CN113746989A - Method, device, equipment and storage medium for customer service intelligent quality inspection - Google Patents
Method, device, equipment and storage medium for customer service intelligent quality inspection Download PDFInfo
- Publication number
- CN113746989A CN113746989A CN202110971226.6A CN202110971226A CN113746989A CN 113746989 A CN113746989 A CN 113746989A CN 202110971226 A CN202110971226 A CN 202110971226A CN 113746989 A CN113746989 A CN 113746989A
- Authority
- CN
- China
- Prior art keywords
- quality
- rule
- voice
- operator
- quality inspection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000012372 quality testing Methods 0.000 claims description 15
- 230000008451 emotion Effects 0.000 claims description 12
- 238000003908 quality control method Methods 0.000 claims description 9
- 238000012552 review Methods 0.000 claims description 5
- 238000003780 insertion Methods 0.000 claims description 4
- 230000037431 insertion Effects 0.000 claims description 4
- 230000008719 thickening Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 description 15
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5175—Call or contact centers supervision arrangements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
Abstract
The application discloses a method, a device, equipment and a storage medium for customer service intelligent quality inspection. The method comprises the following steps: acquiring a voice to be inspected; counting the times of the telephone operator offending the judgment rule in the voice to be detected; and determining the service quality score of the telephone operator in the voice to be quality-checked according to the times and a preset evaluation rule coefficient. The application adopts a plurality of judgment rules, and a judgment coefficient is set for each rule. The scoring is calculated according to the number of offenders, the fine granularity of the quality inspection is improved, the accuracy of the quality inspection is further improved, and the machine automatically scores, so that the objectivity of the scoring quality inspection is improved, and the efficiency of the scoring quality inspection is also improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to a method, a device, equipment and a storage medium for customer service intelligent quality inspection.
Background
For quality inspection of customer service, in the prior art, each recording of a waiter is heard by a manual seat completely, the efficiency of quality inspection is low, the subjective factor is large, and the quality inspection result is often inaccurate. And a correction algorithm automatic correction mechanism is not adopted, so that automatic correction and automatic optimization of a quality inspection result cannot be realized.
Disclosure of Invention
The present application mainly aims to provide a method, an apparatus, a device and a storage medium for customer service intelligent quality inspection, so as to solve the above problems.
In order to achieve the above object, according to one aspect of the present application, there is provided a method for customer service intelligent quality inspection, comprising:
acquiring a voice to be inspected;
counting the times of the telephone operator offending the judgment rule in the voice to be detected;
and determining the service quality score of the telephone operator in the voice to be quality-checked according to the times and a preset evaluation rule coefficient.
In one embodiment, determining the service quality score of the operator in the voice to be quality-checked according to the times and a preset evaluation rule coefficient includes:
when the number of the judgment rules is multiple, determining the frequency of the operator for offending each judgment rule;
summing the times of the operator offending each judgment rule to obtain the total times;
dividing the times of each judgment rule by the total times to calculate a first intermediate weight of each judgment rule;
calculating the product of the first intermediate weight of each judgment rule and the coefficient of each judgment rule;
calculating the reciprocal of the product to obtain a second intermediate weight of each judgment rule;
and calculating the service quality score of the operator according to the second intermediate weight of each judgment rule.
In one embodiment, the calculating the quality of service score of the operator according to the second intermediate weight of each evaluation rule includes:
determining a plurality of second intermediate weights falling within the first interval;
determining a smallest second intermediate weight Q from the set of second intermediate weights;
determining a plurality of second intermediate weights falling within a second interval;
determining a smallest second intermediate weight R from the set of second intermediate weights;
the first interval is separated from the second interval, and the maximum endpoint value of the first interval is smaller than the minimum endpoint value of the second interval;
and calculating the service quality score of the operator according to the second intermediate weight Q and the second intermediate weight R.
In one embodiment, calculating the service quality score of the operator according to the second intermediate weight Q and the second intermediate weight R includes:
calculating a quality of service score for the operator using the following formula:
wherein V is a service quality score;
n is the number of judgment rules;
Biis the second intermediate weight of the ith evaluation rule.
