CN115204664A - Intelligent quality inspection system for customer service quality - Google Patents

Intelligent quality inspection system for customer service quality Download PDF

Info

Publication number
CN115204664A
CN115204664A CN202210821212.0A CN202210821212A CN115204664A CN 115204664 A CN115204664 A CN 115204664A CN 202210821212 A CN202210821212 A CN 202210821212A CN 115204664 A CN115204664 A CN 115204664A
Authority
CN
China
Prior art keywords
quality inspection
quality
rule
data
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
Application number
CN202210821212.0A
Other languages
Chinese (zh)
Inventor
戴良智
高宇栋
李明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Rsvp Technologies Inc
Original Assignee
Rsvp Technologies Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Rsvp Technologies Inc filed Critical Rsvp Technologies Inc
Priority to CN202210821212.0A priority Critical patent/CN115204664A/en
Publication of CN115204664A publication Critical patent/CN115204664A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395Quality analysis or management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/01Customer relationship services
    • G06Q30/012Providing warranty services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/01Customer relationship services
    • G06Q30/015Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
    • G06Q30/016After-sales

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Machine Translation (AREA)

Abstract

The invention relates to an intelligent quality inspection system for customer service quality, which belongs to the technical field of quality inspection and comprises the following components: the rule management module is preset with a rule pool and used for storing a plurality of quality inspection rules; the import module is used for importing the data to be quality-tested into the target quality-testing dataset; the quality inspection task management module is used for generating a quality inspection task according to the data to be quality inspected, and configuring corresponding quality inspection service, a quality inspection task starting mode and a target quality inspection data set; the quality inspection service management module is used for managing quality inspection services, and each quality inspection service corresponds to at least one quality inspection rule; and the quality inspection engine is used for identifying the data to be inspected according to the quality inspection task and carrying out full-quality inspection on the identified data to be inspected according to a preset inspection rule to obtain a quality inspection result. Has the advantages that: the quality inspection task is automatically inspected according to quality inspection rules corresponding to the quality inspection service, so that full-quantity quality inspection is realized, and the quality inspection efficiency is high; the quality inspection is more standard, and the accuracy of the quality inspection result is improved.

Description

Intelligent quality inspection system for customer service quality
Technical Field
The invention relates to the technical field of quality inspection, in particular to an intelligent quality inspection system for customer service quality.
Background
At present, each business has higher requirements on the service quality of customer service, so quality inspection personnel can randomly or according to the seat number perform random inspection on the service data of the customer service, inspect the service data obtained by the random inspection, and evaluate the server quality of each customer service based on the inspection result.
However, in the existing quality inspection scheme, the following defects exist in the manner of manual quality inspection: due to the rapid increase of the business volume and the customer volume, the generated service data volume is large, but the sampling inspection proportion is low, and the risk of missed inspection is large; the quality inspection operation process is complicated, the cost is high, quality inspection personnel are required to be highly dependent on quality inspection experience and patience of the quality inspection personnel, the quality inspection personnel are influenced by subjective factors, the quality inspection efficiency is low, the quality inspection accuracy is unstable, the quality inspection hysteresis is poor, the quality inspection cannot be carried out in time, the online quality inspection and the full-scale quality inspection of service data cannot be realized, and the experience sense is poor.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent quality inspection system for customer service quality.
The technical problem solved by the invention can be realized by adopting the following technical scheme:
an intelligent quality of service system for customer service, comprising:
the rule management module is internally preset with a rule pool for storing a plurality of quality inspection rules;
the import module is used for importing at least one piece of data to be inspected into a target quality inspection data set;
the quality inspection task management module is used for generating a quality inspection task according to the at least one piece of data to be quality inspected, and configuring corresponding quality inspection service, a quality inspection task starting mode and a target quality inspection data set for the quality inspection task;
the quality inspection service management module is respectively connected with the quality inspection task management module and the rule management module and is used for managing the quality inspection services, and each quality inspection service corresponds to at least one quality inspection rule;
and the quality inspection engine is respectively connected with the rule management module and the quality inspection task management module and is used for identifying the data to be inspected according to the quality inspection task and carrying out full quality inspection on the identified data to be inspected according to a preset inspection rule to obtain a quality inspection result.
Preferably, the method further comprises the following steps: and the marketing point mining module is used for analyzing the association degree of each piece of data to be quality tested in the target quality testing data set which is subjected to quality testing according to a preset marketing point set and outputting a marketing mining report.
Preferably, the method further comprises the following steps: the risk control module is used for carrying out user portrait on a user corresponding to each piece of data to be subjected to quality inspection in the target quality inspection data set subjected to quality inspection, carrying out risk analysis according to the user portrait and quality inspection services related to the user, and outputting a risk prediction report corresponding to each piece of data to be subjected to quality inspection;
the risk prediction report comprises at least one or more combinations of complaint types, complaints subjects and risk indexes.
Preferably, the method further comprises the following steps:
the quality re-inspection unit is used for calling the quality inspection engine to perform quality inspection on the target quality inspection data set meeting the quality re-inspection conditions;
the re-quality inspection condition at least comprises one or more combinations of the data to be inspected, the change of the target quality inspection data set and the change of the detection rule, wherein the data to be inspected have no quality inspection in the target quality inspection data set.
Preferably, the rule management module comprises:
the rule creating unit is connected with the rule pool and is used for configuring quality inspection rule information corresponding to a quality inspection point to generate the quality inspection rule and storing the quality inspection rule into the rule pool;
the quality inspection rule information at least comprises any one or more combinations of rule names, rule content descriptions, rule types and dialect conditions.
Preferably, the rule management module further comprises:
and the adjusting unit is connected with the rule creating unit and is used for adjusting the slot position threshold value matched with the quality inspection rule.
Preferably, the quality control engine comprises:
the identification unit is used for carrying out voice identification on the data to be subjected to quality inspection according to a preset voice engine to obtain quality inspection text information;
the rule detection unit is connected with the identification unit and used for carrying out rule check on the quality inspection text information through the voice engine according to the preset detection rule and outputting a detection result corresponding to each preset detection rule;
and the quality inspection unit is connected with the rule detection unit and used for performing semantic understanding on the detection result of the quality inspection text information according to a preset semantic engine and outputting the quality inspection result based on the semantic understanding result.
Preferably, the semantic engine includes a plurality of grammar rule engines corresponding to different service types, and each grammar rule engine has a weight;
further comprising: and the weight engine is connected with the semantic engine and used for distributing corresponding weight to each grammar rule engine and generating the semantic engine corresponding to each quality inspection service.
Preferably, the quality control engine further comprises:
and the scoring unit is used for scoring the detection result of the customer service according to a preset scoring rule, generating a customer service score and including the customer service score in the quality inspection result.
Preferably, the method further comprises the following steps: and the data billboard is used for carrying out statistical analysis according to the data to be quality-tested related to the quality-testing result and/or the quality-testing task and/or the quality-testing service and/or the quality-testing rule and carrying out visual display on the analysis result.
The technical scheme of the invention has the advantages or beneficial effects that:
the intelligent quality inspection system for customer service quality generates a quality inspection task according to data to be inspected, and associates the quality inspection task with corresponding quality inspection service and a target quality inspection data set, so that automatic quality inspection operation is performed according to a quality inspection rule corresponding to the quality inspection service, full quality inspection of all data to be inspected in the target quality inspection data set can be realized, customer service quality is automatically evaluated, and quality inspection efficiency is high; the quality inspection is more standard, and the accuracy of the quality inspection result is improved.
Drawings
Fig. 1 is a block diagram of an intelligent quality inspection system for customer service quality according to a preferred embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
In the preferred embodiment of the present invention, based on the above problems in the prior art, an intelligent quality inspection system for customer service quality is provided, as shown in fig. 1, the system includes:
the rule management module 1 is characterized in that a rule pool 11 is preset in the rule management module 1 and is used for storing a plurality of quality inspection rules;
the import module 2 is used for importing at least one piece of data to be quality-tested into a target quality-testing data set 21;
furthermore, each target quality inspection data set 21 correspondingly has a data set name and description, the data to be quality inspected is imported into the corresponding target quality inspection data set 21 through the import module 2, the data to be quality inspected mainly comprises audio data and a small amount of text data, and the text data is transmitted by adopting an http interface. Specifically, for audio data, audio import in mp3, wav, and m4a formats is supported, and a predetermined amount of data to be quality-checked can be imported at the same time each time. In a preferred embodiment, the data to be tested, which exceeds a predetermined amount, can be packed and compressed before being imported.
Furthermore, after the data is imported, the data to be tested can be edited, newly added, deleted and checked, so that the data can be imported without errors.
The following conditions may result in a data import failure, for example: if the compression packet is too large, uploading an audio compression packet smaller than 200M is recommended; the mono audio contained within the compressed packet is too large, etc. For audio of a typical duration, it takes approximately 2 seconds to import one strip. The lead-in duration increases with the audio length.
Immediately create and execute: the task name (default is data set name + date) needs to be input, the corresponding service is selected, and the quality inspection task is executed immediately when the data set is created. It is also possible to create only data sets requiring manual execution of tasks in the task management panel. This way, the data can be viewed and edited after the data is imported, so that the uploading of the data is confirmed to be error-free.
The quality inspection task management module 3 is used for generating a quality inspection task according to at least one piece of data to be inspected, and configuring corresponding quality inspection service, a quality inspection task starting mode and a target quality inspection data set for the quality inspection task;
the quality inspection service management module 4 is respectively connected with the quality inspection task management module 3 and the rule management module 1 and is used for managing quality inspection services, and each quality inspection service corresponds to at least one quality inspection rule;
and the quality inspection engine 5 is respectively connected with the rule management module 1 and the quality inspection task management module 4 and is used for identifying the data to be inspected according to the quality inspection task and carrying out full quality inspection on the identified data to be inspected according to a preset inspection rule to obtain a quality inspection result.
Specifically, the intelligent quality inspection system for customer service quality generates a quality inspection task according to data to be inspected, and associates the quality inspection task with corresponding quality inspection service and a target quality inspection data set, so that automatic quality inspection operation is performed according to a quality inspection rule corresponding to the quality inspection service, full quality inspection of all data to be inspected in the target quality inspection data set can be realized, customer service quality can be automatically evaluated, and quality inspection efficiency is high; the quality inspection is more standard, and the accuracy of the quality inspection result is improved.
Further, the preset detection rule at least includes any one or more combinations of speech rate detection, volume detection, emotion detection, pause detection, reply speed and reply interval.
As a preferred embodiment, among others, it further includes: and the marketing point mining module 6 is used for analyzing the association degree of each piece of data to be inspected in the quality inspection target data set according to a preset marketing point set and outputting a marketing mining report.
Specifically, aiming at the problem that in the prior art, a customer service generally only cares about things in the responsibility task range of the customer service and cannot effectively grasp other marketing opportunities disclosed in the conversation process with a user, the embodiment of the invention can screen effective information of conversation through identifying conversation intention of the user, corresponding to quality inspection tasks by quality inspection data to be inspected, and analyzing potential requirements of the user through a marketing point mining function, thereby realizing accurate marketing.
Further, the preset marketing point set includes, but is not limited to: violation inquiry, broadband handling, fixed telephone handling, router purchasing, secretary handling, caller identification, insufficient traffic, polyphonic ringtone handling, international long distance handling and the like.
Further, the marketing point mining module 6 has a report export function, and for the target quality inspection data set which has completed quality inspection, the exported marketing mining report can view the quality inspection result of each piece of data to be inspected, and see a complete conversation record, wherein the statement with high relevance to the preset marketing point set is highlighted.
Furthermore, after quality inspection processing is carried out through a quality inspection engine, each piece of data to be inspected corresponds to a quality inspection result, association degree analysis is carried out on the data and the quality inspection results through a preset marketing point set, and statements with association degrees higher than a preset threshold value are highlighted in a conversation recording part in the quality inspection results so as to remind relevant personnel of recommending corresponding marketing products to the user.
In a preferred embodiment, relevancy analysis is performed by means of feature matching of keywords of the marketing point set.
Further, the marketing point mining module 6 can also customize the content of the report, such as displaying the proportion of different marketing points, the number of marketing points changing with the date, and the like.
As a preferred embodiment, the method further comprises the following steps: and the risk control module 7 is used for carrying out user portrait on a user corresponding to each piece of data to be quality tested in the target quality testing data set subjected to quality testing, carrying out risk analysis according to the user portrait and quality testing services related to the user, and outputting a risk prediction report corresponding to each piece of data to be quality tested.
Further, the risk prediction report includes at least one or more combinations of complaint types, complaint subjects, and risk indices. In a preferred embodiment, the complaint types include inward and outward; complaints are made to each application and company when the complaints are internal; the external complaints are complained to 315, departments of industry and commerce and the like.
Specifically, the risk management and control module 7 can be used for drawing pictures of users according to conversations of the users in the data to be inspected and historical data of the users, potential complaints can be found out in advance through complaint risk management and control analysis, follow-up can be conducted in time, complaint amount is reduced, and brands and product images are maintained.
As a preferred embodiment, the method further comprises the following steps:
a quality re-inspection unit (not shown in the figure) for calling the quality inspection engine to perform quality inspection on the target quality inspection data set meeting the quality re-inspection condition;
the re-quality inspection condition at least comprises one or more combinations of the data to be inspected, the target quality inspection data set and the detection rule, wherein the data to be inspected is not subjected to quality inspection in the target quality inspection data set.
Specifically, in this embodiment, before the system of the present invention is used to perform marketing point mining or risk management and control, first, whether the selected target quality inspection data set is subjected to quality inspection or not is determined, and when it is determined that the selected target quality inspection data set is subjected to quality inspection successfully, the marketing point mining module 6 directly performs marketing mining or the risk management and control module 7 performs risk prediction.
If the selected target quality inspection data set is judged to be not quality inspected, the target quality inspection data set is changed or the detection rule is changed, the quality inspection engine 5 is called by the quality inspection restarting unit to restart the quality inspection operation, the quality inspection state is in quality inspection, and the prompt of successful quality inspection is skipped after the quality inspection is finished.
As a preferred embodiment, among others, the rule management module 1 includes:
the rule creating unit 12 is connected with the rule pool 11 and is used for configuring quality inspection rule information corresponding to the quality inspection point to generate a quality inspection rule and storing the quality inspection rule into the rule pool;
the quality inspection rule information at least comprises any one or more combinations of rule names, rule content descriptions, rule types and dialect conditions.
As a preferred embodiment, the rule management module further includes:
and the adjusting unit 13 is connected with the rule creating unit and is used for adjusting the slot position threshold value hit by the matching quality inspection rule.
In a preferred embodiment, the quality inspection engine 5 includes:
the recognition unit 51 is configured to perform voice recognition on the data to be quality-tested according to a preset voice engine to obtain quality-testing text information;
a rule detection unit 52 connected to the recognition unit 51, configured to perform rule checking on the quality inspection text information according to a preset detection rule through the speech engine, and output a detection result corresponding to each preset detection rule;
and the quality inspection unit 53 is connected with the rule detection unit 52 and is used for performing semantic understanding on the detection result of the quality inspection text information according to a preset semantic engine and outputting a quality inspection result based on the semantic understanding result.
Further, the preset detection rule at least includes any one or more combinations of speech rate detection, volume detection, emotion detection, pause detection, reply speed and reply interval.
As a preferred embodiment, the semantic engine includes a plurality of grammar rule engines corresponding to different service types, and each grammar rule engine has a weight;
further comprising: and the weight engine is connected with the semantic engine and used for distributing corresponding weight to each grammar rule engine and generating the semantic engine corresponding to each quality inspection service.
In a preferred embodiment, the quality inspection engine 5 further includes:
and the scoring unit 54 is used for scoring the detection result of the customer service according to a preset scoring rule, generating a customer service score and including the customer service score in the quality inspection result.
As a preferred embodiment, among others, it further includes: and the data billboard is used for carrying out statistical analysis according to the data to be quality-tested related to the quality-test result and/or the quality-test task and/or the quality-test service and/or the quality-test rule and carrying out visual display on the analysis result.
Specifically, in this embodiment, the data analysis interface of the data billboard shows the overall condition of quality inspection; the data statistics details include at least: number of service periods: specifying a total number of services involved in a time period; number of quality inspection files in the period: the total number of files to be quality-checked in a specified time period; the number of rules used during: specifying a total number of rules involved in the task within the time period; number of tasks in the period: the total number of newly built or executed tasks in a specified time period; number of times of task execution during period: the total number of the quality inspection tasks executed in a specified time period; duration of audio: the total audio time length of quality inspection in a specified time period (calculated according to the repeated quality inspection times of the audio); counting the quality inspection recording number: a graph of the number of quality control audios per day over time; the conversation time accounts for: and audio ratio maps of different call durations.
Quality inspection service analysis: the business analysis interface is convenient for a user to check the relevant information of the quality inspection task. And intuitively analyzing the quality inspection rule used in the corresponding time period through the user-defined time period. The traffic statistics details include at least: total number of historical services: the sum of the number of all created services (including deleted services); the execution times of the historical tasks are as follows: the sum of the execution times of all tasks (including deleted traffic); number of service periods: specifying a total number of services involved in a time period; number of times of task execution during period: the total number of the quality inspection tasks executed in a specified time period; number of tasks in the period: the total number of newly built or executed tasks in a specified time period;
further, the method also comprises the following steps: the user authority management module (not shown in the figure) is used for receiving the user to create the user, setting roles for the user and configuring corresponding authorities, wherein the user roles at least comprise an administrator, an operator and a read-only user.
Further, in the above preferred embodiment, the system of the present invention is docked with the communication platform, when the communication platform performs voice transmission with the user, the system of the present invention is notified to establish connection with the user, and after the connection is successful, the voice stream of the communication platform and the user is transmitted to the system of the present invention in real time.
Furthermore, the system of the invention is also connected with a knowledge base, and the knowledge base stores special knowledge of different services, so that the special knowledge is matched from the knowledge base through the identified keywords in the online quality inspection process and is transmitted to the communication platform to be displayed
Further, the method can also comprise the following steps: the system reads the data to be quality-tested from the cloud disk/object storage, then performs off-line quality testing on the data to be quality-tested, and sends a quality testing result to the communication platform after establishing connection with the communication platform.
The technical scheme of the invention has the advantages or beneficial effects that: the intelligent quality inspection system for customer service quality generates a quality inspection task according to the data to be inspected and associates the quality inspection task with the corresponding quality inspection service and the target quality inspection data set, so that automatic quality inspection operation is performed according to the quality inspection rule corresponding to the quality inspection service, full quality inspection of all the data to be inspected in the target quality inspection data set can be realized, the customer service quality is automatically evaluated, and the quality inspection efficiency is high; the quality inspection is more standard, and the accuracy of the quality inspection result is improved.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the spirit and scope of the invention.

Claims (10)

1. An intelligent quality inspection system for customer service quality, comprising:
the rule management module is internally preset with a rule pool for storing a plurality of quality inspection rules;
the import module is used for importing at least one data to be inspected into a target quality inspection data set;
the quality inspection task management module is used for generating a quality inspection task according to the at least one piece of data to be quality inspected, and configuring corresponding quality inspection service, a quality inspection task starting mode and a target quality inspection data set for the quality inspection task;
the quality inspection service management module is respectively connected with the quality inspection task management module and the rule management module and is used for managing the quality inspection services, and each quality inspection service corresponds to at least one quality inspection rule;
and the quality inspection engine is respectively connected with the rule management module and the quality inspection task management module and is used for identifying the data to be inspected according to the quality inspection task and carrying out full quality inspection on the identified data to be inspected according to a preset inspection rule to obtain a quality inspection result.
2. The system of claim 1, further comprising: and the marketing point mining module is used for analyzing the association degree of each piece of data to be quality tested in the target quality testing data set which is subjected to quality testing according to a preset marketing point set and outputting a marketing mining report.
3. The intelligent quality of customer service system of claim 1, further comprising: the risk control module is used for carrying out user portrait on a user corresponding to each piece of data to be subjected to quality inspection in the target quality inspection data set subjected to quality inspection, carrying out risk analysis according to the user portrait and quality inspection services related to the user, and outputting a risk prediction report corresponding to each piece of data to be subjected to quality inspection;
the risk prediction report comprises at least one or more combinations of complaint types, complaints subjects and risk indexes.
4. The intelligent quality of customer service system of claim 2 or 3, further comprising:
the quality re-inspection unit is used for calling the quality inspection engine to perform quality inspection on the target quality inspection data set meeting the quality re-inspection conditions;
the re-quality inspection condition at least comprises one or more combinations of the data to be inspected, the change of the target quality inspection data set and the change of the detection rule, wherein the data to be inspected have no quality inspection in the target quality inspection data set.
5. The intelligent quality of customer service system of claim 1 wherein the rule management module comprises:
the rule creating unit is connected with the rule pool and is used for configuring quality inspection rule information corresponding to a quality inspection point so as to generate the quality inspection rule and store the quality inspection rule into the rule pool;
the quality inspection rule information at least comprises any one or more combinations of rule names, rule content descriptions, rule types and dialect conditions.
6. The intelligent quality of customer service system of claim 5 wherein the rule management module further comprises:
and the adjusting unit is connected with the rule creating unit and is used for adjusting the slot position threshold value matched with the quality inspection rule.
7. The intelligent quality of customer service system of claim 1, wherein the quality inspection engine comprises:
the identification unit is used for carrying out voice identification on the data to be subjected to quality inspection according to a preset voice engine to obtain quality inspection text information;
the rule detection unit is connected with the identification unit and used for carrying out rule check on the quality inspection text information through the voice engine according to the preset detection rule and outputting a detection result corresponding to each preset detection rule;
and the quality inspection unit is connected with the rule detection unit and used for performing semantic understanding on the detection result of the quality inspection text information according to a preset semantic engine and outputting the quality inspection result based on the semantic understanding result.
8. The system of claim 7, wherein said semantic engines include a plurality of grammar rule engines corresponding to different business types, each of said grammar rule engines having a weight;
further comprising: and the weight engine is connected with the semantic engine and used for distributing corresponding weight to each grammar rule engine and generating the semantic engine corresponding to each quality inspection service.
9. The intelligent quality of customer service system of claim 7, wherein the quality inspection engine further comprises:
and the scoring unit is used for scoring the detection result of the customer service according to a preset scoring rule, generating a customer service score and including the customer service score in the quality inspection result.
10. The system of claim 1, further comprising: and the data billboard is used for carrying out statistical analysis according to the data to be quality-tested related to the quality-testing result and/or the quality-testing task and/or the quality-testing service and/or the quality-testing rule and carrying out visual display on the analysis result.
CN202210821212.0A 2022-07-13 2022-07-13 Intelligent quality inspection system for customer service quality Pending CN115204664A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210821212.0A CN115204664A (en) 2022-07-13 2022-07-13 Intelligent quality inspection system for customer service quality

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210821212.0A CN115204664A (en) 2022-07-13 2022-07-13 Intelligent quality inspection system for customer service quality

Publications (1)

Publication Number Publication Date
CN115204664A true CN115204664A (en) 2022-10-18

Family

ID=83579268

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210821212.0A Pending CN115204664A (en) 2022-07-13 2022-07-13 Intelligent quality inspection system for customer service quality

Country Status (1)

Country Link
CN (1) CN115204664A (en)

Similar Documents

Publication Publication Date Title
US10104233B2 (en) Coaching portal and methods based on behavioral assessment data
CN108764649B (en) Insurance sales real-time monitoring method, device, equipment and storage medium
US8494149B2 (en) Monitoring device, evaluation data selecting device, agent evaluation device, agent evaluation system, and program
US8411841B2 (en) Real-time agent assistance
US11714793B2 (en) Systems and methods for providing searchable customer call indexes
US20170277993A1 (en) Virtual assistant escalation
US8045699B2 (en) Method and system for performing automated telemarketing
US20100161315A1 (en) Correlated call analysis
US20160239805A1 (en) Device, system and method for summarizing agreements
US20110044447A1 (en) Trend discovery in audio signals
JP7280438B2 (en) Service quality evaluation product customization platform and method
US20100332287A1 (en) System and method for real-time prediction of customer satisfaction
US20100332477A1 (en) Enhancing Call Center Performance
KR20150138918A (en) Call center system for mesuring service quality of customer service representatives and service quality measuring method
US11955113B1 (en) Electronic signatures via voice for virtual assistants' interactions
US10978095B2 (en) Control of incoming calls
CN110147930A (en) Data statistical approach, device and storage medium based on big data analysis
CN110705309A (en) Service quality evaluation method and system
CN115392958A (en) Live broadcast behavior analysis method, device, equipment and storage medium
JP2005252845A (en) Cti system, cs level judgement method, voice analysis server, and program
US10924611B2 (en) Voice recognition system and call evaluation setting method
CN115204664A (en) Intelligent quality inspection system for customer service quality
CN108268506A (en) A kind of processing method of promotion message, device, terminal and computer readable storage medium
CN115994121A (en) Method, device and storage medium for optimizing intelligent customer service interaction flow
US11438456B2 (en) Techniques for managing softphone repositories and establishing communication channels

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