CN115907784A - Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall - Google Patents
Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall Download PDFInfo
- Publication number
- CN115907784A CN115907784A CN202211355056.XA CN202211355056A CN115907784A CN 115907784 A CN115907784 A CN 115907784A CN 202211355056 A CN202211355056 A CN 202211355056A CN 115907784 A CN115907784 A CN 115907784A
- Authority
- CN
- China
- Prior art keywords
- user
- service
- business hall
- sensitive
- quality inspection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000007689 inspection Methods 0.000 claims abstract description 85
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 230000008451 emotion Effects 0.000 claims abstract description 35
- 238000003860 storage Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 8
- 230000005611 electricity Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 6
- 230000003111 delayed effect Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000011161 development Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008909 emotion recognition Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method and a system for recognizing and actively warning and informing sensitive customers in the service of an electric power business hall are provided, wherein the method comprises the following steps: performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information; sensitive emotion retrieval is carried out on fields in the quality detection result data table, and a user list hit by multiple times of retrieval is obtained; associating user information in a user list with the user portrait, and adding a service sensitive label; in the scene service of the electric power business hall, the user portrait added with the sensitive label is utilized to carry out the accurate identification of sensitive customers and the active early warning notification service. The problems of customer complaint risks, easy event upgrading, delayed event processing and the like caused by potential differentiated services for various types of users in the service process of the business hall in the power industry are solved.
Description
Technical Field
The invention belongs to the technical field of electric power operation, and relates to a method and a system for identifying and actively early warning and notifying service sensitive customers of an electric power business hall.
Background
Under the background of rapid development of information technology, more and more data can be acquired by various industries, but how to better analyze and utilize the data becomes a problem worthy of further discussion at present. For power enterprises, the analysis and application of data by using a big data technology and the practical value of data information are brought into play, which become one of the most important work contents. The user satisfaction is directly related to the survival and development of the power enterprises, and the improvement of the user satisfaction is a key factor of the sustainable development of the enterprises. For a long time, power enterprises take the quality and price of products as the core of development, and neglect the importance of services to a certain extent.
At the present stage, with the increasingly intense competition of the industry, enterprises gradually change the management thinking. The method takes users as centers, better masters the electricity utilization habits and preferences of different users under the support of big data technology, classifies and manages the different users by utilizing user images, and provides precise service in a targeted manner, thereby improving the satisfaction degree of the users and being beneficial to the long-term development of power enterprises.
The off-line service power consumer of the current business hall mainly relates to business such as business consultation transaction, expense inquiry, bill printing and the like. The method is limited by factors such as manpower, working time, knowledge level and the like of the existing manual customer service, the external service standard is inconsistent, the service level is inconsistent, and the customer satisfaction is influenced. At present, service events or customer complaints easily caused by the potential differentiated service for various types of users in the service process of a business hall in the power industry have the following problems: 1) Potential customer complaint risk multiples are increased when the service sensitive or irritable users provide consultation services; 2) The processing is carried out after the service event or the customer complaint occurs, hysteresis exists, and the efficiency is low; 3) The occurrence of the event has the characteristic of instantaneity, and the fermentation and the upgrade of the event are easily caused; 4) Potential customer complaints risk due to oral or communication technical dissatisfaction of the staff. Once a service event or a customer complaint problem occurs, the business hall processes the customer complaint related problem by analyzing the conversation recording or calling the service video, which brings certain trouble to the user and some negative influences to the enterprise image of the marketing power supply company.
In summary, the proposal of the identification and active early warning notification of the sensitive customers in the electric power business hall is a necessary technical means for improving the satisfaction degree of users and realizing the long-term development of electric power enterprises.
Prior art document 1 (CN 111062564A) provides a power customer appeal sensitivity value calculation method, including the steps of: step 100, defining clients who have appeal in different channels in past time periods as power client appeal sensitive sample clients; 200, selecting a client information field related to the sensitivity of the appeal of the power client, and performing secondary calculation and pretreatment on the screened data; step 300, comparing the Kini index with a set threshold value for power customer appeal sensitivity modeling analysis; and 400, performing data modeling and verification on the modeling field by selecting a logistic regression and decision tree data mining algorithm. The client information fields comprise 6 fields of client complaint records, incoming call records, client power failure times, power failure time and electricity charge calculation errors of a business handling overtime box; customer complaints, power consumption habits and business service data statistics are initiatively initiated by users, and no correlation is generated with the self service characteristics of power users.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a method and a system for identifying and actively warning and informing service sensitive customers of a power business hall.
The invention adopts the following technical scheme:
a method for identifying and actively warning and informing sensitive customers in a power business hall comprises the following steps:
step 1: performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information;
step 2, carrying out sensitive emotion retrieval on fields in the quality inspection result data sheet, and obtaining a user list hit by multiple times of retrieval;
step 3, associating user information in the user list with the user portrait, and adding a service sensitive label;
and 4, in the scene service of the electric power business hall, carrying out accurate identification and active early warning notification service on the sensitive client by using the user portrait added with the sensitive label.
The invention also provides the following priority scheme:
preferably, the step 1 comprises the steps of:
step 1.1: the whole amount of the voice is accessed to manual fee-prompting recording and entity business hall service recording, and voice quality inspection analysis is carried out by calling an intelligent quality inspection system;
step 1.2: and analyzing the quality inspection result to obtain emotion and event fields and form a quality inspection analysis result data table containing user information.
Preferably, in step 1.1, the manual fee-prompting recording and the off-line business hall service recording generate a plurality of pieces of quality inspection result table data by calling an intelligent quality inspection system, wherein the quality inspection result table data comprises a voice quality inspection detail table, a voice quality inspection table, an event table and a user information table;
the voice quality inspection list comprises roles, a recording identification text and a conversation occurrence time field;
the voice quality inspection table comprises quality inspection state, recording duration, business hall codes, pickup equipment attributes, employee codes, user events, employee events, session start time and session end time fields;
the event table comprises event codes, event names, event time, business hall names, business hall codes, working window names, working personnel codes and recording duration fields;
the user information table comprises a communication unique identifier, a service type, a work order number or a charging serial number', a user number, an identity card number and a mobile phone number field.
Preferably, the emotions in step 1.2 include anger, complaints, neutrality, pleasure, praise; the events comprise quarreling events and other events; the formed quality inspection analysis result data table comprises a session unique identifier, a user number, an identification number, a mobile phone number, a business hall code, a business hall name, an employee code, an employee name, session start time, session end time, recording duration, emotion and event fields.
Preferably, the step 2 comprises the steps of:
step 2.1: a 360-view associated synchronous quality inspection analysis result data sheet of a marketing 2.0 system;
step 2.2: and (5) searching an emotion field in the quality inspection analysis result data table, and acquiring a user list of 'suspected angry' hit in 2 times or more of searching.
Preferably, in step 3, according to the uniquely associated user number, identification number and contact telephone number in the user list, the user portrait in the 360-view is inversely associated with the user number, and a service sensitive user label is added.
Preferably, the step 4 comprises the steps of:
step 4.1: acquiring user identity information of a user arriving at an entity business hall under a power line;
and 4.2: the user identity information and the information of the business hall where the user is located and the equipment side are uploaded to a data center platform of the marketing system to request for inquiring the user portrait label, and identity recognition of the service sensitive client is carried out;
step 4.3: when the current user is identified as a service sensitive label client, issuing an early warning popup to the current seat to prompt the current user to be a service sensitive user, generating a service early warning event and pushing an event center;
step 4.4: the event center analyzes the service early warning event and forms an early warning task;
step 4.5: and judging the business hall area of the user according to the information of the business hall of the user and the equipment side, inquiring channel information, acquiring the contact way of a responsible person, calling an early warning template to send a short message or telephone notification to issue an early warning notification to a team leader so as to perform special precise service.
Preferably, in step 4.1, the manner of acquiring the user information includes: self-service equipment acquisition, certificate reading and information input;
wherein, self-service equipment acquisition mode contains: the user of the VTM/online national network self-service equipment logs in through a mobile phone number and an electric card user number;
the certificate reading mode is as follows: when a user arrives at a manual seat, reading the identity card through the equipment outside the cabinet to acquire the identity card number of the user according to the business requirement;
the information input mode is as follows: when a user arrives at the manual seat, service personnel input the number of the user card and the contact telephone number of the user through the power service acceptance system to inquire the user service data, so that the number of the user and the contact telephone number are obtained.
Preferably, the information of the business hall and the equipment terminal in step 4.2 includes a business hall code, a self-service equipment number, a login job number of the online national network PC terminal, and a login IP of the online national network PC terminal.
A power business hall service sensitive customer identification and active early warning notification system is used for realizing the method, and the system comprises:
the voice quality inspection analysis module is used for performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information;
the sensitive user identification module is used for carrying out sensitive emotion retrieval on fields in the quality inspection result data table and acquiring a user list hit by multiple times of retrieval;
the sensitive label setting module is used for associating user information in the user list with the user portrait and adding a service sensitive label;
and the sensitive client identification and service module is used for performing accurate identification and active early warning notification service on the sensitive client by using the user portrait added with the sensitive label in the scene service of the electric power business hall.
A terminal comprising a processor and a storage medium; the storage medium is to store instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method.
Compared with the prior art, the method has the advantages that through accurate identification and early warning notification service of the service sensitive customer portrait, the portrait of the power user can be identified without sense, the service sensitive label user can be automatically identified, service early warning is carried out, accurate service is provided in a targeted mode, and potential customer complaint risks are greatly reduced. Through with SMS platform, the platform UNICOM is exhaled outward to intelligence, carry out the early warning notice to team leader or service personnel with the sensitive label user of service to the shop, avoid appearing the condition that the early warning was not notified, specifically still include:
intelligent quality inspection is carried out through offline service conversation recording and manual fee-charging recording of an entity business hall, quality inspection results are analyzed and correlated with user images, and service sensitive labels are added to users who hit the emotion of suspected angry for more than 2 times; when a user arrives at an entity business hall and operates self-service equipment of the electric power business hall, monitoring of network points or manual service, the user identity information is obtained through identity document reading, electric card user number and contact telephone mode; a customer portrait request is viewed from the marketing system 360 through the user identity information, and customer identity identification and customer service sensitive label identification are carried out; after the client is identified as a service sensitive client, generating a service active early warning event and pushing the service active early warning event to an event center; the event center analyzes the service active early warning event, and issues early warning short message or early warning telephone to business hall service personnel (issuing early warning popup notice from the PC end of the network and the country) or team leaders so as to carry out special accurate service, and avoid emotion fluctuation of service sensitive customers and service conflict with the service personnel. The problems of customer complaint risk, easy upgrading of events, delayed event processing and the like caused by potential differentiated services for various types of users in the service process of the business hall in the power industry can be effectively avoided. 1) The user identity information is acquired in various types, so that the full coverage of user information acquisition can be realized; 2) Carrying out service sensitive customer identity identification according to the user information and the marketing system user portrait to realize non-sensitive user portrait comparison; 3) After the service sensitive client is identified, automatically generating an arrival event of a service sensitive label user, analyzing data, and pushing an early warning; 4) The event center carries out targeted notification on the early warning notifications of service personnel or group leaders in a plurality of types, and full coverage with service early warning and service flow closed loop are realized.
Drawings
FIG. 1 is a flow chart of the method for identifying and proactively warning and notifying service sensitive customers in an electric power business hall according to the present invention;
FIG. 2 is a flowchart illustrating a complete implementation of the method for identifying and actively warning and notifying sensitive customers in an electric power business hall according to the present invention;
FIG. 3 is a flow chart of the present invention for utilizing a user portrait with a tag added to identify a sensitive customer accurately and provide active warning notification services;
FIG. 4 is a flowchart of an event center parsing an event and providing accurate service according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. The embodiments described herein are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art without inventive step, are within the scope of protection of the present invention.
As shown in fig. 1-2, embodiment 1 of the present invention provides a power business hall service sensitive customer identification and proactive warning notification method, which in a preferred but non-limiting embodiment of the present invention, comprises the following steps 1-4:
step 1: performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information;
step 1.1: the whole amount is accessed into manual fee-urging recording and entity business hall service recording, and voice quality inspection analysis is carried out by calling an intelligent quality inspection system;
manually charging recording and service recording in an off-line business hall, recording for internal service of national network companies, deploying and collecting in full, and storing recording files.
The manual fee-prompting recording and the off-line business hall service recording generate a plurality of pieces of quality inspection result table data by calling the intelligent quality inspection system.
Wherein entity business office pronunciation quality testing result table includes:
1. voice quality inspection detail list (Manual charge urging, business hall voice quality inspection result list field same)
'id' varchar (32) 'primary key id',
"quality _ id" varchar (64) 'quality inspection id',
delivery _ number ' varchar (32) ' delivery number ',
"role" varchar (20) 'role',
recording _ text 'recording identification text',
the "intersection' text" hit rule, separated by commas in the middle,
"wisdom ' text ' rule type ',
'talk _ time' varchar (20) 'dialog occurrence time',
"rule _ arr ' text ' hit rule type and name, multiple comma split ',
2. phonetic quality testing table
Table field:
"quality _ id" varchar (64) 'quality inspection id',
"file _ id ' varchar (40) ' unstructured id ',
"sn ' varchar (128) ' device sequence ',
"file _ name" varchar (500) 'filename',
"opcode ' varchar (20) ' application coding ',
"status" varchar (10) 'quality inspection status (1 in preparation, 2 in identification, 3 in identification succeeded, 4 in identification failed)',
"record _ time" varchar (20) 'recording duration',
"content _ type" varchar (8) 'file type',
