CN105187674A - Compliance checking method and device for service recorded sound - Google Patents
Compliance checking method and device for service recorded sound Download PDFInfo
- Publication number
- CN105187674A CN105187674A CN201510500179.1A CN201510500179A CN105187674A CN 105187674 A CN105187674 A CN 105187674A CN 201510500179 A CN201510500179 A CN 201510500179A CN 105187674 A CN105187674 A CN 105187674A
- Authority
- CN
- China
- Prior art keywords
- text
- service
- record
- keyword
- 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.)
- Granted
Links
Abstract
The invention discloses a compliance checking method and device for service recorded sound, and belongs to the technical field of communication. The method comprises the following steps: detecting whether a target customer belongs to an unusual customer or not according to a history behavior record of the target customer; if the target customer belongs to the unusual customer, acquiring service recorded sound relevant to the target customer from a call center; converting the service recorded sound into text content; detecting whether the service recorded sound conforms to a service specification or not according to the text content; and if the service recorded sound does not conform to the service specification, storing the service recorded sound and/or the text content to a target location. Through adoption of the compliance checking method and device, the problems of the presence of a large number of missed detection situations and low efficiency due to adoption of a random drawing way in the prior art are solved. On one aspect, the missed detection situations are fully reduced. On the other aspect, the service recorded sound which is detected to be non-conforming service recorded sound is supplied to quality control personnel, and the quality control personnel only needs to perform re-checking, so that the quality control personnel can perform checking in a targeted way, and the checking efficiency is increased.
Description
Technical field
The present invention relates to communication technical field, particularly a kind of conjunction rule inspection method and device of serving recording.
Background technology
Call center refers to and utilizes modern communication and computer technology, processes the operation operationlocation of a large amount of phone incoming call and call business.Such as, common carrier, bank and the enterprise etc. that some relate to promoting service all set up call center, providing business consultation to client, handle and the service such as complaint.
In order to improve the service quality of the operator of call center, guaranteeing that the word term of operator meets service regulation, needing to check the service recording of operator.In the prior art, consider the service recording substantial amounts of call center, adopt the mode randomly drawing service recording.From a large amount of services recording, randomly draw some service recording by quality inspection personnel or system, then by quality inspection personnel, the service recording extracted is listened to and distinguished, check whether it meets service regulation.
In the process realizing the embodiment of the present invention, inventor finds prior art, and at least there are the following problems: on the one hand, and the mode randomly drawed can cause a large amount of undetected situation to occur; On the other hand, the service being supplied to quality inspection personnel often major part of recording is the service recording of closing rule, and only have fraction to be the service recording not conforming to rule, this just causes quality inspection personnel to lack specific aim when checking, checking efficiency is on the low side.
Summary of the invention
Adopting to solve prior art the mode randomly drawed, there is a large amount of undetected situation and inefficient problem, embodiments provide a kind of conjunction rule inspection method and device of serving recording.Described technical scheme is as follows:
First aspect, provide a kind of conjunction rule inspection method of serving recording, described method comprises:
Obtain the historical behavior record of target customer;
Detect described target customer according to described historical behavior record and whether belong to unusual customers;
If described target customer belongs to described unusual customers, then obtain the service relevant to described target customer from call center and record;
Described service recording is converted to content of text;
Detect described service recording according to described content of text and whether meet service regulation, described service regulation refers to the code requirement formulated the service of the operator of described call center;
If described service recording does not meet described service regulation, then described service recording and/or described content of text are stored to target location, described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
Alternatively, described historical behavior record comprises historical transaction record and/or history message registration, described historical transaction record comprises at least one in gold record of coming in and going out, storehouse, Jianping record, profit and loss record and transaction count, and described history message registration comprises talk times and/or complains number of times;
Describedly detect described target customer according to described historical behavior record and whether belong to unusual customers, comprising:
Detect described discrepancy gold record and whether meet the first predetermined condition; If described discrepancy gold record meets described first predetermined condition, then determine that described target customer belongs to the gold abnormality client that comes in and goes out; And/or,
Detect storehouse, described Jianping record and whether meet the second predetermined condition; If storehouse, described Jianping record meets described second predetermined condition, then determine that described target customer belongs to operation exception client; And/or,
Detect described profit and loss record and whether meet the 3rd predetermined condition; If described profit and loss record meets described 3rd predetermined condition, then determine that described target customer belongs to profit and loss unusual customers; And/or,
Detect described transaction count and whether meet the 4th predetermined condition; If described transaction count meets described 4th predetermined condition, then determine that described target customer belongs to transaction unusual customers; And/or,
Detect described talk times and whether meet the 5th predetermined condition; If described talk times meets described 5th predetermined condition, then determine that described target customer belongs to call unusual customers; And/or,
Detect described complaint number of times and whether meet the 6th predetermined condition; If described complaint number of times meets described 6th predetermined condition, then determine that described target customer belongs to and complain client.
Alternatively, described described service recording and/or described content of text are stored to target location, comprise:
Unusual customers classification belonging to described target customer, under being stored to the correspondence classification of described target location by described service recording and/or described content of text;
Wherein, described unusual customers is classified at least one comprised in described discrepancy gold abnormality client, described operation exception client, described profit and loss unusual customers, described transaction unusual customers, described call unusual customers and described complaint client.
Alternatively, describedly detect described service according to described content of text and record whether meet service regulation, comprising:
Detect in n the keyword models preset and whether there is the keyword models matched with described content of text; Wherein, described keyword models comprises a basic keyword, or described keyword models comprises at least two basic keywords and the logical relation symbol for the logical relation between at least two basic keywords described in representing, n is positive integer;
If there is the keyword models matched with described content of text in a described n keyword models, then determine that described service recording does not meet described service regulation.
Alternatively, whether there is the keyword models matched with described content of text in n the keyword models that described detection is preset, comprising:
For i-th keyword models, when described i-th keyword models comprises a basic keyword, detect in described content of text and whether there is described basic keyword; If there is described basic keyword in described content of text, then determine that described i-th keyword models and described content of text match, i is positive integer;
Or,
For i-th keyword models, when described i-th keyword models comprises at least two basic keywords and logical relation symbol, in described content of text, search the described basic keyword that described i-th keyword models comprises; If find basic keyword described at least one in described content of text, then detect the described basic keyword found whether meet described logical relation symbol represented by logical relation; If the described basic keyword found meets the logical relation represented by described logical relation symbol, then determine that described i-th keyword models and described content of text match, i is positive integer.
Second aspect, provide a kind of conjunction rule testing fixture of serving recording, described device comprises:
Record acquisition module, for obtaining the historical behavior record of target customer;
Whether abnormality detection module, belong to unusual customers for detecting described target customer according to described historical behavior record;
Recording acquisition module, for when described target customer belongs to described unusual customers, obtains the service relevant to described target customer and records from call center;
Recording modular converter, for being converted to content of text by described service recording;
Close rule detection module, whether meet service regulation for detecting described service recording according to described content of text, described service regulation refers to the code requirement formulated the service of the operator of described call center;
Memory module, for when described service recording does not meet described service regulation, described service recording and/or described content of text are stored to target location, and described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
Alternatively, described historical behavior record comprises historical transaction record and/or history message registration, described historical transaction record comprises at least one in gold record of coming in and going out, storehouse, Jianping record, profit and loss record and transaction count, and described history message registration comprises talk times and/or complains number of times;
Described abnormality detection module, comprising:
Whether the first detecting unit, meet the first predetermined condition for detecting described discrepancy gold record; If described discrepancy gold record meets described first predetermined condition, then determine that described target customer belongs to the gold abnormality client that comes in and goes out; And/or,
Whether the second detecting unit, meet the second predetermined condition for detecting storehouse, described Jianping record; If storehouse, described Jianping record meets described second predetermined condition, then determine that described target customer belongs to operation exception client; And/or,
Whether the 3rd detecting unit, meet the 3rd predetermined condition for detecting described profit and loss record; If described profit and loss record meets described 3rd predetermined condition, then determine that described target customer belongs to profit and loss unusual customers; And/or,
Whether the 4th detecting unit, meet the 4th predetermined condition for detecting described transaction count; If described transaction count meets described 4th predetermined condition, then determine that described target customer belongs to transaction unusual customers; And/or,
Whether the 5th detecting unit, meet the 5th predetermined condition for detecting described talk times; If described talk times meets described 5th predetermined condition, then determine that described target customer belongs to call unusual customers; And/or,
Whether the 6th detecting unit, meet the 6th predetermined condition for detecting described complaint number of times; If described complaint number of times meets described 6th predetermined condition, then determine that described target customer belongs to and complain client.
Alternatively, described memory module, specifically for the unusual customers classification belonging to described target customer, under being stored to the correspondence classification of described target location by described service recording and/or described content of text;
Wherein, described unusual customers is classified at least one comprised in described discrepancy gold abnormality client, described operation exception client, described profit and loss unusual customers, described transaction unusual customers, described call unusual customers and described complaint client.
Alternatively, described conjunction rule detection module, comprising:
Detecting unit, for detecting the keyword models whether existing in a default n keyword models and match with described content of text; Wherein, described keyword models comprises a basic keyword, or described keyword models comprises at least two basic keywords and the logical relation symbol for the logical relation between at least two basic keywords described in representing, n is positive integer;
Determining unit, for there is the keyword models matched with described content of text in a described n keyword models, determines that described service recording does not meet described service regulation.
Alternatively, described detecting unit, specifically for for i-th keyword models, when described i-th keyword models comprises a basic keyword, detects in described content of text and whether there is described basic keyword; If there is described basic keyword in described content of text, then determine that described i-th keyword models and described content of text match, i is positive integer;
Or, described detecting unit, specifically for for i-th keyword models, when described i-th keyword models comprises at least two basic keywords and logical relation symbol, in described content of text, search the described basic keyword that described i-th keyword models comprises; If find basic keyword described at least one in described content of text, then detect the described basic keyword found whether meet described logical relation symbol represented by logical relation; If the described basic keyword found meets the logical relation represented by described logical relation symbol, then determine that described i-th keyword models and described content of text match, i is positive integer.
The beneficial effect that the technical scheme that the embodiment of the present invention provides is brought comprises:
Whether unusual customers is belonged to by detecting this target customer according to the historical behavior record of target customer, and when detecting that this target customer belongs to unusual customers, the service relevant to this target customer is recorded and is converted to content of text, then whether meet service regulation according to text content detection service recording, and the service recording and/or content of text that do not meet service regulation are supplied to quality inspection personnel; Solve prior art and adopt the mode randomly drawed, there is a large amount of undetected situation and inefficient problem; Substantially reduce undetected situation on the one hand to occur, another aspect is that the service not conforming to rule is recorded owing to providing to quality inspection personnel by systems axiol-ogy, quality inspection personnel only needs to carry out this checking, and contributes to quality inspection personnel and checks targetedly, improves checking efficiency.In addition, be primary dcreening operation condition with unusual customers, contribute to reducing voice and to lard speech with literary allusions the treating capacity of native system, without the need to present treatment of all larding speech with literary allusions to each service recording, thus improve and close rule checking efficiency.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic diagram of a kind of implementation environment involved by the embodiment of the present invention;
Fig. 2 is the flow chart of the conjunction rule inspection method of the service recording that one embodiment of the invention provides;
Fig. 3 is the flow chart of the conjunction rule inspection method of the service recording that another embodiment of the present invention provides;
Fig. 4 is the block diagram of the conjunction rule testing fixture of the service recording that one embodiment of the invention provides;
Fig. 5 is the block diagram of the conjunction rule testing fixture of the service recording that another embodiment of the present invention provides;
Fig. 6 is the structural representation of the server that one embodiment of the invention provides.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Please refer to Fig. 1, it illustrates the schematic diagram of a kind of implementation environment involved by the embodiment of the present invention.This implementation environment can comprise: CRM (CustomerRelationshipManagement, customer relation management) system 100.In embodiments of the present invention, crm system 100 filters out unusual customers for the historical behavior record according to client, and the service relevant to unusual customers recording is converted to content of text, and detect that the service recording that do not meet service regulation and/or content of text are supplied to quality inspection personnel accordingly, checked by quality inspection personnel.
Alternatively, as shown in Figure 1, can comprise in crm system 100: call center system 120, historical behavior register system 140 and voice are larded speech with literary allusions native system 160.Wherein, call center system 120 is for the treatment of phone incoming call and call business.The service recording of operator is stored in the database of call center system 120.The historical behavior record of client is stored in historical behavior register system 140.Especially, when the technical scheme that the present embodiment provides be applied to the service in noble metal service on investment field recording is carried out closing the practical application scene that rule check time, above-mentioned historical behavior record can comprise historical transaction record and/or history message registration.Voice lard speech with literary allusions native system 160 for service recording is converted to content of text.
Said system framework can be realized by a station server, and the server cluster that also can be made up of some station servers realizes.For the purpose of simplifying the description, below in each embodiment of the method, except specified otherwise, with the executive agent of each step for server is illustrated, but restriction is not formed to this.
Please refer to Fig. 2, it illustrates the flow chart of the conjunction rule inspection method of the service recording that one embodiment of the invention provides.This conjunction rule inspection method can comprise following several step:
Step 202, obtains the historical behavior record of target customer.
Step 204, detects target customer according to historical behavior record and whether belongs to unusual customers.
Step 206, if target customer belongs to unusual customers, then obtains the service recording relevant to target customer from call center.
Step 208, is converted to content of text by the service got recording.
Step 210, detect service recording according to content of text and whether meet service regulation, this service regulation refers to the code requirement formulated the service of the operator of call center.
Step 212, if service recording does not meet service regulation, is then stored to target location by service recording and/or content of text, and this target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
In sum, the conjunction rule inspection method that the present embodiment provides, whether unusual customers is belonged to by detecting this target customer according to the historical behavior record of target customer, and when detecting that this target customer belongs to unusual customers, the service relevant to this target customer is recorded and is converted to content of text, then whether meet service regulation according to text content detection service recording, and the service recording and/or content of text that do not meet service regulation are supplied to quality inspection personnel; Solve prior art and adopt the mode randomly drawed, there is a large amount of undetected situation and inefficient problem; Substantially reduce undetected situation on the one hand to occur, another aspect is that the service not conforming to rule is recorded owing to providing to quality inspection personnel by systems axiol-ogy, quality inspection personnel only needs to carry out this checking, and contributes to quality inspection personnel and checks targetedly, improves checking efficiency.In addition, be primary dcreening operation condition with unusual customers, contribute to reducing voice and to lard speech with literary allusions the treating capacity of native system, without the need to present treatment of all larding speech with literary allusions to each service recording, thus improve and close rule checking efficiency.
Please refer to Fig. 3, it illustrates the flow chart of the conjunction rule inspection method of the service recording that another embodiment of the present invention provides.The present embodiment is applied in implementation environment shown in Fig. 1 with this conjunction rule inspection method and is illustrated.This conjunction rule inspection method can comprise following several step:
Step 301, obtains the historical behavior record of target customer.
In the present embodiment, carry out closing the practical application scene of rule inspection to the service recording in noble metal service on investment field to be applied to, historical behavior record comprises historical transaction record and/or history message registration.Wherein, historical transaction record is for reflecting the historical trading behavior of client, and historical transaction record includes but not limited at least one of coming in and going out in gold record, storehouse, Jianping record, profit and loss record and transaction count; History message registration is for reflecting the history call behavior of client, and history message registration includes but not limited to talk times and/or complains number of times.
Step 302, detects target customer according to historical behavior record and whether belongs to unusual customers.
The difference of the recorded information comprised according to historical behavior record, this step comprises following several possible situation:
1, detect gold record of coming in and going out and whether meet the first predetermined condition, if gold record of coming in and going out meets the first predetermined condition, then determine that target customer belongs to the gold abnormality client that comes in and goes out.
Wherein, gold record of coming in and going out includes but not limited to out the amount of money, enters the amount of money, goes out the gold time, enters the recorded informations such as gold time.In actual applications, gold can be gone out in conjunction with such as wholesale, fully go out the abnormal trading situation of gold and so on, set corresponding first predetermined condition.In one example in which, the first predetermined condition can be set as that the amount of money that goes out that single is concluded the business is greater than 300,000.
2, detect storehouse, Jianping record and whether meet the second predetermined condition, if storehouse, Jianping record meets the second predetermined condition, then determine that target customer belongs to operation exception client.
Wherein, storehouse, Jianping record include but not limited to the time of opening a position, the time of closing a position, number of times of opening a position, the recorded informations such as number of times of closing a position.In actual applications, in conjunction with the abnormal trading situation in such as frequent storehouse, Jianping and so on, corresponding second predetermined condition can be set.In one example in which, the number of times that the second predetermined condition is closed a position again after can being set as opening a position in nearest 2 hours exceedes pre-determined number.
3, detect profit and loss record and whether meet the 3rd predetermined condition, if profit and loss record meets the 3rd predetermined condition, then determine that target customer belongs to profit and loss unusual customers.
Wherein, profit and loss record includes but not limited to the recorded information such as the profit amount of money, deficit, profitable time, loss time, profit number of times, loss number of times.In actual applications, in conjunction with the abnormal trading situation of such as wholesale profit and loss and so on, corresponding 3rd predetermined condition can be set.In one example in which, the 3rd predetermined condition can be set as that the total earnings amount of money or the total loss amount of money are greater than 300,000.
4, detect transaction count and whether meet the 4th predetermined condition, if transaction count meets the 4th predetermined condition, then determine that target customer belongs to transaction unusual customers.
In actual applications, in conjunction with not concluding the business, concluding the business too frequent and so on abnormal trading situation after such as Account activation, corresponding 4th predetermined condition can be set.In one example in which, the 4th predetermined condition can be set as that transaction count is less than pre-determined number.
5, detect talk times and whether meet the 5th predetermined condition, if talk times meets the 5th predetermined piece, then determine that target customer belongs to call unusual customers.
In actual applications, can in conjunction with such as number of pass times too much, too frequent and so on the abnormal communication situation of call, set corresponding 5th predetermined condition.In one example in which, the 5th predetermined condition can be set as that talk times is greater than pre-determined number.
6, detect complaint number of times and whether meet the 6th predetermined condition, if complain number of times to meet the 6th predetermined condition, then determine that target customer belongs to and complain client.
In actual applications, can in conjunction with such as complaining number of times too much, complain too frequent and so on abnormal communication situation, set corresponding 6th predetermined condition.In one example in which, the 6th predetermined condition can be set as complaining number of times to be greater than pre-determined number.
In the present embodiment, by setting different abnormality detection conditions, when confirming that target customer is unusual customers, determine the unusual customers classification belonging to it simultaneously, thus the Classification Management realized unusual customers, for the conjunction rule inspection of follow-up quality inspection personnel provides convenient.
Certainly, the above-mentioned classification for unusual customers is only exemplary and explanatory, and in actual applications, can set the unusual customers of different classification according to the actual requirements, and set corresponding abnormality detection condition, the present embodiment does not do concrete restriction to this.
Step 303, if target customer belongs to unusual customers, then obtains the service recording relevant to target customer from call center.
Alternatively, server obtains the customer ID of target customer, obtains the service corresponding with this customer ID and record from the database of call center.
Step 304, is converted to content of text by the service got recording.
Voice lard speech with literary allusions native system adopt speech recognition technology, service recording is converted to content of text.
In a kind of possible execution mode, the telephonic communication between operator and client can be recorded respectively, also namely serve recording and comprise operator's recording and client's recording.Voice lard speech with literary allusions native system can only by operator recording be converted to content of text, and without the need to client recording process, to reduce treating capacity.
Afterwards, whether server meets service regulation according to text content detection service recording, and this service regulation refers to the code requirement formulated the service of the operator of call center.Specifically, this testing process comprises the steps 305 and step 306.
Step 305, detect in n the keyword models preset whether there is the keyword models matched with content of text, n is positive integer.
There is the possible implementation of the following two kinds in keyword models.
The first, keyword models comprises a basic keyword.Wherein, basic keyword can be the responsive vocabulary that business is relevant, rude term or other service taboo language.Basic keyword can set in advance according to practical application scene.To carry out the practical application scene of closing rule inspection to the service recording in noble metal service on investment field, a certain keyword models can comprise the relevant responsive vocabulary of " transaction " this business; Or, the responsive vocabulary that this business that another keyword models can comprise " closing a position " is relevant; Or, then a keyword models can comprise " brain deficiency " this rude term, etc.
The second, keyword models comprises at least two basic keywords and the logical relation symbol for representing the logical relation between these at least two basic keywords.Wherein, basic keyword can be the responsive vocabulary that business is relevant, rude term or other service taboo language.Logical relation symbol include but not limited to following one or more: with (and) or (or), non-(not), neighbouring (near), afterwards (after), before (before) etc.Basic keyword and logical relation symbol all can set according to practical application scene in advance.Still to carry out the practical application scene of closing rule inspection to the service recording in noble metal service on investment field, a certain keyword models can be " transaction and closes a position ", represents and comprises " transaction " and " closing a position " two basic keywords simultaneously; Or another keyword models can be " transaction or brain deficiency ", represents any one the logic keyword comprised in " transaction " or " brain deficiency ", etc.
A default n keyword models is compared with content of text by server one by one, detects whether there is the keyword models matched with text content.Below, so that i-th keyword models and content of text are compared, to the comparison process corresponding to above-mentioned two kinds of possible implementations, be introduced respectively.Wherein, i is positive integer.
For i-th keyword models, when this i-th keyword models comprises a basic keyword, detect in content of text whether there is this basic keyword; If there is this basic keyword in content of text, then determine that this i-th keyword models and content of text match.Such as, i-th keyword models is " transaction ", then detect in content of text and whether there is " transaction " word, if existence, determine that this i-th keyword models and content of text match; Otherwise, if do not exist, determine that this i-th keyword models does not mate with content of text.
For i-th keyword models, when this i-th keyword models comprises at least two basic keywords and logical relation symbol, in content of text, search the basic keyword that this i-th keyword models comprises; If find at least one basic keyword in content of text, then detect the basic keyword found whether meet logical relation symbol represented by logical relation; If the basic keyword found meets the logical relation represented by logical relation symbol, then determine that this i-th keyword models and content of text match.Such as, i-th keyword models is " transaction and closes a position ", then, when finding " transaction " and " closing a position " this two basic keywords in content of text, determine that this i-th keyword models and content of text match simultaneously; Otherwise, if only find one of them basic keyword or do not find basic keyword, then determine that this i-th keyword models does not mate with content of text.
Certainly, the above-mentioned keyword models exemplified is only exemplary and explanatory, in actual applications, can according to practical application scene and requirements set be more various, complicated or keyword models accurately, the present embodiment does not do concrete restriction to this.
Step 306, if there is the keyword models matched with content of text in n the keyword models preset, then the unusual customers classification belonging to target customer, under being stored to the correspondence classification of target location by service recording and/or content of text.
When there is the keyword models matched with content of text in n the keyword models preset, illustrate that this service recording is not for meeting the service recording of service regulation, this service recording and/or content of text are stored to target location by server, and this target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.Correspondingly, quality inspection personnel can obtain service recording and/or content of text from this target location, manually check, and then confirms whether this service recording closes rule.
In the present embodiment, corresponding different unusual customers classification, target location arranges corresponding classification.By the unusual customers classification belonging to target customer, under service recording being stored to the correspondence classification of target location, realize carrying out Classification Management to service recording according to unusual customers classification, contribute to quality inspection personnel and more targetedly and efficiently the inspection of conjunctions rule is carried out to service recording.
In sum, the conjunction rule inspection method that the present embodiment provides, whether unusual customers is belonged to by detecting this target customer according to the historical behavior record of target customer, and when detecting that this target customer belongs to unusual customers, the service relevant to this target customer is recorded and is converted to content of text, then whether meet service regulation according to text content detection service recording, and the service recording and/or content of text that do not meet service regulation are supplied to quality inspection personnel; Solve prior art and adopt the mode randomly drawed, there is a large amount of undetected situation and inefficient problem; Substantially reduce undetected situation on the one hand to occur, another aspect is that the service not conforming to rule is recorded owing to providing to quality inspection personnel by systems axiol-ogy, quality inspection personnel only needs to carry out this checking, and contributes to quality inspection personnel and checks targetedly, improves checking efficiency.In addition, be primary dcreening operation condition with unusual customers, contribute to reducing voice and to lard speech with literary allusions the treating capacity of native system, without the need to present treatment of all larding speech with literary allusions to each service recording, thus improve and close rule checking efficiency.
In addition, also by the abnormality detection condition that setting is different, when confirming that target customer is unusual customers, determine the unusual customers classification belonging to it simultaneously, thus the Classification Management realized unusual customers, for the conjunction rule inspection of follow-up quality inspection personnel provides convenient.
What need supplementary notes is a bit, in the present embodiment, only carry out closing the practical application scene of rule inspection to the service recording in noble metal service on investment field to be applied to, without loss of generality, the conjunction rule inspection method that the present embodiment provides also can be applicable to other practical application scene, as carried out closing the practical application scene of advising and checking to the service recording in stock investment service field, the practical application scene of closing rule inspection is carried out to the service recording of financial investment service field, etc.
Following is apparatus of the present invention embodiment, may be used for performing the inventive method embodiment.For the details do not disclosed in apparatus of the present invention embodiment, please refer to the inventive method embodiment.
Please refer to Fig. 4, it illustrates the block diagram of the conjunction rule testing fixture of the service recording that one embodiment of the invention provides.This conjunction rule testing fixture can be applied in implementation environment shown in Fig. 1.This conjunction rule testing fixture comprises: record acquisition module 410, abnormality detection module 420, recording acquisition module 430, recording modular converter 440, conjunction rule detection module 450 and memory module 460.
Record acquisition module 410, for obtaining the historical behavior record of target customer.
Abnormality detection module 420, the described historical behavior record for getting according to described record acquisition module 410 detects described target customer and whether belongs to unusual customers.
Recording acquisition module 430, for when described abnormality detection module 420 detects that described target customer belongs to described unusual customers, obtains the service relevant to described target customer and records from call center.
Recording modular converter 440, is converted to content of text for the described service recording got by described recording acquisition module 430.
Close rule detection module 450, described content of text for being converted to according to described recording modular converter 440 detects described service recording and whether meets service regulation, and described service regulation refers to the code requirement formulated the service of the operator of described call center.
Memory module 460, for when described conjunction rule detection module 450 detects that described service recording does not meet described service regulation, described service recording and/or described content of text are stored to target location, and described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
In sum, the conjunction rule testing fixture that the present embodiment provides, whether unusual customers is belonged to by detecting this target customer according to the historical behavior record of target customer, and when detecting that this target customer belongs to unusual customers, the service relevant to this target customer is recorded and is converted to content of text, then whether meet service regulation according to text content detection service recording, and the service recording and/or content of text that do not meet service regulation are supplied to quality inspection personnel; Solve prior art and adopt the mode randomly drawed, there is a large amount of undetected situation and inefficient problem; Substantially reduce undetected situation on the one hand to occur, another aspect is that the service not conforming to rule is recorded owing to providing to quality inspection personnel by systems axiol-ogy, quality inspection personnel only needs to carry out this checking, and contributes to quality inspection personnel and checks targetedly, improves checking efficiency.In addition, be primary dcreening operation condition with unusual customers, contribute to reducing voice and to lard speech with literary allusions the treating capacity of native system, without the need to present treatment of all larding speech with literary allusions to each service recording, thus improve and close rule checking efficiency.
Please refer to Fig. 5, it illustrates the block diagram of the conjunction rule testing fixture of the service recording that another embodiment of the present invention provides.This conjunction rule testing fixture can be applied in implementation environment shown in Fig. 1.This conjunction rule testing fixture comprises: record acquisition module 410, abnormality detection module 420, recording acquisition module 430, recording modular converter 440, conjunction rule detection module 450 and memory module 460.
Record acquisition module 410, for obtaining the historical behavior record of target customer.
Abnormality detection module 420, the described historical behavior record for getting according to described record acquisition module 410 detects described target customer and whether belongs to unusual customers.
Recording acquisition module 430, for when described abnormality detection module 420 detects that described target customer belongs to described unusual customers, obtains the service relevant to described target customer and records from call center.
Recording modular converter 440, is converted to content of text for the described service recording got by described recording acquisition module 430.
Close rule detection module 450, described content of text for being converted to according to described recording modular converter 440 detects described service recording and whether meets service regulation, and described service regulation refers to the code requirement formulated the service of the operator of described call center.
Memory module 460, for when described conjunction rule detection module 450 detects that described service recording does not meet described service regulation, described service recording and/or described content of text are stored to target location, and described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
Alternatively, described historical behavior record comprises historical transaction record and/or history message registration, described historical transaction record comprises at least one in gold record of coming in and going out, storehouse, Jianping record, profit and loss record and transaction count, and described history message registration comprises talk times and/or complains number of times;
Described abnormality detection module 420, comprising:
Whether the first detecting unit 420a, meet the first predetermined condition for detecting described discrepancy gold record; If described discrepancy gold record meets described first predetermined condition, then determine that described target customer belongs to the gold abnormality client that comes in and goes out; And/or,
Whether the second detecting unit 420b, meet the second predetermined condition for detecting storehouse, described Jianping record; If storehouse, described Jianping record meets described second predetermined condition, then determine that described target customer belongs to operation exception client; And/or,
Whether the 3rd detecting unit 420c, meet the 3rd predetermined condition for detecting described profit and loss record; If described profit and loss record meets described 3rd predetermined condition, then determine that described target customer belongs to profit and loss unusual customers; And/or,
Whether the 4th detecting unit 420d, meet the 4th predetermined condition for detecting described transaction count; If described transaction count meets described 4th predetermined condition, then determine that described target customer belongs to transaction unusual customers; And/or,
Whether the 5th detecting unit 420e, meet the 5th predetermined condition for detecting described talk times; If described talk times meets described 5th predetermined condition, then determine that described target customer belongs to call unusual customers; And/or,
Whether the 6th detecting unit 420f, meet the 6th predetermined condition for detecting described complaint number of times; If described complaint number of times meets described 6th predetermined condition, then determine that described target customer belongs to and complain client.
Alternatively, described memory module 460, specifically for the unusual customers classification belonging to described target customer, under being stored to the correspondence classification of described target location by described service recording and/or described content of text;
Wherein, described unusual customers is classified at least one comprised in described discrepancy gold abnormality client, described operation exception client, described profit and loss unusual customers, described transaction unusual customers, described call unusual customers and described complaint client.
Alternatively, described conjunction rule detection module 450, comprising:
Detecting unit 450a, for detecting the keyword models whether existing in a default n keyword models and match with described content of text; Wherein, described keyword models comprises a basic keyword, or described keyword models comprises at least two basic keywords and the logical relation symbol for the logical relation between at least two basic keywords described in representing, n is positive integer;
Determining unit 450b, when there is for detecting at described detecting unit 450a in a described n keyword models keyword models matched with described content of text, determines that described service recording does not meet described service regulation.
Alternatively, described detecting unit 450a, specifically for for i-th keyword models, when described i-th keyword models comprises a basic keyword, detects in described content of text and whether there is described basic keyword; If there is described basic keyword in described content of text, then determine that described i-th keyword models and described content of text match, i is positive integer;
Or, described detecting unit 450a, specifically for for i-th keyword models, when described i-th keyword models comprises at least two basic keywords and logical relation symbol, in described content of text, search the described basic keyword that described i-th keyword models comprises; If find basic keyword described at least one in described content of text, then detect the described basic keyword found whether meet described logical relation symbol represented by logical relation; If the described basic keyword found meets the logical relation represented by described logical relation symbol, then determine that described i-th keyword models and described content of text match, i is positive integer.
In sum, the conjunction rule testing fixture that the present embodiment provides, whether unusual customers is belonged to by detecting this target customer according to the historical behavior record of target customer, and when detecting that this target customer belongs to unusual customers, the service relevant to this target customer is recorded and is converted to content of text, then whether meet service regulation according to text content detection service recording, and the service recording and/or content of text that do not meet service regulation are supplied to quality inspection personnel; Solve prior art and adopt the mode randomly drawed, there is a large amount of undetected situation and inefficient problem; Substantially reduce undetected situation on the one hand to occur, another aspect is that the service not conforming to rule is recorded owing to providing to quality inspection personnel by systems axiol-ogy, quality inspection personnel only needs to carry out this checking, and contributes to quality inspection personnel and checks targetedly, improves checking efficiency.In addition, be primary dcreening operation condition with unusual customers, contribute to reducing voice and to lard speech with literary allusions the treating capacity of native system, without the need to present treatment of all larding speech with literary allusions to each service recording, thus improve and close rule checking efficiency.
In addition, also by the abnormality detection condition that setting is different, when confirming that target customer is unusual customers, determine the unusual customers classification belonging to it simultaneously, thus the Classification Management realized unusual customers, for the conjunction rule inspection of follow-up quality inspection personnel provides convenient.
It should be noted that: the conjunction rule testing fixture of the service recording that above-described embodiment provides, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, internal structure by equipment is divided into different functional modules, to complete all or part of function described above.In addition, the embodiment of the method that inspection method is advised in conjunction rule testing fixture and conjunction that above-described embodiment provides belongs to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
Fig. 6 shows the structural representation of the server that one embodiment of the invention provides.This server is for implementing the conjunction rule inspection method of the service recording provided in above-described embodiment.Specifically:
Described server 600 comprises CPU (CPU) 601, comprises the system storage 604 of random access memory (RAM) 602 and read-only memory (ROM) 603, and the system bus 605 of connected system memory 604 and CPU 601.Described server 600 also comprises the basic input/output (I/O system) 606 of transmission information between each device of helping in computer, and for the mass-memory unit 607 of storage operation system 613, application program 614 and other program modules 615.
Described basic input/output 606 includes the input equipment 609 of the display 608 for showing information and the such as mouse, keyboard and so on for user's input information.Wherein said display 608 and input equipment 609 are all connected to CPU 601 by the IOC 610 being connected to system bus 605.Described basic input/output 606 can also comprise IOC 610 for receiving and processing the input from other equipment multiple such as keyboard, mouse or electronic touch pens.Similarly, IOC 610 also provides the output equipment outputting to display screen, printer or other types.
Described mass-memory unit 607 is connected to CPU 601 by the bulk memory controller (not shown) being connected to system bus 605.Described mass-memory unit 607 and the computer-readable medium that is associated thereof provide non-volatile memories for server 600.That is, described mass-memory unit 607 can comprise the computer-readable medium (not shown) of such as hard disk or CD-ROM drive and so on.
Without loss of generality, described computer-readable medium can comprise computer-readable storage medium and communication media.Computer-readable storage medium comprises the volatibility and non-volatile, removable and irremovable medium that realize for any method or technology that store the information such as such as computer-readable instruction, data structure, program module or other data.Computer-readable storage medium comprises RAM, ROM, EPROM, EEPROM, flash memory or its technology of other solid-state storage, CD-ROM, DVD or other optical storage, cassette, tape, disk storage or other magnetic storage apparatus.Certainly, the known described computer-readable storage medium of those skilled in the art is not limited to above-mentioned several.Above-mentioned system storage 604 and mass-memory unit 607 can be referred to as memory.
According to various embodiments of the present invention, the remote computer that described server 600 can also be connected on network by networks such as such as internets runs.Also namely server 600 can be connected to network 612 by the network interface unit 611 be connected on described system bus 605, in other words, network interface unit 611 also can be used to be connected to network or the remote computer system (not shown) of other types.
Described memory also comprises one or more than one program, and described more than one or one program is stored in memory, and is configured to be performed by more than one or one processor.Above-mentioned more than one or one program package is containing the instruction for carrying out following operation:
Obtain the historical behavior record of target customer;
Detect described target customer according to described historical behavior record and whether belong to unusual customers;
If described target customer belongs to described unusual customers, then obtain the service relevant to described target customer from call center and record;
Described service recording is converted to content of text;
Detect described service recording according to described content of text and whether meet service regulation, described service regulation refers to the code requirement formulated the service of the operator of described call center;
If described service recording does not meet described service regulation, then described service recording and/or described content of text are stored to target location, described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
Suppose that above-mentioned is the first possible execution mode, in the execution mode that the second then provided based on the execution mode that the first is possible is possible, described historical behavior record comprises historical transaction record and/or history message registration, described historical transaction record comprises at least one in gold record of coming in and going out, storehouse, Jianping record, profit and loss record and transaction count, and described history message registration comprises talk times and/or complains number of times; Correspondingly, in the memory of described server, also comprise the instruction for performing following operation:
Detect described discrepancy gold record and whether meet the first predetermined condition; If described discrepancy gold record meets described first predetermined condition, then determine that described target customer belongs to the gold abnormality client that comes in and goes out; And/or,
Detect storehouse, described Jianping record and whether meet the second predetermined condition; If storehouse, described Jianping record meets described second predetermined condition, then determine that described target customer belongs to operation exception client; And/or,
Detect described profit and loss record and whether meet the 3rd predetermined condition; If described profit and loss record meets described 3rd predetermined condition, then determine that described target customer belongs to profit and loss unusual customers; And/or,
Detect described transaction count and whether meet the 4th predetermined condition; If described transaction count meets described 4th predetermined condition, then determine that described target customer belongs to transaction unusual customers; And/or,
Detect described talk times and whether meet the 5th predetermined condition; If described talk times meets described 5th predetermined condition, then determine that described target customer belongs to call unusual customers; And/or,
Detect described complaint number of times and whether meet the 6th predetermined condition; If described complaint number of times meets described 6th predetermined condition, then determine that described target customer belongs to and complain client.
In the third the possible execution mode provided based on the execution mode that the second is possible, in the memory of described server, also comprise the instruction for performing following operation:
Unusual customers classification belonging to described target customer, under being stored to the correspondence classification of described target location by described service recording and/or described content of text;
Wherein, described unusual customers is classified at least one comprised in described discrepancy gold abnormality client, described operation exception client, described profit and loss unusual customers, described transaction unusual customers, described call unusual customers and described complaint client.
In the 4th kind of possible execution mode provided based on any one possible execution mode in the execution mode that the first is possible to the third, in the memory of described server, also comprise the instruction for performing following operation:
Detect in n the keyword models preset and whether there is the keyword models matched with described content of text; Wherein, described keyword models comprises a basic keyword, or described keyword models comprises at least two basic keywords and the logical relation symbol for the logical relation between at least two basic keywords described in representing, n is positive integer;
If there is the keyword models matched with described content of text in a described n keyword models, then determine that described service recording does not meet described service regulation.
In the 5th kind of possible execution mode provided based on the 4th kind of possible execution mode, in the memory of described server, also comprise the instruction for performing following operation:
For i-th keyword models, when described i-th keyword models comprises a basic keyword, detect in described content of text and whether there is described basic keyword; If there is described basic keyword in described content of text, then determine that described i-th keyword models and described content of text match, i is positive integer;
Or,
For i-th keyword models, when described i-th keyword models comprises at least two basic keywords and logical relation symbol, in described content of text, search the described basic keyword that described i-th keyword models comprises; If find basic keyword described at least one in described content of text, then detect the described basic keyword found whether meet described logical relation symbol represented by logical relation; If the described basic keyword found meets the logical relation represented by described logical relation symbol, then determine that described i-th keyword models and described content of text match, i is positive integer.
Should be understood that, use in this article, unless context clearly supports exception, singulative " " (" a ", " an ", " the ") is intended to also comprise plural form.It is to be further understood that the "and/or" used in this article refers to comprise any of more than one or one project listed explicitly and likely combine.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be read-only memory, disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. serve a conjunction rule inspection method for recording, it is characterized in that, described method comprises:
Obtain the historical behavior record of target customer;
Detect described target customer according to described historical behavior record and whether belong to unusual customers;
If described target customer belongs to described unusual customers, then obtain the service relevant to described target customer from call center and record;
Described service recording is converted to content of text;
Detect described service recording according to described content of text and whether meet service regulation, described service regulation refers to the code requirement formulated the service of the operator of described call center;
If described service recording does not meet described service regulation, then described service recording and/or described content of text are stored to target location, described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
2. method according to claim 1, it is characterized in that, described historical behavior record comprises historical transaction record and/or history message registration, described historical transaction record comprises at least one in gold record of coming in and going out, storehouse, Jianping record, profit and loss record and transaction count, and described history message registration comprises talk times and/or complains number of times;
Describedly detect described target customer according to described historical behavior record and whether belong to unusual customers, comprising:
Detect described discrepancy gold record and whether meet the first predetermined condition; If described discrepancy gold record meets described first predetermined condition, then determine that described target customer belongs to the gold abnormality client that comes in and goes out; And/or,
Detect storehouse, described Jianping record and whether meet the second predetermined condition; If storehouse, described Jianping record meets described second predetermined condition, then determine that described target customer belongs to operation exception client; And/or,
Detect described profit and loss record and whether meet the 3rd predetermined condition; If described profit and loss record meets described 3rd predetermined condition, then determine that described target customer belongs to profit and loss unusual customers; And/or,
Detect described transaction count and whether meet the 4th predetermined condition; If described transaction count meets described 4th predetermined condition, then determine that described target customer belongs to transaction unusual customers; And/or,
Detect described talk times and whether meet the 5th predetermined condition; If described talk times meets described 5th predetermined condition, then determine that described target customer belongs to call unusual customers; And/or,
Detect described complaint number of times and whether meet the 6th predetermined condition; If described complaint number of times meets described 6th predetermined condition, then determine that described target customer belongs to and complain client.
3. method according to claim 2, is characterized in that, described described service recording and/or described content of text is stored to target location, comprising:
Unusual customers classification belonging to described target customer, under being stored to the correspondence classification of described target location by described service recording and/or described content of text;
Wherein, described unusual customers is classified at least one comprised in described discrepancy gold abnormality client, described operation exception client, described profit and loss unusual customers, described transaction unusual customers, described call unusual customers and described complaint client.
4. according to the arbitrary described method of claims 1 to 3, it is characterized in that, describedly detect described service according to described content of text and record whether meet service regulation, comprising:
Detect in n the keyword models preset and whether there is the keyword models matched with described content of text; Wherein, described keyword models comprises a basic keyword, or described keyword models comprises at least two basic keywords and the logical relation symbol for the logical relation between at least two basic keywords described in representing, n is positive integer;
If there is the keyword models matched with described content of text in a described n keyword models, then determine that described service recording does not meet described service regulation.
5. method according to claim 4, is characterized in that, whether there is the keyword models matched with described content of text, comprising in n the keyword models that described detection is preset:
For i-th keyword models, when described i-th keyword models comprises a basic keyword, detect in described content of text and whether there is described basic keyword; If there is described basic keyword in described content of text, then determine that described i-th keyword models and described content of text match, i is positive integer;
Or,
For i-th keyword models, when described i-th keyword models comprises at least two basic keywords and logical relation symbol, in described content of text, search the described basic keyword that described i-th keyword models comprises; If find basic keyword described at least one in described content of text, then detect the described basic keyword found whether meet described logical relation symbol represented by logical relation; If the described basic keyword found meets the logical relation represented by described logical relation symbol, then determine that described i-th keyword models and described content of text match, i is positive integer.
6. serve a conjunction rule testing fixture for recording, it is characterized in that, described device comprises:
Record acquisition module, for obtaining the historical behavior record of target customer;
Whether abnormality detection module, belong to unusual customers for detecting described target customer according to described historical behavior record;
Recording acquisition module, for when described target customer belongs to described unusual customers, obtains the service relevant to described target customer and records from call center;
Recording modular converter, for being converted to content of text by described service recording;
Close rule detection module, whether meet service regulation for detecting described service recording according to described content of text, described service regulation refers to the code requirement formulated the service of the operator of described call center;
Memory module, for when described service recording does not meet described service regulation, described service recording and/or described content of text are stored to target location, and described target location is for storing the service recording and/or content of text that supply quality inspection personnel to carry out checking.
7. device according to claim 6, it is characterized in that, described historical behavior record comprises historical transaction record and/or history message registration, described historical transaction record comprises at least one in gold record of coming in and going out, storehouse, Jianping record, profit and loss record and transaction count, and described history message registration comprises talk times and/or complains number of times;
Described abnormality detection module, comprising:
Whether the first detecting unit, meet the first predetermined condition for detecting described discrepancy gold record; If described discrepancy gold record meets described first predetermined condition, then determine that described target customer belongs to the gold abnormality client that comes in and goes out; And/or,
Whether the second detecting unit, meet the second predetermined condition for detecting storehouse, described Jianping record; If storehouse, described Jianping record meets described second predetermined condition, then determine that described target customer belongs to operation exception client; And/or,
Whether the 3rd detecting unit, meet the 3rd predetermined condition for detecting described profit and loss record; If described profit and loss record meets described 3rd predetermined condition, then determine that described target customer belongs to profit and loss unusual customers; And/or,
Whether the 4th detecting unit, meet the 4th predetermined condition for detecting described transaction count; If described transaction count meets described 4th predetermined condition, then determine that described target customer belongs to transaction unusual customers; And/or,
Whether the 5th detecting unit, meet the 5th predetermined condition for detecting described talk times; If described talk times meets described 5th predetermined condition, then determine that described target customer belongs to call unusual customers; And/or,
Whether the 6th detecting unit, meet the 6th predetermined condition for detecting described complaint number of times; If described complaint number of times meets described 6th predetermined condition, then determine that described target customer belongs to and complain client.
8. device according to claim 7, is characterized in that,
Described memory module, specifically for the unusual customers classification belonging to described target customer, under being stored to the correspondence classification of described target location by described service recording and/or described content of text;
Wherein, described unusual customers is classified at least one comprised in described discrepancy gold abnormality client, described operation exception client, described profit and loss unusual customers, described transaction unusual customers, described call unusual customers and described complaint client.
9. according to the arbitrary described device of claim 6 to 8, it is characterized in that, described conjunction rule detection module, comprising:
Detecting unit, for detecting the keyword models whether existing in a default n keyword models and match with described content of text; Wherein, described keyword models comprises a basic keyword, or described keyword models comprises at least two basic keywords and the logical relation symbol for the logical relation between at least two basic keywords described in representing, n is positive integer;
Determining unit, for there is the keyword models matched with described content of text in a described n keyword models, determines that described service recording does not meet described service regulation.
10. device according to claim 9, is characterized in that,
Described detecting unit, specifically for for i-th keyword models, when described i-th keyword models comprises a basic keyword, detects in described content of text and whether there is described basic keyword; If there is described basic keyword in described content of text, then determine that described i-th keyword models and described content of text match, i is positive integer;
Or,
Described detecting unit, specifically for for i-th keyword models, when described i-th keyword models comprises at least two basic keywords and logical relation symbol, in described content of text, search the described basic keyword that described i-th keyword models comprises; If find basic keyword described at least one in described content of text, then detect the described basic keyword found whether meet described logical relation symbol represented by logical relation; If the described basic keyword found meets the logical relation represented by described logical relation symbol, then determine that described i-th keyword models and described content of text match, i is positive integer.
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 true CN105187674A (en) | 2015-12-23 |
| CN105187674B 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) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886951A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | A kind of speech detection method, device and equipment |
| CN108491388A (en) * | 2018-03-22 | 2018-09-04 | 平安科技（深圳）有限公司 | Data set acquisition methods, sorting technique, device, equipment and storage medium |
| CN108737667A (en) * | 2018-05-03 | 2018-11-02 | 平安科技（深圳）有限公司 | Voice quality detecting method, device, computer equipment and storage medium |
| CN109902957A (en) * | 2019-02-28 | 2019-06-18 | 腾讯科技（深圳）有限公司 | A kind of 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 |
| CN110598008A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视系统技术有限公司 | Data quality inspection method and device for recorded data and storage medium |
| CN111128233A (en) * | 2019-10-12 | 2020-05-08 | 中国平安财产保险股份有限公司 | Recording detection method and device, electronic equipment and storage medium |
| EP3876549A4 (en) * | 2018-11-02 | 2021-11-17 | One Connect Smart Technology Co., Ltd. (Shenzhen) | Video quality inspection method and apparatus, computer device and storage medium |
Citations (5)
| 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 |
| 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 |
-
2015
- 2015-08-14 CN CN201510500179.1A patent/CN105187674B/en active Active
Patent Citations (5)
| 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 |
| 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 |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886951A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | A kind of speech detection method, device and equipment |
| 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 |
| CN108491388A (en) * | 2018-03-22 | 2018-09-04 | 平安科技（深圳）有限公司 | Data set acquisition methods, sorting technique, device, equipment and storage medium |
| 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 |
| CN108737667A (en) * | 2018-05-03 | 2018-11-02 | 平安科技（深圳）有限公司 | Voice quality detecting method, device, computer equipment and storage medium |
| WO2019210557A1 (en) * | 2018-05-03 | 2019-11-07 | 平安科技（深圳）有限公司 | Voice quality inspection method and device, computer device and storage medium |
| CN110598008A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视系统技术有限公司 | Data quality inspection method and device for recorded data 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 |
| EP3876549A4 (en) * | 2018-11-02 | 2021-11-17 | One Connect Smart Technology Co., Ltd. (Shenzhen) | Video quality inspection method and apparatus, computer device and storage medium |
| CN109902957A (en) * | 2019-02-28 | 2019-06-18 | 腾讯科技（深圳）有限公司 | A kind of data processing method and device |
| 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 |
| CN111128233A (en) * | 2019-10-12 | 2020-05-08 | 中国平安财产保险股份有限公司 | Recording detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105187674B (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105187674A (en) | Compliance checking method and device for service recorded sound | |
| CN105141787A (en) | Service record compliance checking method and device | |
| CN108595157B (en) | Block chain data processing method, device, equipment and storage medium | |
| US11714793B2 (en) | Systems and methods for providing searchable customer call indexes | |
| CN111192004A (en) | Method for displaying current to-do task and subsequent to-do workflow | |
| US20140337072A1 (en) | Actionable workflow based on interaction analytics analysis | |
| US20230139628A1 (en) | Supporting automation of customer service | |
| CN109242460B (en) | Payment system based on multiple payment channels and account checking method thereof | |
| CN105162977A (en) | Excuse recommendation method and device | |
| US20190130490A1 (en) | Systems and Methods for Detecting a Fraudulent Claim During a Call Related to an Insurance Policy | |
| CN111124917A (en) | Public test case management and control method, device, equipment and storage medium | |
| CN111831875A (en) | Data processing method, device, equipment and storage medium | |
| WO2016004104A1 (en) | Enhancing work force management with speech analytics | |
| CN105208226A (en) | Service recording compliance check method and device | |
| CN110298543B (en) | Service tracking method, device, computer equipment and storage medium | |
| CN107172311B (en) | Service evaluation method and terminal equipment | |
| WO2023015615A1 (en) | Multi-channel fund transfer method and apparatus based on prediction model, and device and medium | |
| CN114881739A (en) | Order event processing method and device, electronic equipment and storage medium | |
| CN107273423A (en) | Multimedia message data processing method, device and system | |
| CN114358543A (en) | Information processing method and device | |
| CN102970159A (en) | Method and device for data audit and repairing treatment | |
| CN110782351A (en) | Data processing method, system, device and storage medium suitable for daily end transaction | |
| CN115543662B (en) | Method and related device for issuing kafka message data | |
| CN116843169A (en) | Work order processing method, apparatus, device, storage medium, and program product | |
| US20230336507A1 (en) | System and method for implementing client service aspect of enterprise |
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. |