CN111667284B - Customer service switching method and device - Google Patents
Customer service switching method and device Download PDFInfo
- Publication number
- CN111667284B CN111667284B CN202010506163.2A CN202010506163A CN111667284B CN 111667284 B CN111667284 B CN 111667284B CN 202010506163 A CN202010506163 A CN 202010506163A CN 111667284 B CN111667284 B CN 111667284B
- Authority
- CN
- China
- Prior art keywords
- early warning
- customer
- emotion
- level
- customer service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 87
- 230000008451 emotion Effects 0.000 claims abstract description 181
- 230000008909 emotion recognition Effects 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims description 36
- 238000000605 extraction Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 4
- 230000002996 emotional effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 208000013875 Heart injury Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Acoustics & Sound (AREA)
- Finance (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Hospice & Palliative Care (AREA)
- Child & Adolescent Psychology (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a customer service switching method and device, wherein the method comprises the following steps: when a customer accesses a customer service system, an intelligent customer service is connected to the customer, and the collected call voice of the customer is converted into a voice signal; carrying out emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal; determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice image of the client; judging whether a customer meets preset customer service switching conditions or not according to emotion levels, early warning levels and early warning times; if so, switching the client to the artificial customer service, generating early warning information, and updating the early warning information and emotion labels corresponding to the conversation voice of the client to sound images. By the method and the system, when the emotion of the customer is abnormal, the customer is switched to the artificial customer service in time, so that the artificial customer service soothes the customer, and therefore better quality service is provided for the customer.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a customer service switching method and device.
Background
Currently, customer service systems are applied to enterprises in various fields and industries, such as municipal, public security, postal, telecommunication, banking, insurance, IT and other industries, and can effectively improve the service level and the operation efficiency of the enterprises. The customer service system is a set of working platform supporting the on-line instant communication between customers and the artificial customer service, and along with the development of artificial intelligence technology, the customer service system introduces intelligent customer service, and the intelligent customer service can effectively guide customers to transact simple services, can replace the artificial customer service to perform some simple and repeated works, effectively reduces the workload of the artificial customer service and reduces the operation cost of the customer service system.
The existing intelligent customer service generally converts the voice of a customer into characters, provides services such as business handling, business inquiry and the like for the customer according to the content of the characters, cannot sense the emotion change of the customer in the process of providing the service for the customer, and cannot switch to the artificial customer service in time when the emotion of the customer is abnormal, so that the artificial customer service can pacify the emotion of the customer in time; therefore, the customer experience to the customer service system is extremely poor, and the customer satisfaction degree is reduced.
Disclosure of Invention
In view of the above, the present invention provides a customer service switching method, which is applied to recognize emotion of a customer through call voice of the customer, and switch the customer from intelligent customer service to artificial customer service when the emotion of the customer is abnormal, so that the artificial customer service pacifies the customer.
The invention also provides a customer service switching device which is used for ensuring the realization and application of the method in practice.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a customer service switching method, comprising:
when a customer accesses a customer service system, an intelligent customer service is connected to the customer, call voice of the customer is collected, and the call voice is converted into a voice signal;
carrying out emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal;
determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client;
judging whether the customer meets preset customer service switching conditions according to the emotion level, the early warning level and the early warning times;
and if the customer meets the customer service switching condition, switching the customer to the manual customer service, generating early warning information, and updating the early warning information and the emotion label corresponding to the conversation voice of the customer to the sound portrait.
The method, optionally, further comprises:
extracting the voice characteristics of the client from the voice signals according to a preset voice characteristic extraction method, and updating the voice characteristics into the sound image.
In the above method, optionally, the determining, according to the emotion tag and the audio-visual of the client, the emotion level, the early warning level and the early warning times of the client includes:
determining an emotion level corresponding to the emotion label according to a preset emotion level rule;
analyzing the sound image to determine each early warning level calculation factor and each early warning record;
determining the number of the early warning records belonging to a preset time period according to the early warning time of each early warning record, and determining the early warning times according to the number;
according to a preset early warning level calculation method, calculating the emotion level, the early warning times and the early warning level calculation factors, and determining the early warning level according to the calculation result.
In the above method, optionally, the determining whether the client meets a preset customer service switching condition includes:
comparing the emotion level with a preset emotion level, comparing the early warning level with a preset early warning level, and comparing the early warning times with preset early warning times;
if the emotion level is smaller than the preset emotion level, the early warning level is smaller than the preset early warning level and the early warning times are smaller than the preset early warning times, the client does not meet the preset customer service switching conditions; otherwise, the client meets the preset customer service switching condition.
