CN105187674B - Compliance checking method and device for service recording - Google Patents
Compliance checking method and device for service recording Download PDFInfo
- Publication number
- CN105187674B CN105187674B CN201510500179.1A CN201510500179A CN105187674B CN 105187674 B CN105187674 B CN 105187674B CN 201510500179 A CN201510500179 A CN 201510500179A CN 105187674 B CN105187674 B CN 105187674B
- Authority
- CN
- China
- Prior art keywords
- customer
- record
- abnormal
- service
- text content
- 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 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 174
- 238000001514 detection method Methods 0.000 claims abstract description 45
- 238000007689 inspection Methods 0.000 claims abstract description 40
- 230000006399 behavior Effects 0.000 claims description 56
- 238000012545 processing Methods 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000012372 quality testing Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 10
- 239000010970 precious metal Substances 0.000 claims description 7
- 238000000605 extraction Methods 0.000 abstract description 8
- 238000004891 communication Methods 0.000 abstract description 6
- 238000003908 quality control method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000012552 review Methods 0.000 description 5
- 230000002547 anomalous effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241001122315 Polites Species 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 229910000510 noble metal Inorganic materials 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a compliance checking method and device for service recording, and belongs to the technical field of communication. The method comprises the following steps: detecting whether the target client belongs to an abnormal client or not according to the historical behavior record of the target client; if the target customer belongs to the abnormal customer, obtaining a service record related to the target customer from the call center; converting the service recording into text content; detecting whether the service record accords with the service specification or not according to the text content; and if the service specification is not met, storing the service recording and/or the text content to the target position. The invention solves the problems of a large number of missed detection conditions and low efficiency in the prior art by adopting a random extraction mode; on the one hand, the occurrence of the condition of missing inspection is fully reduced, on the other hand, the quality inspection personnel only need to recheck the service record which is detected as not compliant by the system and is provided for the quality inspection personnel, so that the quality inspection personnel can inspect the service record in a targeted manner, and the inspection efficiency is improved.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a compliance checking method and apparatus for service recording.
Background
The call center is an operation place for processing a large amount of incoming and outgoing telephone services by using modern communication and computer technologies. For example, communication carriers, banks, and some enterprises involved in business promotion are equipped with call centers to provide services such as business consultation, handling, and complaint to customers.
In order to improve the service quality of the operator of the call center and ensure that the wording of the operator conforms to the service specification, the service recording of the operator needs to be checked. In the prior art, a method of randomly extracting service records is adopted in consideration of the huge number of service records of a call center. And randomly extracting a plurality of service records from a large number of service records through quality testing personnel or a system, and then listening and distinguishing the extracted service records by the quality testing personnel to check whether the service records meet the service specification.
In the process of implementing the embodiment of the present invention, the inventor finds that the prior art has at least the following problems: on one hand, the random extraction mode can cause a large number of missed detection situations; on the other hand, most of the service records provided for quality control personnel are compliant service records, and only a small part of the service records are non-compliant service records, which results in that the quality control personnel lack pertinence during inspection and the inspection efficiency is low.
Disclosure of Invention
In order to solve the problems of a large number of missed detection conditions and low efficiency in the prior art which adopts a random extraction mode, the embodiment of the invention provides a compliance checking method and device for service recording. The technical scheme is as follows:
in a first aspect, a compliance check method for service records is provided, the method is used for screening service records in the field of precious metal, stock or financial investment service for compliance check of quality control personnel, and the method comprises the following steps:
acquiring a historical behavior record of a target client, wherein the historical behavior record comprises a historical transaction record and/or a historical call record, the historical behavior record is used for reflecting the historical transaction behavior of the target client, the historical call record is used for reflecting the historical call behavior of the target client, and the target client is a user requesting service provided by an operator of a call center;
detecting whether the target customer belongs to an abnormal customer according to the historical behavior record, wherein the abnormal customer refers to a customer with abnormal transaction condition and/or abnormal call condition in the historical behavior record, and the abnormal customer comprises at least one of the following: abnormal clients of deposit and withdrawal detected based on the deposit and withdrawal record, abnormal clients of operation detected based on the build-up flat warehouse record, abnormal clients of profit and loss detected based on the profit and loss record, abnormal clients of transaction detected based on the transaction times, abnormal clients of call detected based on the call times and complaint clients detected based on the complaint times;
if the target customer belongs to the abnormal customer, obtaining a service record related to the target customer from a call center;
converting the service recording into text content;
detecting whether the service record meets a service specification according to the text content, wherein the service specification refers to a specification requirement made on the service of an operator of the call center;
if the service record does not meet the service specification, storing the service record and/or the text content to a corresponding classification of a target position according to the abnormal customer classification to which the target customer belongs, wherein the target position is used for storing the service record and/or the text content for quality testing personnel to recheck; wherein the abnormal customer classification comprises at least one of the abnormal deposit and withdrawal customer, the abnormal operation customer, the abnormal profit and loss customer, the abnormal transaction customer, the abnormal call customer and the complaint customer.
Optionally, the historical transaction record comprises at least one of the deposit and withdrawal record, the bunk building record, the profit and loss record and the transaction number, and the historical call record comprises the call number and/or the complaint number;
the detecting whether the target customer belongs to an abnormal customer according to the historical behavior record comprises the following steps:
detecting whether the deposit and withdrawal record meets a first preset condition; if the deposit-withdrawal record meets the first preset condition, determining that the target customer belongs to the abnormal deposit-withdrawal customer; and/or the presence of a gas in the gas,
detecting whether the leveling record meets a second preset condition; if the leveling record meets the second preset condition, determining that the target customer belongs to the abnormal operation customer; and/or the presence of a gas in the gas,
detecting whether the profit-loss record meets a third preset condition; if the profit-loss record meets the third preset condition, determining that the target customer belongs to the profit-loss abnormal customer; and/or the presence of a gas in the gas,
detecting whether the transaction times meet a fourth preset condition; if the transaction times meet the fourth preset condition, determining that the target customer belongs to the transaction abnormal customer; and/or the presence of a gas in the gas,
detecting whether the number of calls meets a fifth preset condition or not; if the number of calls meets the fifth preset condition, determining that the target customer belongs to the abnormal call customer; and/or the presence of a gas in the gas,
detecting whether the complaint times meet a sixth preset condition; and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
Optionally, the detecting whether the service recording conforms to a service specification according to the text content includes:
detecting whether a keyword model matched with the text content exists in n preset keyword models or not; the keyword model comprises a basic keyword, or the keyword model comprises at least two basic keywords and a logic relation character used for representing the logic relation between the at least two basic keywords, and n is a positive integer;
and if the keyword model matched with the text content exists in the n keyword models, determining that the service recording does not accord with the service specification.
Optionally, the detecting whether a keyword model matched with the text content exists in the preset n keyword models includes:
for the ith keyword model, detecting whether the basic keyword exists in the text content or not under the condition that the ith keyword model comprises the basic keyword; if the basic keywords exist in the text content, determining that the ith keyword model is matched with the text content, wherein i is a positive integer;
or,
for an ith keyword model, under the condition that the ith keyword model comprises at least two basic keywords and a logical relation character, searching the basic keywords contained in the ith keyword model in the text content; if at least one basic keyword is found in the text content, detecting whether the found basic keyword conforms to the logic relationship represented by the logic relationship symbol; and if the found basic keywords accord with the logic relation represented by the logic relation symbol, determining that the ith keyword model is matched with the text content, wherein i is a positive integer.
In a second aspect, there is provided a compliance check device for service recording, the device is used for screening service recording in the field of precious metal, stock or financial investment service for compliance check of quality inspection personnel, the device comprises:
the system comprises a record acquisition module, a call center processing module and a call center processing module, wherein the record acquisition module is used for acquiring historical behavior records of a target client, the historical behavior records comprise historical transaction records and/or historical call records, the historical behavior records are used for reflecting historical transaction behaviors of the target client, the historical call records are used for reflecting historical call behaviors of the target client, and the target client is a user requesting services provided by an operator of the call center;
an abnormal detection module, configured to detect whether the target customer belongs to an abnormal customer according to the historical behavior record, where the abnormal customer is a customer with an abnormal transaction condition and/or an abnormal call condition in the historical behavior record, and the abnormal customer includes at least one of the following: abnormal clients of deposit and withdrawal detected based on the deposit and withdrawal record, abnormal clients of operation detected based on the build-up flat warehouse record, abnormal clients of profit and loss detected based on the profit and loss record, abnormal clients of transaction detected based on the transaction times, abnormal clients of call detected based on the call times and complaint clients detected based on the complaint times;
the recording acquisition module is used for acquiring a service recording related to the target customer from a call center under the condition that the target customer belongs to the abnormal customer;
the recording conversion module is used for converting the service recording into text content;
a compliance detection module, configured to detect whether the service record meets a service specification according to the text content, where the service specification refers to a specification requirement made for a service of an operator of the call center;
the storage module is used for storing the service recording and/or the text content to a corresponding classification of a target position according to the abnormal customer classification of the target customer when the service recording does not accord with the service specification, wherein the target position is used for storing the service recording and/or the text content for quality testing personnel to review; wherein the abnormal customer classification comprises at least one of the abnormal deposit and withdrawal customer, the abnormal operation customer, the abnormal profit and loss customer, the abnormal transaction customer, the abnormal call customer and the complaint customer.
Optionally, the historical transaction record comprises at least one of the deposit and withdrawal record, the bunk building record, the profit and loss record and the transaction number, and the historical call record comprises the call number and/or the complaint number;
the anomaly detection module includes:
the first detection unit is used for detecting whether the deposit and withdrawal record meets a first preset condition or not; if the deposit-withdrawal record meets the first preset condition, determining that the target customer belongs to the abnormal deposit-withdrawal customer; and/or the presence of a gas in the gas,
the second detection unit is used for detecting whether the leveling record meets a second preset condition; if the leveling record meets the second preset condition, determining that the target customer belongs to the abnormal operation customer; and/or the presence of a gas in the gas,
the third detection unit is used for detecting whether the profit and loss records meet a third preset condition or not; if the profit-loss record meets the third preset condition, determining that the target customer belongs to the profit-loss abnormal customer; and/or the presence of a gas in the gas,
the fourth detection unit is used for detecting whether the transaction times meet a fourth preset condition or not; if the transaction times meet the fourth preset condition, determining that the target customer belongs to the transaction abnormal customer; and/or the presence of a gas in the gas,
a fifth detecting unit, configured to detect whether the number of times of call meets a fifth predetermined condition; if the number of calls meets the fifth preset condition, determining that the target customer belongs to the abnormal call customer; and/or the presence of a gas in the gas,
a sixth detecting unit, configured to detect whether the number of complaints meets a sixth predetermined condition; and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
Optionally, the compliance detection module includes:
the detection unit is used for detecting whether a keyword model matched with the text content exists in preset n keyword models or not; the keyword model comprises a basic keyword, or the keyword model comprises at least two basic keywords and a logic relation character used for representing the logic relation between the at least two basic keywords, and n is a positive integer;
and the determining unit is used for determining that the service sound recording does not accord with the service specification under the condition that the keyword model matched with the text content exists in the n keyword models.
Optionally, the detecting unit is specifically configured to, for an ith keyword model, detect whether the text content includes a basic keyword or not when the ith keyword model includes the basic keyword; if the basic keywords exist in the text content, determining that the ith keyword model is matched with the text content, wherein i is a positive integer;
or, the detecting unit is specifically configured to, for an ith keyword model, search the basic keywords included in the ith keyword model in the text content when the ith keyword model includes at least two basic keywords and a logical relation character; if at least one basic keyword is found in the text content, detecting whether the found basic keyword conforms to the logic relationship represented by the logic relationship symbol; and if the found basic keywords accord with the logic relation represented by the logic relation symbol, determining that the ith keyword model is matched with the text content, wherein i is a positive integer.
In a third aspect, there is provided a computer-readable storage medium having stored therein a program for implementing the compliance checking method for service sound recording according to the first aspect.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
detecting whether the target client belongs to an abnormal client or not according to the historical behavior record of the target client, converting the service recording related to the target client into text content under the condition that the target client belongs to the abnormal client, detecting whether the service recording meets the service specification or not according to the text content, and providing the service recording and/or the text content which does not meet the service specification to quality control personnel; the problem that in the prior art, a random extraction mode is adopted, a large number of missed detection conditions exist, and the efficiency is low is solved; on the one hand, the occurrence of the condition of missing inspection is fully reduced, on the other hand, the quality inspection personnel only need to recheck the service record which is detected as not compliant by the system and is provided for the quality inspection personnel, so that the quality inspection personnel can inspect the service record in a targeted manner, and the inspection efficiency is improved. In addition, the abnormal client is used as a preliminary screening condition, the processing amount of the voice-to-text system is reduced, text conversion processing is not needed to be carried out on each service record, and therefore compliance checking efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic illustration of an implementation environment in which embodiments of the invention are concerned;
FIG. 2 is a flow diagram of a compliance checking method for service sound recordings provided by one embodiment of the present invention;
FIG. 3 is a flowchart of a compliance checking method for service sound recording according to another embodiment of the present invention;
FIG. 4 is a block diagram of a compliance checking device for service sound recordings provided by one embodiment of the present invention;
FIG. 5 is a block diagram of a compliance checking device for service sound recordings provided in accordance with another embodiment of the present invention;
fig. 6 is a schematic structural diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Referring to fig. 1, a schematic diagram of an implementation environment according to an embodiment of the invention is shown. The implementation environment may include: CRM (Customer Relationship Management) system 100. In the embodiment of the invention, the CRM system 100 is used for screening out abnormal customers according to the historical behavior records of the customers, converting the service records related to the abnormal customers into text contents, detecting the service records and/or the text contents which do not meet the service specification according to the text contents, providing the service records and/or the text contents to quality control personnel, and rechecking by the quality control personnel.
Optionally, as shown in fig. 1, CRM system 100 may include: call center system 120, historical behavior recording system 140, and speech to text system 160. Wherein the call center system 120 is used to handle incoming and outgoing telephone traffic. The call center system 120 has a database in which the operator's service record is stored. The historical behavior record system 140 stores historical behavior records of clients. Particularly, when the technical solution provided by this embodiment is applied to an actual application scenario of compliance check on a service recording in the precious metal investment service field, the historical behavior record may include a historical transaction record and/or a historical call record. The voice to text system 160 is used to convert the service recording to text content.
The system architecture can be realized by one server or a server cluster consisting of a plurality of servers. For the sake of simplifying the description, in the following method embodiments, the execution subject of each step is exemplified as a server except for the specific description, but the present invention is not limited thereto.
Referring to fig. 2, a flowchart of a compliance checking method for service audio records according to an embodiment of the present invention is shown. The compliance checking method may include the steps of:
And step 204, detecting whether the target customer belongs to an abnormal customer according to the historical behavior record.
And step 206, if the target customer belongs to the abnormal customer, acquiring the service record related to the target customer from the call center.
In step 208, the obtained service recording is converted into text content.
In summary, in the compliance check method provided in this embodiment, whether the target client belongs to an abnormal client is detected according to the historical behavior record of the target client, and under the condition that the target client belongs to the abnormal client, the service record related to the target client is converted into the text content, and then whether the service record meets the service specification is detected according to the text content, and the service record and/or the text content which does not meet the service specification is provided to the quality inspector; the problem that in the prior art, a random extraction mode is adopted, a large number of missed detection conditions exist, and the efficiency is low is solved; on the one hand, the occurrence of the condition of missing inspection is fully reduced, on the other hand, the quality inspection personnel only need to recheck the service record which is detected as not compliant by the system and is provided for the quality inspection personnel, so that the quality inspection personnel can inspect the service record in a targeted manner, and the inspection efficiency is improved. In addition, the abnormal client is used as a preliminary screening condition, the processing amount of the voice-to-text system is reduced, text conversion processing is not needed to be carried out on each service record, and therefore compliance checking efficiency is improved.
Please refer to fig. 3, which illustrates a flowchart of a compliance checking method for service audio records according to another embodiment of the present invention. The present embodiment is illustrated by applying the compliance checking method to the implementation environment shown in fig. 1. The compliance checking method may include the steps of:
In this embodiment, taking an actual application scenario of compliance check of service records in the precious metal investment service field as an example, the historical behavior record includes a historical transaction record and/or a historical call record. The historical transaction records are used for reflecting the historical transaction behaviors of the customers, and include but are not limited to at least one of cash-in and cash-out records, flat-cabin building records, profit and loss records and transaction times; the historical call log is used to reflect the historical call behavior of the customer, and includes, but is not limited to, the number of calls and/or the number of complaints.
And step 302, detecting whether the target customer belongs to an abnormal customer according to the historical behavior record.
According to different record information contained in the historical behavior record, the method comprises the following possible situations:
1. and detecting whether the deposit record meets a first preset condition, and if the deposit record meets the first preset condition, determining that the target customer belongs to the abnormal deposit-withdrawing customer.
The deposit and withdrawal record includes but is not limited to record information such as deposit amount, deposit time and the like. In practical application, the corresponding first predetermined condition can be set in combination with abnormal transaction conditions such as large amount of money, full amount of money and the like. In one example, the first predetermined condition may be that the payout amount for a single transaction is greater than 30 ten thousand.
2. And detecting whether the leveling record meets a second preset condition, and if the leveling record meets the second preset condition, determining that the target customer belongs to the customer with abnormal operation.
The flat-bin establishing records include, but are not limited to, record information such as the time of the flat bin establishing, the number of the flat bin establishing and the like. In practical applications, the corresponding second predetermined condition may be set in conjunction with abnormal transaction conditions such as frequent flat-binning. In one example, the second predetermined condition may be that the number of times of leveling after binning within the last 2 hours exceeds a predetermined number of times.
3. And detecting whether the profit-loss record meets a third preset condition, and if the profit-loss record meets the third preset condition, determining that the target customer belongs to the profit-loss abnormal customer.
The profit-loss record includes, but is not limited to, record information such as profit amount, loss amount, profit time, loss time, profit times, loss times and the like. In practical applications, the corresponding third predetermined condition may be set in connection with abnormal transaction conditions such as large profit and loss. In one example, the third predetermined condition may be set to a total profit or a total loss greater than 30 ten thousand.
4. And detecting whether the transaction frequency meets a fourth preset condition, and if the transaction frequency meets the fourth preset condition, determining that the target customer belongs to a transaction abnormal customer.
In practical applications, the corresponding fourth predetermined condition may be set in combination with abnormal transaction conditions, such as no transaction after account activation, and too frequent transaction. In one example, the fourth predetermined condition may be that the number of transactions is less than a predetermined number.
5. And detecting whether the call times meet a fifth preset condition, and if the call times meet the fifth preset condition, determining that the target customer belongs to a customer with abnormal call.
In practical applications, the corresponding fifth predetermined condition may be set in combination with abnormal call situations, such as excessive passing times and frequent calls. In one example, the fifth predetermined condition may be that the number of calls is greater than a predetermined number of times.
6. And detecting whether the number of complaints meets a sixth preset condition, and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
In practical applications, the sixth predetermined condition may be set in combination with abnormal call situations, such as excessive complaints and frequent complaints. In one example, the sixth predetermined condition may be that the number of complaints is greater than the predetermined number.
In the embodiment, different abnormality detection conditions are set, and under the condition that the target customer is an abnormal customer, the abnormal customer category to which the target customer belongs is determined at the same time, so that the classified management of the abnormal customer is realized, and convenience is provided for the follow-up compliance inspection of quality inspection personnel.
Of course, the above classification for the abnormal clients is only exemplary and explanatory, and in practical applications, the abnormal clients of different classifications may be set according to actual requirements, and corresponding abnormal detection conditions may be set, which is not specifically limited in this embodiment.
Optionally, the server obtains a client identifier of the target client, and obtains a service recording corresponding to the client identifier from a database of the call center.
The voice-to-text system converts the service recording into text content by adopting a voice recognition technology.
In one possible embodiment, the telephone communication between the operator and the client may be recorded separately, i.e., the service recording includes the operator recording and the client recording. The voice to text system may simply convert the operator recording to text content without processing the customer recording to reduce processing.
And then, the server detects whether the service record conforms to a service specification according to the text content, wherein the service specification refers to a specification requirement made on the service of an operator of the call center. Specifically, the detection process includes the following steps 305 and 306.
There are two possible implementations of the keyword model as follows.
First, the keyword model includes a basic keyword. The basic keywords can be sensitive words related to business, polite words or other service banners. The basic keywords can be preset according to the actual application scene. Taking an actual application scene of performing compliance check on service records in the noble metal investment service field as an example, a certain keyword model can comprise sensitive words related to the business of 'transaction'; alternatively, another keyword model may include "flat-bin" that is a business-related sensitive vocabulary; alternatively, yet another keyword model may include an unfortunate word of "brain disability," and so on.
Second, the keyword model includes at least two basic keywords and a logical relation character for representing a logical relation between the at least two basic keywords. The basic keywords can be sensitive words related to business, polite words or other service banners. Logical relators include, but are not limited to, one or more of the following: and (and), or (or), not (not), near (near), after (after), before (before), etc. The basic keywords and the logic relation characters can be preset according to the actual application scene. Still taking the practical application scenario of performing compliance check on the service recording in the noble metal investment service field as an example, a certain keyword model can be 'trade and flat bin', and represents that two basic keywords of 'trade' and 'flat bin' are included at the same time; alternatively, another keyword model may be "deal or" brainstorming ", meaning that any logical keyword including" deal "or" brainstorming "is included, and so on.
The server compares the preset n keyword models with the text content one by one, and detects whether a keyword model matched with the text content exists. Next, taking the comparison between the ith keyword model and the text content as an example, the comparison processes corresponding to the two possible implementation manners are introduced respectively.
Wherein i is a positive integer.
For the ith keyword model, detecting whether the basic keyword exists in the text content under the condition that the ith keyword model comprises the basic keyword; and if the basic keyword exists in the text content, determining that the ith keyword model is matched with the text content. For example, if the ith keyword model is "transaction", detecting whether a word of "transaction" exists in the text content, and if yes, determining that the ith keyword model is matched with the text content; otherwise, if the keyword does not exist, the ith keyword model is determined not to be matched with the text content.
For the ith keyword model, under the condition that the ith keyword model comprises at least two basic keywords and a logic relation character, searching the basic keywords contained in the ith keyword model in the text content; if at least one basic keyword is found in the text content, detecting whether the found basic keyword accords with the logical relationship represented by the logical relationship symbol; and if the searched basic keywords accord with the logical relation represented by the logical relation symbol, determining that the ith keyword model is matched with the text content. For example, if the ith keyword model is "deal and flat", the ith keyword model is determined to be matched with the text content under the condition that two basic keywords, namely "deal" and "flat", are found in the text content at the same time; otherwise, if only one of the basic keywords is found or the basic keywords are not found, determining that the ith keyword model is not matched with the text content.
Of course, the above-mentioned keyword models are only exemplary and explanatory, and in practical applications, more various, complex or precise keyword models can be set according to practical application scenarios and requirements, which is not specifically limited in this embodiment.
And under the condition that the keyword model matched with the text content exists in the preset n keyword models, the service record is indicated as the service record not conforming to the service specification, the server stores the service record and/or the text content to a target position, and the target position is used for storing the service record and/or the text content for quality testing personnel to review. Accordingly, quality testing personnel can obtain the service recording and/or the text content from the target position, manually check the service recording and further confirm whether the service recording is in compliance.
In this embodiment, corresponding to different abnormal customer classifications, a corresponding classification is set for the target location. By storing the service records to the corresponding classification of the target position according to the abnormal customer classification to which the target customer belongs, the service records are classified and managed according to the abnormal customer classification, and quality testing personnel can be helped to perform compliance check on the service records more pertinently and efficiently.
In summary, in the compliance check method provided in this embodiment, whether the target client belongs to an abnormal client is detected according to the historical behavior record of the target client, and under the condition that the target client belongs to the abnormal client, the service record related to the target client is converted into the text content, and then whether the service record meets the service specification is detected according to the text content, and the service record and/or the text content which does not meet the service specification is provided to the quality inspector; the problem that in the prior art, a random extraction mode is adopted, a large number of missed detection conditions exist, and the efficiency is low is solved; on the one hand, the occurrence of the condition of missing inspection is fully reduced, on the other hand, the quality inspection personnel only need to recheck the service record which is detected as not compliant by the system and is provided for the quality inspection personnel, so that the quality inspection personnel can inspect the service record in a targeted manner, and the inspection efficiency is improved. In addition, the abnormal client is used as a preliminary screening condition, the processing amount of the voice-to-text system is reduced, text conversion processing is not needed to be carried out on each service record, and therefore compliance checking efficiency is improved.
In addition, different abnormal detection conditions are set, and under the condition that the target customer is the abnormal customer, the abnormal customer classification to which the target customer belongs is determined at the same time, so that the classified management of the abnormal customer is realized, and convenience is brought to the follow-up compliance inspection of quality inspection personnel.
It should be noted that, in this embodiment, only the actual application scenario of compliance check on the service recording in the precious metal investment service field is taken as an example, and without loss of generality, the compliance check method provided in this embodiment may also be applied to other actual application scenarios, such as an actual application scenario of compliance check on the service recording in the stock investment service field, an actual application scenario of compliance check on the service recording in the financial investment service field, and the like.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Referring to fig. 4, a block diagram of a compliance checking device for service sound recording according to an embodiment of the present invention is shown. The compliance checking device may be used in the implementation environment shown in fig. 1. The compliance checking device includes: the recording module comprises a record acquisition module 410, an anomaly detection module 420, a recording acquisition module 430, a recording conversion module 440, a compliance detection module 450, and a storage module 460.
And a record obtaining module 410, configured to obtain a historical behavior record of the target client.
An anomaly detection module 420, configured to detect whether the target customer belongs to an anomalous customer according to the historical behavior record obtained by the record obtaining module 410.
A record obtaining module 430, configured to obtain a service record related to the target customer from a call center when the anomaly detection module 420 detects that the target customer belongs to the anomalous customer.
A recording conversion module 440, configured to convert the service recording acquired by the recording acquisition module 430 into text content.
A compliance detection module 450, configured to detect whether the service record meets a service specification according to the text content converted by the record conversion module 440, where the service specification refers to a specification requirement made for a service of an operator of the call center.
A storing module 460, configured to store the service recording and/or the text content to a target location when the compliance detecting module 450 detects that the service recording does not meet the service specification, where the target location is used to store the service recording and/or the text content for quality control personnel to review.
In summary, the compliance check device provided in this embodiment detects whether the target client belongs to an abnormal client according to the historical behavior record of the target client, converts the service record related to the target client into a text content when the target client is detected to belong to the abnormal client, then detects whether the service record meets the service specification according to the text content, and provides the service record and/or the text content that does not meet the service specification to the quality control staff; the problem that in the prior art, a random extraction mode is adopted, a large number of missed detection conditions exist, and the efficiency is low is solved; on the one hand, the occurrence of the condition of missing inspection is fully reduced, on the other hand, the quality inspection personnel only need to recheck the service record which is detected as not compliant by the system and is provided for the quality inspection personnel, so that the quality inspection personnel can inspect the service record in a targeted manner, and the inspection efficiency is improved. In addition, the abnormal client is used as a preliminary screening condition, the processing amount of the voice-to-text system is reduced, text conversion processing is not needed to be carried out on each service record, and therefore compliance checking efficiency is improved.
Referring to fig. 5, a block diagram of a compliance checking apparatus for service sound recording according to another embodiment of the present invention is shown. The compliance checking device may be used in the implementation environment shown in fig. 1. The compliance checking device includes: the recording module comprises a record acquisition module 410, an anomaly detection module 420, a recording acquisition module 430, a recording conversion module 440, a compliance detection module 450, and a storage module 460.
And a record obtaining module 410, configured to obtain a historical behavior record of the target client.
An anomaly detection module 420, configured to detect whether the target customer belongs to an anomalous customer according to the historical behavior record obtained by the record obtaining module 410.
A record obtaining module 430, configured to obtain a service record related to the target customer from a call center when the anomaly detection module 420 detects that the target customer belongs to the anomalous customer.
A recording conversion module 440, configured to convert the service recording acquired by the recording acquisition module 430 into text content.
A compliance detection module 450, configured to detect whether the service record meets a service specification according to the text content converted by the record conversion module 440, where the service specification refers to a specification requirement made for a service of an operator of the call center.
A storing module 460, configured to store the service recording and/or the text content to a target location when the compliance detecting module 450 detects that the service recording does not meet the service specification, where the target location is used to store the service recording and/or the text content for quality control personnel to review.
Optionally, the historical behavior record comprises a historical transaction record and/or a historical call record, the historical transaction record comprises at least one of an income/income record, a leveling record, a profit/loss record and a transaction number, and the historical call record comprises a call number and/or a complaint number;
the anomaly detection module 420 includes:
a first detecting unit 420a, configured to detect whether the deposit and withdrawal record meets a first predetermined condition; if the deposit-withdrawal record meets the first preset condition, determining that the target customer belongs to a deposit-withdrawal abnormal customer; and/or the presence of a gas in the gas,
a second detecting unit 420b, configured to detect whether the leveling record meets a second predetermined condition; if the leveling record meets the second preset condition, determining that the target customer belongs to an abnormal operation customer; and/or the presence of a gas in the gas,
a third detecting unit 420c, configured to detect whether the profit-loss record meets a third predetermined condition; if the profit-loss record meets the third preset condition, determining that the target customer belongs to a profit-loss abnormal customer; and/or the presence of a gas in the gas,
a fourth detecting unit 420d, configured to detect whether the transaction number meets a fourth predetermined condition; if the transaction times meet the fourth preset condition, determining that the target customer belongs to a transaction abnormal customer; and/or the presence of a gas in the gas,
a fifth detecting unit 420e, configured to detect whether the number of times of call meets a fifth predetermined condition; if the number of calls meets the fifth preset condition, determining that the target customer belongs to a customer with abnormal calls; and/or the presence of a gas in the gas,
a sixth detecting unit 420f, configured to detect whether the number of complaints meets a sixth predetermined condition; and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
Optionally, the storage module 460 is specifically configured to store the service record and/or the text content to the corresponding classification of the target location according to the abnormal customer classification to which the target customer belongs;
wherein the abnormal customer classification comprises at least one of the abnormal deposit and withdrawal customer, the abnormal operation customer, the abnormal profit and loss customer, the abnormal transaction customer, the abnormal call customer and the complaint customer.
Optionally, the compliance detection module 450 includes:
the detecting unit 450a is configured to detect whether a keyword model matching the text content exists in n preset keyword models; the keyword model comprises a basic keyword, or the keyword model comprises at least two basic keywords and a logic relation character used for representing the logic relation between the at least two basic keywords, and n is a positive integer;
a determining unit 450b, configured to determine that the service record does not meet the service specification when the detecting unit 450a detects that a keyword model matching the text content exists in the n keyword models.
Optionally, the detecting unit 450a is specifically configured to, for an ith keyword model, detect whether the text content has a basic keyword or not when the ith keyword model includes the basic keyword; if the basic keywords exist in the text content, determining that the ith keyword model is matched with the text content, wherein i is a positive integer;
or, the detecting unit 450a is specifically configured to, for an ith keyword model, search the basic keywords included in the ith keyword model in the text content when the ith keyword model includes at least two basic keywords and a logical relation character; if at least one basic keyword is found in the text content, detecting whether the found basic keyword conforms to the logic relationship represented by the logic relationship symbol; and if the found basic keywords accord with the logic relation represented by the logic relation symbol, determining that the ith keyword model is matched with the text content, wherein i is a positive integer.
In summary, the compliance check device provided in this embodiment detects whether the target client belongs to an abnormal client according to the historical behavior record of the target client, converts the service record related to the target client into a text content when the target client is detected to belong to the abnormal client, then detects whether the service record meets the service specification according to the text content, and provides the service record and/or the text content that does not meet the service specification to the quality control staff; the problem that in the prior art, a random extraction mode is adopted, a large number of missed detection conditions exist, and the efficiency is low is solved; on the one hand, the occurrence of the condition of missing inspection is fully reduced, on the other hand, the quality inspection personnel only need to recheck the service record which is detected as not compliant by the system and is provided for the quality inspection personnel, so that the quality inspection personnel can inspect the service record in a targeted manner, and the inspection efficiency is improved. In addition, the abnormal client is used as a preliminary screening condition, the processing amount of the voice-to-text system is reduced, text conversion processing is not needed to be carried out on each service record, and therefore compliance checking efficiency is improved.
In addition, different abnormal detection conditions are set, and under the condition that the target customer is the abnormal customer, the abnormal customer classification to which the target customer belongs is determined at the same time, so that the classified management of the abnormal customer is realized, and convenience is brought to the follow-up compliance inspection of quality inspection personnel.
It should be noted that: the compliance checking device for service recording provided in the above embodiment is only illustrated by the division of the above functional modules, and in practical applications, the above function allocation may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the compliance checking device and the method embodiment of the compliance checking method provided by the above embodiments belong to the same concept, and the specific implementation process thereof is detailed in the method embodiment and will not be described herein again.
Fig. 6 is a schematic structural diagram of a server according to an embodiment of the present invention. The server is used for implementing the compliance check method of the service recording provided in the embodiment. Specifically, the method comprises the following steps:
the server 600 includes a Central Processing Unit (CPU)601, a system memory 604 including a Random Access Memory (RAM)602 and a Read Only Memory (ROM)603, and a system bus 605 connecting the system memory 604 and the central processing unit 601. The server 600 also includes a basic input/output system (I/O system) 606, which facilitates the transfer of information between devices within the computer, and a mass storage device 607, which stores an operating system 613, application programs 614, and other program modules 615.
The basic input/output system 606 includes a display 608 for displaying information and an input device 609 such as a mouse, keyboard, etc. for a user to input information. Wherein the display 608 and the input device 609 are connected to the central processing unit 601 through an input output controller 610 connected to the system bus 605. The basic input/output system 606 may also include an input/output controller 610 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 610 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 607 is connected to the central processing unit 601 through a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer-readable media provide non-volatile storage for the server 600. That is, the mass storage device 607 may include a computer-readable medium (not shown) such as a hard disk or CD-ROM drive.
Without loss of generality, the computer-readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the foregoing. The system memory 604 and mass storage device 607 described above may be collectively referred to as memory.
The server 600 may also operate as a remote computer connected to a network via a network, such as the internet, in accordance with various embodiments of the present invention. That is, the server 600 may be connected to the network 612 through the network interface unit 611 connected to the system bus 605, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 611.
The memory also includes one or more programs stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for:
acquiring a historical behavior record of a target client;
detecting whether the target customer belongs to an abnormal customer according to the historical behavior record;
if the target customer belongs to the abnormal customer, obtaining a service record related to the target customer from a call center;
converting the service recording into text content;
detecting whether the service record meets a service specification according to the text content, wherein the service specification refers to a specification requirement made on the service of an operator of the call center;
and if the service record does not accord with the service specification, storing the service record and/or the text content to a target position, wherein the target position is used for storing the service record and/or the text content for quality testing personnel to recheck.
Given the above first possible implementation, in a second possible implementation provided as a basis for the first possible implementation, the historical behavior record includes a historical transaction record and/or a historical call record, the historical transaction record includes at least one of an income/income record, a leveling record, a profit/loss record and a transaction number, and the historical call record includes a call number and/or a complaint number; accordingly, the memory of the server further contains instructions for:
detecting whether the deposit and withdrawal record meets a first preset condition; if the deposit-withdrawal record meets the first preset condition, determining that the target customer belongs to a deposit-withdrawal abnormal customer; and/or the presence of a gas in the gas,
detecting whether the leveling record meets a second preset condition; if the leveling record meets the second preset condition, determining that the target customer belongs to an abnormal operation customer; and/or the presence of a gas in the gas,
detecting whether the profit-loss record meets a third preset condition; if the profit-loss record meets the third preset condition, determining that the target customer belongs to a profit-loss abnormal customer; and/or the presence of a gas in the gas,
detecting whether the transaction times meet a fourth preset condition; if the transaction times meet the fourth preset condition, determining that the target customer belongs to a transaction abnormal customer; and/or the presence of a gas in the gas,
detecting whether the number of calls meets a fifth preset condition or not; if the number of calls meets the fifth preset condition, determining that the target customer belongs to a customer with abnormal calls; and/or the presence of a gas in the gas,
detecting whether the complaint times meet a sixth preset condition; and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
In a third possible implementation manner provided as the basis for the second possible implementation manner, the memory of the server further includes instructions for performing the following operations:
storing the service recording and/or the text content to the corresponding classification of the target position according to the abnormal client classification of the target client;
wherein the abnormal customer classification comprises at least one of the abnormal deposit and withdrawal customer, the abnormal operation customer, the abnormal profit and loss customer, the abnormal transaction customer, the abnormal call customer and the complaint customer.
In a fourth possible implementation manner provided on the basis of any one of the first to third possible implementation manners, the memory of the server further includes instructions for performing the following operations:
detecting whether a keyword model matched with the text content exists in n preset keyword models or not; the keyword model comprises a basic keyword, or the keyword model comprises at least two basic keywords and a logic relation character used for representing the logic relation between the at least two basic keywords, and n is a positive integer;
and if the keyword model matched with the text content exists in the n keyword models, determining that the service recording does not accord with the service specification.
In a fifth possible implementation manner provided as the basis of the fourth possible implementation manner, the memory of the server further includes instructions for performing the following operations:
for the ith keyword model, detecting whether the basic keyword exists in the text content or not under the condition that the ith keyword model comprises the basic keyword; if the basic keywords exist in the text content, determining that the ith keyword model is matched with the text content, wherein i is a positive integer;
or,
for an ith keyword model, under the condition that the ith keyword model comprises at least two basic keywords and a logical relation character, searching the basic keywords contained in the ith keyword model in the text content; if at least one basic keyword is found in the text content, detecting whether the found basic keyword conforms to the logic relationship represented by the logic relationship symbol; and if the found basic keywords accord with the logic relation represented by the logic relation symbol, determining that the ith keyword model is matched with the text content, wherein i is a positive integer.
It should be understood that, as used herein, the singular forms "a," "an," "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A compliance check method of service records, which is used for screening service records in the field of precious metal, stock or financial investment service for compliance check of quality inspection personnel, the method comprising:
acquiring a historical behavior record of a target client, wherein the historical behavior record comprises a historical transaction record and/or a historical call record, the historical behavior record is used for reflecting the historical transaction behavior of the target client, the historical call record is used for reflecting the historical call behavior of the target client, and the target client is a user requesting service provided by an operator of a call center;
detecting whether the target customer belongs to an abnormal customer according to the historical behavior record, wherein the abnormal customer refers to a customer with abnormal transaction condition and/or abnormal call condition in the historical behavior record, and the abnormal customer comprises at least one of the following: abnormal clients of deposit and withdrawal detected based on the deposit and withdrawal record, abnormal clients of operation detected based on the build-up flat warehouse record, abnormal clients of profit and loss detected based on the profit and loss record, abnormal clients of transaction detected based on the transaction times, abnormal clients of call detected based on the call times and complaint clients detected based on the complaint times;
if the target customer belongs to the abnormal customer, obtaining a service record related to the target customer from a call center;
converting the service recording into text content;
detecting whether the service record meets a service specification according to the text content, wherein the service specification refers to a specification requirement made on the service of an operator of the call center;
if the service record does not meet the service specification, storing the service record and/or the text content to a corresponding classification of a target position according to the abnormal customer classification to which the target customer belongs, wherein the target position is used for storing the service record and/or the text content for rechecking by the quality testing personnel; wherein the abnormal customer classification comprises at least one of the abnormal deposit and withdrawal customer, the abnormal operation customer, the abnormal profit and loss customer, the abnormal transaction customer, the abnormal call customer and the complaint customer.
2. The method of claim 1, wherein the historical transaction record comprises at least one of the cash-in and cash-out record, the flat-out record, the profit-loss record, and the number of transactions, and wherein the historical call record comprises the number of calls and/or the number of complaints;
the detecting whether the target customer belongs to an abnormal customer according to the historical behavior record comprises the following steps:
detecting whether the deposit and withdrawal record meets a first preset condition; if the deposit-withdrawal record meets the first preset condition, determining that the target customer belongs to the abnormal deposit-withdrawal customer; and/or the presence of a gas in the gas,
detecting whether the leveling record meets a second preset condition; if the leveling record meets the second preset condition, determining that the target customer belongs to the abnormal operation customer; and/or the presence of a gas in the gas,
detecting whether the profit-loss record meets a third preset condition; if the profit-loss record meets the third preset condition, determining that the target customer belongs to the profit-loss abnormal customer; and/or the presence of a gas in the gas,
detecting whether the transaction times meet a fourth preset condition; if the transaction times meet the fourth preset condition, determining that the target customer belongs to the transaction abnormal customer; and/or the presence of a gas in the gas,
detecting whether the number of calls meets a fifth preset condition or not; if the number of calls meets the fifth preset condition, determining that the target customer belongs to the abnormal call customer; and/or the presence of a gas in the gas,
detecting whether the complaint times meet a sixth preset condition; and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
3. The method according to claim 1 or 2, wherein the detecting whether the service recording complies with a service specification according to the text content comprises:
detecting whether a keyword model matched with the text content exists in n preset keyword models or not; the keyword model comprises a basic keyword, or the keyword model comprises at least two basic keywords and a logic relation character used for representing the logic relation between the at least two basic keywords, and n is a positive integer;
and if the keyword model matched with the text content exists in the n keyword models, determining that the service recording does not accord with the service specification.
4. The method according to claim 3, wherein the detecting whether there is a keyword model matching the text content in the preset n keyword models comprises:
for the ith keyword model, detecting whether the basic keyword exists in the text content or not under the condition that the ith keyword model comprises the basic keyword; if the basic keywords exist in the text content, determining that the ith keyword model is matched with the text content, wherein i is a positive integer;
or,
for an ith keyword model, under the condition that the ith keyword model comprises at least two basic keywords and a logical relation character, searching the basic keywords contained in the ith keyword model in the text content; if at least one basic keyword is found in the text content, detecting whether the found basic keyword conforms to the logic relationship represented by the logic relationship symbol; and if the found basic keywords accord with the logic relation represented by the logic relation symbol, determining that the ith keyword model is matched with the text content, wherein i is a positive integer.
5. A compliance check device for service recordings, the device being used for screening service recordings in the field of precious metal, stock or financial investment services for compliance checking by quality testing personnel, the device comprising:
the system comprises a record acquisition module, a call center processing module and a call center processing module, wherein the record acquisition module is used for acquiring historical behavior records of a target client, the historical behavior records comprise historical transaction records and/or historical call records, the historical behavior records are used for reflecting historical transaction behaviors of the target client, the historical call records are used for reflecting historical call behaviors of the target client, and the target client is a user requesting services provided by an operator of the call center;
an abnormal detection module, configured to detect whether the target customer belongs to an abnormal customer according to the historical behavior record, where the abnormal customer is a customer with an abnormal transaction condition and/or an abnormal call condition in the historical behavior record, and the abnormal customer includes at least one of the following: abnormal clients of deposit and withdrawal detected based on the deposit and withdrawal record, abnormal clients of operation detected based on the build-up flat warehouse record, abnormal clients of profit and loss detected based on the profit and loss record, abnormal clients of transaction detected based on the transaction times, abnormal clients of call detected based on the call times and complaint clients detected based on the complaint times;
the recording acquisition module is used for acquiring a service recording related to the target customer from a call center under the condition that the target customer belongs to the abnormal customer;
the recording conversion module is used for converting the service recording into text content;
a compliance detection module, configured to detect whether the service record meets a service specification according to the text content, where the service specification refers to a specification requirement made for a service of an operator of the call center;
the storage module is used for storing the service record and/or the text content to a corresponding classification of a target position according to the abnormal customer classification to which the target customer belongs under the condition that the service record does not accord with the service specification, wherein the target position is used for storing the service record and/or the text content for rechecking by the quality testing personnel; wherein the abnormal customer classification comprises at least one of the abnormal deposit and withdrawal customer, the abnormal operation customer, the abnormal profit and loss customer, the abnormal transaction customer, the abnormal call customer and the complaint customer.
6. The apparatus of claim 5, wherein the historical transaction record comprises at least one of the cash-in and cash-out record, the flat-out record, the profit-loss record, and the number of transactions, and wherein the historical call record comprises the number of calls and/or the number of complaints;
the anomaly detection module includes:
the first detection unit is used for detecting whether the deposit and withdrawal record meets a first preset condition or not; if the deposit-withdrawal record meets the first preset condition, determining that the target customer belongs to the abnormal deposit-withdrawal customer; and/or the presence of a gas in the gas,
the second detection unit is used for detecting whether the leveling record meets a second preset condition; if the leveling record meets the second preset condition, determining that the target customer belongs to the abnormal operation customer; and/or the presence of a gas in the gas,
the third detection unit is used for detecting whether the profit and loss records meet a third preset condition or not; if the profit-loss record meets the third preset condition, determining that the target customer belongs to the profit-loss abnormal customer; and/or the presence of a gas in the gas,
the fourth detection unit is used for detecting whether the transaction times meet a fourth preset condition or not; if the transaction times meet the fourth preset condition, determining that the target customer belongs to the transaction abnormal customer; and/or the presence of a gas in the gas,
a fifth detecting unit, configured to detect whether the number of times of call meets a fifth predetermined condition; if the number of calls meets the fifth preset condition, determining that the target customer belongs to the abnormal call customer; and/or the presence of a gas in the gas,
a sixth detecting unit, configured to detect whether the number of complaints meets a sixth predetermined condition; and if the number of complaints meets the sixth preset condition, determining that the target customer belongs to the complaint customer.
7. The apparatus of claim 5 or 6, wherein the compliance detection module comprises:
the detection unit is used for detecting whether a keyword model matched with the text content exists in preset n keyword models or not; the keyword model comprises a basic keyword, or the keyword model comprises at least two basic keywords and a logic relation character used for representing the logic relation between the at least two basic keywords, and n is a positive integer;
and the determining unit is used for determining that the service sound recording does not accord with the service specification under the condition that the keyword model matched with the text content exists in the n keyword models.
8. The apparatus of claim 7,
the detection unit is specifically configured to, for an ith keyword model, detect whether the text content includes a basic keyword or not when the ith keyword model includes the basic keyword; if the basic keywords exist in the text content, determining that the ith keyword model is matched with the text content, wherein i is a positive integer;
or,
the detection unit is specifically configured to, for an ith keyword model, search the basic keywords included in the ith keyword model in the text content when the ith keyword model includes at least two basic keywords and a logical relation character; if at least one basic keyword is found in the text content, detecting whether the found basic keyword conforms to the logic relationship represented by the logic relationship symbol; and if the found basic keywords accord with the logic relation represented by the logic relation symbol, determining that the ith keyword model is matched with the text content, wherein i is a positive integer.
9. A computer-readable storage medium, characterized in that a program for implementing the compliance checking method of service sound recording according to any one of claims 1 to 4 is stored in the computer-readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510500179.1A CN105187674B (en) | 2015-08-14 | 2015-08-14 | Compliance checking method and device for service recording |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510500179.1A CN105187674B (en) | 2015-08-14 | 2015-08-14 | Compliance checking method and device for service recording |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105187674A CN105187674A (en) | 2015-12-23 |
| CN105187674B true CN105187674B (en) | 2020-02-14 |
Family
ID=54909511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510500179.1A Active CN105187674B (en) | 2015-08-14 | 2015-08-14 | Compliance checking method and device for service recording |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105187674B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886951B (en) * | 2016-09-29 | 2021-07-23 | 百度在线网络技术（北京）有限公司 | Voice detection method, device and equipment |
| CN108491388B (en) * | 2018-03-22 | 2021-02-23 | 平安科技（深圳）有限公司 | Data set acquisition method, classification method, device, equipment and storage medium |
| CN108737667B (en) * | 2018-05-03 | 2021-09-10 | 平安科技（深圳）有限公司 | Voice quality inspection method and device, computer equipment and storage medium |
| CN110598008B (en) * | 2018-06-13 | 2023-08-18 | 杭州海康威视系统技术有限公司 | Method and device for detecting quality of recorded data and storage medium |
| CN109472487A (en) * | 2018-11-02 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Video quality detecting method, device, computer equipment and storage medium |
| CN109902937B (en) * | 2019-01-31 | 2024-07-19 | 平安科技（深圳）有限公司 | Quality inspection method and device for task data, computer equipment and storage medium |
| CN109902957B (en) * | 2019-02-28 | 2022-12-09 | 腾讯科技（深圳）有限公司 | Data processing method and device |
| CN110288192A (en) * | 2019-05-23 | 2019-09-27 | 平安科技（深圳）有限公司 | Quality detecting method, device, equipment and storage medium based on multiple Checking models |
| CN111128233B (en) * | 2019-10-12 | 2024-06-25 | 中国平安财产保险股份有限公司 | Recording detection method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456344A (en) * | 2010-10-22 | 2012-05-16 | 中国电信股份有限公司 | System and method for analyzing customer behavior characteristic based on speech recognition technique |
| CN102622552A (en) * | 2012-04-12 | 2012-08-01 | 焦点科技股份有限公司 | Detection method and detection system for fraud access to business to business (B2B) platform based on data mining |
| CN103235828A (en) * | 2013-05-13 | 2013-08-07 | 中科数据技术(苏州)有限公司 | Grade analyzing and adjusting method of indexes of information data score card |
| CN104598579A (en) * | 2015-01-14 | 2015-05-06 | 北京京东尚科信息技术有限公司 | Automatic question and answer method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7937302B1 (en) * | 2002-11-20 | 2011-05-03 | The Pnc Financial Services Group, Inc. | Methods and systems for monitoring, analyzing and reporting information in association with collateralized financial instruments |
-
2015
- 2015-08-14 CN CN201510500179.1A patent/CN105187674B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456344A (en) * | 2010-10-22 | 2012-05-16 | 中国电信股份有限公司 | System and method for analyzing customer behavior characteristic based on speech recognition technique |
| CN102622552A (en) * | 2012-04-12 | 2012-08-01 | 焦点科技股份有限公司 | Detection method and detection system for fraud access to business to business (B2B) platform based on data mining |
| CN103235828A (en) * | 2013-05-13 | 2013-08-07 | 中科数据技术(苏州)有限公司 | Grade analyzing and adjusting method of indexes of information data score card |
| CN104598579A (en) * | 2015-01-14 | 2015-05-06 | 北京京东尚科信息技术有限公司 | Automatic question and answer method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105187674A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105187674B (en) | Compliance checking method and device for service recording | |
| CN105141787A (en) | Service record compliance checking method and device | |
| CN108763499B (en) | Call quality inspection method, device, equipment and storage medium based on intelligent voice | |
| US11714793B2 (en) | Systems and methods for providing searchable customer call indexes | |
| US10446135B2 (en) | System and method for semantically exploring concepts | |
| US10049661B2 (en) | System and method for analyzing and classifying calls without transcription via keyword spotting | |
| US8326643B1 (en) | Systems and methods for automated phone conversation analysis | |
| US9571652B1 (en) | Enhanced diarization systems, media and methods of use | |
| US20160142534A1 (en) | Systems, methods, and media for determining fraud patterns and creating fraud behavioral models | |
| CN111831875B (en) | Data processing method, device, equipment and storage medium | |
| CN110598008A (en) | Data quality inspection method and device for recorded data and storage medium | |
| CN110310127B (en) | Recording acquisition method, recording acquisition device, computer equipment and storage medium | |
| KR20160039273A (en) | System and method for discovering and exploring concepts | |
| US8452841B2 (en) | Text chat for at-risk customers | |
| CN112734352A (en) | Document auditing method and device based on data dimensionality | |
| CN113283814A (en) | Business processing efficiency determination method and device, electronic equipment and readable storage medium | |
| CN107273423A (en) | Multimedia message data processing method, device and system | |
| CN105208226A (en) | Service recording compliance check method and device | |
| CN112347510B (en) | Desensitizing method and desensitizing device | |
| WO2022173045A1 (en) | Information processing device | |
| CN115905243A (en) | Data table updating method, electronic device and storage medium | |
| CN113869872A (en) | Method, system, electronic device and medium for automatically generating work log | |
| CN117493420A (en) | Financial cloud data processing method, device, equipment and medium | |
| CN115914463A (en) | Risk detection method and device and electronic equipment | |
| CN112200655A (en) | Application auditing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201700 Qingpu District, Shanghai green Ping Road, No. 1, building 153, room C, room 1, Applicant after: Shanghai silver competition computer science and Technology Co., Ltd. Address before: 201700 Qingpu District, Shanghai green Ping Road, No. 1, building 153, room C, room 1, Applicant before: SHANGHAI YINTIANXIA TECHNOLOGY CO., LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210408 Address after: 201702 room 295, area G, 2nd floor, No.158 Shuanglian Road, Xujing Town, Qingpu District, Shanghai Patentee after: SHANGHAI JINDASHI NETWORK TECHNOLOGY Co.,Ltd. Address before: 201700 room 153, area C, 1st floor, building 1, No. 1362, Huqingping Road, Qingpu District, Shanghai Patentee before: SHANGHAI YINSAI COMPUTER TECHNOLOGY Co.,Ltd. |