In one embodiment, the evaluation rule includes: text rules, mute rules, speech rate rules, emotion rules, volume rules, and hard-plug rules;
the text rule is that the key words prohibited from appearing appear in the conversation of the telephone operator;
the mute rule is that the mute time of the telephone operator in the conversation is greater than a preset time threshold;
the speech rate rule is that the speech rate of the telephone operator in the conversation is greater than a preset speech rate threshold value;
the emotion rule is that the telephone operator has prohibited emotion in the conversation;
the volume rule is that the volume of the telephone operator in the conversation exceeds a preset volume threshold value or is smaller than the preset volume threshold value; for example, too much volume, or too little volume, would violate the rules.
The strong insertion rule is that the telephone operator forcibly interrupts the client in the conversation to insert the robbing call.
In one implementation mode, whether the obtained voice to be quality-checked is qualified is determined according to the service quality score of the operator and a preset service quality score standard value;
if not, highlighting and highlighting the voice to be quality-tested, and classifying the voice to be quality-tested into a quality-test abnormal voice catalog;
and classifying all the abnormal quality control voices in the abnormal quality control voice catalog according to a judgment rule as a unit.
In one embodiment, the method further comprises: and sending the quality inspection abnormal voice directory to a manual reinspection platform so as to carry out manual reinspection.
In one embodiment, after sending the quality inspection abnormal voice directory to the manual review platform, the method further comprises:
converting the voice to be tested into a text;
setting a highlighted title in the text, or thickening and highlighting part of text content to prompt specific positions which do not accord with the rules and exist in the text; so that quality testing personnel can quickly locate and search.
In order to achieve the above object, according to a second aspect of the present application, there is provided an apparatus for customer service intelligent quality inspection, comprising:
the acquisition module is used for acquiring the voice to be subjected to quality inspection;
the statistic module is used for counting the times of the telephone operator offending the judgment rule in the voice to be quality checked;
and the scoring module is used for determining the service quality score of the telephone operator in the voice to be quality-tested according to the times and a preset evaluation rule coefficient.
In a third aspect, the present application further provides a device for customer service intelligent quality inspection, including: at least one processor and at least one memory; the memory is to store one or more program instructions; the processor is configured to execute one or more program instructions to perform the method of any one of the above.
According to a fourth aspect of the present application, there is provided a computer readable storage medium having one or more program instructions embodied therein for performing the steps of any of the above.
In the embodiment of the application, the times of the operator offending judgment rule in the voice to be quality-checked are counted; and determining the service quality score of the telephone operator in the voice to be quality-checked according to the times and a preset evaluation rule coefficient. The accuracy of the service quality scoring of the telephone operators is improved. A plurality of evaluation rules are adopted, and an evaluation coefficient is set for each rule. The scoring is calculated according to the number of offenders, automatic scoring is realized, and the machine automatic scoring improves the objectivity of scoring quality inspection and improves the efficiency of scoring quality inspection.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a flow chart of a method of customer service intelligent quality inspection according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of another method for quality inspection according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an apparatus for customer service intelligent quality inspection according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device for customer service intelligent quality inspection according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all 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 application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the invention and its embodiments and are not intended to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meanings of these terms in the present invention can be understood by those skilled in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meanings of the above terms in the present invention can be understood by those of ordinary skill in the art according to specific situations.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
For quality evaluation of customer service, the conventional method is that a system automatically performs quality inspection-submits an artificial seat for rechecking, if a problem exists, the system is marked, and if no problem exists, a quality inspection result is submitted, and the quality inspection result is completely heard by the artificial seat through a piece of voice, so that not only time and efficiency cannot be guaranteed, but also human factors exist, and a correction algorithm automatic correction mechanism is hardly adopted, so that automatic correction and automatic optimization of the quality inspection result cannot be realized.
Based on this, the present application proposes a method for customer service intelligent quality inspection, see the flow chart of a method for customer service intelligent quality inspection shown in fig. 1; the method comprises the following steps:
step S102, obtaining a voice to be inspected;
specifically, the service of the operator may be recorded in advance, an identifier ID may be set for each operator, an identifier ID may be set for the recording of each time period, the recording of several important time periods may be extracted from the customer service recording of the operator all day, and the length of the time period may be flexibly set, for example, the time period may be 5 minutes or 10 minutes.
And step S104, counting the times of the operator offending the judgment rule in the voice to be quality checked.
Wherein, the evaluation rule can be flexibly set. Including but not limited to one or more of the following:
the text rule is that the key words prohibited to appear in the conversation of the telephone operator;
the mute rule is that the mute time of the telephone operator in the conversation is greater than a preset time threshold;
the speech rate rule is that the speech rate of the telephone operator in the conversation is greater than a preset speech rate threshold value;
the emotion rule is that the telephone operator has prohibited emotion in the conversation;
the volume rule is that the volume of the telephone operator in the conversation exceeds a preset volume threshold value or is smaller than the preset volume threshold value; for example, too much volume, or too little volume, would violate the rules.
The strong insertion rule is that the telephone operator forcibly interrupts the client in the conversation to insert the robbing call.
And step S106, determining the service quality score of the telephone operator in the voice to be quality-checked according to the times and a preset evaluation rule coefficient.
The method of the invention can realize the automatic quantitative scoring and quantification of the service quality of the attendants according to the judgment rules, thereby improving the accuracy of the service quality judgment. And moreover, a plurality of evaluation rules are preset, each evaluation rule has a corresponding evaluation weight, the extensive service quality is refined into a plurality of different evaluation rules, and the scores of operators are combed according to each rule. Fine and fine granularity.
Besides the scores of a single time period, the records of the operator in a plurality of time periods in the day can be obtained, and the comprehensive quality score of the operator in the day is calculated according to the scores of the records in each time period in the records in the plurality of time periods. The total quality score of the operator in one week and one month can also be calculated, and particularly, the total quality score can be calculated according to the comprehensive quality score of each day. Specifically, the calculation may be performed by an averaging method.
In one embodiment, in step S106, the service quality score of the operator in the voice to be quality tested is determined according to the number of times and a preset evaluation rule coefficient, and specifically the following steps are taken:
when the number of the judgment rules is multiple, determining the frequency of the operator for offending each judgment rule;
summing the times of the operator offending each judgment rule to obtain the total times;
dividing the times of each judgment rule by the total times to calculate a first intermediate weight of each judgment rule;
calculating the product of the first intermediate weight of each judgment rule and the coefficient of each judgment rule;
calculating the reciprocal of the product to obtain a second intermediate weight of each judgment rule;
and calculating the service quality score of the operator according to the second intermediate weight of each judgment rule.
Illustratively, the evaluation rules include: text rules, mute rules, speech rate rules, emotion rules, volume rules, and hard-plug rules;
the text rule is that the key words prohibited to appear in the conversation of the telephone operator;
the mute rule is that the mute time of the telephone operator in the conversation is greater than a preset time threshold;
the speech rate rule is that the speech rate of the telephone operator in the conversation is greater than a preset speech rate threshold value;
the emotion rule is that the telephone operator has prohibited emotion in the conversation;
the volume rule is that the volume of the telephone operator in the conversation exceeds a preset volume threshold value or is smaller than the preset volume threshold value;
the strong insertion rule is that the telephone operator forcibly interrupts the client in the conversation to insert the robbing call.
And respectively assigning rule coefficients to each evaluation rule as follows: a1, a2, A3, a4, a5, a 6; wherein 0< A1 … A6< 1.
It should be emphasized that the above-mentioned rule coefficients are manually set in advance and are fixed. The evaluation coefficient for each rule can be determined from a large number of data samples based on big data analysis.
Illustratively, the rule coefficient a1 for a text rule is 0.1; the rule coefficient a2 for the mute rule is 0.2; speech rate rule A3 is 0.1; the rule coefficient a4 for the emotional rule is 0.2; the rule coefficient a5 of the volume rule is 0.1; the rule coefficient a6 for the strong rule of interpolation is 0.2.
The statistics of the times of 6 quality inspection rules in each voice is as follows: x1, X2, X3, X4, X5, X6;
the proportion of each rule is: t1, T2, T3, T4, T5, T6;
see in particular Table 1
| Evaluation rule | Coefficient of regularity | Number of times | Specific gravity of |
| Text rules | A1 | X1 | T1 |
| Silence rules | A2 | X2 | T2 |
| Speed of speech rules | A3 | X3 | T3 |
| Rules of emotion | A4 | X4 | T4 |
| Volume rule | A5 | X5 | T5 |
| Rule of inserting a call | A6 | X6 | T6 |
TABLE 1
Wherein T is a first intermediate weight; a is a preset rule coefficient;
a second intermediate weight, denoted by B;
in an embodiment, when the quality of service score of the operator is obtained by calculating according to the second intermediate weight of each evaluation rule, the following steps are specifically adopted:
determining a plurality of second intermediate weights falling within the first interval;
determining a smallest second intermediate weight Q from the set of second intermediate weights;
determining a plurality of second intermediate weights falling within a second interval;
determining a smallest second intermediate weight R from the set of second intermediate weights;
the first interval is separated from the second interval, and the maximum endpoint value of the first interval is smaller than the minimum endpoint value of the second interval;
and calculating the service quality score of the operator according to the second intermediate weight Q and the second intermediate weight R.
The first interval and the second interval can be flexibly and randomly selected.
In one embodiment, when the service quality score of the operator is calculated according to the second intermediate weight Q and the second intermediate weight R, the service quality score of the operator is calculated by using the following formula:
wherein V is a service quality score; n is the number of judgment rules;
Biis the second intermediate weight of the ith evaluation rule.
Illustratively, 30000 speech samples qualified by standard quality inspection are taken, and X, Y, Z, W is calculated; (X < Y, Z < W, and X < W are set). Wherein X, Y, Z, W are the thresholds of the second intermediate weights, respectively.
Care must be taken to ensure that three of B1, B2, B3, B4, B5, B6 fall between X, Y and the remaining three fall between Z, W.
To determine X, Y, Z, W as described above, specifically, from the 30000 samples described above, a second weight in each sample is determined: b1, B2, B3, B4, B5, B6; a set of second weights is obtained, in which 180000 pieces of second weight data are included.
Determining minimum value B from the above-mentioned second weight setminAnd a maximum value BMAX；
If the above-mentioned minimum value B is presentminAnd a maximum value BMAXIs an integer, then X is BminW is BMAX。
If the above-mentioned minimum value B is presentminAnd a maximum value BMAXIs a decimal number; rounding, in particular, the closest minimum value B is takenminThe integer value of (a) is X; x is less than Bmin(ii) a Take the closest maximum BMAXThe integer value of (A) is W; w is greater than BMAX。
Y, Z is an integer and is located between X and W, and can be adjusted according to the actual B value distribution of the sample.
The spacing between X and W is finite, as evidenced by a large amount of experimental data, and the gap typically floats within a finite range.
For example, if X is 100 and W is 103, Y may be set to 101 and Z to 102.
And taking a piece of voice to be tested to input into the system, calculating and confirming whether three of B1, B2, B3, B4, B5 and B6 fall between X, Y and the other three fall between Z, W, if not, directly judging that the voice does not accord with the quality testing rule, directly judging that the voice is abnormal quality testing voice, highlighting and marking the voice in a striking way, and classifying the voice into a quality testing abnormal voice catalogue.
Taking a piece of voice to be tested, and calculating whether three of B1, B2, B3, B4, B5 and B6 fall between X, Y and the rest three fall between Z, W, if the confirmation is yes, assigning Q-max { three B values falling between X, Y } and R-mix { three B values falling between Z, W };
then, the following steps are carried out: v ═ 3Q +3R)/(B1+ B2+ … + B6) × 100%.
If V is greater than or equal to 90%, the quality testing voice is considered to be qualified, and OK is output; if V is less than 90%, the quality testing voice is considered to be unqualified, then the quality testing rules corresponding to two Bi in Q and R are marked to prompt that the voice file has problems in the two corresponding quality testing rules, the text file corresponding to the rules is automatically corrected to meet the requirements of the quality testing rules, but the voice file is displayed in a bold and highlight mode and a striking title is added to prompt the problem point of the voice and the position of the voice, and therefore quality testing personnel can conveniently and quickly locate and search the voice.
For unqualified voices, special processing can be performed, so that manual conformity is facilitated, and in one implementation mode, whether the acquired voices to be subjected to quality inspection are qualified or not is determined according to the service quality score of the telephone operator and a preset service quality score standard value; and if the voice to be subjected to quality inspection is not qualified, highlighting and highlighting the voice to be subjected to quality inspection, and classifying the voice to be subjected to quality inspection into a quality inspection abnormal voice catalog.
In order to realize classification and more detailed management, in one embodiment, in the quality inspection abnormal voice directory, all quality inspection abnormal voices are classified according to a judgment rule as a unit.
Illustratively, in the quality testing abnormal voice directory, the number of voice pieces corresponding to each rule is recorded. After clicking each voice, the text of the quality testing abnormal voice can be displayed.
For example, the number of the abnormal voice of the quality control corresponding to the text rule is 10; the 10 voices that indicate a quality control anomaly all violate the text rules for the operator. The 10 operators may be the same operator or a plurality of different operators. If the number of the operators is multiple different operators, respectively counting according to each operator, for example, the number of the operators A is 5; the number of the operators B is 3; the number of the operator C corresponds to 2.
If the voice list is not qualified, the voice list with abnormal quality inspection can be sent to a manual re-inspection platform, so that manual re-inspection can be realized. After sending the quality inspection abnormal voice catalog to a manual re-inspection platform, converting the voice to be inspected into a text; setting a highlighted title in the text, or thickening and highlighting part of text content to prompt specific positions which do not accord with the rules and exist in the text; so that quality testing personnel can quickly locate and search.
Referring to FIG. 2, a schematic flow diagram of another quality inspection method is shown; and (4) extracting 80% of the customer service record files for quality inspection, extracting 30% of samples to be inspected for quality inspection, and automatically performing quality inspection according to the set rules of the system. Manual re-judgment, wherein the quality of the seat is checked and re-judged manually, and positive and negative feedback is output according to a judgment rule; if the error rate is less than 10%, judging to be qualified, and performing positive feedback; if the error rate is more than or equal to 10%, judging that the product is unqualified, and performing negative feedback and feedback reinspection. The system automatically corrects the calculation formula, and rechecks after correction. The invention provides a system for automatically detecting quality according to a set quality detection rule, and an automatic quality detection correction mechanism with an autonomous design correction algorithm is provided, so that automatic quality detection according to the set rule and automatic correction classification feedback can be realized by voice, the speed and accuracy of intelligent quality detection are greatly improved, closed loop self-promotion of the system is completed, and the cost of human resources is saved.
The application provides an intelligent quality inspection rule judgment method fusing a customer service quality evaluation system, which can realize automatic quality inspection according to system setting rules, give out quality inspection result classification, and give out striking marks for different types of quality inspection voices so as to be convenient for later-stage quick searching and positioning. The method is combined with an automatic quality inspection and correction algorithm correction mechanism, so that the quality inspection result can be obtained quickly, the quality inspection speed can be increased quickly by using the method next time, and the result can be obtained directly for the voice which does not accord with the rule, so that the whole quality inspection time of the voice can be saved. The method has the advantages that the method for judging the intelligent quality inspection rule is provided, automatic quality inspection is realized, quality inspection results are classified and marked, later-stage quick searching and positioning are facilitated, and efficiency is remarkably improved compared with manual quality inspection and positioning searching; the method comprising the correction mechanism of the correction algorithm can be used for positioning whether the voice accords with the rule or not at one time before quality inspection, so that the time of all voice quality inspection is saved. According to the technical scheme, the intelligent quality inspection automatic rule judgment, the intelligent quality inspection accuracy improvement and the system quality inspection performance optimization can be realized, the closed loop of the system is automatically improved, the human resource cost is saved, and the automatic correction and the automatic optimization of the quality inspection result can be realized.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
In a second aspect, the present application further provides a device for customer service intelligent quality inspection, which is shown in fig. 3; the device includes:
an obtaining module 31, configured to obtain a voice to be quality checked;
the statistic module 32 is used for counting the times of the telephone operator offending the judgment rule in the voice to be quality checked;
and the scoring module 33 is configured to determine the service quality score of the operator in the voice to be quality-checked according to the number of times and a preset evaluation rule coefficient.
In one embodiment, the scoring module 33 is further configured to determine the number of times that the operator violates each evaluation rule when the evaluation rule is multiple;
summing the times of the operator offending each judgment rule to obtain the total times;
dividing the times of each judgment rule by the total times to calculate a first intermediate weight of each judgment rule;
calculating the product of the first intermediate weight of each judgment rule and the coefficient of each judgment rule;
calculating the reciprocal of the product to obtain a second intermediate weight of each judgment rule;
and calculating the service quality score of the operator according to the second intermediate weight of each judgment rule.
In an embodiment, the scoring module 33 is further configured to calculate, according to the second intermediate weight of each judgment rule, a service quality score of the operator, specifically including:
determining a plurality of second intermediate weights falling within the first interval;
determining a smallest second intermediate weight Q from the set of second intermediate weights;
determining a plurality of second intermediate weights falling within a second interval;
determining a smallest second intermediate weight R from the set of second intermediate weights;
the first interval is separated from the second interval, and the maximum endpoint value of the first interval is smaller than the minimum endpoint value of the second interval;
and calculating the service quality score of the operator according to the second intermediate weight Q and the second intermediate weight R.
In an embodiment, the scoring module 33 is further configured to calculate, according to the second intermediate weight Q and the second intermediate weight R, a service quality score of the operator, which specifically includes:
calculating a quality of service score for the operator using the following formula:
wherein V is a service quality score;
n is the number of judgment rules;
Biis the second intermediate weight of the ith evaluation rule.
In an embodiment, the system further includes a determining module 34, configured to determine whether the obtained voice to be quality tested is qualified according to the service quality score of the operator and a preset standard value of the service quality score;
if not, highlighting and highlighting the voice to be quality-tested, and classifying the voice to be quality-tested into a quality-test abnormal voice catalog;
and classifying all the abnormal quality control voices in the abnormal quality control voice catalog according to a judgment rule as a unit.
In an embodiment, the system further includes a sending module 35, configured to send the quality inspection abnormal voice directory to the manual review platform, so as to enable manual review.
In an embodiment, the system further includes a conversion processing module 36, configured to send a quality inspection abnormal voice directory to the manual review platform, and then convert the voice to be inspected into a text; setting a highlighted title in the text, or thickening and highlighting part of text content to prompt specific positions which do not accord with the rules and exist in the text; so that quality testing personnel can quickly locate and search.
According to a third aspect of the present application, an electronic device for customer service intelligent quality inspection is provided, referring to the schematic structural diagram of an electronic device for customer service intelligent quality inspection shown in fig. 4; comprises at least one processor 41 and at least one memory 42; the memory 42 is for storing one or more program instructions; the processor 41 is configured to execute one or more program instructions to perform any one of the methods described above.
In a fourth aspect, the present application also proposes a computer-readable storage medium having embodied therein one or more program instructions for executing the method of any one of the above.
The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The processor reads the information in the storage medium and completes the steps of the method in combination with the hardware.
The storage medium may be a memory, for example, which may be volatile memory or nonvolatile memory, or which may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory.
The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
The storage media described in connection with the embodiments of the invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that the functionality described in the present invention may be implemented in a combination of hardware and software in one or more of the examples described above. When software is applied, the corresponding functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for customer service intelligent quality inspection is characterized by comprising the following steps:
acquiring a voice to be inspected;
counting the times of the telephone operator offending the judgment rule in the voice to be detected;
and determining the service quality score of the telephone operator in the voice to be quality-checked according to the times and a preset evaluation rule coefficient.
2. The method for customer service intelligent quality inspection according to claim 1,
determining the service quality score of the telephone operator in the voice to be quality tested according to the times and a preset evaluation rule coefficient, wherein the step comprises the following steps:
when the number of the judgment rules is multiple, determining the frequency of the operator for offending each judgment rule;
summing the times of the operator offending each judgment rule to obtain the total times;
dividing the times of each judgment rule by the total times to calculate a first intermediate weight of each judgment rule;
calculating the product of the first intermediate weight of each judgment rule and the coefficient of each judgment rule;
calculating the reciprocal of the product to obtain a second intermediate weight of each judgment rule;
and calculating the service quality score of the operator according to the second intermediate weight of each judgment rule.
3. The method of customer service intelligent quality inspection according to claim 2,
the calculating the service quality score of the operator according to the second intermediate weight of each judgment rule comprises the following steps:
determining a plurality of second intermediate weights falling within the first interval;
determining a smallest second intermediate weight Q from the set of second intermediate weights;
determining a plurality of second intermediate weights falling within a second interval;
determining a smallest second intermediate weight R from the set of second intermediate weights;
the first interval is separated from the second interval, and the maximum endpoint value of the first interval is smaller than the minimum endpoint value of the second interval;
and calculating the service quality score of the operator according to the second intermediate weight Q and the second intermediate weight R.
4. The method of customer service intelligent quality inspection according to claim 3,
calculating to obtain the service quality score of the operator according to the second intermediate weight Q and the second intermediate weight R, wherein the method comprises the following steps:
calculating a quality of service score for the operator using the following formula:
wherein V is a service quality score;
n is the number of judgment rules;
Biis the second intermediate weight of the ith evaluation rule.
5. The method for customer service intelligent quality inspection according to claim 1,
the evaluation rule comprises the following steps: text rules, mute rules, speech rate rules, emotion rules, volume rules, and hard-plug rules;
the text rule is that the key words prohibited from appearing appear in the conversation of the telephone operator;
the mute rule is that the mute time of the telephone operator in the conversation is greater than a preset time threshold;
the speech rate rule is that the speech rate of the telephone operator in the conversation is greater than a preset speech rate threshold value;
the emotion rule is that the telephone operator has prohibited emotion in the conversation;
the volume rule is that the volume of the telephone operator in the conversation exceeds a preset volume threshold value or is smaller than the preset volume threshold value;
the strong insertion rule is that the telephone operator forcibly interrupts the client in the conversation to insert the robbing call.
6. The method for customer service intelligent quality inspection according to claim 1,
determining whether the obtained voice to be quality-checked is qualified or not according to the service quality score of the operator and a preset service quality score standard value;
if not, highlighting and highlighting the voice to be quality-tested, and classifying the voice to be quality-tested into a quality-test abnormal voice catalog;
and classifying all the abnormal quality control voices in the abnormal quality control voice catalog according to a judgment rule as a unit.
7. The method of customer service intelligent quality inspection according to claim 1, further comprising: and sending the quality inspection abnormal voice directory to a manual reinspection platform so as to carry out manual reinspection.
8. The method of claim 1, wherein after sending the quality inspection abnormal voice directory to the manual review platform, the method further comprises:
converting the voice to be tested into a text;
setting a highlighted title in the text, or thickening and highlighting part of text content to prompt specific positions which do not accord with the rules and exist in the text; so that quality testing personnel can quickly locate and search.
9. The utility model provides a device of customer service intelligence quality control which characterized in that includes:
the acquisition module is used for acquiring the voice to be subjected to quality inspection;
the statistic module is used for counting the times of the telephone operator offending the judgment rule in the voice to be quality checked;
and the scoring module is used for determining the service quality score of the telephone operator in the voice to be quality-tested according to the times and a preset evaluation rule coefficient.
10. An apparatus for intelligent quality inspection of customer service, comprising: at least one processor and at least one memory; the memory is to store one or more program instructions; the processor, configured to execute one or more program instructions to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110971226.6A CN113746989A (en) | 2021-08-23 | 2021-08-23 | Method, device, equipment and storage medium for customer service intelligent quality inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110971226.6A CN113746989A (en) | 2021-08-23 | 2021-08-23 | Method, device, equipment and storage medium for customer service intelligent quality inspection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113746989A true CN113746989A (en) | 2021-12-03 |
Family
ID=78732361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110971226.6A Pending CN113746989A (en) | 2021-08-23 | 2021-08-23 | Method, device, equipment and storage medium for customer service intelligent quality inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113746989A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170154293A1 (en) * | 2014-06-16 | 2017-06-01 | Panasonic Intellectual Property Management Co., Ltd. | Customer service appraisal device, customer service appraisal system, and customer service appraisal method |
| CN109327632A (en) * | 2018-11-23 | 2019-02-12 | 深圳前海微众银行股份有限公司 | Intelligent quality inspection system, method and the computer readable storage medium of customer service recording |
| CN111147669A (en) * | 2019-12-30 | 2020-05-12 | 科讯嘉联信息技术有限公司 | Full real-time automatic service quality inspection system and method |
| CN111263009A (en) * | 2020-01-17 | 2020-06-09 | 北京三快在线科技有限公司 | Quality inspection method, device, equipment and medium for telephone recording |
| CN111405128A (en) * | 2020-03-24 | 2020-07-10 | 中国—东盟信息港股份有限公司 | Call quality inspection system based on voice-to-text conversion |
| CN111917924A (en) * | 2020-07-29 | 2020-11-10 | 上海博泰悦臻电子设备制造有限公司 | Customer service voice quality inspection method and related equipment |
| CN112804400A (en) * | 2020-12-31 | 2021-05-14 | 中国工商银行股份有限公司 | Customer service call voice quality inspection method and device, electronic equipment and storage medium |
| CN112885332A (en) * | 2021-01-08 | 2021-06-01 | 天讯瑞达通信技术有限公司 | Voice quality inspection method, system and storage medium |
| WO2021138898A1 (en) * | 2020-01-10 | 2021-07-15 | 深圳市欢太科技有限公司 | Speech recognition result detection method and apparatus, and storage medium |
-
2021
- 2021-08-23 CN CN202110971226.6A patent/CN113746989A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170154293A1 (en) * | 2014-06-16 | 2017-06-01 | Panasonic Intellectual Property Management Co., Ltd. | Customer service appraisal device, customer service appraisal system, and customer service appraisal method |
| CN109327632A (en) * | 2018-11-23 | 2019-02-12 | 深圳前海微众银行股份有限公司 | Intelligent quality inspection system, method and the computer readable storage medium of customer service recording |
| CN111147669A (en) * | 2019-12-30 | 2020-05-12 | 科讯嘉联信息技术有限公司 | Full real-time automatic service quality inspection system and method |
| WO2021138898A1 (en) * | 2020-01-10 | 2021-07-15 | 深圳市欢太科技有限公司 | Speech recognition result detection method and apparatus, and storage medium |
| CN111263009A (en) * | 2020-01-17 | 2020-06-09 | 北京三快在线科技有限公司 | Quality inspection method, device, equipment and medium for telephone recording |
| CN111405128A (en) * | 2020-03-24 | 2020-07-10 | 中国—东盟信息港股份有限公司 | Call quality inspection system based on voice-to-text conversion |
| CN111917924A (en) * | 2020-07-29 | 2020-11-10 | 上海博泰悦臻电子设备制造有限公司 | Customer service voice quality inspection method and related equipment |
| CN112804400A (en) * | 2020-12-31 | 2021-05-14 | 中国工商银行股份有限公司 | Customer service call voice quality inspection method and device, electronic equipment and storage medium |
| CN112885332A (en) * | 2021-01-08 | 2021-06-01 | 天讯瑞达通信技术有限公司 | Voice quality inspection method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020082579A1 (en) | Risk review and approval method, device, storage medium, and server | |
| CN110619506B (en) | Post image generation method, post image generation device and electronic equipment | |
| CN110555101A (en) | customer service knowledge base updating method, device, equipment and storage medium | |
| CN110213152B (en) | Method, device, server and storage medium for identifying junk mails | |
| CN108460025A (en) | Criminal case automates measurement of penalty method, apparatus and computer readable storage medium | |
| CN111046141B (en) | Text library keyword refining method based on historical time characteristics | |
| CN112101807A (en) | Method and related device for comprehensively evaluating customer value of group in telecommunication industry | |
| CN112200375A (en) | Prediction model generation method, prediction model generation device, and computer-readable medium | |
| CN110457357B (en) | Lawyer recommendation method based on neural network and related equipment | |
| CN112101692B (en) | Identification method and device for mobile internet bad quality users | |
| CN114971693A (en) | Engineering cost consultation management system based on BIM | |
| DE102013101871A1 (en) | Word-based speech analysis and speech analysis facility | |
| CN111061998A (en) | Analysis model and method for economic measurement | |
| Lněnička | E-government Development Index and its Comparison in the EU Member States | |
| CN113746989A (en) | Method, device, equipment and storage medium for customer service intelligent quality inspection | |
| CN111611973A (en) | Method, device and storage medium for identifying target user | |
| CN115378928B (en) | Monitoring method and system based on cloud service | |
| CN112383828A (en) | Experience quality prediction method, equipment and system with brain-like characteristic | |
| CN110677269B (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| CN116431826A (en) | Knowledge graph updating method, device, equipment and storage medium | |
| CN112241820A (en) | Risk identification method and device for key nodes in fund flow and computing equipment | |
| CN105786929A (en) | Information monitoring method and device | |
| WO2021073258A1 (en) | Task follow-up method, apparatus and device based on emotion analysis, and storage medium | |
| CN110955727B (en) | Automatic student homework recording system | |
| CN113435842A (en) | Business process processing method and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |