CN109726372A - Generation method, device and the computer-readable medium of work order based on message registration - Google Patents

Generation method, device and the computer-readable medium of work order based on message registration Download PDF

Info

Publication number
CN109726372A
CN109726372A CN201711043042.3A CN201711043042A CN109726372A CN 109726372 A CN109726372 A CN 109726372A CN 201711043042 A CN201711043042 A CN 201711043042A CN 109726372 A CN109726372 A CN 109726372A
Authority
CN
China
Prior art keywords
list
client
text information
customer service
call text
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711043042.3A
Other languages
Chinese (zh)
Inventor
刘昊骋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201711043042.3A priority Critical patent/CN109726372A/en
Publication of CN109726372A publication Critical patent/CN109726372A/en
Pending legal-status Critical Current

Links

Abstract

The present invention provides generation method, device and the computer-readable medium of a kind of work order based on message registration.Its method includes: the call text information according to client and customer service, obtains the essential information of client;The answer list of the problem of generating model according to call text information and list trained in advance, generate client list and customer service;According to the answer list of list the problem of the essential information of client, client and customer service, the work order based on message registration is generated.Technical solution of the present invention can automatically generate the work order based on message registration, with it is in the prior art manually fill in work order compared with, can be time saving, laborsaving, effectively improve the formation efficiency of work order.