The method, optionally, further comprises:
and when the customer is switched to the manual customer service, a customer service switching report is generated, and the customer service switching report is displayed to the manual customer service, so that the manual customer service can provide service for the customer by referring to the customer service switching report.
A customer service switching device, comprising:
the system comprises an acquisition unit, a voice conversion unit and a voice conversion unit, wherein the acquisition unit is used for connecting an intelligent customer service for a customer when the customer accesses a customer service system, acquiring call voice of the customer and converting the call voice into a voice signal;
the marking unit is used for carrying out emotion recognition on the voice signal by applying a preset emotion recognition method and marking a corresponding emotion label for the voice signal;
the determining unit is used for determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client;
the judging unit is used for judging whether the client meets preset customer service switching conditions according to the emotion level, the early warning level and the early warning times;
and the switching unit is used for switching the customer to the manual customer service if the customer meets the customer service switching condition, generating early warning information and updating the early warning information and emotion labels corresponding to the conversation voice of the customer to the sound portrait.
The above device, optionally, further comprises:
and the extraction unit is used for extracting the voice characteristics of the client from the voice signal according to a preset voice characteristic extraction method and updating the voice characteristics into the sound image.
The above apparatus, optionally, the determining unit includes:
the first determining subunit is used for determining the emotion level corresponding to the emotion label according to a preset emotion level rule;
the analysis subunit is used for analyzing the sound image to determine each early warning level calculation factor and each early warning record;
the second determining subunit is used for determining the number of the early warning records belonging to a preset time period according to the early warning time of each early warning record and determining the early warning times according to the number;
and the calculating subunit is used for calculating the emotion level, the early warning times and the early warning level calculation factors according to a preset early warning level calculation method, and determining the early warning level according to the calculated result.
The above device, optionally, the determining unit includes:
the comparison subunit is used for comparing the emotion level with a preset emotion level, comparing the early warning level with a preset early warning level and comparing the early warning times with preset early warning times;
a judging subunit, configured to, if the emotion level is less than the preset emotion level, the early warning level is less than the preset early warning level, and the early warning frequency is less than the preset early warning frequency, failing to satisfy a preset customer service switching condition; otherwise, the client meets the preset customer service switching condition.
The above device, optionally, further comprises:
and the display unit is used for generating a customer service switching report when the customer is switched to the manual customer service, and displaying the customer service switching report to the manual customer service so that the manual customer service can provide service for the customer by referring to the customer service switching report.
Compared with the prior art, the invention has the following advantages:
the invention provides a customer service switching method, which comprises the following steps: when a customer accesses a customer service system, an intelligent customer service is connected to the customer, call voice of the customer is collected, and the call voice is converted into a voice signal; carrying out emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal; determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client; judging whether the customer meets preset customer service switching conditions according to the emotion level, the early warning level and the early warning times; and if the customer meets the customer service switching condition, switching the customer to the manual customer service, generating early warning information, and updating the early warning information and the emotion label corresponding to the conversation voice of the customer to the sound portrait. The invention can identify the emotion of the call voice of the client, and mark the corresponding emotion label for the call voice, and when the emotion of the client is abnormal, the client can be switched to the artificial customer service in time, so that the artificial customer service can pacify the client.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a method flowchart of a customer service switching method provided in an embodiment of the present invention;
fig. 2 is a flowchart of another method of customer service switching according to an embodiment of the present invention;
FIG. 3 is a flowchart of another method of customer service switching according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a customer service switching device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The invention is operational with numerous general purpose or special purpose computing device environments or configurations. For example: personal computers, server computers, consumer or portable devices, tablet devices, multiprocessor systems, distributed computing environments that include any of the above devices or devices, and so forth.
The embodiment of the invention provides a customer service switching method, which can be applied to an intelligent customer service system or a call center platform, wherein an execution subject of the method can be a processor of a computer terminal or various mobile devices which are built into the intelligent customer service system or the call center platform, a flow chart of the method is shown in fig. 1, and the specific description is as follows:
s101, when a customer accesses a customer service system, an intelligent customer service is connected to the customer, call voice of the customer is collected, and the call voice is converted into a voice signal.