service _ code ' varchar (600) ' shop floor coding ',
"equivalent _ code" varchar (128) 'pick-up coding',
"equipment _ attribute" varchar (10) 'pickup attribute',
"employee _ code" varchar (64) 'employee code',
"business _ event" text communication 'user event',
work _ standard _ event ' text common ' employee event ',
"interaction _ node" varchar (20) 'interaction node',
"sound _ begin _ time ' varchar (20) ' conversation start time ',
"sound _ end _ time" varchar (20) 'session end time',
"mode" varchar (20) 'state',
push _ status ' varchar (32) ' push state ',
"create _ time ' varchar (20) ' creation time ',
"create _ name" varchar (20) 'create person',
change time ' varchar (30) ' modification time ',
change name ' varchar (20) ' modifier ',
'detail _ file _ id' varchar (40) 'quality inspection detail uploads unstructured id',
3. event table
Table field:
batch id ' varchar (60) ' batch number ',
"file _ id" varchar (60) 'unstructured id',
"event _ code" varchar (60) 'event coding',
"event _ name" varchar (200) 'event name',
"event _ time ' varchar (60) ' event time ',
"sn 'varchar (30) device serial number',
"yyt _ name ' varchar (200) ' business hall name ',
"yyt _ code ' varchar (40) ' shop floor coding ',
"window _ name ' varchar (200) ' work window name ',
"employee _ name" varchar (100) 'staff name',
"employee _ code" varchar (100) 'staff code',
"record _ time" varchar (40) 'recording duration',
'ai _ quality _ detail _ id' varchar (60) 'quality inspection unstructured id',
"status" varchar (3) '0, not downloaded, 1, downloaded',
"create _ time ' varchar (60) ' creation time ',
change time ' varchar (60) ' modification time ',
quality _ id ' varchar (64) ' quality id ',
"push _ status" varchar (32) 'push state 0 push 1 push 2 push failed',
push time ' varchar (60) ' push time ',
whether the is _ receive 'varchar (20)' receives event 0 is 1 or not,
"event _ role ' varchar (20) '1. User, 2. Staff ',
4. user information meter (upload clear outside cabinet)
Table field:
'id' varchar (50) 'Primary Key',
'chainId' varchar (100) 'one-way session unique identifier',
"type 'varchar (100)' service type, 1: and (3) passing home, 2: the payment of' the fee is carried out,
"number" varchar (100) 'work order number or pay-for-run number',
'ConsNo' varchar (100) 'house number',
"idNumber" varchar (100) 'identification number',
"phone ' varchar (100) ' cell phone number ', step 1.2: and analyzing the quality inspection result to obtain emotion and event fields and form a quality inspection analysis result data table containing user information.
Analyzing the data of the plurality of quality inspection result tables in the step 1.1 to obtain emotion and event fields;
table field: "emotion' varchar (3) client emotion: according to the voice quality inspection list, the field names are listed as follows: analyzing the hit rule, and according to an intelligent quality inspection emotion recognition engine, an emotion recognition feedback result comprises the following steps: anger, complaints, neutrality, pleasure, praise;
according to business requirements, the hit angry emotion is defined as: suspected anger, complaints of hits, neutrality, pleasure, praise, and others. One-pass voice quality test results hit multiple emotions, table field: the customer emotion has only one emotional outcome.
Table field: "event _ name 'varchar (3)' quarry event: and (4) judging according to an intelligent quality inspection recognition engine-quality inspection rule, and returning an event name through an event name field of an event table ' event _ name ' varchar (200) ' in clear codes. According to the business requirement, the event name is transmitted back as a quarreline event, and the table field is as follows: the quarrel event is analyzed and stored as yes; the event name is returned as other event names, table field: analyzing and storing the quarrel event as no;
analyzing the data of the plurality of quality inspection result tables to generate a voice analysis result data table as follows:
voice analysis result data sheet
Table field:
"chan _ id" (primary key) one-way session unique identifier',
the ' cons _ no ' user number ' is from the user information table, and the acquisition of the PC end input number of the network
"id _ number 'identification number', derived from the user information table: identification card number, and identification card reading and acquiring by equipment outside cabinet
Phone 'cell phone number' derived from the user information table: mobile phone number, and PC end input and upload of network state network
Service _ code 'shop code' from event table
Service _ name 'Business office name' from event table
'Equipment _ code' pickup encoding 'from Voice quality Chart'
Employee code from the Speech quality inspection Table
"employee _ name ' varchar (64) ' employee name ' from the event table
"sound _ begin _ time ' varchar (20) ' conversation start time ' derived from speech quality table
"Sound _ end _ time ' varchar (20) ' Session end time ' from a Voice checklist
"record _ time ' varchar (40) ' recording duration ' from event table
"emotion 'varchar (3)' client emotion, 1: suspected anger, 2. Others', results from field parsing results of the rules for hit in the speech quality List
"event _ name 'varchar (3)' a quarrel event: 1. yes, 2. No', result from event table event name field resolution
"reproduction _ id ' varchar (60) ' TXT text file unstructured id ',
file _ id ' varchar (60) ' audio unstructured id ',
step 2, carrying out sensitive emotion retrieval on fields in the quality inspection result data sheet, and obtaining a user list hit by multiple times of retrieval;
step 2.1: a 360-view association synchronization quality inspection analysis result data table of the marketing 2.0 system; the method comprises the following steps:
(1) Encrypting and transmitting the voice analysis result data table and the internal network to a provincial data center station;
(2) The marketing 2.0 system data center station requests the provincial data center station to carry out table synchronization;
(3) Marketing 2.0 system data center station obtains a voice analysis result data table;
(4) The voice analysis result data table is synchronously associated with the marketing 2.0 system-360 view.