Description

Generation method, device and the computer-readable medium of work order based on message registration
[technical field]
The present invention relates to computer application technology more particularly to a kind of generation sides of the work order based on message registration Method, device and computer-readable medium.
[background technique]
For the ease of providing better service for user, existing many service organizations both provide customer service platform, provide visitor Family hot line the problem of to listen to client and suggestion, and provides solution in time for client.
It is most of to be realized using artificial customer service in existing customer service platform.The incoming call of client is answered in artificial customer service, and The problem of in client's call logging procedure, obtaining the essential information of client, listening to client, the problem of recording client.Simultaneously also It needs to provide solution for client, and the solution of client's offer is provided.And based on the above issues, hand filling this The work order of customer service.
But in the prior art, the work order whole process of customer service needs contact staff's hand filling, therefore work in the prior art Single generating process is time-consuming, laborious, and formation efficiency is lower.
[summary of the invention]
The present invention provides generation method, device and the computer-readable mediums of a kind of work order based on message registration, use In raising work order formation efficiency.
The present invention provides a kind of generation method of work order based on message registration, which comprises
According to the call text information of client and customer service, the essential information of the client is obtained;
The problem of generating model according to the call text information and list trained in advance, generate client list with The answer list of the customer service;
According to the answer list of list and the customer service the problem of essential information of the client, the client, base is generated In the work order of message registration.
Still optionally further, in method as described above, according to the call text information of client and customer service, the visitor is obtained Before the essential information at family, the method also includes:
The voice communication for monitoring client and customer service records;
The voice communication is recorded and carries out speech recognition, obtains the call text information of client and customer service.
Still optionally further, in method as described above, according to the call text information of client and customer service, the visitor is obtained The essential information at family, specifically includes:
The identification information of the client of preset format is obtained from the call text information;
The essential information of the client is obtained from user information database according to the identification information of the client.
Still optionally further, raw according to the call text information and list trained in advance in method as described above At model, the problem of generating the client list and the customer service answer list, specifically include:
Extracted respectively from the call text information client the first call text information and the customer service the Two call text informations;
The problem of generating model according to the first call text information and the list, map client list;
Model is generated according to the second call text information and the list, maps the answer list of the customer service.
Still optionally further, it in method as described above, is generated according to the first call text information and the list Model, the problem of mapping the client list, specifically include:
Word segmentation processing is carried out to the first call text information, obtains several first participles;
According to several first participles and pre-set dictionary, it is corresponding to generate the first call text information First participle feature representation;
The first participle feature representation is input to the list to generate in model, so that list generation model is defeated The list the problem of client out;
Further, model is generated according to the second call text information and the list, maps the solution of the customer service List is answered, is specifically included:
Word segmentation processing is carried out to the second call text information, obtains several second participles;
According to several second participles and the dictionary, it is second point corresponding to generate the second call text information Word feature representation;
The second participle feature representation is input to the list to generate in model, so that list generation model is defeated The answer list of the customer service out.
Still optionally further, raw according to the call text information and list trained in advance in method as described above At model, the problem of generating the client list and the customer service answer list before, the method also includes:
Several training datas are acquired, include: the training call of trained client and training customer service in training data described in each item The known answer list of text information, the known problem list of the trained client and the trained customer service;
According to training data described in each item, the training list generates model.
The present invention provides a kind of generating means of work order based on message registration, and described device includes:
Customer information obtains module and obtains the basic of the client for the call text information according to client and customer service Information;
List generation module generates institute for generating model according to the call text information and list trained in advance The answer list of the problem of stating client list and the customer service;
Work order generation module, for according to list the problem of essential information, the client of the client and the customer service Answer list, generate the work order based on message registration.
Still optionally further, in device as described above, further includes:
Module is monitored, the voice communication for monitoring client and customer service records;
Speech recognition module carries out speech recognition for recording to the voice communication, obtains the described of client and customer service Call text information.
Still optionally further, in device as described above, the customer information obtains module, is specifically used for:
The identification information of the client of preset format is obtained from the call text information;
The essential information of the client is obtained from user information database according to the identification information of the client.
Still optionally further, in device as described above, the list generation module, comprising:
Information extracting unit, for extracting the first call text envelope of the client respectively from the call text information Second call text information of breath and the customer service;
Problem list map unit, for generating model, mapping according to the first call text information and the list The problem of client list;
List map unit is answered, for generating model, mapping according to the second call text information and the list The answer list of the customer service.
Still optionally further, in device as described above, described problem list map unit is specifically used for:
Word segmentation processing is carried out to the first call text information, obtains several first participles;
According to several first participles and pre-set dictionary, it is corresponding to generate the first call text information First participle feature representation;
The first participle feature representation is input to the list to generate in model, so that list generation model is defeated The list the problem of client out;
Further, the answer list map unit, is specifically used for:
Word segmentation processing is carried out to the second call text information, obtains several second participles;
According to several second participles and the dictionary, it is second point corresponding to generate the second call text information Word feature representation;
The second participle feature representation is input to the list to generate in model, so that list generation model is defeated The answer list of the customer service out.