In the method provided by the embodiment of the invention, when a customer uses communication equipment to access a customer service system, a processor of the customer service system connects intelligent customer service in the customer service system, collects call voice of the customer, wherein the call voice is call voice in a call process of the customer and the intelligent customer, and a preset voice conversion module is applied to pre-emphasis, short-time analysis, framing, windowing and breakpoint detection of the call voice to obtain an effective voice signal, and the voice conversion module can be an analog-to-digital converter; the voice signal is a digital signal or an electric signal corresponding to the call voice.
S102, performing emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal.
In the method provided by the embodiment of the invention, a preset emotion recognition method is applied, emotion characteristics in a voice signal are extracted, corresponding emotion is determined according to the emotion characteristics, and an emotion label corresponding to the emotion is marked on the voice signal; emotional characteristics include, but are not limited to, information in the amplitude, spectrum, etc. of the speech signal; the emotion tags in the present invention include, but are not limited to, general anger tags, happy tags, wounded tags, super anger tags, and other tags; different emotional characteristics correspond to different emotional tags. The emotion recognition method can be a specific voice emotion recognition model and voice emotion recognition algorithm, and emotion is recognized by extracting emotion characteristics.
And S103, determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client.
In the method provided by the embodiment of the invention, the audio-visual image of the client is called, and the audio-visual image is an audio database constructed by data with different dimensions; and determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the sound data in the sound image. The audio-visual image in the invention is composed of seven dimensions of data of client level, client basic information, client duration, client liveness level, client voice characteristics, voice emotion data and early warning information; the client level is a client level determined according to the client basic information, and the client level can be divided into 5 levels: first stage, second stage, third stage, fourth stage and fifth stage, first stage < second stage < third stage < fourth stage < fifth stage, fifth stage is the highest stage, different stages are denoted by different numbers, first stage is denoted by numeral 1, second stage is denoted by numeral 2, third stage is denoted by numeral 3, fourth stage is denoted by numeral 4, and fifth stage is denoted by numeral 5.
In the method provided by the embodiment of the invention, the early warning level is divided into 5 levels: a first pre-warning level indicated by the number 1, a second pre-warning level indicated by the number 2, a third pre-warning level indicated by the number 3, a fourth pre-warning level indicated by the number 4, a fifth pre-warning level indicated by the number 5, wherein the pre-warning levels gradually rise from the first level to the fifth level.
In the method provided by the embodiment of the invention, the basic information of the client comprises, but is not limited to, the occupation, sex, age, date of birth and other information of the client; the client duration is the duration from registration to current, wherein different duration is represented by different values, and in the method provided by the invention, when the client duration is less than or equal to 3 months, the client duration is represented by a number 1; when the client continuous storage time is more than 3 months and less than or equal to 6 months, the client continuous storage time is represented by a numeral 2; when the client continuous storage time is more than 6 months and less than or equal to 12 months, the client continuous storage time is represented by a numeral 3; when the client continuous storage time is more than 12 months and less than or equal to 36 months, the client continuous storage time is represented by a number 4; when the client is stored for longer than 36 months, the number 5 is used for indicating.
In the method provided by the embodiment of the invention, the client activity is determined according to the data of the frequency of using related products by the client, wherein the client activity level is divided into five levels, namely: a first level of activity indicated by the number 1, a second level of activity indicated by the number 2, a third level of activity indicated by the number 3, a fourth level of activity indicated by the number 4 and a fifth level of activity indicated by the number 5, the greater the frequency of use of the relevant product by the customer, the higher the activity thereof from the first level to the fifth level, the highest level of activity. The customer voice features comprise basic voice features of customers and voice features extracted from conversation voice; basic speech features of a customer include, but are not limited to, speech features in terms of occupation, gender, and age; the speech emotion data is an emotion tag for tagging a speech signal of a client, an emotion feature extracted from the speech signal, and the like.
And S104, judging whether the customer meets preset customer service switching conditions according to the emotion level, the early warning level and the early warning times.
In the method provided by the embodiment of the invention, a preset early warning module is called, and whether the client meets preset switching conditions is judged according to the emotion level, the early warning level and the early warning times.
And S105, if the customer meets the customer service switching condition, switching the customer to the manual customer service, generating early warning information, and updating the early warning information and emotion labels corresponding to conversation voice of the customer to the sound portrait.
In the method provided by the embodiment of the invention, if the customer meets the customer service switching condition, the customer is switched to the manual service so that the manual customer service provides service for the customer; in the invention, the generated early warning information comprises, but is not limited to, data information such as early warning records, early warning levels, early warning times, call duration with intelligent customer service, emotion labels and the like, wherein the early warning records comprise time information of switching a customer from the intelligent customer service to the artificial customer service, and the early warning records are records generated when the customer is switched from the intelligent customer service to the artificial customer service. In the method provided by the embodiment of the invention, after the customer is switched to the manual customer service, the early warning information and the emotion information of the conversation voice of the customer are updated into the data of the corresponding dimension of the sound image.