Step 2.2: and (5) searching an emotion field in the quality inspection analysis result data table, and acquiring a user list of 'suspected angry' hit in 2 times or more of searching.
Step 3, associating user information in the user list with the user portrait, and adding a service sensitive label;
and according to the uniquely associated user number, the identity card number and the contact phone in the user list, reversely associating the user portrait in the view 360 with the user number, and adding a service sensitive user label. The method specifically comprises the following steps:
(1) A 360-view setting timing task of a marketing 2.0 system scans 360 user image data tables and voice analysis result data tables;
(2) Scanning a table field: "cons _ no" user number "," id _ number "identification number", "phone number", "inventory" varchar (3)' client emotion, 1: suspected anger, 2. Others
(3) The user information is correlated, and the correlation algorithm is as follows: the customer code, the user account number, the identity card number and the mobile phone number are preferably uniquely associated, and due to the particularity of the power marketing service, the customer code is a unique power user identity identifier, the same customer code and the user name, a plurality of user account numbers or mobile phone numbers may exist.
(4) Client emotion retrieval: scanning a table field: ',' emotion 'varchar (3)' client emotion, same client code, table field: client mood, 2 and above hits: suspected angry results, 360 views customer portrait add: and (3) a service sensitive tag which is only shown or called in the Jiangsu power content marketing system.
And 4, in the scene service of the electric power business hall, carrying out accurate identification and active early warning notification service on sensitive customers by utilizing the user portrait added with the sensitive label. As shown in fig. 3, the method specifically includes:
step 4.1: taking a functional scene of early warning of users in an entity business hall under a power line as an example, acquiring user identity information of the users reaching the entity business hall under the power line;
the method for acquiring the user information comprises the following steps: self-service equipment acquires, certificate reads, information entry:
the self-service equipment acquisition mode comprises: and the queuing machine swipes an identity card to obtain a number, and the VTM/Internet self-service equipment user logs in through a mobile phone number and an electric card user number.
The certificate reading mode is as follows: and when the user arrives at the manual seat, the identity card is read through the outside-cabinet cleaning equipment according to the service requirement, and the identity card number of the user is obtained. ( Clear equipment outside the cabinet is the integrated display device of artifical seat customer service in electric power entity business office, and is integrated: seat information display, password keyboard, electronic signature, identity card reading, union pay card swiping and other functions )
The information input mode is as follows: when a user arrives at a manual seat, a service person inputs a user number of a card and a user contact telephone through a network national network PC (personal computer) end (a power service acceptance system) to inquire user service data, so that the user number and the contact telephone are obtained.
Step 4.2: the user identity information and the information of the business hall where the user is located and the equipment side are uploaded to a data center platform of the marketing system to request for inquiring the user portrait label, and identity recognition of the service sensitive client is carried out;
step 4.3: when the current user is identified as a service sensitive label client, the interface is called back, an early warning popup is issued to a PC (personal computer) end of a national network of the current seat to prompt the current user as a service sensitive user, a service early warning event is generated and an event center is pushed;
step 4.2-step 4.3, according to the account number, the user identity card number and the contact call, inquiring the user portrait label in a 360-degree view of a platform in the marketing 2.0 system data, if a service sensitive label added to the current user is identified (the emotion of the user appears more than 2 times of suspected angry), identifying the current user as a service sensitive customer, and generating a service early warning event by the marketing 2.0 system and pushing the service early warning event to an event center for early warning;
and calling a query interface through the PC end of the network, querying information of the portrait of the user in the marketing 2.0 system data through the user number, the user identity card number and the contact telephone, confirming that the current user is a service sensitive user, calling back the label name through the interface, and prompting popup at the PC end of the network.
Step 4.4: the event center analyzes the service early warning event and forms an early warning task;
step 4.5: and judging the business hall area of the user according to the information of the business hall of the user and the equipment side, inquiring channel information, acquiring the contact way of a responsible person, calling an early warning template to send a short message or telephone notification to issue an early warning notification to a team leader so as to perform special precise service.
Step 4.4-step 4.5, as shown in fig. 4, the service early warning event obtained by the event center includes user information (user number, identification card number, contact phone), business hall information (business hall code, self-service device number), and early warning event name: service sensitive user arrival. Analyzing the service early warning event:
(1) Inquiring the channel information of the marketing 2.0 system according to the business hall code, obtaining the name of the business hall and the contact telephone of the business responsible person
(2) And generating an early warning notification task (system popup window/short message telephone early warning) according to the business hall information (business hall code and self-service equipment number). The business hall name and the business responsible person contact telephone are obtained through the channel information, the event center is called to pre-configure a service early warning telephone or short message template, and the business responsible person of the business hall is informed of the arrival of the service sensitive user through a short message or a telephone.
(3) The event center issues early warning notifications to the team leaders by calling the outbound platform or the short message platform to provide accurate service for users, and avoids emotion fluctuation of service sensitive customers.
Embodiment 2 of the present invention provides a system for identifying and actively warning and notifying a sensitive customer in a power business hall, which is used for implementing the method, and the service system includes:
the voice quality inspection analysis module is used for performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information;
the sensitive user identification module is used for carrying out sensitive emotion retrieval on fields in the quality inspection result data sheet and acquiring a user list hit by multiple times of retrieval;
the sensitive label setting module is used for associating the user information in the user list with the user portrait and adding a service sensitive label;
and the sensitive client identification and service module is used for performing accurate identification and active early warning notification service on the sensitive client by using the user portrait added with the sensitive label in the scene service of the electric power business hall.
Embodiment 3 of the present invention provides a plurality of power terminals (cabinet outside, queuing machine, internet network, VTM), including a touch screen, a processor, a storage medium, and an identification module; the storage medium is to store instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method.
Embodiment 4 of the invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method.
Compared with the prior art, the method has the advantages that intelligent quality inspection is carried out through offline service conversation recording and manual fee-prompting recording of the entity business hall, quality inspection results are analyzed and correlated with user pictures, and service sensitive labels are added to users who hit the suspected angry emotion for more than 2 times; when a user arrives at an entity business hall and operates self-service equipment of the electric power business hall, network monitoring or manual service, user identity information is acquired through identity document reading, a user number of a telephone card and a contact telephone mode; a customer portrait request is viewed from the marketing system 360 through the user identity information, and customer identity identification and customer service sensitive label identification are carried out; after the client is identified as a service sensitive client, generating a service active early warning event and pushing the service active early warning event to an event center; the event center analyzes the service active early warning event, and issues early warning short message or early warning telephone to business hall service personnel (issuing early warning popup notice from the PC end of the network and the country) or team leaders so as to carry out special accurate service, and avoid emotion fluctuation of service sensitive customers and service conflict with the service personnel. The problems of customer complaint risk, easy upgrading of events, delayed event processing and the like caused by potential differentiated services for various types of users in the service process of the business hall in the power industry can be effectively avoided.
According to the invention, through accurate identification and early warning notification service of the service sensitive customer portrait, power user portrait non-sensory identification can be realized, the service sensitive label user is automatically identified, service early warning is carried out, accurate service is provided in a targeted manner, and potential customer complaint risks are greatly reduced. Through with SMS platform, the platform UNICOM of calling out outside of intelligence, carry out the early warning notice to team leader or service personnel with the sensitive label user of service to the shop, avoid appearing the condition that the early warning is not notified, specifically still include:
the method comprises the steps that power user service voice conversation is collected, collected and retained, power user service voice intelligent voice analysis is conducted, voice analysis results are analyzed and associated with user portrait, a power marketing system 360 views the user portrait and adds a special label, and a user arrives at an entity business hall under a power line and obtains user identity information (user number input, mobile phone number input and cabinet outside clear equipment identity card reading) through power business hall self-service equipment (VTM equipment, internet and national network equipment and queuing machine) and manual service (manual seat); requesting service sensitive customer identity identification from a user portrait of a marketing system according to user identity information; and identifying that the user is a service sensitive label client, calling back a popup prompt of a PC (personal computer) end of the Internet and China network as a result, generating a service early warning event, pushing an event center to form an early warning task, inquiring channel information-business responsible person contact way according to business hall information, calling an early warning template to send a short message or telephone notification to issue an early warning notification to a team leader, and performing special precise service. The method and the system have the advantages that special analysis is carried out by using full-collection user service conversation records, the self service characteristics of power users are correlated, the sensitive subdivision groups of the power customer service experience of the customers are clarified, the target customers sensitive to the power customer service experience appeal are searched in a targeted mode by analyzing the group characteristics and designing differentiated services, targeted power management services are developed, and the satisfaction degree of sensitive customers is improved.
The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present disclosure may be assembler instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the disclosure are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (12)
1. The method for recognizing and actively early warning and informing the sensitive customers in the service of the electric power business hall is characterized in that:
the method comprises the following steps:
step 1: performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information;
step 2, carrying out sensitive emotion retrieval on fields in the quality inspection result data sheet, and obtaining a user list hit by multiple times of retrieval;
step 3, associating user information in the user list with the user portrait, and adding a service sensitive label;
and 4, in the scene service of the electric power business hall, carrying out accurate identification and active early warning notification service on sensitive customers by utilizing the user portrait added with the sensitive label.