Further, the answer list map unit, is specifically used for:
Word segmentation processing is carried out to the second call text information, obtains several second participles;
According to several second participles and the dictionary, it is second point corresponding to generate the second call text information Word feature representation;
The second participle feature representation is input to the list to generate in model, so that list generation model is defeated The answer list of the customer service out.
Still optionally further, in device as described above, further includes:
Acquisition module includes: trained client and training visitor for acquiring several training datas, in training data described in each item Training call text information, the known problem list of the trained client and the known solution list of the trained customer service of clothes It is single;
Training module, is used for the training data according to each item, and the training list generates model.
The present invention also provides a kind of computer equipment, the equipment includes:
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes the generation method of the work order based on message registration as described above.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor The generation method of the work order based on message registration as described above is realized when row.
Generation method, device and the computer-readable medium of work order based on message registration of the invention, by according to visitor The call text information at family and customer service, obtains the essential information of client;It is raw according to call text information and list trained in advance At model, the problem of generating client list and customer service answer list;According to list the problem of the essential information of client, client and The answer list of customer service generates the work order based on message registration.Technical solution of the present invention can be automatically generated based on call note The work order of record, with it is in the prior art manually fill in work order compared with, can be time saving, laborsaving, effectively improve the life of work order At efficiency.
[Detailed description of the invention]
Fig. 1 is the flow chart of the generation method embodiment one of the work order of the invention based on message registration.
Fig. 2 is the flow chart of the generation method embodiment two of the work order of the invention based on message registration.
Fig. 3 is the structure chart of the generating means embodiment one of the work order of the invention based on message registration.
Fig. 4 is the structure chart of the generating means embodiment two of the work order of the invention based on message registration.
Fig. 5 is the structure chart of computer equipment embodiment of the invention.
Fig. 6 is a kind of exemplary diagram of computer equipment provided by the invention.
[specific embodiment]
To make the objectives, technical solutions, and advantages of the present invention clearer, right in the following with reference to the drawings and specific embodiments The present invention is described in detail.
Fig. 1 is the flow chart of the generation method embodiment one of the work order of the invention based on message registration.As shown in Figure 1, The generation method of the work order based on message registration of the present embodiment, can specifically include following steps:
100, according to the call text information of client and customer service, the essential information of client is obtained;
The executing subject of the generation method of the work order based on message registration of the present embodiment is the work order based on message registration Generating means, should the generating means of work order based on message registration can be set in the customer service platform side of service provider, with It can be based on message registration, help customer service to automatically generate work order, save contact staff and be manually generated work order.
In practical application, client can seek advice from business relevant with the service that oneself is enjoyed when seeking advice from customer service Information, for example, the client of purchase financing can seek advice from the related problem of financing.It is relevant that the client of application loan can seek advice from loan Problem.The problem of for the ease of improving customer service quality, client being accurately positioned, customer service can inquire the identification information of client, such as ID card No., phone number or mailbox etc. are capable of the identification information of unique identification client.Then customer service can root According to the identification information of client, the product of user purchase is obtained from the user information database of service provider, convenient for visitor The problem of family, is positioned, the problem of client is more clearly understood, to provide more accurately answer for user.It is based on The above, it is known that the identification information of client is generally included in the call text information of client and customer service, it is practical In, it can be recorded in work order directly using the identification information of the client as the essential information of the client.
In addition, the identification information due to client can be ID card No., phone number or mailbox, all have one Fixed format, if ID card No. and phone number are respectively provided with preset length, mailbox has preset special format, according to The particularity of identification information can be easy to get the identification information of client from call text information.For example, In the present embodiment, according to the call text information of client and customer service, the essential information of client is obtained, can specifically include: from logical The identification information that client is obtained in text information is talked about, using the identification information of client as the essential information of the client.
Or the essential information of the client in work order may include information more abundant.At this time according to client and customer service Call text information, obtains the essential information of client, can specifically include: the visitor of preset format is obtained from call text information The identification information at family;The essential information of client is obtained from user information database according to the identification information of client.Here User information database be specially the user information database of service provider, wherein can recorde all clients of the service provider All information, certainly also include client identification information.Such as the name of client, ID card No., mailbox, purchase Service product etc. essential information.
101, the problem of model being generated according to call text information and list trained in advance, generating client list and customer service Answer list;
In the present embodiment, trained list generates model in advance, and neural network model can be used for prototype, pass through depth Responsibility of strategy training obtains.In this way, generating model using the list after training, visitor can be obtained to call text information identification The problem of family declaration form and customer service answer list.
102, it according to the answer list of list the problem of the essential information of client, client and customer service, generates based on call note The work order of record.
For example, the answer list of the problem of essential information for the client that will acquire, client list and customer service, inputs together Into trouble ticket template, corresponding position is inserted, the work order based on message registration can be automatically generated.
The generation method of the work order based on message registration of the present embodiment passes through the call text envelope according to client and customer service Breath, obtains the essential information of client;The problem of generating model according to call text information and list trained in advance, generate client The answer list of list and customer service;According to the answer list of list the problem of the essential information of client, client and customer service, base is generated In the work order of message registration.The technical solution of the present embodiment can automatically generate the work order based on message registration, with the prior art In work order of manually filling in compare, can be time saving, laborsaving, effectively improve the formation efficiency of work order.
In addition, in the prior art, contact staff not only needs the problem of listening to client in the call with client, for visitor Family provides solution, while also needing hand filling work order, can also have record information and lose, cause not record visitor completely The problem of family, and the technical solution of the present embodiment is used, it can guarantee the integrality and accuracy of the work order generated.
Moreover, in the prior art, contact staff not only needs the problem of listening to client in the call with client, for visitor Family provides solution, while also needing hand filling work order, in this way, will lead to contact staff can not focus on understanding and Customer issue is handled, the service level of customer service is caused to decline.And the technical solution of the present embodiment, work order can be automatically generated, it can The problem of client can be listened to absorbedly with client personnel, and be absorbed in and provide solution for client, without use science and engineering list It writes, so as to effectively improve the service ability of customer service, enhances the Experience Degree of client.
Fig. 2 is the flow chart of the generation method embodiment two of the work order of the invention based on message registration.The present embodiment The generation method of work order based on message registration, on the basis of the technical solution of above-mentioned embodiment illustrated in fig. 1, further more Technical solution of the present invention is introduced in detail.As shown in Fig. 2, the generation method of the work order based on message registration of the present embodiment, It can specifically include following steps:
200, the voice communication for monitoring client and customer service records;
The customer service platform side of service provider is arranged in the generating means of the work order based on message registration of the present embodiment, can To listen to the voice communication record of each client and customer service.
201, voice communication is recorded and carries out speech recognition, obtain the call text information of client and customer service;
In the present embodiment, the generating means of the work order based on message registration, which can record voice communication, carries out voice voice Voice communication record is converted to call text information by identification.
202, the identification information of the client of preset format is obtained from call text information;
203, the essential information of client is obtained from user information database according to the identification information of client;
Similarly, the identification information of the client of the present embodiment can for the ID card No. of client, phone number or Mailbox, step 202 specifically can be with reference to the related records of above-mentioned embodiment illustrated in fig. 1 to 203 implementation, and details are not described herein.
204, the first call text information of client and the second call text of customer service are extracted respectively from call text information This information;
Specifically, the voice of different people has different sound characteristics, in the present embodiment, can remember to voice communication When record carries out speech recognition, different labels is done when to the speech recognition of the people of alternative sounds feature, i.e., by client and visitor The call text information of clothes is distinguished using different labels.In this way, visitor can be extracted from all call text informations The first call text information at family and the second call text information of customer service.
205, the problem of generating model according to the first call text information and list trained in advance, map client list;
Such as the step 205, it can specifically include following steps:
(a1) word segmentation processing is carried out to the first call text information, obtains several first participles;
(b1) according to several first participles and pre-set dictionary, the first call text information corresponding first is generated Segment feature representation;
(c1) first participle feature representation is input to list to generate in model, so that list generates model output client's Problem list.
In the present embodiment, word segmentation processing can be carried out to the first call text information of client, can specifically used existing Participle strategy to first call text information segment.Dictionary can also be previously provided in the present embodiment, in the dictionary It may include all words for the enquirement and answer aspect for covering all products of the service provider, can guarantee visitor in this way Word in the enquirement at family can hit some word in the dictionary.So the quantity for the word for including in the dictionary is sure to It is enough more.
Then, the numerous word in dictionary is arranged in sequence, and establishes a size equal to word number in dictionary The feature vector of amount, each position corresponds to a word in dictionary in feature vector.Then the first call text is successively analyzed Whether each first participle that information segments hits certain word in dictionary, if hit, by feature vector with first point The element of word corresponding position is set as 1, and otherwise the element of the position is 0, obtains first participle feature representation.Or further also First participle feature representation can be normalized, be then input to list and generate in model, so that list generates model output The problem of client list.Since each first participle in the first call text information can characterize the enquirement of client, it is based on The first call text information generates model according to trained list, the problem of client can be mapped out list.
It further optionally, can also be according to the appearance of each first participle when being normalized to first participle feature representation Frequency normalizes feature vector, occurs so that the numerical value of the corresponding element in position of the high first participle of the frequency of occurrences is greater than The numerical value of the corresponding element in position of the low first participle of frequency.
206, model is generated according to the second call text information and list trained in advance, maps the answer list of customer service;
Such as the step 206, it can specifically include following steps:
(a2) word segmentation processing is carried out to the second call text information, obtains several second participles;
(b2) according to several second participles and dictionary, the corresponding second participle mark sheet of the second call text information is generated It reaches;
(c2) the second participle feature representation is input to list to generate in model, so that list generates model output customer service Answer list.
With reference to above-mentioned steps (a1)-(c1) implementation principle, step (a2)-(c2) specific implementation process may be implemented, Referring in detail to the record of above-mentioned related embodiment, details are not described herein.
207, it according to the answer list of list the problem of the essential information of client, client and customer service, generates based on call note The work order of record.
Finally by the answer list of list and customer service the problem of the essential information of the above-mentioned client got, client, together It is input in trouble ticket template, inserts corresponding position, the work order based on message registration can be automatically generated.
The generation method of the work order based on message registration of the present embodiment can be automatic by using above-mentioned technical proposal Generate the work order based on message registration, with it is in the prior art manually fill in work order compared with, can be time saving, laborsaving, effectively The formation efficiency of ground raising work order.
It should be noted that the step 205 of the embodiment described in the step 101 and Fig. 2 of above-mentioned embodiment illustrated in fig. 1 it Before, can also specifically it include the following steps:
(a3) several training datas are acquired, include: the training call of trained client and training customer service in each training data The known answer list of text information, the known problem list of training client and training customer service;
(b3) according to each training data, training list generates model.
For example, the item number of the training data acquired in the present embodiment can achieve 15,600,000 or more, the training number of acquisition According to item number it is more, the problem of trained list generates model mapping client list and customer service answer list it is more accurate.
Before training, a list is first selected to generate the prototype of model, and generate each parameter in model to the list and assign Give initial value.It is available to arrive for the training call text information of training client and training customer service in every training data The training call text information of training client and the training call text information of training customer service.And according to the instruction of each training data The training call text information and pre-set dictionary for practicing client, obtain the participle feature representation of each trained client, Yi Jigen According to the training call text information and pre-set dictionary of the training customer service of each training data, point of each trained customer service is obtained Word feature representation can segment feature representation with reference to the first participle feature representation and second in above-described embodiment respectively in detail Acquisition modes.
Then the participle feature representation of the training client of each training data is input to list and generates model, it is corresponding at this time List generates the problem of training client of model output prediction list.The problem of detecting the training client of prediction list and the instruction The known problem list for practicing client compares, if list is asked with the known of the training client the problem of training client of prediction Topic list is inconsistent, and adjustment list generates the parameter of model, so that list is intended to the instruction the problem of training client of prediction Practice the known problem list of client.It then proceedes to train, the participle feature representation of the training customer service of the training data is input to List generates model, and corresponding list generates the answer list of the training customer service of model output prediction at this time.Detection prediction is somebody's turn to do The answer list of training customer service is compared with the known solution list of the training customer service is single-phase, if the answer of the training customer service of prediction List and the known answer list of the training customer service are inconsistent, continue to adjust the parameter that list generates model, so that prediction is somebody's turn to do The answer list of training customer service is intended to the known answer list of the training customer service.It is all used for each training data above-mentioned Mode is trained, adjustment list generate model parameter, until list generate model output prediction the problem of list with The problem of knowing list is consistent, the answer list of the prediction of output and the single cause of known solution list, determines that list generates mould at this time The parameter of type, so that it is determined that list generates model.
Further optionally, list and the answer list of customer service use together the problem of the client of training in the above embodiments One list generates model to realize.In practical application, two lists can also be trained to generate by the way of above-described embodiment Model, such as the list of problem list generate model and answer the list generation model of list.Such as when training, training is used only The training call text information of client, the list of training problem list generate model.Using only the training call text of training customer service The list of this information, training answer list generates model.Then respectively using the call text information and problem list of client The problem of list generates model, maps client list generates mould using the call text information of customer service and the list of answer list Type maps the answer list of customer service, can refer to the record of above-described embodiment in detail, details are not described herein.
Fig. 3 is the structure chart of the generating means embodiment one of the work order of the invention based on message registration.As shown in figure 3, The generating means of the work order based on message registration of the present embodiment, can specifically include:
Customer information obtains module 10 according to the call text information of client and customer service, obtains the essential information of client;
The problem of list generation module 11 generates model according to call text information and list trained in advance, generates client The answer list of list and customer service;
Work order generation module 12 obtains the essential information for the client that module 10 obtains, list generation module according to customer information 11 generate client the problem of list and customer service answer list, generate the work order based on message registration.
The generating means of the work order based on message registration of the present embodiment are realized by using above-mentioned module based on call note The realization principle and technical effect of the generation of the work order of record are identical as the realization of above-mentioned related method embodiment, can join in detail It is admitted to the record for stating related method embodiment, details are not described herein.
Fig. 4 is the structure chart of the generating means embodiment two of the work order of the invention based on message registration.As shown in figure 4, The generating means of the work order based on message registration of the present embodiment on the basis of the technical solution of above-mentioned embodiment illustrated in fig. 3 into One step introduces technical solution of the present invention in further detail.
As shown in figure 4, the generating means of the work order based on message registration of the present embodiment, further includes:
Monitor the voice communication record that module 13 is used to monitor client and customer service;
Speech recognition module 14, which is used to record voice communication, carries out speech recognition, obtains the call text of client and customer service Information.
Accordingly, customer information obtains the call that module 10 identifies obtained client and customer service according to speech recognition module 14 Text information obtains the essential information of client;
List generation module 11 identifies obtained call text information and table trained in advance according to speech recognition module 14 The answer list of the problem of list generates model, generates client list and customer service;
Still optionally further, in the generating means of the work order based on message registration of the present embodiment, customer information obtains mould Block 10 is specifically used for:
The identification information of the client of preset format is obtained from call text information;
The essential information of client is obtained from user information database according to the identification information of client.
Still optionally further, as shown in figure 4, in the generating means of the work order based on message registration of the present embodiment, list Generation module 11 includes:
Information extracting unit 111 is used to identify from speech recognition module 14 extracts visitor respectively in obtained call text information The first call text information at family and the second call text information of customer service;
The the first call text information and table that problem list map unit 112 is used to be extracted according to information extracting unit 111 The problem of list generates model, maps client list;
The the second call text information and table that answer list map unit 113 is used to be extracted according to information extracting unit 111 It is single to generate model, map the answer list of customer service.
Still optionally further, in the generating means of the work order based on message registration of the present embodiment, the mapping of problem list is single Member 112 is specifically used for:
Word segmentation processing is carried out to the first call text information that information extracting unit 111 extracts, obtains several first participles;
According to several first participles and pre-set dictionary, the corresponding first participle of the first call text information is generated Feature representation;
First participle feature representation is input to list to generate in model, so that the problem of list generates model output client List;
Further, answer list map unit 113 is specifically used for:
Word segmentation processing is carried out to the second call text information that information extracting unit 111 extracts, obtains several second participles;
According to several second participles and dictionary, the corresponding second participle feature representation of the second call text information is generated;
Second participle feature representation is input to list to generate in model, so that list generates the answer of model output customer service List.
Still optionally further, as shown in figure 4, also being wrapped in the generating means of the work order based on message registration of the present embodiment It includes:
Acquisition module 15 includes: trained client and training customer service in each training data for acquiring several training datas Training call text information, training client known problem list and training customer service known answer list;
Training module 16 is used for each training data acquired according to acquisition module 15, and training list generates model.
Accordingly, the first call text envelope that problem list map unit 112 is used to be extracted according to information extracting unit 111 The problem of breath and the list of the training of training module 16 generate model, map client list;
The the second call text information and instruction that answer list map unit 113 is used to be extracted according to information extracting unit 111 The list for practicing the training of module 16 generates model, maps the answer list of customer service.
The generating means of the work order based on message registration of the present embodiment are realized by using above-mentioned module based on call note The realization principle and technical effect of the generation of the work order of record are identical as the realization of above-mentioned related method embodiment, can join in detail It is admitted to the record for stating related method embodiment, details are not described herein.
Fig. 5 is the structure chart of computer equipment embodiment of the invention.As shown in figure 5, the computer equipment of the present embodiment, It include: one or more processors 30 and memory 40, memory 40 works as memory for storing one or more programs The one or more programs stored in 40 are executed by one or more processors 30, so that one or more processors 30 are realized such as The generation method of work order of the figure 1 above-embodiment illustrated in fig. 2 based on message registration.To include multiple places in embodiment illustrated in fig. 5 For reason device 30.
For example, Fig. 6 is a kind of exemplary diagram of computer equipment provided by the invention.Fig. 6, which is shown, to be suitable for being used to realizing this The block diagram of the exemplary computer device 12a of invention embodiment.The computer equipment 12a that Fig. 6 is shown is only an example, Should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, computer equipment 12a is showed in the form of universal computing device.The component of computer equipment 12a can To include but is not limited to: one or more processor 16a, system storage 28a connect different system components (including system Memory 28a and processor 16a) bus 18a.
Bus 18a indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller, Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 12a typically comprises a variety of computer system readable media.These media can be it is any can The usable medium accessed by computer equipment 12a, including volatile and non-volatile media, moveable and immovable Jie Matter.
System storage 28a may include the computer system readable media of form of volatile memory, such as deposit at random Access to memory (RAM) 30a and/or cache memory 32a.Computer equipment 12a may further include it is other it is removable/ Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34a can be used for reading Write immovable, non-volatile magnetic media (Fig. 6 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 6, The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each Driver can be connected by one or more data media interfaces with bus 18a.System storage 28a may include at least One program product, the program product have one group of (for example, at least one) program module, these program modules are configured to hold The function of the above-mentioned each embodiment of Fig. 1-Fig. 4 of the row present invention.
Program with one group of (at least one) program module 42a/utility 40a, can store and deposit in such as system In reservoir 28a, such program module 42a include --- but being not limited to --- operating system, one or more application program, It may include the reality of network environment in other program modules and program data, each of these examples or certain combination It is existing.Program module 42a usually executes the function and/or method in above-mentioned each embodiment of Fig. 1-Fig. 4 described in the invention.
Computer equipment 12a can also be with one or more external equipment 14a (such as keyboard, sensing equipment, display 24a etc.) communication, the equipment interacted with computer equipment 12a communication can be also enabled a user to one or more, and/or (such as network interface card is adjusted with any equipment for enabling computer equipment 12a to be communicated with one or more of the other calculating equipment Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 22a.Also, computer equipment 12a can also by network adapter 20a and one or more network (such as local area network (LAN), wide area network (WAN) and/or Public network, such as internet) communication.As shown, network adapter 20a passes through its of bus 18a and computer equipment 12a The communication of its module.It should be understood that although not shown in the drawings, other hardware and/or software can be used in conjunction with computer equipment 12a Module, including but not limited to: microcode, device driver, redundant processor, external disk drive array, RAID system, tape Driver and data backup storage system etc..
Processor 16a by the program that is stored in system storage 28a of operation, thereby executing various function application and Data processing, such as realize the generation method of the work order based on message registration shown in above-described embodiment.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor The generation method of the work order as shown in above-described embodiment based on message registration is realized when row.
The computer-readable medium of the present embodiment may include in the system storage 28a in above-mentioned embodiment illustrated in fig. 6 RAM30a, and/or cache memory 32a, and/or storage system 34a.
With the development of science and technology, the route of transmission of computer program is no longer limited by tangible medium, it can also be directly from net Network downloading, or obtained using other modes.Therefore, the computer-readable medium in the present embodiment not only may include tangible Medium can also include invisible medium.
The computer-readable medium of the present embodiment can be using any combination of one or more computer-readable media. Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be Any computer-readable medium other than computer readable storage medium, which can send, propagate or Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.? Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service It is connected for quotient by internet).
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read- Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.

Claims (14)

1. a kind of generation method of the work order based on message registration, which is characterized in that the described method includes:
According to the call text information of client and customer service, the essential information of the client is obtained;
According to the call text information and list generation model trained in advance, the problem of generating the client list and described The answer list of customer service;
According to the answer list of list and the customer service the problem of essential information of the client, the client, generate based on logical Talk about the work order of record.
2. the method according to claim 1, wherein obtaining institute according to the call text information of client and customer service Before the essential information for stating client, the method also includes:
The voice communication for monitoring client and customer service records;
The voice communication is recorded and carries out speech recognition, obtains the call text information of client and customer service.
3. the method according to claim 1, wherein obtaining institute according to the call text information of client and customer service The essential information for stating client, specifically includes:
The identification information of the client of preset format is obtained from the call text information;
The essential information of the client is obtained from user information database according to the identification information of the client.
4. method according to claim 1 to 3, which is characterized in that according to the call text information and training in advance List generate model, the problem of generating the client list and the customer service answer list, specifically include:
It extracts the first call text information of the client respectively from the call text information and the second of the customer service is led to Talk about text information;
The problem of generating model according to the first call text information and the list, map client list;
Model is generated according to the second call text information and the list, maps the answer list of the customer service.
5. according to the method described in claim 4, it is characterized in that, raw according to the first call text information and the list At model, the problem of mapping the client list, specifically include:
Word segmentation processing is carried out to the first call text information, obtains several first participles;
According to several first participles and pre-set dictionary, the first call text information corresponding first is generated Segment feature representation;
The first participle feature representation is input to the list to generate in model, so that the list generates model and exports institute The problem of stating client list;
Further, model is generated according to the second call text information and the list, maps the solution list of the customer service It is single, it specifically includes:
Word segmentation processing is carried out to the second call text information, obtains several second participles;
According to several second participles and the dictionary, it is special to generate corresponding second participle of the second call text information Sign expression;
The second participle feature representation is input to the list to generate in model, so that the list generates model and exports institute State the answer list of customer service.
6. the method according to claim 1, wherein according to the call text information and list trained in advance Before the problem of generating model, generating client list and the answer list of the customer service, the method also includes:
Several training datas are acquired, include: the training call text of trained client and training customer service in training data described in each item The known answer list of information, the known problem list of the trained client and the trained customer service;
According to training data described in each item, the training list generates model.
7. a kind of generating means of the work order based on message registration, which is characterized in that described device includes:
Customer information obtains module and obtains the essential information of the client for the call text information according to client and customer service;
List generation module generates the visitor for generating model according to the call text information and list trained in advance The problem of family list and the customer service answer list;
Work order generation module, for the solution according to list and the customer service the problem of essential information, the client of the client List is answered, the work order based on message registration is generated.
8. device according to claim 7, which is characterized in that described device further include:
Module is monitored, the voice communication for monitoring client and customer service records;
Speech recognition module carries out speech recognition for recording to the voice communication, obtains the call of client and customer service Text information.
9. device according to claim 7, which is characterized in that the customer information obtains module, is specifically used for:
The identification information of the client of preset format is obtained from the call text information;
The essential information of the client is obtained from user information database according to the identification information of the client.
10. according to any device of claim 7-9, which is characterized in that the list generation module, comprising:
Information extracting unit, for from it is described call text information in extract respectively the client first call text information and Second call text information of the customer service;
Problem list map unit, for generating model according to the first call text information and the list, described in mapping The problem of client list;
List map unit is answered, for generating model according to the second call text information and the list, described in mapping The answer list of customer service.
11. device according to claim 10, which is characterized in that described problem list map unit is specifically used for:
Word segmentation processing is carried out to the first call text information, obtains several first participles;
According to several first participles and pre-set dictionary, the first call text information corresponding first is generated Segment feature representation;
The first participle feature representation is input to the list to generate in model, so that the list generates model and exports institute The problem of stating client list;
Further, the answer list map unit, is specifically used for:
Word segmentation processing is carried out to the second call text information, obtains several second participles;
According to several second participles and the dictionary, it is special to generate corresponding second participle of the second call text information Sign expression;
The second participle feature representation is input to the list to generate in model, so that the list generates model and exports institute State the answer list of customer service.
12. device according to claim 7, which is characterized in that described device further include:
Acquisition module includes: trained client and training customer service for acquiring several training datas, in training data described in each item Training call text information, the known problem list of the trained client and the known answer list of the trained customer service;
Training module, is used for the training data according to each item, and the training list generates model.
13. a kind of computer equipment, which is characterized in that the equipment includes:
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real Now such as method as claimed in any one of claims 1 to 6.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor Shi Shixian method for example as claimed in any one of claims 1 to 6.
CN201711043042.3A 2017-10-31 2017-10-31 Generation method, device and the computer-readable medium of work order based on message registration Pending CN109726372A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711043042.3A CN109726372A (en) 2017-10-31 2017-10-31 Generation method, device and the computer-readable medium of work order based on message registration

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711043042.3A CN109726372A (en) 2017-10-31 2017-10-31 Generation method, device and the computer-readable medium of work order based on message registration

Publications (1)

Publication Number Publication Date
CN109726372A true CN109726372A (en) 2019-05-07

Family

ID=66293076

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711043042.3A Pending CN109726372A (en) 2017-10-31 2017-10-31 Generation method, device and the computer-readable medium of work order based on message registration

Country Status (1)

Country Link
CN (1) CN109726372A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110225210A (en) * 2019-06-18 2019-09-10 北京智合大方科技有限公司 Based on call abstract Auto-writing work order method and system
CN110689357A (en) * 2019-09-23 2020-01-14 四川新网银行股份有限公司 Work order generation method for online customer service based on machine learning
CN111835921A (en) * 2020-07-16 2020-10-27 普强时代(珠海横琴)信息技术有限公司 Real-time automatic telephone traffic summary system and method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110225210A (en) * 2019-06-18 2019-09-10 北京智合大方科技有限公司 Based on call abstract Auto-writing work order method and system
CN110689357A (en) * 2019-09-23 2020-01-14 四川新网银行股份有限公司 Work order generation method for online customer service based on machine learning
CN110689357B (en) * 2019-09-23 2022-08-26 四川新网银行股份有限公司 Work order generation method for online customer service based on machine learning
CN111835921A (en) * 2020-07-16 2020-10-27 普强时代(珠海横琴)信息技术有限公司 Real-time automatic telephone traffic summary system and method

Similar Documents

Publication Publication Date Title
US10236001B2 (en) Passive enrollment method for speaker identification systems
CN107481720B (en) Explicit voiceprint recognition method and device
CN109726372A (en) Generation method, device and the computer-readable medium of work order based on message registration
CN107220847A (en) Advertisement placement method, device, server, computer equipment and computer-readable recording medium
CN107193973A (en) The field recognition methods of semanteme parsing information and device, equipment and computer-readable recording medium
WO2014049461A1 (en) Captioning using socially derived acoustic profiles
CN107680019A (en) A kind of implementation method of Examination Scheme, device, equipment and storage medium
CN109446990A (en) Method and apparatus for generating information
CN109192194A (en) Voice data mask method, device, computer equipment and storage medium
CN108012173A (en) A kind of content identification method, device, equipment and computer-readable storage medium
CN108597519A (en) A kind of bill classification method, apparatus, server and storage medium
KR102318642B1 (en) Online platform using voice analysis results
CN110232340A (en) Establish the method, apparatus of video classification model and visual classification
CN109785846A (en) The role recognition method and device of the voice data of monophonic
CN108052577A (en) A kind of generic text content mining method, apparatus, server and storage medium
CN110163257A (en) Method, apparatus, equipment and the computer storage medium of drawing-out structure information
CN109599095A (en) A kind of mask method of voice data, device, equipment and computer storage medium
CN110245580A (en) A kind of method, apparatus of detection image, equipment and computer storage medium
CN108830980A (en) Security protection integral intelligent robot is received in Study of Intelligent Robot Control method, apparatus and attendance
CN109325091A (en) Update method, device, equipment and the medium of points of interest attribute information
CN109670055A (en) A kind of multi-medium data checking method, device, equipment and storage medium
CN110598008A (en) Data quality inspection method and device for recorded data and storage medium
US10769648B2 (en) Automated business reviews based on patron sentiment
CN109063624A (en) Information processing method, system, electronic equipment and computer readable storage medium
US20160351185A1 (en) Voice recognition device and method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20191205

Address after: 201210 room j1328, floor 3, building 8, No. 55, Huiyuan Road, Jiading District, Shanghai

Applicant after: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.

Address before: 100085 Baidu building, No. 10, ten Street, Haidian District, Beijing

Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd.

TA01 Transfer of patent application right
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20190507

Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd.

Assignor: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.

Contract record no.: X2019110000009

Denomination of invention: Work order generation method and device based on call records and computer readable medium

License type: Exclusive License

Record date: 20191218

EE01 Entry into force of recordation of patent licensing contract