In the method provided by the embodiment of the invention, when a customer accesses a customer service system, an intelligent customer service is connected to the customer, the call voice of the customer is collected, and the call voice is converted into a voice information signal; carrying out emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal; determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client; judging whether the customer meets preset customer service switching conditions or not according to the emotion level, the early warning level and the early warning times; and if the customer meets the customer service switching condition, switching the customer to the manual customer service, generating early warning information, and updating the early warning information and the emotion label corresponding to the conversation voice of the customer to the sound portrait. When the customer communicates with an intelligent customer in a customer service system, carrying out emotion recognition on communication voice of the customer, marking a corresponding emotion label, judging whether the customer meets preset customer service switching conditions according to emotion levels, early warning levels and early warning times, and switching the customer to manual customer service if the customer meets the customer service switching conditions so as to enable the manual customer service to provide service for the customer; by the method and the system, the customer can be switched from intelligent customer service to artificial customer service in time when the emotion of the customer is abnormal, and the artificial customer service is used for pacifying the customer, so that the satisfaction degree and the use experience of the customer are improved, and the situation that the image of an enterprise is damaged in the customer can be avoided.
In the method provided by the embodiment of the invention, if the customer is judged not to meet the customer service switching method, the customer is not switched to the artificial customer service, and when the customer and the intelligent customer service end the call, a call record is generated, and the emotion label for marking the call voice is updated to the sound image of the customer in the call process.
In the method provided by the embodiment of the invention, a voice characteristic extraction method preset in a voice characteristic module is applied, the voice characteristic of a client is extracted from the voice signal, and the extracted voice characteristic is updated to the voice image of the client; the voice characteristic extraction method applied in the invention can be a Mel frequency cepstrum coefficient (Mel Frequency Cepstrum Coefficient, MFCC) method, the voice characteristic of the client can be extracted from the voice signal by using the MFCC method, and the extracted voice characteristic is updated to the voice image of the client, so that the voice data in the voice image of the client can be more abundant.
In the method provided by the embodiment of the invention, the process of determining the emotion level, the early warning level and the early warning times of the client can be described as follows with reference to fig. 2:
s201, determining an emotion level corresponding to the emotion label according to a preset emotion level rule.
In the method provided by the embodiment of the invention, the emotion level corresponding to the emotion label is determined, and the emotion level rule in the invention specifically comprises the following steps: when the emotion label is a super anger label, the emotion level is 5, and the emotion level is represented by a number 5; when the emotion label is a general anger label, the emotion level is 4, and the emotion level is represented by a number 4; when the emotion label is a heart injury label, the emotion grade is grade 3 and is represented by a numeral 3; when the emotion label is a happy label, the emotion level is 2, and the user number is 2; when the emotion label is other labels, the emotion level is 1, and the emotion label is indicated by a numeral 1. The emotion level corresponding to the emotion level may be determined according to the content in the emotion level rule.
S202, analyzing the sound image to determine each early warning level calculation factor and each early warning record.
In the method provided by the embodiment of the invention, the sound image is analyzed to obtain all early warning level calculation factors and all early warning records from the sound data of the sound image; the early warning record is a record of switching a customer from intelligent customer service to artificial customer service; the calculation factors of all the early warning levels are respectively as follows: a client level factor, a client duration factor, a client liveness level factor, and an early warning level factor; the early warning level factor is the early warning level in early warning records of the latest customer switching from intelligent customer service to artificial customer service. The client level factor is a number representing a client level, the client duration factor is a number representing a client duration, the client liveness level factor is a number representing a client liveness, and the early warning level factor is a number representing an early warning level in an early warning record updated last time in the sound portrait.
S203, determining the number of the early warning records in a preset time period according to the early warning time of each early warning record, and determining the early warning times according to the number.
In the method provided by the embodiment of the invention, the early warning record contains early warning time, and the early warning time is the time for switching the customer from intelligent customer service to artificial customer service; in the method provided by the invention, one year can be divided into 12 time periods, one month corresponds to one time period, and the preset time period is the time period which is effective currently; the method can be realized in such a way that the current time is 3 months 3, and the preset time period is 3 months; 1 month and 2 months are effective time periods, and 4 months and subsequent months are non-effective time periods; this is one implementation of the predetermined time period, and other derived implementations are within the scope of the present invention. In the method provided by the invention, the number of the early warning records belonging to the preset time period is determined through the early warning time contained in the early warning records, and the determined number is determined as the early warning times, in other words, the number of the early warning records belonging to the preset time period is 5, and the early warning times is 5.
S204, calculating the emotion level, the early warning times and the early warning level calculation factors according to a preset early warning level calculation method, and determining the early warning level according to the calculation result.
According to the method provided by the embodiment of the invention, numbers representing emotion levels, early warning times and calculation factors of all early warning levels are substituted into a calculation formula according to a calculation formula in a preset early warning level calculation method to calculate, a calculation result is obtained, and the early warning level is determined according to the calculation result, wherein the calculation result is a positive number value, if the value is less than or equal to 5, an integer of the value is taken as the early warning level, and if the value is greater than 5, the 5 th level of the highest early warning level is determined; the calculation formula in the early warning level calculation method is as follows:
calculation result = client level factor 10% + client duration factor 5% + client liveness level factor 5% + number of early warning times 30% + early warning level factor 30% + emotion level 20%;
according to the method provided by the embodiment of the invention, the emotion grade corresponding to the emotion label is determined, the early warning times and all early warning grade calculation factors are determined by analyzing the sound image of the client, the emotion grade, the early warning times and all early warning grade calculation factors are calculated, and the early warning grade is determined according to the result obtained by calculation, so that the current early warning grade of the client can be obtained, and more accurate data is provided for judging whether the client meets the preset customer service switching condition or not.
In the method provided by the embodiment of the invention, a specific process for judging whether the client meets the preset customer service switching condition is shown in fig. 3, and the specific description is as follows:
s301, comparing the emotion level with a preset emotion level, comparing the early warning level with a preset early warning level, and comparing the early warning times with preset early warning times.
In the method provided by the embodiment of the invention, the customer service switching condition is provided with a preset emotion level, a preset early warning level and a preset early warning frequency, the emotion level is compared with the preset emotion level, the early warning level is compared with the preset early warning level, and the early warning frequency is compared with the preset early warning frequency, so as to judge whether the emotion level is smaller than the preset emotion level, the early warning level is smaller than the preset early warning level and the early warning frequency is smaller than the preset early warning frequency; in the method provided by the invention, the preset emotion level is 4, the preset early warning level is a fourth early warning level, and the preset early warning times are 4; the preset emotion level, the preset early warning level and the preset early warning times can be set according to actual requirements.
S302, if the emotion level is smaller than the preset emotion level, the early warning level is smaller than the preset early warning level and the early warning times are smaller than the preset early warning times, the client does not meet preset customer service switching conditions; otherwise, the client meets the preset customer service switching condition.
In the method provided by the embodiment of the invention, if the emotion level is smaller than the preset emotion level, the early warning level is smaller than the preset early warning level and the early warning times are smaller than the preset early warning times, the client does not meet the preset customer service switching condition and is not switched to the manual customer service; if any one of the following conditions is met, the client meets the preset client switching condition;
case 1): the emotion level is greater than or equal to a preset emotion level;
case 2): the early warning level is greater than or equal to a preset early warning level;
case 3): the early warning times are greater than or equal to the preset early warning times;
the customer meets the preset customer service switching condition, and the customer is switched to the manual customer service, so that the manual customer service provides service for the customer.
According to the method provided by the embodiment of the invention, when the emotion of the customer is abnormal, the customer can be switched to the artificial customer service in time, so that the artificial customer service can pacify the emotion of the customer in time, and a better service is provided for the customer.
In the method provided by the embodiment of the invention, when the customer is switched to the manual customer service, a customer service switching report is generated, and the customer service switching report is displayed to the manual customer service, so that the manual customer service can provide service for the customer by referring to the customer service switching report. In the invention, the customer service switching report can be text, and the customer service switching report comprises, but is not limited to, early warning information during switching, emotion labels of voice signals and the like.
According to the method provided by the embodiment of the invention, the customer service switching report is generated and displayed to the artificial customer service, so that the artificial customer service has a certain direction in the process of soothing the emotion of the customer, and the current situation of the customer is quickly known by the artificial customer service, so that the artificial customer service takes corresponding soothing measures.
The specific implementation process and derivative manner of the above embodiments are all within the protection scope of the present invention.
Corresponding to the method shown in fig. 1, the embodiment of the present invention further provides a customer service switching device, which is used for implementing the method shown in fig. 1, where the customer service switching device provided in the embodiment of the present invention may be applied to a computer terminal or various mobile devices, and the schematic structural diagram of the customer service switching device is shown in fig. 4, and specifically includes:
the collecting unit 401 is configured to, when a client accesses a customer service system, connect an intelligent customer service to the client, collect call voice of the client, and convert the call voice into a voice signal;
a marking unit 402, configured to apply a preset emotion recognition method to perform emotion recognition on the speech signal, and mark a corresponding emotion label for the speech signal;
a determining unit 403, configured to determine, according to the emotion tag and the sound image of the client, an emotion level, an early warning level, and an early warning number of times of the client;
the judging unit 404 is configured to judge whether the client meets a preset customer service switching condition according to the emotion level, the early warning level and the early warning times;
and the switching unit 405 is configured to switch the client to a manual customer service if the client meets the customer service switching condition, generate early warning information, and update the early warning information and an emotion tag corresponding to a call voice of the client to the sound portrait.
In the device provided by the embodiment of the invention, when a customer accesses a customer service system, an intelligent customer service is connected to the customer, the call voice of the customer is collected, and the call voice is converted into a voice information signal; carrying out emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal; determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client; judging whether the customer meets preset customer service switching conditions or not according to the emotion level, the early warning level and the early warning times; and if the customer meets the customer service switching condition, switching the customer to the manual customer service, generating early warning information, and updating the early warning information and the emotion label corresponding to the conversation voice of the customer to the sound portrait. When the customer communicates with an intelligent customer in a customer service system, carrying out emotion recognition on communication voice of the customer, marking a corresponding emotion label, judging whether the customer meets preset customer service switching conditions according to emotion levels, early warning levels and early warning times, and switching the customer to manual customer service if the customer meets the customer service switching conditions; according to the invention, when the emotion of the customer is abnormal, the customer is switched from the intelligent customer service to the artificial customer service in time, so that the artificial customer service provides services for the customer, and the artificial customer service pacifies the customer, so that the satisfaction degree and the use experience of the customer are improved, and the situation that an enterprise is damaged in the customer's mind can be avoided.
Based on the foregoing solution, the device provided by the embodiment of the present invention may further be configured:
and the extraction unit is used for extracting the voice characteristics of the client from the voice signal according to a preset voice characteristic extraction method and updating the voice characteristics into the sound image.
Based on the foregoing solution, the determining unit 403 in the apparatus provided by the embodiment of the present invention may be configured to:
the first determining subunit is used for determining the emotion level corresponding to the emotion label according to a preset emotion level rule;
the analysis subunit is used for analyzing the sound image to determine each early warning level calculation factor and each early warning record;
the second determining subunit is used for determining the number of the early warning records belonging to a preset time period according to the early warning time of each early warning record and determining the number as early warning times;
and the calculating subunit is used for calculating the emotion level, the early warning times and the early warning level calculation factors according to a preset early warning level calculation method, and determining the early warning level according to the calculated result.
Based on the foregoing solution, the determining unit 404 in the apparatus provided by the embodiment of the present invention may be configured to:
the comparison subunit is used for comparing the emotion level with a preset emotion level, comparing the early warning level with a preset early warning level and comparing the early warning times with preset early warning times;
a judging subunit, configured to, if the emotion level is less than the preset emotion level, the early warning level is less than the preset early warning level, and the early warning frequency is less than the preset early warning frequency, failing to satisfy a preset customer service switching condition; otherwise, the client meets the preset customer service switching condition.
Based on the foregoing solution, the device provided by the embodiment of the present invention may further be configured:
and the display unit is used for generating a customer service switching report when the customer is switched to the manual customer service, and displaying the customer service switching report to the manual customer service so that the manual customer service can provide service for the customer by referring to the customer service switching report.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The customer service switching method is characterized by comprising the following steps of:
when a customer accesses a customer service system, an intelligent customer service is connected to the customer, call voice of the customer is collected, and the call voice is converted into a voice signal;
carrying out emotion recognition on the voice signal by applying a preset emotion recognition method, and marking a corresponding emotion label for the voice signal; the emotion tag includes: anger label, happy label, wounded label and super anger label, and different emotions correspond to different emotion labels;
determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client;
judging whether the customer meets preset customer service switching conditions according to the emotion level, the early warning level and the early warning times;
if the customer meets the customer service switching condition, switching the customer to a manual customer service, generating early warning information, and updating the early warning information and emotion labels corresponding to conversation voice of the customer to the sound portrait;
wherein, according to the emotion label and the voice portrait of the customer, determining the emotion level, the early warning level and the early warning times of the customer comprises:
determining an emotion level corresponding to the emotion label according to a preset emotion level rule;
analyzing the sound image to determine each early warning level calculation factor and each early warning record;
determining the number of the early warning records belonging to a preset time period according to the early warning time of each early warning record, and determining the early warning times according to the number;
according to a preset early warning level calculation method, calculating the emotion level, the early warning times and the early warning level calculation factors, and determining the early warning level according to the calculation result.
2. The method as recited in claim 1, further comprising:
extracting the voice characteristics of the client from the voice signals according to a preset voice characteristic extraction method, and updating the voice characteristics into the sound image.
3. The method of claim 1, wherein the determining whether the customer meets a preset customer service switching condition comprises:
comparing the emotion level with a preset emotion level, comparing the early warning level with a preset early warning level, and comparing the early warning times with preset early warning times;
if the emotion level is smaller than the preset emotion level, the early warning level is smaller than the preset early warning level and the early warning times are smaller than the preset early warning times, the client does not meet the preset customer service switching conditions; otherwise, the client meets the preset customer service switching condition.
4. The method as recited in claim 1, further comprising:
and when the customer is switched to the manual customer service, a customer service switching report is generated, and the customer service switching report is displayed to the manual customer service, so that the manual customer service can provide service for the customer by referring to the customer service switching report.
5. A customer service switching device, comprising:
the system comprises an acquisition unit, a voice conversion unit and a voice conversion unit, wherein the acquisition unit is used for connecting an intelligent customer service for a customer when the customer accesses a customer service system, acquiring call voice of the customer and converting the call voice into a voice signal;
the marking unit is used for carrying out emotion recognition on the voice signal by applying a preset emotion recognition method and marking a corresponding emotion label for the voice signal; the emotion tag includes: anger label, happy label, wounded label and super anger label, and different emotions correspond to different emotion labels;
the determining unit is used for determining the emotion level, the early warning level and the early warning times of the client according to the emotion label and the voice portrait of the client;
the judging unit is used for judging whether the client meets preset customer service switching conditions according to the emotion level, the early warning level and the early warning times;
the switching unit is used for switching the customer to the manual customer service if the customer meets the customer service switching condition, generating early warning information and updating the early warning information and emotion labels corresponding to the conversation voice of the customer to the sound portrait;
wherein the determining unit includes:
the first determining subunit is used for determining the emotion level corresponding to the emotion label according to a preset emotion level rule;
the analysis subunit is used for analyzing the sound image to determine each early warning level calculation factor and each early warning record;
the second determining subunit is used for determining the number of the early warning records belonging to a preset time period according to the early warning time of each early warning record and determining the early warning times according to the number;
and the calculating subunit is used for calculating the emotion level, the early warning times and the early warning level calculation factors according to a preset early warning level calculation method, and determining the early warning level according to the calculated result.
6. The apparatus as recited in claim 5, further comprising:
and the extraction unit is used for extracting the voice characteristics of the client from the voice signal according to a preset voice characteristic extraction method and updating the voice characteristics into the sound image.
7. The apparatus according to claim 5, wherein the judging unit includes:
the comparison subunit is used for comparing the emotion level with a preset emotion level, comparing the early warning level with a preset early warning level and comparing the early warning times with preset early warning times;
a judging subunit, configured to, if the emotion level is less than the preset emotion level, the early warning level is less than the preset early warning level, and the early warning frequency is less than the preset early warning frequency, failing to satisfy a preset customer service switching condition; otherwise, the client meets the preset customer service switching condition.
8. The apparatus as recited in claim 5, further comprising:
and the display unit is used for generating a customer service switching report when the customer is switched to the manual customer service, and displaying the customer service switching report to the manual customer service so that the manual customer service can provide service for the customer by referring to the customer service switching report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506163.2A CN111667284B (en) | 2020-06-05 | 2020-06-05 | Customer service switching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506163.2A CN111667284B (en) | 2020-06-05 | 2020-06-05 | Customer service switching method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111667284A CN111667284A (en) | 2020-09-15 |
| CN111667284B true CN111667284B (en) | 2024-02-13 |
Family
ID=72386758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010506163.2A Active CN111667284B (en) | 2020-06-05 | 2020-06-05 | Customer service switching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111667284B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185385A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Intelligent client processing method and system for power supply field |
| CN112269863A (en) * | 2020-10-15 | 2021-01-26 | 和美（深圳）信息技术股份有限公司 | Man-machine conversation data processing method and system of intelligent robot |
| CN113051386B (en) * | 2021-04-30 | 2024-02-02 | 中国银行股份有限公司 | Adjustment method and device for transferring manual service, electronic equipment and storage medium |
| CN113435912A (en) * | 2021-06-29 | 2021-09-24 | 平安科技（深圳）有限公司 | Data analysis method, device, equipment and medium based on client portrait |
| CN113312468B (en) * | 2021-07-30 | 2021-11-05 | 平安科技（深圳）有限公司 | Conversation mode-based conversation recommendation method, device, equipment and medium |
| CN117061668A (en) * | 2023-09-21 | 2023-11-14 | 广州易风健康科技股份有限公司 | Multi-station AI telephone customer service management method based on emotion recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330706A (en) * | 2017-06-06 | 2017-11-07 | 上海航动科技有限公司 | A kind of electricity battalion's customer service system and commercial operation pattern based on artificial intelligence |
| WO2020000912A1 (en) * | 2018-06-28 | 2020-01-02 | 杭州海康威视数字技术股份有限公司 | Behavior detection method and apparatus, and electronic device and storage medium |
| CN110890096A (en) * | 2019-10-12 | 2020-03-17 | 深圳供电局有限公司 | Intelligent voice system and method based on voice analysis |
| CN111161733A (en) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | Control method and device for intelligent voice service |
-
2020
- 2020-06-05 CN CN202010506163.2A patent/CN111667284B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330706A (en) * | 2017-06-06 | 2017-11-07 | 上海航动科技有限公司 | A kind of electricity battalion's customer service system and commercial operation pattern based on artificial intelligence |
| WO2020000912A1 (en) * | 2018-06-28 | 2020-01-02 | 杭州海康威视数字技术股份有限公司 | Behavior detection method and apparatus, and electronic device and storage medium |
| CN110890096A (en) * | 2019-10-12 | 2020-03-17 | 深圳供电局有限公司 | Intelligent voice system and method based on voice analysis |
| CN111161733A (en) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | Control method and device for intelligent voice service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111667284A (en) | 2020-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667284B (en) | Customer service switching method and device | |
| US20230300247A1 (en) | Voice and speech recognition for call center feedback and quality assurance | |
| CN106782615B (en) | Voice data emotion detection method, device and system | |
| CN109767787B (en) | Emotion recognition method, device and readable storage medium | |
| US8005676B2 (en) | Speech analysis using statistical learning | |
| US20080082330A1 (en) | Systems and methods for analyzing audio components of communications | |
| CN105657129A (en) | Call information obtaining method and device | |
| CN113488024B (en) | Telephone interrupt recognition method and system based on semantic recognition | |
| KR101795593B1 (en) | Device and method for protecting phone counselor | |
| CN111683317B (en) | Prompting method and device applied to earphone, terminal and storage medium | |
| CN110933225B (en) | Call information acquisition method and device, storage medium and electronic equipment | |
| CN110717410A (en) | Voice emotion and facial expression bimodal recognition system | |
| JP6183841B2 (en) | Call center term management system and method for grasping signs of NG word | |
| JP5532781B2 (en) | Waiting service server, waiting service system using the server, and expected end time calculation method for waiting service | |
| CN110889008B (en) | Music recommendation method and device, computing device and storage medium | |
| US10522135B2 (en) | System and method for segmenting audio files for transcription | |
| CN111326142A (en) | Text information extraction method and system based on voice-to-text and electronic equipment | |
| CN114067842B (en) | Customer satisfaction degree identification method and device, storage medium and electronic equipment | |
| CN115831125A (en) | Speech recognition method, device, equipment, storage medium and product | |
| CN110765242A (en) | Method, device and system for providing customer service information | |
| CN111985231B (en) | Unsupervised role recognition method and device, electronic equipment and storage medium | |
| US20110197206A1 (en) | System, Method And Program Product For Analyses Based On Agent-Customer Interactions And Concurrent System Activity By Agents | |
| WO2019163700A1 (en) | Customer service support device, customer service support method, recording medium with customer service support program stored therein | |
| CN112908299B (en) | Customer demand information identification method and device, electronic equipment and storage medium | |
| CN110888986B (en) | Information pushing method, device, electronic equipment and computer readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |