CN110533343A - Data processing method, device and the electronic equipment of intelligent customer service system - Google Patents
Data processing method, device and the electronic equipment of intelligent customer service system Download PDFInfo
- Publication number
- CN110533343A CN110533343A CN201910834046.6A CN201910834046A CN110533343A CN 110533343 A CN110533343 A CN 110533343A CN 201910834046 A CN201910834046 A CN 201910834046A CN 110533343 A CN110533343 A CN 110533343A
- Authority
- CN
- China
- Prior art keywords
- customer service
- intelligent customer
- service
- quality evaluation
- service system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000013441 quality evaluation Methods 0.000 claims abstract description 132
- 230000036449 good health Effects 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 39
- 230000006399 behavior Effects 0.000 claims description 48
- 230000008901 benefit Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 238000012954 risk control Methods 0.000 claims description 14
- 230000008451 emotion Effects 0.000 claims description 12
- 230000036541 health Effects 0.000 claims description 12
- 230000003252 repetitive effect Effects 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000003542 behavioural effect Effects 0.000 claims description 5
- 230000036651 mood Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 abstract description 14
- 238000013473 artificial intelligence Methods 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 10
- 238000012423 maintenance Methods 0.000 abstract description 8
- 230000000875 corresponding effect Effects 0.000 description 37
- 239000011159 matrix material Substances 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 10
- 238000003058 natural language processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001303 quality assessment method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application provides data processing method, device and the electronic equipment of a kind of intelligent customer service system, is related to field of artificial intelligence.This method comprises: obtaining the conversational services data and user behavior data of intelligent customer service system in the setting period first；Dialogue-based service data and user behavior data determine the index value of each quality evaluation index in the setting period；According to the index value of quality evaluation index, determine that the service healthiness of intelligent customer service system, service healthiness are used to be characterized in the service quality of intelligent customer service system in the setting period.The application determines service healthiness by the conversational services data and user behavior data of intelligent customer service system, the service quality of intelligent customer service system is assessed using service healthiness, maintenance test collection is not needed, and the data that assessment uses are more abundant, it can be realized and the service quality of intelligent customer service system is comprehensively assessed, improve Evaluated effect.
Description
Technical field
This application involves field of computer technology, specifically, this application involves at a kind of data of intelligent customer service system
Manage method, apparatus and electronic equipment.
Background technique
Artificial intelligence (Artificial Intelligence, AI) is to utilize digital computer or digital computer control
Machine simulation, extension and the intelligence for extending people of system, perception environment obtain knowledge and the reason using Knowledge Acquirement optimum
By, method, technology and application system.In other words, artificial intelligence is a complex art of computer science, it attempts to understand
The essence of intelligence, and produce a kind of new intelligence machine that can be made a response in such a way that human intelligence is similar.Artificial intelligence
The design principle and implementation method for namely studying various intelligence machines make machine have the function of perception, reasoning and decision.
It is the mode of offering customers service from the single channel of traditional manual telephone system to more with the development of artificial intelligence
Memberization channel gradually develops, and more and more enterprises begin to use the form of intelligent customer service to provide service.
In the prior art, the service quality of intelligent customer service to be assessed, a kind of mode is the subjective determination based on people,
This assessment mode can not accomplish objective assessment, and assess inefficiency；Another way is the test set based on building
To test the intention assessment rate of intelligent customer service, and then the service quality of assessment intelligent customer service, this assessment mode needs maintenance survey
Examination collection easily occurs in over-fitting on test set and the bad problem of Evaluated effect, and assesses the data direction used and compare
It is single, inadequate system and comprehensively.
Summary of the invention
This application provides data processing method, device and the electronic equipment of a kind of intelligent customer service system, can solve existing
There is following problem present in technology: assessing the service quality of intelligent customer service system by way of manually determining, can not accomplish
Objective evaluation, and assess inefficiency；The service quality that intelligent customer service is tested based on the test set of building, which needs to safeguard, to be surveyed
Examination collection easily occurs in over-fitting on test set and the bad problem of Evaluated effect, and assesses the data direction used and compare
It is single, inadequate system and comprehensively.
Specific technical solution provided by the embodiments of the present application is as follows:
In a first aspect, the embodiment of the present application provides a kind of data processing method of intelligent customer service system, this method comprises:
Obtain the conversational services data and user behavior data of intelligent customer service system in the setting period；
Based on the conversational services data and user behavior data, the finger of each quality evaluation index in the setting period is determined
Scale value；
According to the index value of the quality evaluation index, the service healthiness of the intelligent customer service system, the clothes are determined
Business health degree is used to be characterized in the service quality of the intelligent customer service system in the setting period.
Second aspect, provides a kind of data processing equipment of intelligent customer service system, which includes:
Module is obtained, for obtaining the conversational services data and user behavior data of intelligent customer service system in the setting period；
First determining module determines each in the setting period for being based on the conversational services data and user behavior data
The index value of a quality evaluation index；
Second determining module determines the intelligent customer service system for the index value according to the quality evaluation index
Service healthiness, the service healthiness are used to be characterized in the service quality of the intelligent customer service system in the setting period.
The third aspect provides a kind of electronic equipment, which includes:
One or more processors；
Memory；
One or more application program, wherein one or more application programs be stored in memory and be configured as by
One or more processors execute, and one or more programs are configured to: executing any according to first aspect or first aspect
The data processing method of intelligent customer service system shown in possible implementation.
Technical solution provided by the present application has the benefit that
This application provides data processing method, device and the electronic equipments of a kind of intelligent customer service system, obtain set first
The conversational services data and user behavior data of intelligent customer service system in fixed cycle；Dialogue-based service data and user behavior number
According to the index value of each quality evaluation index in the determining setting period；According to the index value of quality evaluation index, intelligence visitor is determined
The service healthiness of dress system, service healthiness are used to be characterized in the service quality of intelligent customer service system in the setting period.This Shen
Service healthiness please is determined by the conversational services data of intelligent customer service system and user behavior data, utilizes service healthiness
The service quality of intelligent customer service system is assessed, maintenance test collection is not needed, and it is more abundant to assess the data used, it can
The service quality of intelligent customer service system is comprehensively assessed in realization, improves Evaluated effect.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, institute in being described below to the embodiment of the present application
Attached drawing to be used is needed to be briefly described.
Fig. 1 is a kind of flow diagram of the data processing method of intelligent customer service system provided by the embodiments of the present application；
Fig. 2 is that intelligent customer service system provided by the embodiments of the present application service daily in 1 to 7 January in 2019 is strong
Kang Du and general health degree calculated result display diagram；
Fig. 3 is the calculating process schematic diagram of the service healthiness of computational intelligence customer service system provided by the embodiments of the present application；
Fig. 4 is the structural schematic diagram of the data processing equipment of intelligent customer service system provided by the embodiments of the present application；
Fig. 5 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and cannot be construed to the limitation to the application.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in the description of the present application
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
The executing subject of technical scheme is computer equipment, including but not limited to server, PC, notes
This computer, tablet computer, smart phone etc..Computer equipment includes user equipment and the network equipment.Wherein, user equipment includes
But be not limited to computer, smart phone, PAD etc.；The network equipment includes but is not limited to single network server, multiple network servers
The server group of composition or cloud consisting of a large number of computers or network servers in cloud computing, wherein cloud computing is distribution
One kind that formula calculates, a super virtual computer consisting of a loosely coupled set of computers.Wherein, computer equipment
Can isolated operation realize the application, also can access network and by interactive operation with other computer equipments in network come
Realize the application.Wherein, network locating for computer equipment include but is not limited to internet, wide area network, Metropolitan Area Network (MAN), local area network,
VPN network etc..
With artificial intelligence technology research and progress, research and application is unfolded in multiple fields in artificial intelligence technology, such as
Common smart home, intelligent wearable device, virtual assistant, intelligent sound box, intelligent marketing, unmanned, automatic Pilot, nobody
Machine, robot, intelligent medical, intelligent customer service etc., it is believed that with the development of technology, artificial intelligence technology will obtain in more fields
To application, and play more and more important value.Scheme provided by the embodiments of the present application is related to the intelligent customer service skill of artificial intelligence
Art is illustrated especially by following examples.
Technical scheme is during intelligent customer service and user conversate, using natural language processing (Nature
Language processing, NLP) technology to user input information identify.Natural language processing is computer science neck
An important directions in domain and artificial intelligence field.It studies to be able to achieve between people and computer and be carried out effectively with natural language
The various theory and methods of communication.Natural language processing is one and melts linguistics, computer science, mathematics in the science of one.
Therefore, the research in this field will be related to natural language, i.e. people's language used in everyday, so it has with philological research
Close connection.Natural language processing technique generally includes text-processing, semantic understanding, machine translation, robot question and answer, knows
Know the technologies such as map.
How the technical solution of the application and the technical solution of the application are solved with specifically embodiment below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, embodiments herein is described.
Firstly, noun involved in the embodiment of the present application is introduced:
Intelligent customer service system: the dialog mode artificial intelligence customer service system based on dialogue platform, which can be in user
When asking questions, the problem of understanding user intention, and be intended to automatic reply user according to problem.
The embodiment of the present application provides a kind of data processing method of intelligent customer service system, as shown in Figure 1, this method packet
It includes:
Step S101 obtains the conversational services data and user behavior data of intelligent customer service system in the setting period；
Specifically, in multiple periods of setting intelligent customer service system service quality evaluation, call in quality assessment data library
The corresponding conversational services data of intelligent customer service system and user behavior data in each setting period.Wherein, the period can root
According to specifically being set, it is specifically as follows day, week, moon etc..Quality assessment data library be in advance by intelligent customer service system and
User conversate caused by the database established of all conversational services data and user behavior data.
Service log data caused by conversational services data may include intelligent customer service system and user conversates.One
Secondary session refers to user's session since single accesses intelligent customer service system, exits intelligent customer service system finishing session to user
Process.The conversational services data of session include that user's single access intelligent customer service system starts to the user to exit
Intelligent customer service system, generated service log data in this period may include: that (session each time is corresponding for session identification
One session identification), (user proposes a problem to session wheel number, and intelligent customer service system provides a corresponding answer, for a wheel
Session, each time session include at least one wheel session), information the problem of user in conversation procedure, intelligent customer service in conversation procedure
The answer information of reply, the turnaround time etc. of intelligent customer service in session.
User behavior data include user after leaving intelligent customer service system in preset time in artificial customer service system institute
The behavioral data of generation, can specifically include: user exits the time of intelligent customer service system, and user is in default after session
The service log data of the interior artificial customer service system of access, access the time etc. of artificial customer service system.
In one possible implementation, the conversational services data of intelligent customer service system and user in the setting period are obtained
Behavioral data, comprising:
It is identified according to type of service, obtains the service trade in the intelligent customer service default period corresponding to type of service mark
The conversational services data and user behavior data of business；
The service that service healthiness in technical scheme can correspond to service business for intelligent customer service system is strong
Kang Du.
In practical applications, intelligent customer service system corresponds to multiple service traffic class, wherein for service traffic class
Specific division mode and granularity of division the embodiment of the present application are not construed as limiting.For example, wechat payment transaction, king's honor business,
It again include secondary traffic wechat payment real-name authentication business etc. under wechat payment transaction.The corresponding industry of each service traffic class
Service type mark.Each service traffic class includes multiple services channels again, for example, voice communication (Interactive Voice
Response, IVR) channel, artificial customer service instant messaging channel, AI intelligent customer service channel etc..Obtaining intelligence in the setting period
It when the conversational services data and user behavior data of customer service system, is identified according to type of service, is looked into quality assessment data library
Conversational services data and user behavior data that type of service identifies corresponding intelligent customer service system service business are ask out, for true
Determine the service healthiness that intelligent customer service system corresponds to service business.
In one example, according to the type of service ID of wechat payment transaction, user A and intelligent customer service system 24 hours are obtained
Within the conversational services data that conversate for wechat payment transaction and user behavior data.
Step S102, dialogue-based service data and user behavior data determine that each quality evaluation refers in the setting period
Target index value；
Wherein, quality evaluation index is to characterize the data of the different dimensions of intelligent customer service system service quality, according to session
Service data and user behavior data can calculate the corresponding index value of each quality evaluation index.
In one possible implementation, quality evaluation index includes at least one of the following:
Service smooth index, service satisfaction index, Service Benefit index or risk control index；
It may include following dimension that technical scheme, which carries out quality evaluation to intelligent customer service system: service is unobstructed
Dimension, service satisfaction dimension, Service Benefit dimension or risk control dimension.
Wherein, service smooth index is for characterizing the service patency of intelligent customer service system within a preset time, for example, intelligence
Energy customer service system is capable of providing service in 7*24 hours in the state of servicing unobstructed, is not in the feelings of service blocking delay
Condition.
Service satisfaction index is used for the service of two aspects of the problem of characterizing intelligent customer service resolution ability and user experience
Quality.
The benefit height for generation that Service Benefit index is used to characterize intelligent customer service and user conversates.
Risk control index is used to characterize the session identification accuracy of intelligent customer service system.Intelligent customer service system is bringing effect
While rate is promoted, some risks can be also introduced, intelligent customer service system is based on natural language processing when conversating with user
Technology inputs information to user and identifies, there is the problem of cannot much identifying user or the case where of giving an irrelevant answer,
The experience of user is caused to decline.If being finally very easy to develop into because intelligent customer service accidentally answers the complaint dispute for causing user
Risk session accurately identifies risk session so intelligent customer service system is extremely important to the identification of risk in real time, allows people
Actively intervention can be good at reducing risk for work customer service.
Technical scheme is by servicing unobstructed dimension, service satisfaction dimension, Service Benefit dimension or risk control
The evaluation index of the several dimensions of dimension assesses the service quality of intelligent customer service system, increases the reliable of the comprehensive sum of assessment
Property.
In one possible implementation, service smooth index include response time or guidance patency rate at least one
；Service satisfaction index includes that closed loop rate, recall rate, user's enquirement repetitive rate, service satisfactory rate or user emotion are positive
At least one of in rate；Service Benefit index includes at least one in session amount, service satisfactory rate, closed loop rate or recall rate；
Risk control index includes risk identification accuracy rate；
Wherein, response time (Respond rate, RT) refers to that user asks questions for first in proposition, arrives intelligent customer service
The duration of the problem is replied, response time is shorter, illustrates that period of reservation of number is shorter, therefore can be from this angle estimator intelligence visitor
The service patency of dress system.
The robot that guidance patency rate (Guide rate, GR) is used to characterize intelligent customer service system successfully boots up user to people
The degree of work customer service system；When the service mode combined using intelligent customer service system and artificial customer service system, user is proposed
After asking questions, intelligent customer service system is accessed first, when intelligent customer service system can not solve when asking questions of user's proposition, intelligence
Can customer service system user can be guided to access artificial customer service system, first guidance user submit a question details work order to artificial customer service
In system, then again artificial treatment feedback result to user.The index value for guiding unimpeded rate can be the number that successfully boots up with
The ratio of total guidance number.Draw that unimpeded rate is higher, illustrates that the guidance capability of intelligent customer service system is stronger, whether is intelligent customer service system
Guidance user has got the service quality that effective service is able to reflect out intelligent customer service system, wherein effective service refers to use
Family has been accessed the channel of intelligent customer service System guides and has been proposed and asked questions.For example, user B and intelligent customer service system are understood
Words, consulting wechat pay relevant issues, and since customer problem needs manually to veritify subscriber identity information, intelligent customer service system can not
It solves, therefore intelligent customer service system sends hyperlink to user, and prompts user's access link to fill in list and be committed to artificial visitor
Dress system, until when conversation end, with the hyperlink is not accessed per family, then this time session guidance failure.
Closed loop rate (close loop rate, CLR) is used to characterize closed loop session amount ratio shared in total service conversation amount
Example.Wherein, closed loop session refers to that intelligent customer service system does not guide user to go artificial customer service system, and user in conversation procedure
Any service rows are not generated in intelligent customer service system and artificial customer service system exiting in the intelligent customer service systemic presupposition time
For data, closed loop rate is higher, then the last leg service of user occurs higher in the ratio of intelligent customer service system, illustrates intelligent visitor
It is stronger that dress system tackles problems on one's own ability.Therefore the service quality of intelligent customer service system can be assessed from the angle of closed loop rate.
Recall rate (Recall rate, RR) is used to characterize the ability of intelligent customer service system answer customer problem.Recall rate
Index value can provide the session round of answer and the ratio of total question and answer round to the speaking ability by random question of user for intelligent customer service system
Value, recall rate is higher, indicates that intelligent customer service system more can answer out user's various problem seeked advice from, illustrates intelligent visitor
The coverage area for the problem of dress system can be handled is bigger, therefore, can assess the clothes of intelligent customer service system from the angle of recall rate
Business quality.
User put question to repetitive rate (repeat question rate, RQR) for characterize user and intelligent customer service system into
The repetitive rate of same problem is proposed when guild is talked about.User puts question to the index value of repetitive rate that can propose to repeat in a session for user
The ratio of number is always taken turns in the number of problem and session.Because intelligent customer service system is limited for challenge understandability, do not do
Method accomplishes every a word of correct understanding user, so when intelligent customer service can not quick and precisely reply when asking questions of user,
It will lead to user and be repeated as many times the case where proposing same problem.User puts question to repetitive rate higher, then illustrates that more problems cannot get
It effectively replies, the service quality of intelligent customer service system is lower.
Service satisfactory rate (service Satisfied rate, SSR) conversates for characterizing with intelligent customer service system
The ratio for the user being satisfied with afterwards.The calculating of service satisfaction index value may include following two mode: the first is only
Consideration takes part in the user that service satisfactory rate participates in evaluation and electing, and calculates and always participates in evaluation and electing the ratio of number of users to the number of users Zhan of service satisfactory
As service satisfactory rate；Another kind is that switching artificial customer service system in family is occupied using the session wheel number of user and intelligent customer service system
The ratio of number predict service satisfactory rate.Service satisfactory rate is higher, then illustrates that the service quality of intelligent customer service system is higher,
It therefore, can be from the service quality of the angle estimator intelligent customer service system of service satisfaction.
User emotion forward direction rate (emotion positive rate, EPR) is used to characterize user and intelligent customer service system
Robot conversate after positive mood session amount ratio shared in total session amount.User and intelligent customer service system exist
In conversation procedure, natural language processing is carried out to the information of user's input, identifies that the positive session round Zhan of user emotion is total
The ratio of session round.Because user emotion is more biased to actively, then illustrate, Service Quality more satisfied to the service of intelligent customer service system
Amount is higher, and therefore, the angle that can be fluctuated from identification user emotion carry out evaluation services quality.
Session amount (sum of conversation, SC) is used to characterize the volume of services of intelligent customer service system service user.Meeting
Words amount is more, then the quantity of the number or service user that illustrate intelligent customer service system service user is more, and the benefit of generation is got over
It is high.
Risk identification accuracy rate (Risk Identification Accuracy, RIA) can be known for intelligent customer service system
Not Chu true wind dangerous section singly account for the ratio of overall risk work order.Intelligent customer service system can identify risk work order in real time, allow artificial
It intervenes, whether can audit after manpower intervention is real risk work order.Risk identification accuracy rate is higher, illustrates intelligent customer service system
It is stronger to the recognition capability of risk.Wherein, risk work order includes but is not limited to: having the corresponding work order of user complained and be inclined to, instead
Feedback life receives the corresponding work order of user for threatening and wanting help, and has the corresponding work order of the user of heavy losses on property, repeatedly
The visiting corresponding work order of urgent user.
It should be noted that service satisfactory rate is higher, then illustrate that the value of intelligent customer service system service is higher；Closed loop rate is got over
Height then illustrates that the problem-solving ability of intelligent customer service system is stronger, and benefit is higher；Recall rate is higher, illustrates intelligent customer service system
The coverage area for the problem of system can be handled is bigger, and benefit is higher.Therefore, service satisfactory rate, closed loop rate, recall rate both can be used as
Service satisfaction index, and can be used as risk control index.
In one example, service smooth index correspond to index value can by response time or guide patency rate at least
Even if a Xiang Jinhang；The index value of service satisfaction index can put question to repetitive rate, service by closed loop rate, recall rate, user
At least one in satisfaction rate or user emotion forward direction rate is calculated；The index value of Service Benefit index can pass through session
At least one in amount, service satisfactory rate, closed loop rate or recall rate is calculated；Risk control index can pass through risk identification
Accuracy rate is calculated.
Step S103 determines the service healthiness of intelligent customer service system according to the index value of quality evaluation index, and service is strong
Kang Du is used to be characterized in the service quality of intelligent customer service system in the setting period.
According to health of the index value computational intelligence customer service system of the quality evaluation index of multiple dimensions within the setting period
Degree, assesses the service quality of intelligent customer service system by health degree, evaluation and building test set compared to human subjective
Appraisal procedure, can it is more objective and comprehensively assess intelligent customer service system service quality, save maintenance test collection at
This, and avoid the problem that Evaluated effect is bad caused by over-fitting on test set.
In one possible implementation, according to the index value of quality evaluation index, the clothes of intelligent customer service system are determined
Business health degree, comprising: determine the weight of each quality evaluation index；According to the index value of each quality evaluation index and respectively
The weight of a quality evaluation index, determines the service healthiness of intelligent customer service system.
In practical applications, for the method for determination of weight, it can determine that each quality evaluation refers to based on CRITIC algorithm
Target weight, CRITIC algorithm not only allow for the standard deviation of quality evaluation index, while also contemplating each quality evaluation index
Between conflicting.If standard deviation is bigger, indicate that the degree of variation of its index value is bigger, the information content provided is bigger, then
Its weight also Ying Yue great.Conversely, the standard deviation of quality evaluation index is smaller, means that the degree of variation of its index value is smaller, mention
The information content of confession is smaller, then its weight also should be smaller；Conflicting between quality evaluation index is between quality evaluation index
Correlation based on, as having stronger positive correlation (related coefficient is closer to 1) between two quality evaluation indexs, illustrate two
A quality evaluation index conflicting is lower, shows that two quality evaluation indexs have biggish similitude in the information of reflection；When
Two quality evaluation indexs have stronger negatively correlated (related coefficient closer -1), illustrate the conflict of two quality evaluation indexs
Property it is bigger, show the two quality evaluation indexs reflection information on have biggish difference.
Furthermore it is possible to which significance level or the different quality assessment according to different dimensions belonging to quality evaluation index refer to
Target significance level, be the corresponding weight of each quality evaluation target setting, according to the index value of each quality evaluation index with
And the service healthiness of the weight calculation intelligent customer service system of each quality evaluation index.
By for each quality evaluation target setting weight, according to the index value of each quality evaluation index and each
The weight of quality evaluation index determines the service healthiness of intelligent customer service system, corresponding by adjusting each quality evaluation index
Weight make the method for evaluating quality of intelligent customer service with more flexibility to calculate service healthiness.
In one example, setting type of service mark and assessment cycle, according to type of service mark and assessment cycle in number
According to conversational services data and user behavior data is called in library, it is logical that service is calculated according to conversational services data and user behavior data
Freely, service satisfaction, the quality evaluation index of Service Benefit, risk control four dimensions, are determined each based on CRITIC algorithm
The weight of index, according to the quality evaluation index of each dimension and the corresponding weight of each index, computational intelligence customer service system
The schematic diagram of service healthiness, calculating process is as shown in Figure 3.
In one possible implementation, the conversational services data of intelligent customer service system and user in the setting period are obtained
Behavioral data, comprising: obtain the conversational services data and user behavior data of intelligent customer service system in the setting period, preset period of time
Including at least two periods, at least two periods include set the period and setting the period at least one be associated with the period；It determines each
The weight of a quality evaluation index, comprising: according to it is each association the period respectively corresponding to conversational services data and user behavior
Data determine the index value of each quality evaluation index in each association period；Referred to according to every two quality evaluation in the setting period
The corresponding each index value of mark, determines the related coefficient in the setting period between every two quality evaluation index；For each
Quality evaluation index determines that quality evaluation refers to based on all index values corresponding to quality evaluation index and all related coefficients
Target information content；According to each respective information content of quality evaluation index, the weight of each quality evaluation index is determined.
In practical applications, the method for determination of weight corresponding for each quality evaluation index, can be more by obtaining
The conversational services data and user behavior data in a period carry out calculating determining information content to determine.
Wherein, the matrix such as (1) for obtaining the quality evaluation index composition of the n dimension in m period is shown:
Wherein, the either element in matrix (1), the element x of such as the i-th row jth columni,j, indicate j-th in i-th of period
The index value of quality evaluation index；Every a line in matrix (1) indicates the index value of n quality evaluation index of a cycle；
Each column indicate the index value of the same quality evaluation index in m period.
Optionally, it if the dimension of each quality evaluation index obtained, the order of magnitude are different, is commented to eliminate each quality
Estimate the dimension of index, the different influences of the order of magnitude, then carry out data normalization processing, matrix (1) is carried out according to formula (2)
Processing:
Wherein, zi,jThe index value of j-th of quality evaluation index in i-th of period in representing matrix (1) carries out standard
The standardized index value obtained after changing；J-th of quality evaluation index in representing matrix (1) representing matrix (1)
The maximum value of index value within m period；J-th of quality evaluation index is m week in representing matrix (1)
The minimum value of index value in phase.
Direct index is the positively related quality evaluation index of service quality with intelligent customer service；Negative index be and intelligent customer service
The quality evaluation index of service quality negative correlation；Direct index in technical scheme include: guidance patency rate, closed loop rate,
Recall rate, service satisfactory rate, user emotion forward direction rate, session amount, risk identification accuracy rate；Negative index includes: response time, uses
Put question to repetitive rate in family.
Related coefficient between every two quality evaluation index is determined according to formula (3):
Wherein, rtjThe index value and jth column element of quality evaluation index corresponding to t column element in representing matrix (1)
Related coefficient between the index value of corresponding quality evaluation index；xi,tFor the element that the i-th row t in matrix (1) is arranged, table
Show the index value of t-th of quality evaluation index in i-th of period；Indicate t-th of mass in each period in m period
The mean value of the index value of evaluation index；xi,jFor the element that the i-th row jth in matrix (1) arranges, j-th in i-th of period is indicated
The index value of quality evaluation index；Indicate the index value of j-th of quality evaluation index in each period in m period
Mean value.
In one possible implementation, based on all index values corresponding to quality evaluation index and all phase relations
Number, determines the information content of quality evaluation index, comprising: according to the corresponding all index values of quality evaluation index, determine that quality is commented
Estimate the corresponding standard deviation of index；Quality evaluation index is determined based on the corresponding standard deviation of quality evaluation index and all related coefficients
Information content.
The information content of j-th of quality evaluation index in each period is determined according to formula (4) in m period:
Wherein, CjThe information content of quality evaluation index corresponding to jth column element in representing matrix (1)；δjRepresenting matrix
(1) standard deviation of jth column quality evaluation index in:
The corresponding weight of each quality evaluation index is determined according to formula (6):
Wherein, WjIndicate the weight of j-th of index.
The service healthiness H of intelligent customer service system is determined according to formula (7)i:
In one possible implementation, this method further include:
According to the weight of the index value of each quality evaluation index in each association period and each quality evaluation index, really
Intelligent customer service system is determined in the service healthiness in each association period；According to setting the period in each period service healthiness,
Determine intelligent customer service system in the service healthiness of setting period.
In practical applications, it is determined that after the service healthiness in each period in preset period of time, calculating can be passed through
The mean value of multiple cycle service health degrees, or the corresponding weight of service healthiness in setting each period, pass through weighted calculation
Mode, the service healthiness of preset period of time is determined, to reflect intelligent customer service system in the service quality of preset period of time
Situation.
In one example, using quality evaluation index: response time, guidance patency rate, closed loop rate, recall rate, Yong Huti
It asks repetitive rate, service satisfactory rate, mood forward direction rate, risk identification accuracy rate, the index value of session amount, calculates on January 1st, 2019
The service healthiness daily to intelligent customer service system on the 7th, using the service healthiness on January 3rd, 2019 as general health degree, such as
Shown in Fig. 2.
In one example, wechat some month of payment transaction No. 1, No. 2, No. 3 service quality have been respectively obtained by counting
Index value, as shown in table 1:
| Time | RT | GR | CLR | RR | RQR | SSR | EPR | RIA | SC |
| No. 1 | 0.01 | 0.64 | 0.77 | 0.76 | 0.1 | 0.6 | 0.61 | 0.66 | 10.47 |
| No. 2 | 0.011 | 0.66 | 0.7 | 0.75 | 0.11 | 0.55 | 0.58 | 0.7 | 10.77 |
| No. 3 | 0.01 | 0.67 | 0.75 | 0.74 | 0.12 | 0.6 | 0.62 | 0.72 | 10.41 |
Table 1
Data normalization processing is carried out to the data in table 1, it is as shown in table 2 to obtain data:
Table 2
It calculates information content and weight is as shown in table 3:
Table 3
The health degree finally obtained is as shown in table 4:
| Time | Health degree |
| No. 1 | 0.53068728 |
| No. 2 | 0.429756379 |
| No. 3 | 0.659444906 |
Table 4
The data processing method of intelligent customer service system provided by the embodiments of the present application obtains intelligence visitor in the setting period first
The conversational services data and user behavior data of dress system；Dialogue-based service data and user behavior data determine setting week
The index value of each quality evaluation index in phase；According to the index value of quality evaluation index, the service of intelligent customer service system is determined
Health degree, service healthiness are used to be characterized in the service quality of intelligent customer service system in the setting period.The application passes through intelligence visitor
The conversational services data of dress system and user behavior data determine service healthiness, and intelligent visitor is assessed using service healthiness
The service quality of dress system does not need maintenance test collection, and assesses the data used and more enrich, and can be realized to intelligent visitor
The service quality of dress system is comprehensively assessed, and Evaluated effect is improved.
Based on principle identical with method shown in Fig. 1, a kind of intelligent customer service system is additionally provided in embodiment of the disclosure
The data processing equipment 40 of system, as shown in figure 4, the data processing equipment 40 of the intelligent customer service system includes:
Module 41 is obtained, for obtaining the conversational services data and user behavior number of intelligent customer service system in the setting period
According to；
First determining module 42 determines in the setting period for being based on the conversational services data and user behavior data
The index value of each quality evaluation index；
Second determining module 43 determines the intelligent customer service system for the index value according to the quality evaluation index
Service healthiness, the service healthiness be used for be characterized in it is described setting the period in the intelligent customer service system Service Quality
Amount.
In one possible implementation, the second determining module 43 is specifically used for:
Determine the weight of each quality evaluation index；
According to the index value of each quality evaluation index and the weight of each quality evaluation index, intelligent customer service is determined
The service healthiness of system.
In one possible implementation, quality evaluation index includes at least one of the following:
Service smooth index, service satisfaction index, Service Benefit index or risk control index；
Wherein, risk control index is used to characterize the session identification accuracy of intelligent customer service system.
In one possible implementation, service smooth index include response time or guidance patency rate at least one
；
Service satisfaction index includes closed loop rate, recall rate, user's enquirement repetitive rate, service satisfactory rate or user emotion
At least one of in positive rate；
Service Benefit index includes at least one in session amount, service satisfactory rate, closed loop rate or recall rate；
Risk control index includes risk identification accuracy rate；
Wherein, the robot that guidance patency rate is used to characterize intelligent customer service system successfully boots up user to artificial customer service system
Degree；
Closed loop rate is used to characterize closed loop session amount ratio shared in total service conversation amount, wherein closed loop session refers to
User is not in intelligent customer service system and artificial customer service in preset time in this conversation procedure and after this conversation end
The session of system generation behavioral data；
User emotion forward direction rate is for characterizing the positive mood after the robot of user and intelligent customer service system conversate
Session amount ratio shared in total session amount.
In one possible implementation, module 41 is obtained to be specifically used for:
The conversational services data and user behavior data of intelligent customer service system in the setting period are obtained, preset period of time includes extremely
Few two periods, at least two periods include setting at least one of period and setting period to be associated with the period；
Second determining module 43 is specifically used for:
According to it is each association the period respectively corresponding to conversational services data and user behavior data, determine each association period
Each quality evaluation index index value；
According to each index value corresponding to every two quality evaluation index in the setting period, determine every two in the setting period
Related coefficient between a quality evaluation index；
For each quality evaluation index, based on all index values corresponding to quality evaluation index and all phase relations
Number, determines the information content of quality evaluation index；
According to each respective information content of quality evaluation index, the weight of each quality evaluation index is determined.
In one possible implementation, the second determining module 43 is specifically used for:
According to the corresponding all index values of quality evaluation index, the corresponding standard deviation of quality evaluation index is determined；
The information content of quality evaluation index is determined based on the corresponding standard deviation of quality evaluation index and all related coefficients.
In one possible implementation, the second determining module 43 is specifically used for:
According to the weight of the index value of each quality evaluation index in each association period and each quality evaluation index, really
Intelligent customer service system is determined in the service healthiness in each association period；
According to the service healthiness in each period in the setting period, determine that intelligent customer service system is strong in the service of setting period
Kang Du.
In one possible implementation, module 41 is obtained to be specifically used for:
It is identified according to type of service, obtains the service trade in the intelligent customer service default period corresponding to type of service mark
The conversational services data and user behavior data of business；Wherein, service healthiness is that intelligent customer service system corresponds to service business
Service healthiness.
The data processing equipment of the intelligent customer service system of the embodiment of the present disclosure can be performed provided by embodiment of the disclosure
The data processing method of intelligent customer service system, realization principle is similar, the number of the intelligent customer service system in the embodiment of the present disclosure
According to the data processing that movement performed by each module in processing unit is with the intelligent customer service system in each embodiment of the disclosure
Step in method is corresponding, the detailed functions of each module of the data processing equipment of intelligent customer service system is described specific
May refer to hereinbefore shown in corresponding intelligent customer service system data processing method in description, details are not described herein again.
The data processing equipment of intelligent customer service system provided by the embodiments of the present application obtains intelligence visitor in the setting period first
The conversational services data and user behavior data of dress system；Dialogue-based service data and user behavior data determine setting week
The index value of each quality evaluation index in phase；According to the index value of quality evaluation index, the service of intelligent customer service system is determined
Health degree, service healthiness are used to be characterized in the service quality of intelligent customer service system in the setting period.The application passes through intelligence visitor
The conversational services data of dress system and user behavior data determine service healthiness, and intelligent visitor is assessed using service healthiness
The service quality of dress system does not need maintenance test collection, and assesses the data used and more enrich, and can be realized to intelligent visitor
The service quality of dress system is comprehensively assessed, and Evaluated effect is improved.
Above-described embodiment describes the data processing equipment of intelligent customer service system from the angle of virtual module, following from entity
The angle of module introduces a kind of electronic equipment, specific as follows shown:
The embodiment of the present application provides a kind of electronic equipment, as shown in figure 5, electronic equipment shown in fig. 5 5000 includes: place
Manage device 5001 and memory 5003.Wherein, processor 5001 is connected with memory 5003, is such as connected by bus 5002.It is optional
Ground, electronic equipment 5000 can also include transceiver 5004.It should be noted that transceiver 5004 is not limited to one in practical application
A, the structure of the electronic equipment 5000 does not constitute the restriction to the embodiment of the present application.
Processor 5001 can be CPU, general processor, DSP, ASIC, FPGA or other programmable logic device, crystalline substance
Body pipe logical device, hardware component or any combination thereof.It, which may be implemented or executes, combines described by present disclosure
Various illustrative logic blocks, module and circuit.Processor 5001 is also possible to realize the combination of computing function, such as wraps
It is combined containing one or more microprocessors, DSP and the combination of microprocessor etc..
Bus 5002 may include an access, and information is transmitted between said modules.Bus 5002 can be pci bus or
Eisa bus etc..Bus 5002 can be divided into address bus, data/address bus, control bus etc..Only to be used in Fig. 5 convenient for indicating
One thick line indicates, it is not intended that an only bus or a type of bus.
Memory 5003 can be ROM or can store the other kinds of static storage device of static information and instruction, RAM
Or the other kinds of dynamic memory of information and instruction can be stored, it is also possible to EEPROM, CD-ROM or other CDs
Storage, optical disc storage (including compression optical disc, laser disc, optical disc, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium
Or other magnetic storage apparatus or can be used in carry or store have instruction or data structure form desired program generation
Code and can by any other medium of computer access, but not limited to this.
Memory 5003 is used to store the application code for executing application scheme, and is held by processor 5001 to control
Row.Processor 5001 is for executing the application code stored in memory 5003, to realize aforementioned either method embodiment
Shown in content.
The embodiment of the present application provides a kind of electronic equipment, the electronic equipment in the embodiment of the present application include: memory and
Processor；At least one program is stored in the memory, when for being executed by the processor, compared with prior art:
The conversational services data and user behavior data of intelligent customer service system in the setting period are obtained first；Dialogue-based service data and
User behavior data determines the index value of each quality evaluation index in the setting period；According to the index value of quality evaluation index,
Determine that the service healthiness of intelligent customer service system, service healthiness are used to be characterized in the service of intelligent customer service system in the setting period
Quality.The application determines service healthiness by the conversational services data and user behavior data of intelligent customer service system, utilizes
Service healthiness assesses the service quality of intelligent customer service system, does not need maintenance test collection, and assess the data used more
Add abundant, can be realized and the service quality of intelligent customer service system is comprehensively assessed, improve Evaluated effect.
The embodiment of the present application provides a kind of computer readable storage medium, is stored on the computer readable storage medium
Computer program allows computer to execute corresponding contents in preceding method embodiment when run on a computer.With
The prior art is compared, and obtains the conversational services data and user behavior data of intelligent customer service system in the setting period first；It is based on
Conversational services data and user behavior data determine the index value of each quality evaluation index in the setting period；It is commented according to quality
The index value for estimating index determines the service healthiness of intelligent customer service system, and service healthiness is for being characterized in intelligence in the setting period
The service quality of energy customer service system.The application is determined by the conversational services data and user behavior data of intelligent customer service system
Service healthiness assesses the service quality of intelligent customer service system using service healthiness, does not need maintenance test collection, Er Qieping
The data for estimating use are more abundant, can be realized and comprehensively assessed the service quality of intelligent customer service system, improve and comment
Estimate effect.
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of data processing method of intelligent customer service system, which is characterized in that the described method includes:
Obtain the conversational services data and user behavior data of intelligent customer service system in the setting period；
Based on the conversational services data and user behavior data, the finger of each quality evaluation index in the setting period is determined
Scale value；
According to the index value of the quality evaluation index, the service healthiness of the intelligent customer service system is determined, the service is strong
Kang Du is used to be characterized in the service quality of the intelligent customer service system in the setting period.
2. the method according to claim 1, wherein the index value according to the quality evaluation index, really
The service healthiness of the fixed intelligent customer service system, comprising:
Determine the weight of each quality evaluation index；
According to the index value of each quality evaluation index and the weight of each quality evaluation index, determine described in
The service healthiness of intelligent customer service system.
3. the method according to claim 1, wherein the quality evaluation index includes at least one of the following:
Service smooth index, service satisfaction index, Service Benefit index or risk control index；
Wherein, the risk control index is used to characterize the session identification accuracy of intelligent customer service system.
4. according to the method described in claim 3, it is characterized in that, the service smooth index includes that response time or guidance are logical
At least one of in smooth rate；
The service satisfaction index includes closed loop rate, recall rate, user's enquirement repetitive rate, service satisfactory rate or user emotion
At least one of in positive rate；
The Service Benefit index includes at least one in session amount, service satisfactory rate, closed loop rate or recall rate；
The risk control index includes risk identification accuracy rate；
Wherein, the robot that the guidance patency rate is used to characterize intelligent customer service system successfully boots up user to artificial customer service system
Degree；
The closed loop rate is used to characterize closed loop session amount ratio shared in total service conversation amount, wherein closed loop session refers to
User is not in intelligent customer service system and artificial customer service in preset time in this conversation procedure and after this conversation end
The session of system generation behavioral data；
The user emotion forward direction rate is for characterizing the forward direction after the robot of user and the intelligent customer service system conversate
The session amount of mood ratio shared in total session amount.
5. method according to claim 1-4, which is characterized in that intelligent customer service system in the acquisition setting period
The conversational services data and user behavior data of system, comprising:
Obtain the conversational services data and user behavior data of the intelligent customer service system in the setting period, the preset period of time packet
Included at least two periods, at least two period includes at least one of the setting period being associated with week in the setting period
Phase；
The weight of each quality evaluation index of determination, comprising:
According to respective corresponding conversational services data and user behavior data of each association period, determines and each be associated with each of period
The index value of a quality evaluation index；
According to each index value corresponding to quality evaluation index described in every two in the setting period, when determining the setting
Related coefficient in section between quality evaluation index described in every two；
For each quality evaluation index, based on all index values corresponding to the quality evaluation index to it is all related
Coefficient determines the information content of the quality evaluation index；
According to each respective information content of quality evaluation index, the weight of each quality evaluation index is determined.
6. according to the method described in claim 5, it is characterized in that, described based on all corresponding to the quality evaluation index
Index value and all related coefficients determine the information content of the quality evaluation index, comprising:
According to the corresponding all index values of the quality evaluation index, the corresponding standard deviation of the quality evaluation index is determined；
The information of the quality evaluation index is determined based on the corresponding standard deviation of the quality evaluation index and all related coefficients
Amount.
7. according to the method described in claim 5, it is characterized in that, the method also includes:
According to the index value and each quality evaluation index of each quality evaluation index in each association period
Weight, determine the intelligent customer service system it is each it is described association the period service healthiness；
According to the service healthiness in each period in the setting period, determine the intelligent customer service system in the setting period
Service healthiness.
8. method according to claim 1-4, which is characterized in that intelligent customer service system in the acquisition setting period
The conversational services data and user behavior data of system, comprising:
It is identified according to type of service, obtains the clothes in the intelligent customer service default period corresponding to type of service mark
The conversational services data and user behavior data of business business；
Wherein, the service healthiness is the service healthiness that the intelligent customer service system corresponds to the service business.
9. a kind of data processing equipment of intelligent customer service system, which is characterized in that described device includes:
Module is obtained, for obtaining the conversational services data and user behavior data of intelligent customer service system in the setting period；
First determining module determines each matter in the setting period for being based on the conversational services data and user behavior data
Measure the index value of evaluation index；
Second determining module determines the service of the intelligent customer service system for the index value according to the quality evaluation index
Health degree, the service healthiness are used to be characterized in the service quality of the intelligent customer service system in the setting period.
10. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors, one or more of programs are configured to: being executed according to claim 1~8
The data processing method of described in any item intelligent customer service systems.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910834046.6A CN110533343B (en) | 2019-09-04 | 2019-09-04 | Data processing method and device of intelligent customer service system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910834046.6A CN110533343B (en) | 2019-09-04 | 2019-09-04 | Data processing method and device of intelligent customer service system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110533343A true CN110533343A (en) | 2019-12-03 |
| CN110533343B CN110533343B (en) | 2023-12-15 |
Family
ID=68667033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910834046.6A Active CN110533343B (en) | 2019-09-04 | 2019-09-04 | Data processing method and device of intelligent customer service system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533343B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143537A (en) * | 2019-12-30 | 2020-05-12 | 税友软件集团股份有限公司 | Service method, device, equipment and medium based on intelligent customer service system |
| CN111311286A (en) * | 2020-02-27 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Intelligent customer service data processing method and device, computing equipment and storage medium |
| CN112200450A (en) * | 2020-09-30 | 2021-01-08 | 深圳壹账通智能科技有限公司 | Customer service distribution method, device and medium |
| CN113128794A (en) * | 2019-12-27 | 2021-07-16 | 北京国双科技有限公司 | Quantization evaluation method and device |
| CN113610399A (en) * | 2021-08-09 | 2021-11-05 | 广州品唯软件有限公司 | Risk monitoring method, system and device for customer service background |
| CN113780610A (en) * | 2020-12-02 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Customer service portrait construction method and device |
| CN115221306A (en) * | 2022-09-21 | 2022-10-21 | 北京云迹科技股份有限公司 | Automatic response evaluation method and device |
| CN116542566A (en) * | 2023-05-09 | 2023-08-04 | 广东圣千科技有限公司 | Interactive scoring method and system for intelligent skin care customer service |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103811009A (en) * | 2014-03-13 | 2014-05-21 | 华东理工大学 | Smart phone customer service system based on speech analysis |
| CN107220353A (en) * | 2017-06-01 | 2017-09-29 | 深圳追科技有限公司 | A kind of intelligent customer service robot satisfaction automatic evaluation method and system |
| US20180060818A1 (en) * | 2016-08-31 | 2018-03-01 | Ricoh Company, Ltd. | Conference assistance system and conference assistance method |
| CN107862423A (en) * | 2017-06-28 | 2018-03-30 | 陆金所（上海）科技服务有限公司 | System evaluation method, intelligent evaluation system and computer-readable recording medium |
| CN107967267A (en) * | 2016-10-18 | 2018-04-27 | 中兴通讯股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN108198017A (en) * | 2017-12-22 | 2018-06-22 | 中国联合网络通信集团有限公司 | Personalized customer service processing method and processing device |
| CN109242324A (en) * | 2018-09-18 | 2019-01-18 | 阿里巴巴集团控股有限公司 | Appraisal procedure, device and the equipment of customer service level |
| BR102017019881A2 (en) * | 2017-09-15 | 2019-04-16 | Milton Augusto Barbosa | SUSTAINABLE, SHARED AND COLLABORATIVE DELIVERY SERVICES SUPPORTING INFORMATION TECHNOLOGY, PROGRAMS, SOFTWARES AND APPLICATION |
| CN109919671A (en) * | 2019-02-27 | 2019-06-21 | 上海宝尊电子商务有限公司 | The high efficiency smart client service method and system of a kind of Electronic Commerce field customer orientation |
-
2019
- 2019-09-04 CN CN201910834046.6A patent/CN110533343B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103811009A (en) * | 2014-03-13 | 2014-05-21 | 华东理工大学 | Smart phone customer service system based on speech analysis |
| US20180060818A1 (en) * | 2016-08-31 | 2018-03-01 | Ricoh Company, Ltd. | Conference assistance system and conference assistance method |
| CN107967267A (en) * | 2016-10-18 | 2018-04-27 | 中兴通讯股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN107220353A (en) * | 2017-06-01 | 2017-09-29 | 深圳追科技有限公司 | A kind of intelligent customer service robot satisfaction automatic evaluation method and system |
| CN107862423A (en) * | 2017-06-28 | 2018-03-30 | 陆金所（上海）科技服务有限公司 | System evaluation method, intelligent evaluation system and computer-readable recording medium |
| BR102017019881A2 (en) * | 2017-09-15 | 2019-04-16 | Milton Augusto Barbosa | SUSTAINABLE, SHARED AND COLLABORATIVE DELIVERY SERVICES SUPPORTING INFORMATION TECHNOLOGY, PROGRAMS, SOFTWARES AND APPLICATION |
| CN108198017A (en) * | 2017-12-22 | 2018-06-22 | 中国联合网络通信集团有限公司 | Personalized customer service processing method and processing device |
| CN109242324A (en) * | 2018-09-18 | 2019-01-18 | 阿里巴巴集团控股有限公司 | Appraisal procedure, device and the equipment of customer service level |
| CN109919671A (en) * | 2019-02-27 | 2019-06-21 | 上海宝尊电子商务有限公司 | The high efficiency smart client service method and system of a kind of Electronic Commerce field customer orientation |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113128794A (en) * | 2019-12-27 | 2021-07-16 | 北京国双科技有限公司 | Quantization evaluation method and device |
| CN111143537A (en) * | 2019-12-30 | 2020-05-12 | 税友软件集团股份有限公司 | Service method, device, equipment and medium based on intelligent customer service system |
| CN111311286A (en) * | 2020-02-27 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Intelligent customer service data processing method and device, computing equipment and storage medium |
| CN111311286B (en) * | 2020-02-27 | 2023-04-07 | 腾讯科技（深圳）有限公司 | Intelligent customer service data processing method and device, computing equipment and storage medium |
| CN112200450A (en) * | 2020-09-30 | 2021-01-08 | 深圳壹账通智能科技有限公司 | Customer service distribution method, device and medium |
| CN113780610A (en) * | 2020-12-02 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Customer service portrait construction method and device |
| CN113610399A (en) * | 2021-08-09 | 2021-11-05 | 广州品唯软件有限公司 | Risk monitoring method, system and device for customer service background |
| CN115221306A (en) * | 2022-09-21 | 2022-10-21 | 北京云迹科技股份有限公司 | Automatic response evaluation method and device |
| CN116542566A (en) * | 2023-05-09 | 2023-08-04 | 广东圣千科技有限公司 | Interactive scoring method and system for intelligent skin care customer service |
| CN116542566B (en) * | 2023-05-09 | 2023-11-21 | 广东圣千科技有限公司 | Interactive scoring method and system for intelligent skin care customer service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533343B (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110533343A (en) | Data processing method, device and the electronic equipment of intelligent customer service system | |
| Saya et al. | The impact of institutional influences on perceived technological characteristics and real options in cloud computing adoption | |
| Ochodek et al. | Simplifying effort estimation based on Use Case Points | |
| Swain et al. | Handbook of human-reliability analysis with emphasis on nuclear power plant applications. Final report | |
| Hagen | Do fixed-term contracts increase the long-term employment opportunities of the unemployed? | |
| Baarslag et al. | An automated negotiation agent for permission management | |
| Tung et al. | A novel approach to collaborative testing in a crowdsourcing environment | |
| Palomares et al. | The state-of-practice in requirements elicitation: an extended interview study at 12 companies | |
| Walker et al. | The emergence of data analytics in auditing: Perspectives from internal and external auditors through the lens of institutional theory | |
| Park et al. | Human resource allocation in software project with practical considerations | |
| CN111181757B (en) | Information security risk prediction method and device, computing equipment and storage medium | |
| Sadiq et al. | More on elicitation of software requirements and prioritization using AHP | |
| Huang et al. | An efficient decision support system for the selection of appropriate crowd in crowdsourcing | |
| Shahidi et al. | Assessing the organizational readiness for implementing knowledge management in organizations | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| Verma et al. | Restless Multi-Armed Bandits for Maternal and Child Health: Results from Decision-Focused Learning. | |
| Üsfekes et al. | Auction‐based serious game for bug tracking | |
| Carvalho et al. | Studies on the Accuracy of Ensembles of Cloud-Based Technologies for Sentiment Analysis. | |
| CN111382909A (en) | Rejection inference method based on survival analysis model expansion bad sample and related equipment | |
| Awwad et al. | Efficient worker selection through history-based learning in crowdsourcing | |
| CN107067128A (en) | Task quality detecting method, the method and device for determining dereferenced user | |
| Clingingsmith | Mental accounts and the mutability of altruism: An experiment with online workers | |
| Steinbauer et al. | Chatbots assisting German business management applications | |
| KR102156587B1 (en) | Method for increase and decrease operating of worker and inspector of crowdsourcing based project for artificial intelligence training data generation | |
| CN114090733A (en) | Learning resource recommendation method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |