer service client When conversation message, the robot customer service is being switched to session with the state in the subsequent session business at the consumer user end Suspended state, and control the second message interactive unit 65 and execute message exchange operations.In artificial and robot customer service collaboration In the course of work, by the cooperation of status control unit and second message interactive unit in the robot customer service, so that manually The priority of customer service is higher, and artificial customer service is as needed, can actively intervene at any time, therefore better clothes can be provided for customer Business.
In specific implementation, the robot customer service may also include that conversation end detection unit 67, be suitable for judging the visitor Whether the session taken between client and the consumer user end terminates;The status control unit 64 is further adapted for when determining institute When stating the conversation end between customer service client and the consumer user end, restore the robot customer service objective with the customer State between the end of family in subsequent session business is session status.
When robot customer service determines the conversation end between the customer service client and the consumer user end, restore certainly The state in subsequent session business between the consumer user end is session status, i.e., intervenes and complete in artificial customer service When, the state of robot customer service is automatically switched back into, realizes the seamless connection of artificial customer service Yu robot customer service, so as to Advanced optimize the service experience of customer.
In an embodiment of the present invention, the conversation end detection unit 67 comprises at least one of the following:
It is idle whether up in advance to be adapted to detect for the second message interactive unit 65 for first detection sub-unit (not shown) If duration, and when reaching preset duration, determine the conversation end between the customer service client and the consumer user end;
Second detection sub-unit (not shown) is adapted to detect for the session from the customer service client and completes signal, And when detecting that signal is completed in the session from the customer service client, the customer service client and the consumer user are determined Conversation end between end.
For example, first detection sub-unit determines that sessionless disappears between the customer service client and the consumer user end Breath transmission when detecting that session window is closed or detects the customer service client up to preset duration or the second detection sub-unit When holding the content comprising display session completion in the conversation message sent, letter is completed in the session that the customer service client is sent automatically Number, artificial customer service intervention can be automatically identified and completed, so as to reduce the operation of artificial customer service, reduce the work of artificial customer service It measures, is provided conveniently for artificial customer service.
The embodiment of the invention also provides the customer service systems that can be realized above-mentioned client service method, referring to Fig.1 shown in customer service System.
In specific implementation, the consumer user end and customer service client can be presented in a variety of forms.For example, described Consumer user end and customer service client can be built in the program in browser and when detecting that browser page is opened Automatic running.For another example, the consumer user end and customer service client are independent applications client, are built in general-purpose computations The desktop computer of machine function, mobile phone, in car-mounted terminal and can start and run under the operation of customer tablet computer.For another example, institute It states consumer user end and customer service client can also be to be built in product supplier or ISP is special customized in customer With in equipment, the special equipment can be used for exhibiting and selling or service experience during customer and product supplier or ISP into Row consulting and feedback, preferably to meet customer demand.
It is understood that the way of realization at the consumer user end and customer service client conversed can be identical, it can also With difference, as long as compatible identical communication protocol can be realized session.
Wherein consumer user end 11, the specific structure of customer service client 12 and robot customer service 13 and working principle etc. are specific Implementation may refer to the introduction in the various embodiments described above, and which is not described herein again.
In specific implementation, robot customer service can simultaneously with the session of multiple consumer user ends, robot customer service The conversation message received can be forwarded to different customer service clients.When the consumer user end and customer service for being in session status When client is multiple, when robot customer service determination can not from main process task or when can not identify the conversation message, in order to Reply the conversation message of customer as early as possible, can be according to the task amount of the customer service client in session status, it will be described Conversation message and corresponding pacifying property response message from consumer user end are sent to the least customer service client of task amount.Example Such as, 10 artificial customer services are shared from the background, respectively correspond 10 different customer service clients, it can be according to current each customer service client Hold the quantity at consumer user end corresponding to the conversation message of processing, the conversation message that the customer service robot can will receive It evenly distributes to each customer service client.
In specific implementation, in order to make customer obtain preferably consistent formula service, while the clothes of each artificial customer service being improved Business efficiency, the robot customer service are suitable for when the consumer user end and customer service client that are in session status being multiple, and really Determining itself can not be from main process task or when can not identify the conversation message, according to the task of the customer service client in session status Amount, is sent to the least customer service client of task amount for the conversation message from consumer user end.Implement in the present invention one Example in, the robot customer service can also by by it is described can not handle or unrecognized conversation message corresponding to pacifying property answer It answers message and is sent to the customer service client for processing consumer user end conversation message before together, to avoid artificial visitor Clothes do not know about with the exchanging information for customer and influence the experience of customer.
It is understood that as needed, forwarded the messages in customer service client process in the robot customer service, it can It, can be by specific repeating process to consider that a variety of allocation strategies, each allocation strategy can configure different priority simultaneously It is matched, is not detailed herein according to priority orders.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage Medium may include: ROM, RAM, disk or CD etc..
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute Subject to the range of restriction.

Claims (29)

1. a kind of customer service system method of servicing characterized by comprising
When robot customer service is received from the conversation message at consumer user end, detects and itself whether be in session hang-up shape State;
When the robot customer service detects that itself is in session suspended state, the consumer user end and customer service client are executed The transmission operation of conversation message between end;
When the robot customer service, which detects, itself is not in session suspended state, by the robot customer service from main process task institute State conversation message;In autonomous treatment process, when meeting preset session suspension condition, the robot customer service is cut in execution Shift to the process of session suspended state;
When determining the conversation end between the customer service client and the consumer user end, restore from the customer The state in session service between client is session status;
It is described when the robot customer service detects and itself is not in session suspended state, independently by the robot customer service Manage the conversation message, comprising: identify the content of the conversation message;According to the content of the conversation message, determine that itself is It is no can be from conversation message described in main process task;When determining that itself can be from conversation message described in main process task, from the clothes stored The matched response message of content institute of extraction and the conversation message in resource of being engaged in, and sent to the consumer user end;
It is described in autonomous treatment process, when meeting preset session suspension condition, execute by the robot customer service switch To the process of session suspended state, comprising: when determine itself can not from main process task or when can not identify the conversation message, incite somebody to action from It is set as session suspended state in the state in the subsequent session business at the consumer user end, extraction disappears with the session The pacifying property response message of the content matching of breath is simultaneously sent to the consumer user end, and will it is described itself can not from main process task or Unrecognized conversation message is sent to customer service client;
The customer service system provides artificial customer service, robot customer service described in the above process and the artificial customer service seamless connection.
2. customer service system method of servicing according to claim 1, which is characterized in that further include:
The robot customer service can not disappear described from pacifying property response corresponding to main process task or unrecognized conversation message Breath can not be sent to the customer service client with described from together with main process task or unrecognized conversation message.
3. customer service system method of servicing according to claim 1, which is characterized in that when the robot customer service detects certainly It is in after session suspended state, further includes:
When the robot customer service does not receive from the conversation message of the customer service client, the robot customer service identification The content of the conversation message extracts the pacifying property response message with the content matching of the conversation message and is sent to the Gu Objective client.
4. customer service system method of servicing according to claim 1, which is characterized in that further include:
When being in session status in the session service at the robot customer service and the consumer user end, and receive from described It, will be from the session service with the consumer user end when conversation message that customer service client is sent to the consumer user end In session status be switched to session suspended state, and execute session between the customer service client and the consumer user end and disappear The transmitting of breath operates.
5. customer service system method of servicing according to claim 1, which is characterized in that the determination customer service client with Conversation end between the consumer user end, comprises at least one of the following:
Determine that the transmission of sessionless message reaches preset duration between the customer service client and the consumer user end;
Detect that signal is completed in the session of the customer service client.
6. customer service system method of servicing according to claim 5, which is characterized in that the customer service client is detecting meeting Hair when talking about close or when detecting the content completed in conversation message that the customer service client is sent comprising display session Signal is completed in the session out.
7. customer service system method of servicing according to claim 1, which is characterized in that the pacifying property response message is suitable for table Sign customer service is in the state for finding problem answers.
8. customer service system method of servicing according to claim 1, which is characterized in that the Service Source includes: language warp Test data and customer service resource data.
9. customer service system method of servicing according to claim 8, which is characterized in that according to scene will with consumer user end it Between conversation message carry out classification split obtain the customer service resource data of different scenes classification.
10. customer service system method of servicing according to claim 9, which is characterized in that further include: carry out big data machine instruction Practice, to identify scene type belonging to conversation message.
11. customer service system method of servicing according to claim 9 or 10, which is characterized in that described to be disappeared according to the session The content of breath, it is determined whether can be from conversation message described in main process task, comprising:
Determine whether the robot customer service can independently answer the content of the conversation message according to the language empirical data;
When determining that the robot customer service can not answer according to the language empirical data, the content of the conversation message is determined Affiliated scene type;
When determining that the robot customer service can independently answer according to the language empirical data, or there are the conversation messages Content belonging to scene type when, determine that the robot customer service can be from conversation message described in main process task.
12. customer service system method of servicing according to claim 11, which is characterized in that described to be determined to from main process task When the conversation message, the matched response message of content institute of extraction and the conversation message from the Service Source stored, Include:
When determining that the robot customer service can independently answer according to the language empirical data, from the language experience stored It is extracted in data and the matched response message of the content of conversation message institute;
When determination can not independently answer according to the language empirical data, from the customer service resource data stored belonging to extraction Under scene with the matched response message of the content of conversation message institute.
13. customer service system method of servicing according to claim 1, which is characterized in that the form of the conversation message includes Following at least one: sentence, data link, voice, image and the video of natural language text composition.
14. customer service system method of servicing according to claim 13, which is characterized in that described image include it is following at least its Middle one kind: the either statically or dynamically picture with semantic information, or be the targeted product of customer's session or the photograph of service object Piece or screenshotss information.
15. a kind of robot customer service characterized by comprising
First message interactive unit suitable for receiving the conversation message from consumer user end, and returns and the conversation message The matched response message of content institute;
State detection unit, suitable for when the first message interactive unit is received from the conversation message at consumer user end, Detect the robot customer service with the state in the session service at the consumer user end;
From Main Processor Unit, suitable for detecting that the robot customer service is not in session suspended state when the state detection unit When, institute is back to by the first message interactive unit from conversation message described in main process task, and by response message obtained State consumer user end;
Status control unit is suitable for described from the autonomous treatment process of Main Processor Unit, when meeting preset suspension condition, Controlling the robot customer service is being session suspended state with the state in the subsequent session business at the consumer user end;
Second message interactive unit, suitable for detecting that the robot customer service is in session and hangs up shape when the state detection unit When state, the conversation message that the first message interactive unit receives is transmitted to customer service client;And the customer service will be come from The conversation message of client is sent to corresponding consumer user end by the first message interactive unit;
Conversation end detection unit, suitable for judging whether the session between the customer service client and the consumer user end ties Beam;
It is described from Main Processor Unit include: recognition unit, suitable for detecting the robot customer service when the state detection unit When being not in session suspended state, the content of conversation message received by the first message interactive unit is identified;Ability is sentenced Disconnected unit determines that the robot customer service is suitable for the content of the conversation message identified according to the recognition unit It is no can be from conversation message described in main process task;Storage unit is suitable for storage service resource;First response message generation unit is fitted It is single from the storage in when the ability judging unit determines that the robot customer service can be from conversation message described in main process task It is extracted in the Service Source of member storage and the matched response message of the content of conversation message institute;
The status control unit, suitable for determining that the robot customer service can not be from main process task or nothing when the ability judging unit Method identify the conversation message when, control the robot customer service with the shape in the subsequent session business at the consumer user end State is session suspended state;It is described from Main Processor Unit further include: the second response message generation unit, be suitable in the state control It is being that shape is hung up in session with the state in the subsequent session business at the consumer user end that unit processed, which controls the robot customer service, When state, the pacifying property response with the content matching of the conversation message is extracted from the Service Source that the storage unit stores and is disappeared Breath;The first message interactive unit is further adapted for the pacifying property response message with the content matching of the conversation message It is back to the consumer user end;
The status control unit is further adapted for when the conversation end between the determining customer service client and the consumer user end When, restoring state of the robot customer service between the consumer user end in subsequent session business is session status;
Customer service system provides artificial customer service, the robot customer service and the artificial customer service seamless connection.
16. robot customer service according to claim 15, which is characterized in that the second message interactive unit be further adapted for by It is described can not from pacifying property response message corresponding to main process task or unrecognized conversation message and it is described can not be from main process task Or unrecognized conversation message is sent to the customer service client together.
17. robot customer service according to claim 15, which is characterized in that it is described from Main Processor Unit, it is further adapted for working as institute It states state detection unit and detects that the robot customer service is being session with the state in the session service at the consumer user end Suspended state, and when the second message interactive unit is not received from the conversation message of the customer service client, identify institute The content of conversation message is stated, the pacifying property response message with the content matching of the conversation message is extracted and is sent to the customer Client.
18. robot customer service according to claim 15, which is characterized in that the status control unit is further adapted in institute It states in session status in the session service at robot customer service and the consumer user end, and the second message interactive unit connects When receiving from the conversation message of the customer service client, by the robot customer service in the rear extended meeting with the consumer user end State in call business is switched to session suspended state, and controls the second message interactive unit and execute message exchange operations.
19. robot customer service according to claim 15, which is characterized in that the conversation end detection unit includes following It is at least one:
First detection sub-unit, is adapted to detect for whether the second message interactive unit free time reaches preset duration, and default reaching When duration, the conversation end between the customer service client and the consumer user end is determined;Second detection sub-unit is suitable for inspection It surveys the session from the customer service client and completes signal, and detecting the session completion signal from the customer service client When, determine the conversation end between the customer service client and the consumer user end.
20. robot customer service according to claim 15, which is characterized in that the Service Source that the storage unit is stored It include: language empirical data and customer service resource data.
21. robot customer service according to claim 20, which is characterized in that further include machine training unit, be suitable for institute It states robot and carries out the training of big data machine, to identify that scene type belonging to conversation message, the scene type are according to field Conversation message between consumer user end is carried out classification fractionation and obtained by scape.
22. the robot customer service according to claim 20 or 21, which is characterized in that the ability judging unit, comprising:
First judgment sub-unit, is adapted to determine that whether the robot customer service can independently answer according to the language empirical data The content of the conversation message;
Second judgment sub-unit, suitable for determining that the robot customer service can not be autonomous according to when first judgment sub-unit When language empirical data is answered, scene type belonging to the content of the conversation message is determined.
23. robot customer service according to claim 22, which is characterized in that the first response message generation unit, packet It includes:
First generates subelement, suitable for can independently be answered according to the language empirical data when the determining robot customer service When, it extracts from the language empirical data that the storage unit is stored and disappears with the matched response of the content of the conversation message Breath;
Second generates subelement, suitable for when determining that the robot customer service can not answer according to the language empirical data, from It is matched with the content of conversation message institute under scene belonging to being extracted in the customer service resource data that the storage unit is stored Response message.
24. robot customer service according to claim 15, which is characterized in that the pacifying property response message is suitable for characterization visitor Clothes are in the state for finding problem answers.
25. robot customer service according to claim 15, which is characterized in that the form of the conversation message include with down toward Few one kind: sentence, data link, voice, image and the video of natural language text composition.
26. robot customer service according to claim 25, which is characterized in that described image includes following at least one of Kind: the either statically or dynamically picture with semantic information, or for the targeted product of customer's session or service object photo or Screenshotss information.
27. a kind of customer service system characterized by comprising consumer user end, suitable for what is conversated with the consumer user end Customer service client and the described in any item robot customer services of claim 15-26, the customer service client and the consumer user End passes through the robot customer service session.
28. customer service system according to claim 27, which is characterized in that the robot customer service is suitable for when in session shape The consumer user end of state and customer service client are multiple, and determine that itself from main process task or can not can not identify that the session disappears When breath, according to the task amount of the customer service client in session status, by the conversation message from consumer user end and right The pacifying property response message answered is sent to the least customer service client of task amount.
29. customer service system according to claim 27, which is characterized in that the robot customer service is suitable for when in session shape The consumer user end of state and customer service client are multiple, and determine that itself from main process task or can not can not identify that the session disappears It when breath, is recorded, will be located before described itself can not be sent to from main process task or unrecognized conversation message according to conversation message Managed the customer service client of consumer user end conversation message.
CN201511025278.5A 2015-12-30 2015-12-30 Customer service system and its method of servicing, robot customer service Active CN105553833B (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
CN201811074976.8A CN109245995B (en) 2015-12-30 2015-12-30 Robot customer service and customer service system
CN201511025278.5A CN105553833B (en) 2015-12-30 2015-12-30 Customer service system and its method of servicing, robot customer service
CN201811075502.5A CN109150701B (en) 2015-12-30 2015-12-30 Customer service system service method
US15/390,172 US10063702B2 (en) 2015-12-30 2016-12-23 Intelligent customer service systems, customer service robots, and methods for providing customer service
US16/043,415 US11032419B2 (en) 2015-12-30 2018-07-24 Intelligent customer service systems, customer service robots, and methods for providing customer service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201511025278.5A CN105553833B (en) 2015-12-30 2015-12-30 Customer service system and its method of servicing, robot customer service

Related Child Applications (2)

Application Number Title Priority Date Filing Date
CN201811074976.8A Division CN109245995B (en) 2015-12-30 2015-12-30 Robot customer service and customer service system
CN201811075502.5A Division CN109150701B (en) 2015-12-30 2015-12-30 Customer service system service method

Publications (2)

Publication Number Publication Date
CN105553833A CN105553833A (en) 2016-05-04
CN105553833B true CN105553833B (en) 2019-03-05

Family

ID=55832772

Family Applications (3)

Application Number Title Priority Date Filing Date
CN201811075502.5A Active CN109150701B (en) 2015-12-30 2015-12-30 Customer service system service method
CN201811074976.8A Active CN109245995B (en) 2015-12-30 2015-12-30 Robot customer service and customer service system
CN201511025278.5A Active CN105553833B (en) 2015-12-30 2015-12-30 Customer service system and its method of servicing, robot customer service

Family Applications Before (2)

Application Number Title Priority Date Filing Date
CN201811075502.5A Active CN109150701B (en) 2015-12-30 2015-12-30 Customer service system service method
CN201811074976.8A Active CN109245995B (en) 2015-12-30 2015-12-30 Robot customer service and customer service system

Country Status (1)

Country Link
CN (3) CN109150701B (en)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106899487B (en) * 2016-07-06 2020-11-03 创新先进技术有限公司 Communication processing method, device, server and equipment
CN106503242B (en) * 2016-11-08 2019-04-19 上海智臻智能网络科技股份有限公司 A kind of intelligent interactive method, device and server
CN106934452A (en) * 2017-01-19 2017-07-07 深圳前海勇艺达机器人有限公司 Robot dialogue method and system
US20210142807A1 (en) * 2017-06-29 2021-05-13 Optim Corporation Call center conversational content display system, method, and program
CN107609058B (en) * 2017-08-25 2021-05-18 维沃移动通信有限公司 Sales method, robot customer service end, artificial customer service end and user end
CN109587358A (en) * 2017-09-29 2019-04-05 吴杰 Artificial intelligence customer service turns artificial customer service call method
CN108197167A (en) * 2017-12-18 2018-06-22 深圳前海微众银行股份有限公司 Human-computer dialogue processing method, equipment and readable storage medium storing program for executing
CN110224919A (en) * 2018-03-02 2019-09-10 汪俊霞 A kind of quasi- true man's chat robots
CN109544183A (en) * 2018-11-27 2019-03-29 网宿科技股份有限公司 A kind of business consultation method and device
CN109784942A (en) * 2018-12-20 2019-05-21 深圳市愚公科技有限公司 More service side's online customer service information processing units and its information processing method
CN109670031A (en) * 2018-12-29 2019-04-23 中国银行股份有限公司 Data processing method and device
CN111416728B (en) * 2019-01-08 2023-12-05 北京汇钧科技有限公司 Method, system, equipment and medium for predicting session end and online customer service
CN111416833B (en) * 2019-01-08 2024-02-09 北京京东尚科信息技术有限公司 Method and device for judging session end, electronic equipment and readable medium
CN111611351B (en) * 2019-02-25 2023-08-01 北京嘀嘀无限科技发展有限公司 Control method and device for online customer service session and electronic equipment
CN109922070B (en) * 2019-03-13 2021-11-26 北京奇艺世纪科技有限公司 Automatic reply method and device
CN112130907A (en) * 2019-06-05 2020-12-25 阿里巴巴集团控股有限公司 Session processing method and device and electronic equipment
CN110995940A (en) * 2019-09-30 2020-04-10 厦门快商通科技股份有限公司 Harassment visitor identification method and device, electronic equipment and medium
CN111586243A (en) * 2020-04-20 2020-08-25 深圳震有科技股份有限公司 Voice scheduling method and device, intelligent terminal and storage medium
CN112583896B (en) * 2020-11-30 2023-03-21 北京达佳互联信息技术有限公司 Session management method, session management device, electronic equipment, session management server and storage medium
CN115361355A (en) * 2022-08-15 2022-11-18 天津五八驾考信息技术有限公司 Driving school information processing method, device, equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102739557A (en) * 2011-04-08 2012-10-17 腾讯科技(深圳)有限公司 User distribution method and device in customer services
CN103279528A (en) * 2013-05-31 2013-09-04 俞志晨 Question-answering system and question-answering method based on man-machine integration
CN104731895A (en) * 2015-03-18 2015-06-24 北京京东尚科信息技术有限公司 Auto-answer method and device
CN105072173A (en) * 2015-08-03 2015-11-18 谌志群 Customer service method and system for automatically switching between automatic customer service and artificial customer service
CN105162688A (en) * 2015-08-13 2015-12-16 北京智齿博创科技有限公司 Method for chatting with online customer service representative

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060074831A1 (en) * 2004-09-20 2006-04-06 Hyder Andrew D Virtual assistant
US9160850B2 (en) * 2006-04-07 2015-10-13 Oracle Otc Subsidiary Llc Method and system for informing customer service agent of details of user's interaction with voice-based knowledge retrieval system
CN101431573B (en) * 2007-11-08 2013-02-20 上海撼世网络科技有限公司 Method and equipment for implementing automatic customer service through human-machine interaction technology
CN101556669A (en) * 2008-04-11 2009-10-14 上海赢思软件技术有限公司 Method and device for conducting personalized marketing with user by using human-computer interaction technology

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102739557A (en) * 2011-04-08 2012-10-17 腾讯科技(深圳)有限公司 User distribution method and device in customer services
CN103279528A (en) * 2013-05-31 2013-09-04 俞志晨 Question-answering system and question-answering method based on man-machine integration
CN104731895A (en) * 2015-03-18 2015-06-24 北京京东尚科信息技术有限公司 Auto-answer method and device
CN105072173A (en) * 2015-08-03 2015-11-18 谌志群 Customer service method and system for automatically switching between automatic customer service and artificial customer service
CN105162688A (en) * 2015-08-13 2015-12-16 北京智齿博创科技有限公司 Method for chatting with online customer service representative

Also Published As

Publication number Publication date
CN109245995A (en) 2019-01-18
CN105553833A (en) 2016-05-04
CN109150701A (en) 2019-01-04
CN109245995B (en) 2021-04-23
CN109150701B (en) 2020-07-10

Similar Documents

Publication Publication Date Title
CN105553833B (en) Customer service system and its method of servicing, robot customer service
CN105577529B (en) Robot customer service and its client service method, intelligent customer service system
US11032419B2 (en) Intelligent customer service systems, customer service robots, and methods for providing customer service
JP7404467B2 (en) Dynamic communication routing based on consistency weighting and routing rules
US11057520B2 (en) System and method of sentiment modeling and application to determine optimized agent action
JP7259030B2 (en) Automated bot creation based on scripts
US11494566B2 (en) Systems and methods for adaptive emotion based automated emails and/or chat replies
US8503664B1 (en) Quality review of contacts between customers and customer service agents
CN112306708A (en) Enhanced digital messaging
US10129396B1 (en) System and method for providing self-service while on hold during a customer interaction
WO2020125775A1 (en) Multi-service-party online customer service information processing method and apparatus
CN111131005A (en) Dialogue method, device, equipment and storage medium of customer service system
US20210144106A1 (en) Systems and methods of instant-messaging bot supporting human-machine symbiosis
JP2017072976A (en) Information processing system, information processing method, and program
CN113840040B (en) Man-machine cooperation outbound method, device, equipment and storage medium
CN114500757A (en) Voice interaction method and device, computer equipment and storage medium
CN111045510A (en) Man-machine interaction method and system based on augmented reality
WO2021109741A1 (en) Serving method, apparatus, system and device, and storage medium
CN112053165A (en) Information interaction method, device, server and storage medium
KR20240124405A (en) Response control device and response control method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20180930

Address after: 201803 7, 398 Lane 1555, Jiangxi Road, Jinsha, Jiading District, Shanghai.

Applicant after: SHANGHAI ZHIZHEN INTELLIGENT NETWORK SCIENCE & TECHNOLOGY CO., LTD.

Applicant after: Guizhou little love robot technology Co., Ltd.

Address before: 201803 7, 398 Lane 1555, Jiangxi Road, Jinsha, Jiading District, Shanghai.

Applicant before: SHANGHAI ZHIZHEN INTELLIGENT NETWORK SCIENCE & TECHNOLOGY CO., LTD.

GR01 Patent grant
GR01 Patent grant