2. The power business hall service sensitive customer identification and proactive alert notification method of claim 1, wherein:
the step 1 comprises the following steps:
step 1.1: the whole amount is accessed into manual fee-urging recording and entity business hall service recording, and voice quality inspection analysis is carried out by calling an intelligent quality inspection system;
step 1.2: and analyzing the quality inspection result to obtain emotion and event fields and form a quality inspection analysis result data table containing user information.
3. The power business hall service sensitive customer identification and proactive alert notification method of claim 2, wherein:
in step 1.1, by calling an intelligent quality inspection system, generating a plurality of quality inspection result table data including a voice quality inspection detail table, a voice quality inspection table, an event table and a user information table according to manual charge-urging recording and offline business hall service recording;
the voice quality inspection list comprises roles, a recording identification text and a conversation occurrence time field;
the voice quality inspection table comprises quality inspection state, recording duration, business hall codes, pickup equipment attributes, employee codes, user events, employee events, session start time and session end time fields;
the event table comprises event codes, event names, event time, business hall names, business hall codes, working window names, working personnel codes and recording duration fields;
the user information table comprises a session unique identifier, a service type, a work order number or a charging serial number', a user number, an identity card number and a mobile phone number field.
4. The method of claim 2 for identification and active warning notification of sensitive customers for electricity business hall service, wherein the method comprises:
the emotions in step 1.2 include anger, complaints, neutrality, pleasure, praise; the events include quarrel events and other events; the formed quality inspection analysis result data table comprises a session unique identifier, a user number, an identification number, a mobile phone number, a business hall code, a business hall name, an employee code, an employee name, session start time, session end time, recording duration, emotion and event fields.
5. The power business hall service sensitive customer identification and proactive alert notification method of claim 1, wherein:
the step 2 comprises the following steps:
step 2.1: a 360-view association synchronization quality inspection analysis result data table of the marketing 2.0 system;
step 2.2: and (5) searching an emotion field in the quality inspection analysis result data table, and acquiring a user list of 'suspected angry' hit in 2 times or more of searching.
6. The power business hall service sensitive customer identification and proactive alert notification method of claim 1, wherein:
and 3, reversely associating the user portrait in the view 360 with the user number according to the uniquely associated user number, the identity card number and the contact telephone in the user list, and adding a service sensitive user label.
7. The power business hall service sensitive customer identification and proactive alert notification method of claim 1, wherein:
the step 4 comprises the following steps:
step 4.1: acquiring user identity information of a user arriving at an entity business hall under a power line;
step 4.2: the user identity information and the information of the business hall where the user is located and the equipment side are uploaded to a data center platform of the marketing system to request for inquiring the user portrait label, and identity recognition of the service sensitive client is carried out;
step 4.3: when the current user is identified as a service sensitive label client, issuing an early warning popup to a current seat to prompt the current user as a service sensitive user, generating a service early warning event and pushing an event center;
step 4.4: the event center analyzes the service early warning event and forms an early warning task;
step 4.5: and judging the business hall area of the user according to the information of the business hall of the user and the equipment side, inquiring channel information, acquiring the contact way of a responsible person, calling an early warning template to send a short message or a telephone notification to issue an early warning notification to a team leader so as to perform special precise service.
8. The power business hall service sensitive customer identification and proactive alert notification method of claim 7, wherein:
in step 4.1, the manner of obtaining the user information includes: self-service equipment acquisition, certificate reading and information input;
wherein, self-service equipment obtains the mode and contains: the queuing machine swipes an identity card to obtain a number, and a VTM/Internet national network self-service equipment user logs in through a mobile phone number and an electric card user number;
the certificate reading mode is as follows: when a user arrives at a manual seat, the identity card is read through the outside-cabinet equipment according to the service requirement, and the identity card number of the user is obtained;
the information input mode is as follows: when a user arrives at the manual seat, service personnel input the number of the user of the electric card and the contact telephone of the user through the electric power service acceptance system to inquire the service data of the user, so that the number of the user and the contact telephone are obtained.
9. The power business hall service sensitive customer identification and proactive alert notification method of claim 7, wherein:
and 4.2, the information of the business hall and the equipment end comprises a business hall code, a self-service equipment number, a login job number of a network and country PC end and a login IP of the network and country PC end.
10. A power business hall service sensitive customer identification and proactive alert notification system for implementing the method of any of claims 1-9, characterized by:
the system comprises:
the voice quality inspection analysis module is used for performing voice quality inspection on the historical scene recording, analyzing fields in a quality inspection result, and forming a quality inspection analysis result data table after associating the fields with user information;
the sensitive user identification module is used for carrying out sensitive emotion retrieval on fields in the quality inspection result data table and acquiring a user list hit by multiple times of retrieval;
the sensitive label setting module is used for associating the user information in the user list with the user portrait and adding a service sensitive label;
and the sensitive client identification and service module is used for performing accurate identification and active early warning notification service on the sensitive client by using the user portrait added with the sensitive label in the scene service of the electric power business hall.
11. A terminal comprising a processor and a storage medium; the method is characterized in that:
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 9.
12. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211355056.XA CN115907784A (en) | 2022-11-01 | 2022-11-01 | Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211355056.XA CN115907784A (en) | 2022-11-01 | 2022-11-01 | Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115907784A true CN115907784A (en) | 2023-04-04 |
Family
ID=86484209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211355056.XA Pending CN115907784A (en) | 2022-11-01 | 2022-11-01 | Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907784A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116523529A (en) * | 2023-06-27 | 2023-08-01 | 国网江苏省电力有限公司营销服务中心 | Application method and system of manual fee-forcing quality inspection and quality inspection result in customer view |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8667072B1 (en) * | 2011-10-24 | 2014-03-04 | West Corporation | Method and apparatus of providing live support service in a notification system |
| CN106815709A (en) * | 2016-12-06 | 2017-06-09 | 国网福建省电力有限公司 | One kind service quick response center support system and method |
| CN111062564A (en) * | 2019-11-08 | 2020-04-24 | 广东电网有限责任公司 | Method for calculating power customer appeal sensitive value |
| CN111489765A (en) * | 2019-01-28 | 2020-08-04 | 国家电网有限公司客户服务中心 | Telephone traffic service quality inspection method based on intelligent voice technology |
| CN112101971A (en) * | 2020-11-19 | 2020-12-18 | 佰聆数据股份有限公司 | Sensitive client identification method, system and storage medium |
| CN114398512A (en) * | 2021-08-26 | 2022-04-26 | 北京中云金诺科技有限公司 | Big data-based voice portrait analysis method for communication operator business customer |
-
2022
- 2022-11-01 CN CN202211355056.XA patent/CN115907784A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8667072B1 (en) * | 2011-10-24 | 2014-03-04 | West Corporation | Method and apparatus of providing live support service in a notification system |
| CN106815709A (en) * | 2016-12-06 | 2017-06-09 | 国网福建省电力有限公司 | One kind service quick response center support system and method |
| CN111489765A (en) * | 2019-01-28 | 2020-08-04 | 国家电网有限公司客户服务中心 | Telephone traffic service quality inspection method based on intelligent voice technology |
| CN111062564A (en) * | 2019-11-08 | 2020-04-24 | 广东电网有限责任公司 | Method for calculating power customer appeal sensitive value |
| CN112101971A (en) * | 2020-11-19 | 2020-12-18 | 佰聆数据股份有限公司 | Sensitive client identification method, system and storage medium |
| CN114398512A (en) * | 2021-08-26 | 2022-04-26 | 北京中云金诺科技有限公司 | Big data-based voice portrait analysis method for communication operator business customer |
Non-Patent Citations (1)
| Title |
|---|
| 柯方圆;钟永颉;胡瑞瑞;: "基于客户画像的供电营业厅精准服务探索", 电力需求侧管理, no. 1 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116523529A (en) * | 2023-06-27 | 2023-08-01 | 国网江苏省电力有限公司营销服务中心 | Application method and system of manual fee-forcing quality inspection and quality inspection result in customer view |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230029707A1 (en) | System and method for automated agent assistance within a cloud-based contact center | |
| US10318098B2 (en) | System and method of communication analysis | |
| US9898743B2 (en) | Systems and methods for automatic generation of a relationship management system | |
| US20140040249A1 (en) | Fact Checker Engine | |
| CN1987913A (en) | Method and system of recommending solutions with an expert system | |
| US20120215538A1 (en) | Performance measurement for customer contact centers | |
| KR102160615B1 (en) | System for managing untact business and method thereof | |
| CN113408846A (en) | Telephone marketing management method and system based on AI artificial intelligence | |
| CN115907784A (en) | Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall | |
| CN111652399A (en) | System for realizing non-inductive face-brushing number-taking in face recognition of tax service hall | |
| CN111210057A (en) | Method for predicting complaints of mobile phone internet users | |
| CN110727759B (en) | Method and device for determining theme of voice information | |
| US20230342864A1 (en) | System and method for automatically responding to negative content | |
| CN116308731A (en) | Account collection processing method and device | |
| US20210409543A1 (en) | Cumulative average spectral entropy analysis for tone and speech classification | |
| US20210056600A1 (en) | Systems and methods for real-time processing of audio feedback | |
| CN116523529A (en) | Application method and system of manual fee-forcing quality inspection and quality inspection result in customer view | |
| CN114169701A (en) | Electric power customer multi-call service risk early warning method | |
| CN110544114A (en) | Method and device for identifying and rating user group aiming at marketing preference | |
| CN118098282A (en) | Event reporting method and electronic equipment | |
| CN117834782A (en) | Call content processing method and device | |
| CN116320164A (en) | Call center service receipt creation method, device, equipment and storage medium | |
| CN118200446A (en) | Service list processing method and device | |
| CN112784038A (en) | Information identification method, system, computing device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |