CN107800900A - Communicating data processing method, device, storage medium and computer equipment - Google Patents
Communicating data processing method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN107800900A CN107800900A CN201710612991.2A CN201710612991A CN107800900A CN 107800900 A CN107800900 A CN 107800900A CN 201710612991 A CN201710612991 A CN 201710612991A CN 107800900 A CN107800900 A CN 107800900A
- Authority
- CN
- China
- Prior art keywords
- feature words
- word
- banquet
- occurrence number
- attending
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 239000012141 concentrate Substances 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 18
- 235000021167 banquet Nutrition 0.000 claims description 116
- 230000004044 response Effects 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 230000003993 interaction Effects 0.000 abstract description 10
- 230000036541 health Effects 0.000 description 6
- 238000013075 data extraction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/523—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
- H04M3/5232—Call distribution algorithms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention relates to a kind of communicating data processing method, device, storage medium and computer equipment, methods described includes:Temporally the cycle obtains the user voice data in history voice conversation;To identifying that the session text that the user voice data obtains segments to obtain feature word set;Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;The accounting that each Feature Words obtain in current time period is determined, the difference between the accounting obtained with the historical time cycle before current time period;Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;Corresponding personal call passage is distributed for the Feature Words of selection.The scheme that the application provides improves the efficiency of phone interaction.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of communicating data processing method, device, storage medium
And computer equipment.
Background technology
With the development of computer technology, interacted using phone and phone contact staff, by distance communicating come real
Existing various types of business handlings and consulting are more and more conventional.However, in traditional man-machine interactively, user need with phone
After contact staff is conversed, the phone contact staff demand of oneself is actively informed, contact staff is again passively according to the language of user
Sound content is the business that user handles correlation so that phone interacts less efficient.
The content of the invention
Based on this, it is necessary to for the low problem of phone interactive efficiency in traditional man-machine interactively, there is provided a kind of communicating data
Processing method, device, storage medium and computer equipment.
A kind of communicating data processing method, methods described include:
Temporally the cycle obtains the user voice data in history voice conversation;
To identifying that the session text that the user voice data obtains segments to obtain feature word set;
Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;
The accounting that each Feature Words obtain in current time period is determined, during with history before current time period
Between the cycle obtain accounting between difference;
Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;
Corresponding personal call passage is distributed for the Feature Words of selection.
In one embodiment, the session text that the described pair of identification user voice data obtains segments to obtain Feature Words
Collection, including:
To identifying that the session text that the user voice data obtains segments to obtain independent word;
Semanteme classifies to obtain independent lexon collection to the individually word as belonging to the individually word;
Selecting each individually lexon concentrates the independent word of occurrence number highest to obtain feature word set as Feature Words;
The accounting for obtaining the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words, bag
Include:
Each Feature Words are concentrated for Feature Words, acquisition current signature word selects independent lexon certainly and concentrates each individually word
Occurrence number sum, the occurrence number as current signature word;
Determine that the occurrence number of each Feature Words accounts for the accounting of the occurrence number sum of each Feature Words.
In one embodiment, methods described also includes:
Collect each history service data corresponding to mark of attending a banquet;
It is determined that the degree of correlation between the history service data for mark of respectively attending a banquet and the Feature Words of selection;
Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;
The mark of attending a banquet of preset ratio is chosen from the mark of attending a banquet of sequence is the first;
Attending a banquet for selection is attended a banquet into terminal association to the personal call passage corresponding to mark.
In one embodiment, methods described also includes:
Established with user terminal after communication connection and send voice guidance message to the user terminal;
The personal call passage that user terminal described in real-time reception selects according to the guidance information;
The communication connection established between user terminal terminal of attending a banquet corresponding with the personal call passage of selection.
In one embodiment, methods described also includes:
It is determined that the type of service belonging to the Feature Words chosen;
Professional knowledge information is obtained from Service Database corresponding with the type of service;
Response template corresponding with the type of service is generated according to the professional knowledge information;
The response template is sent to terminal of being attended a banquet corresponding to mark of being attended a banquet described in selection.
A kind of communicating data processing unit, described device include:
First acquisition module, the user voice data in history voice conversation is obtained for the temporally cycle;
Word-dividing mode, for identifying that the session text that the user voice data obtains segments to obtain feature word set;
Second acquisition module, the occurrence number of each Feature Words is concentrated to account for the occurrence number of each Feature Words for obtaining Feature Words
The accounting of sum;
Determining module, the accounting obtained for determining each Feature Words in current time period, with current time week
Difference between the accounting that the historical time cycle before phase obtains;
Module is chosen, is more than preset difference value and the Feature Words inconsistent with default word for choosing the difference that mutually should determine that;
Distribute module, for distributing corresponding personal call passage for the Feature Words of selection.
In one embodiment, the word-dividing mode is additionally operable to the session text obtained to identifying the user voice data
Participle obtains independent word;Semanteme classifies to obtain independent lexon collection to the individually word as belonging to the individually word;Select each independent
Lexon concentrates the independent word of occurrence number highest to obtain feature word set as Feature Words;
Second acquisition module is additionally operable to concentrate each Feature Words for Feature Words, obtains current signature word and selects certainly
Independent lexon concentrates the occurrence number sum of each individually word, the occurrence number as current signature word;Determine going out for each Feature Words
Occurrence number accounts for the accounting of the occurrence number sum of each Feature Words.
In one embodiment, described device also includes:
Relating module, for collecting each history service data corresponding to mark of attending a banquet;It is determined that the history for mark of respectively attending a banquet
The degree of correlation between service data and the Feature Words of selection;Corresponding mark of attending a banquet is arranged according to degree of correlation descending
Sequence;The mark of attending a banquet of preset ratio is chosen from the mark of attending a banquet of sequence is the first;Attending a banquet for selection is attended a banquet end corresponding to mark
End is associated to the personal call passage.
A kind of computer-readable recording medium, is stored with that computer is executable to be referred on the computer-readable recording medium
Order, when the computer executable instructions are executed by processor so that the computing device following steps:
Temporally the cycle obtains the user voice data in history voice conversation;
To identifying that the session text that the user voice data obtains segments to obtain feature word set;
Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;
The accounting that each Feature Words obtain in current time period is determined, during with history before current time period
Between the cycle obtain accounting between difference;
Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;
Corresponding personal call passage is distributed for the Feature Words of selection.
A kind of computer equipment, including memory and processor, computer executable instructions are stored in the memory,
When the computer executable instructions are by the computing device so that the computing device following steps:
Temporally the cycle obtains the user voice data in history voice conversation;
To identifying that the session text that the user voice data obtains segments to obtain feature word set;
Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;
The accounting that each Feature Words obtain in current time period is determined, during with history before current time period
Between the cycle obtain accounting between difference;
Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;
Corresponding personal call passage is distributed for the Feature Words of selection.
Above-mentioned communicating data processing method, device, storage medium and computer equipment, temporally the cycle from user in history
User voice data extraction in voice conversation represents the Feature Words of user's request, obtains the respective occurrence number of these Feature Words
Account for the accounting of the occurrence number sum of these Feature Words, and determine the accounting that each Feature Words obtain in current time period, with
Difference between the accounting that the historical time cycle before current time period obtains.Preset when the corresponding difference of Feature Words is more than
Difference and with default word it is inconsistent when, judge the related portfolio showed increased of recent this feature word, be automatically this feature word point
With personal call passage, the letter of Feature Words related service so can be actively provided the user by the personal call passage of distribution
Breath, so as to improve the efficiency of phone interaction.
Brief description of the drawings
Fig. 1 is the applied environment figure of communicating data processing method in one embodiment;
Fig. 2 is the internal structure schematic diagram of one embodiment Computer equipment;
Fig. 3 is the schematic flow sheet of communicating data processing method in one embodiment;
Fig. 4 is the schematic flow sheet of communicating data processing method in another embodiment;
Fig. 5 is the structured flowchart of communicating data processing unit in one embodiment;
Fig. 6 is the structured flowchart of communicating data processing unit in another embodiment.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the applied environment figure of communicating data processing method in one embodiment.Reference picture 1, communicating data processing
Method is applied to communicating data processing system.Communicating data processing system includes user terminal 110, server 120 and attended a banquet end
End 130, user terminal 110 and terminal 130 of attending a banquet can be communicated by network with server 120.User terminal 110 can be used
The mobile terminal or fixed call terminal that family uses.Server 120 can be independent physical server, can also
It is the server cluster that multiple physical servers are formed.Terminal of attending a banquet 130 is fixed call terminal, and terminal of each attending a banquet correspond to
One fixed operator attendance.Multiple terminal-pairs of attending a banquet answer a personal call passage.The temporally cycle of server 120, from
User voice data extraction of the family in history voice conversation represents the Feature Words of user's request, and it is respective to obtain these Feature Words
Occurrence number accounts for the accounting of the occurrence number sum of these Feature Words, and the accounting to be obtained in current time period, with working as
Difference between the accounting that historical time cycle before the preceding time cycle obtains is more than preset difference value and inconsistent with default word
Feature Words distribution personal call passage so that user enjoys consulting, the service such as business handling that seat personnel provides.
Fig. 2 is the internal structure schematic diagram of one embodiment Computer equipment.The computer equipment can be taken in Fig. 1
Business device 120.As shown in Fig. 2 the computer equipment include by system bus connection processor, non-volatile memory medium,
Built-in storage and network interface.Wherein, the non-volatile memory medium of the computer equipment can storage program area and computer
Executable instruction, when the computer executable instructions are performed, it may be such that a kind of communicating data processing method of computing device.Should
The processor of computer equipment is used to provide calculating and control ability, supports the operation of whole computer equipment.The built-in storage
In can store computer executable instructions, when the computer executable instructions are executed by processor, the computer is executable to be referred to
A kind of communicating data processing method provided for realizing following embodiment is provided.The computer equipment can also by network with
User terminal and/or terminal of attending a banquet connection, receive user terminal and/or the speech data of terminal of attending a banquet transmission.Art technology
Personnel are appreciated that the structure shown in Fig. 2, and only the block diagram of the part-structure related to application scheme, is not formed
The restriction for the terminal being applied thereon to application scheme, specific terminal can include more more or less than shown in figure
Part, either combine some parts or arranged with different parts.
As shown in figure 3, in one embodiment, there is provided a kind of communicating data processing method.The present embodiment is mainly with this
Method is applied to the server 120 in above-mentioned Fig. 1 to illustrate.Reference picture 3, the communicating data processing method specifically include as
Lower step:
S302, temporally the cycle obtain history voice conversation in user voice data.
Wherein, voice conversation is the session that voice answer is carried out between seat personnel and user.User voice data be
The speech data of caused user during voice conversation.History voice conversation is the voice conversation having occurred and that.Time cycle
Refer to the cycle for carrying out data acquisition, such as one or more days, week or the moon.
Specifically, server judges whether the time reaches the cycle for meeting the time cycle instantly after the time cycle is formulated
Property time point.For example daily predetermined time of periodic point in time is monthly preset day.Server is judging that the time reaches week instantly
During phase property time point, the user voice data in history voice conversation is obtained.Wherein, user voice data is stored in server
Database, file or caching etc..
In one embodiment, user terminal can pass through telephone network by way of dialing service number with server
Voice conversation is established, user's caused speech data in voice conversation is gathered, the user voice data of collection is passed through into phone
Network is sent to server.The user voice data received can be stored in database, caching or file by server, with
Read when needing.
In one embodiment, user terminal can also be established by initiating the network request of voice conversation with server
Internet connects, and so as to establish the voice conversation based on internet, gathers user's caused speech data in voice conversation, will
The user voice data of collection is sent to server by internet.The user voice data received can be stored in by server
In database, caching or file, to be read when needing.
S304, the session text obtained to identification user voice data segment to obtain feature word set.
Wherein, participle refers to a continuous character string being cut into multiple individually character or character strings.It is special
Sign word refers to the character or character string with semantic meaning representation function.
Specifically, server can carry out feature extraction to user voice data, obtain user vocal feature number to be identified
According to being then based on acoustic model and carry out voice sub-frame processing to user vocal feature data to be identified obtaining multiple phonemes, root
According to the corresponding relation of candidate word and phoneme in candidate's character library, multiple phonemes that processing obtains are converted into character string, recycled
The character string that language model adjustment conversion obtains, so as to obtain the session text for meeting natural language pattern.
Further, server can use default participle mode to carry out word segmentation processing to session text, obtain multiple words
Symbol or character string, filtered out from obtained character string with actual semantic character or character string as feature
Word, form feature word set.Feature word set can include one or more Feature Words.Wherein, default participle mode can be base
In character match, the participle mode based on semantic understanding or based on statistics.
Further, server filtered out from obtained character or character string with actual semantic character or
When character string is as Feature Words, specifically stop words can be filtered out from obtained character or character string.Wherein, stop words is
Refer to a kind of function character functional character or character string that natural language includes, this kind of function character functional character or character string have no actual language
Justice, including represent the tone character or character string and expression certain logical relation concatenation character or character string etc. of the tone.Tool
Body, tone character such as " " or " " etc., concatenation character such as " " or " " etc., tone character string such as " and
" or " being exactly " etc., concatenation character sequence such as " as " or " then " etc..
S306, obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words.
Wherein, the occurrence number of Feature Words is that Feature Words occur in the session text for identifying to obtain by user voice data
Number.Specifically, server can unite after the session text obtained to identification user voice data segments to obtain feature word set
Meter Feature Words concentrate the number that each Feature Words occur in the session text for identifying to obtain by user voice data, obtain each feature
The occurrence number of word, then be calculated each Feature Words occurrence number account for each Feature Words occurrence number sum accounting.
For example, Feature Words, which are concentrated, includes " health insurance ", " all-purpose card " and " medical insurance " three Feature Words.Wherein,
Feature Words " health insurance " obtain the number occurred in the session text for identifying to obtain by user voice data in current time period
For 185 times, Feature Words " all-purpose card " go out in current time period obtains the session text for identifying to obtain by user voice data
Existing number is 260 times, the meeting that Feature Words " medical insurance " are identified to obtain in current time period acquisition by user voice data
In words text the number that occurs for 97 so, the occurrence numbers of Feature Words " health insurance " account for each Feature Words occurrence number it
The accounting of sum is:185/ (185+160+97)=41.86%.
S308, the accounting that each Feature Words obtain in current time period is determined, with the history before current time period
Difference between the accounting that time cycle obtains.
Specifically, each Feature Words that server can be concentrated for the Feature Words obtained in current time period, are obtained
During current time period, occurrence number accounts for the accounting of the occurrence number sum of each Feature Words, and before current time period
The historical time cycle when, occurrence number accounts for the accounting of the occurrence number sum of each Feature Words, then calculates between two accountings
Difference.Wherein, the historical time cycle before current time period can be the upper time adjacent with current time period
Cycle any time of cycle or time before current time period.
S310, choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word.
Wherein, preset difference value is the accounting that the Feature Words pre-set obtain in current time period, and in current time
Difference between the accounting that the historical time cycle before cycle obtains.Preset difference value is configured as selection distribution personal call and led to
The condition of the Feature Words in road.When the accounting that Feature Words obtain in current time period, with the history before current time period
Difference between the accounting that time cycle obtains is more than preset difference value, then judges that this feature word meets to be allocated personal call passage
Condition.Default word is the Feature Words pre-set, and server distributes corresponding personal call passage for default word.
Specifically, each Feature Words that server can be concentrated in the Feature Words for being obtained in current time period determine should
The accounting that Feature Words obtain in current time period, with before current time period the historical time cycle obtain accounting it
Between difference after, by each difference of determination one by one compared with preset difference value, filter out the difference that mutually should determine that be more than it is default
The Feature Words of difference.Server can choose the feature inconsistent with default word again by the Feature Words filtered out compared with default word
Word.
S312, corresponding personal call passage is distributed for the Feature Words of selection.
Wherein, personal call passage is the talking path for being exclusively used in a certain specific transactions.For example it is exclusively used in the logical of health insurance
Talking path, or it is exclusively used in the talking path of medical insurance.Specifically, the Feature Words that server is chosen represent user's current focus
Emphasis, server can distribute corresponding passage for this feature word after selected characteristic word, provide corresponding exclusive service.
Above-mentioned communicating data processing method, temporally user voice data of the cycle from user in history voice conversation carry
Substitute the Feature Words of table user's request, obtain the occurrence number sum that the respective occurrence number of these Feature Words accounts for these Feature Words
Accounting, and the accounting that each Feature Words obtain in current time period is determined, with the historical time before current time period
Difference between the accounting that cycle obtains.When the corresponding difference of Feature Words be more than preset difference value and it is inconsistent with default word when, sentence
The related portfolio showed increased of fixed recent this feature word, distributes personal call passage for this feature word automatically, can so lead to
The personal call passage for crossing distribution actively provides the user the information of Feature Words related service, so as to improve the effect of phone interaction
Rate.
In one embodiment, step S304 includes:The session text obtained to identification user voice data segments to obtain
Independent word;The semanteme as belonging to independent word classifies to obtain independent lexon collection to independent word;Select each individually lexon and concentrate occurrence number
The independent word of highest obtains feature word set as Feature Words.Step S306 includes:Each Feature Words are concentrated for Feature Words, are obtained
Current signature word selects the occurrence number sum that independent lexon certainly concentrates each individually word, goes out occurrence as current signature word
Number;Determine that the occurrence number of each Feature Words accounts for the accounting of the occurrence number sum of each Feature Words.
Wherein, independent word is to represent single semantic character or character string.
In one embodiment, server can carry out word segmentation processing using the participle mode based on character match, it will words
Text is syncopated as single character one by one according to order from front to back or from back to front, then by the single character and standard dictionary
Matched.If the match is successful, the character is obtained as an independent word;If it fails to match, by increasing a word
Symbol continues to match, until character all matching completions that session text includes.
In one embodiment, server can also carry out positive matching participle and reverse matching point to session text simultaneously
Word.When the word segmentation result that two kinds segment modes is identical, will segment obtained multiple individually characters or character strings as
Independent word.When the word segmentation result that two kinds segment mode differs, the single character that two kinds of participle modes obtain is calculated respectively
Or the quantity of character string, single character or character string that the few participle mode of quantity of calculating obtains are chosen to make
For independent word.
Further, server can determine that obtained each individually semanteme belonging to word, by the affiliated semantic independent word of identical
Same class is divided into, obtains multiple individually lexon collection.For each obtained independent lexon collection, server can be selected therefrom again
Go out the independent word of occurrence number highest as Feature Words, to represent corresponding individually lexon collection, so as to obtain feature word set.For
The each Feature Words of Feature Words concentration, because the independent word that lexon is concentrated each individually belongs to identical semanteme, server can be by respectively
Feature Words select the occurrence number sum that independent lexon certainly concentrates each individually word, the occurrence number as each Feature Words;Count again
Calculate each Feature Words occurrence number account for each Feature Words occurrence number sum accounting.
In above-described embodiment, identical semantic independent word will be belonged to and be divided into same class, and therefrom select occurrence number most
Then Feature Words as representative are selected independent lexon certainly and concentrated by high independent word as representing, the appearance of each individually word
Occurrence number of the number sum as this feature word so that it is more reasonable to the statistics of Feature Words occurrence number, so that selecting
The Feature Words gone out can more reflect the emphasis of user's current focus.
In one embodiment, the communicating data processing method also includes:Collect each history clothes corresponding to mark of attending a banquet
Business data;It is determined that the degree of correlation between the history service data for mark of respectively attending a banquet and the Feature Words of selection;According to degree of correlation descending
Corresponding mark of attending a banquet is ranked up;The mark of attending a banquet of preset ratio is chosen from the mark of attending a banquet of sequence is the first;It will choose
Attend a banquet terminal association attended a banquet corresponding to mark to personal call passage.
Wherein, mark of attending a banquet is used for one seat personnel of unique mark.Mark of attending a banquet can include numeral, letter and symbol
Number at least one of character character string.History service data refers to that seat personnel provides the user online in historical time
Business consultation and the online message registration of business handling.History service data include connected online call quantity, often lead to
The data such as the corresponding message registration of line call and user feedback.
Specifically, server can obtain each history service data corresponding to mark of attending a banquet, and calculate going through for mark of respectively attending a banquet
The degree of correlation between history service data and the Feature Words of selection, so as to be arranged according to the degree of correlation corresponding mark of attending a banquet
Sequence.During sequence, according to degree of correlation descending sort, high forward of the degree of correlation and the degree of correlation is low rearward.Server can be again from sequence
Mark of attending a banquet in, since degree of correlation highest attends a banquet mark, according to sequence attend a banquet mark total amount preset percentage come
Selection is attended a banquet mark.Such as shared X mark sequences of attending a banquet, then X*10% in the top mark of attending a banquet is taken, is now preset
Ratio can be 10%.Server can be corresponding with the Feature Words of selection special again by the terminal of being attended a banquet corresponding to mark of attending a banquet of selection
Associated with talking path.
In the present embodiment, the degree of correlation between the history service data for mark of attending a banquet and the Feature Words of selection as according to
According to the personal call passage for the Feature Words distribution of selection associates terminal of attending a banquet, and is provided the user by known seat personnel
Service, so as to improve the efficiency of phone interaction.
In one embodiment, the communicating data processing method also includes:The backward use of communication connection is established with user terminal
Family terminal sends voice guidance message;The personal call passage that real-time reception user terminal selects according to guidance information;Establish and use
Communication connection between family terminal terminal of attending a banquet corresponding with the personal call passage of selection.
Wherein, voice guidance message is the information for guiding user to select business service.For example health insurance consulting please perform XX
Operation, universal life insurance account inquiries please perform XX operations etc..
Specifically, server can call IVR system to send voice guidance message, the voice guidance message bag to user terminal
Include the information of voice prompt of the selection to type of service.User terminal can play the information of voice prompt, by acquired user
Operation information send to server.Server is after the operation information of user terminal transmission is received, according to default operation
Feature Words corresponding to corresponding relation determination between information and Feature Words, and it is corresponding with the Feature Words determined to establish user terminal
Communication connection between terminal of being attended a banquet corresponding to personal call passage.
In the present embodiment, server obtains the personal call passage of user's selection by voice guidance message, builds in real time
Communication connection between vertical user terminal terminal of attending a banquet corresponding with the personal call passage, so as to be connected in real time as this is special
The professional seat personnel distributed with talking path carries out phone with user and interacted, and improves phone interactive efficiency.
In one embodiment, the communicating data processing method also includes:It is determined that the service class belonging to the Feature Words chosen
Type;Professional knowledge information is obtained from Service Database corresponding with type of service;According to the generation of professional knowledge information and business
Response template corresponding to type;Response template is sent to the terminal of being attended a banquet corresponding to mark of attending a banquet of selection.
Wherein, type of service includes card industry service type, banking type, stock exchange transaction type and insurance business
Type etc. is therein a variety of.And insurance business type may include life insurance business type, health insurance type of service, Investment-linked insurance business
The subservice type such as type.
Specifically, attend a banquet and the Feature Words of multiple types of service are stored in Service Database.And it is provided with every kind of service class
The corresponding relation of type and one or more Feature Words, has the Feature Words of corresponding relation with type of service, is as subordinated to the industry
The Feature Words of service type.Server, can be according to this feature word corresponding service class after the Feature Words that user terminal is chosen are determined
The corresponding relation of type, determine the type of service belonging to it.
Further, server is provided with calling interface corresponding with Service Database also directed to different service types, and
The interface interchange resource of corresponding identical or different quantity is assigned with for different types of service.After type of service is determined, clothes
Being engaged in device can be according to interface corresponding with the type of service be called, and Service Database corresponding with the type of service establishes connection.
Further, the professional knowledge information of the Service Database corresponding service type is stored in Service Database.
Professional knowledge information includes business relevant knowledge and problem and the knowledge information answered.Knowledge information includes some professional term solution
Release, the information such as calculation formula, operation flow.Server Service Database corresponding with the type of service establish connection after, from
Professional knowledge information is obtained in the Service Database.Server can generate corresponding with type of service further according to professional knowledge information
Response template, and response template is sent to the terminal of being attended a banquet corresponding to mark of attending a banquet of selection.
In the present embodiment, known by further automatically providing the business related to Feature Words inquired to terminal of attending a banquet
Know information and response template, make seat personnel in the related professional knowledge information of needs retrieval to answer the problem of user seeks advice from
When, improve the acquisition efficiency to problem answers.
As shown in figure 4, in a specific embodiment, communicating data processing method comprises the following steps:
S402, temporally the cycle obtain history voice conversation in user voice data.
S404, the session text obtained to identification user voice data segment to obtain independent word;It is semantic as belonging to independent word
Independent word is classified to obtain independent lexon collection;Selecting each individually lexon concentrates the independent word of occurrence number highest to be obtained as Feature Words
To feature word set.
S406, each Feature Words are concentrated for Feature Words, acquisition current signature word selects independent lexon certainly and concentrates each list
The occurrence number sum of only word, the occurrence number as current signature word;Determine that the occurrence number of each Feature Words accounts for each Feature Words
Occurrence number sum accounting.
S408, the accounting that each Feature Words obtain in current time period is determined, with the history before current time period
Difference between the accounting that time cycle obtains.
S410, choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;For selection
Feature Words distribute corresponding personal call passage.
S412, collect each history service data corresponding to mark of attending a banquet;It is determined that the history service data for mark of respectively attending a banquet
The degree of correlation between the Feature Words of selection;Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;From the seat of sequence
Seat mark is the first to act the mark of attending a banquet for choosing preset ratio;Attending a banquet for selection is attended a banquet into terminal association to special logical corresponding to mark
Talking path.
S414, it is determined that the type of service belonging to the Feature Words chosen;Obtained from Service Database corresponding with type of service
Take professional knowledge information;Response template corresponding with type of service is generated according to professional knowledge information;By response template send to
The terminal of being attended a banquet corresponding to mark of attending a banquet chosen.
S416, establish communication connection rear line terminal with user terminal and send voice guidance message;Real-time reception user
The personal call passage that terminal selects according to guidance information;Establish user terminal and corresponding attended a banquet with the personal call passage selected
Communication connection between terminal.
In the present embodiment, temporally user voice data extraction of the cycle from user in history voice conversation represents use
The Feature Words of family demand, the accounting that the respective occurrence number of these Feature Words accounts for the occurrence number sum of these Feature Words is obtained,
And the accounting that each Feature Words obtain in current time period is determined, obtained with the historical time cycle before current time period
Accounting between difference.When the corresponding difference of Feature Words be more than preset difference value and it is inconsistent with default word when, judge in the recent period should
The related portfolio showed increased of Feature Words, distributes personal call passage for this feature word automatically, can so pass through distribution
Personal call passage actively provides the user the information of Feature Words related service, so as to improve the efficiency of phone interaction.
Secondly, the personal call passage for the distribution of this feature word, which is associated with corresponding to familiar high seat personnel, attends a banquet end
End, and the professional knowledge information related to Feature Words and response template inquired is provided, make seat personnel need to retrieve phase
During the problem of professional knowledge information of pass is to answer user's consulting, the acquisition efficiency to problem answers is improved, is further increased
The efficiency of phone interaction.
As shown in figure 5, in one embodiment, there is provided a kind of communicating data processing unit 500, communicating data processing
Device 500 includes:First acquisition module 501, word-dividing mode 502, the second acquisition module 503, determining module 504, selection module
505 and distribute module 506.
First acquisition module 501, the user voice data in history voice conversation is obtained for the temporally cycle.
Word-dividing mode 502, the session text for being obtained to identification user voice data segment to obtain feature word set.
Second acquisition module 503, the occurrence number of each Feature Words is concentrated to account for the appearance of each Feature Words for obtaining Feature Words
The accounting of number sum.
Determining module 504, the accounting obtained for determining each Feature Words in current time period, and in current time period
Difference between the accounting that the historical time cycle before obtains.
Module 505 is chosen, is more than preset difference value and the feature inconsistent with default word for choosing the difference that mutually should determine that
Word.
Distribute module 506, for distributing corresponding personal call passage for the Feature Words of selection.
Above-mentioned communicating data processing unit 500, temporally user speech number of the cycle from user in history voice conversation
The Feature Words of user's request are represented according to extraction, obtain the occurrence number that the respective occurrence number of these Feature Words accounts for these Feature Words
The accounting of sum, and the accounting that each Feature Words obtain in current time period is determined, with the history before current time period
Difference between the accounting that time cycle obtains.When the corresponding difference of Feature Words is more than preset difference value and inconsistent with default word
When, judge the related portfolio showed increased of recent this feature word, distribute personal call passage automatically for this feature word, so i.e.
The information of Feature Words related service can be actively provided the user by the personal call passage of distribution, so as to improve phone interaction
Efficiency.
In one embodiment, word-dividing mode 502 is additionally operable to segment the session text that identification user voice data obtains
Obtain independent word;The semanteme as belonging to independent word classifies to obtain independent lexon collection to independent word;Select each individually lexon and concentrate and occur
The independent word of number highest obtains feature word set as Feature Words.Second acquisition module 503 is additionally operable to concentrate often for Feature Words
Individual Feature Words, obtain current signature word and select the occurrence number sum that independent lexon certainly concentrates each individually word, as current spy
Levy the occurrence number of word;Determine that the occurrence number of each Feature Words accounts for the accounting of the occurrence number sum of each Feature Words.
In the present embodiment, identical semantic independent word will be belonged to and is divided into same class, and therefrom select occurrence number most
Then Feature Words as representative are selected independent lexon certainly and concentrated by high independent word as representing, the appearance of each individually word
Occurrence number of the number sum as this feature word so that it is more reasonable to the statistics of Feature Words occurrence number, so that selecting
The Feature Words gone out can more reflect the emphasis of user's current focus.
As shown in fig. 6, in one embodiment, communicating data processing unit 500 also includes:Relating module 507.
Relating module 507, for collecting each history service data corresponding to mark of attending a banquet;It is determined that mark of respectively attending a banquet is gone through
The degree of correlation between history service data and the Feature Words of selection;Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;
The mark of attending a banquet of preset ratio is chosen from the mark of attending a banquet of sequence is the first;By the terminal pass of being attended a banquet corresponding to mark of attending a banquet of selection
It is coupled to personal call passage.
In the present embodiment, the degree of correlation between the history service data for mark of attending a banquet and the Feature Words of selection as according to
According to the personal call passage for the Feature Words distribution of selection associates terminal of attending a banquet, and is provided the user by known seat personnel
Service, so as to improve the efficiency of phone interaction.
In one embodiment, relating module 507 is additionally operable to establish communication connection rear line terminal hair with user terminal
Sending voice guidance information;The personal call passage that real-time reception user terminal selects according to guidance information;Establish user terminal with
Communication connection between terminal of being attended a banquet corresponding to the personal call passage of selection.
In the present embodiment, server obtains the personal call passage of user's selection by voice guidance message, builds in real time
Communication connection between vertical user terminal terminal of attending a banquet corresponding with the personal call passage, so as to be connected in real time as this is special
The professional seat personnel distributed with talking path carries out phone with user and interacted, and improves phone interactive efficiency.
In one embodiment, relating module 507 is additionally operable to determine the type of service belonging to the Feature Words of selection;From with industry
Professional knowledge information is obtained in Service Database corresponding to service type;Generated according to professional knowledge information corresponding with type of service
Response template;Response template is sent to the terminal of being attended a banquet corresponding to mark of attending a banquet of selection.
In the present embodiment, known by further automatically providing the business related to Feature Words inquired to terminal of attending a banquet
Know information and response template, make seat personnel in the related professional knowledge information of needs retrieval to answer the problem of user seeks advice from
When, improve the acquisition efficiency to problem answers.
In one embodiment, there is provided a kind of computer-readable recording medium, store on computer-readable recording medium
There are computer executable instructions, when computer executable instructions are executed by processor so that computing device following steps:On time
Between the cycle obtain history voice conversation in user voice data;The session text obtained to identification user voice data segments
To feature word set;Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;Really
The accounting that fixed each Feature Words obtain in current time period, with accounting for for the historical time cycle acquisition before current time period
Difference than between;Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;For selection
Feature Words distribute corresponding personal call passage.
In one embodiment, the session text obtained to identification user voice data segments to obtain feature word set, including:
The session text obtained to identification user voice data segments to obtain independent word;Semanteme is classified to independent word as belonging to independent word
To independent lexon collection;Selecting each individually lexon concentrates the independent word of occurrence number highest to obtain feature word set as Feature Words.Obtain
The accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words is taken, including:For Feature Words
Each Feature Words are concentrated, current signature word is obtained and selects the occurrence number sum that independent lexon certainly concentrates each individually word, as
The occurrence number of current signature word;Determine that the occurrence number of each Feature Words accounts for the accounting of the occurrence number sum of each Feature Words.
In one embodiment, when computer executable instructions are executed by processor, also to walk below computing device
Suddenly:Collect each history service data corresponding to mark of attending a banquet;It is determined that the history service data for mark of respectively attending a banquet and the spy chosen
Levy the degree of correlation between word;Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;It is the first from the mark of attending a banquet of sequence
Act the mark of attending a banquet for choosing preset ratio;Attending a banquet for selection is attended a banquet into terminal association to personal call passage corresponding to mark.
In one embodiment, when computer executable instructions are executed by processor, also to walk below computing device
Suddenly:Communication connection rear line terminal, which is established, with user terminal sends voice guidance message;Real-time reception user terminal is according to drawing
Lead the personal call passage of information selection;Establish between user terminal terminal of attending a banquet corresponding with the personal call passage of selection
Communication connection.
In one embodiment, when computer executable instructions are executed by processor, also to walk below computing device
Suddenly:It is determined that the type of service belonging to the Feature Words chosen;Professional knowledge is obtained from Service Database corresponding with type of service
Information;Response template corresponding with type of service is generated according to professional knowledge information;Response template is sent into attending a banquet to selection
Attended a banquet corresponding to mark terminal.
Above-mentioned storage medium, temporally user voice data extraction of the cycle from user in history voice conversation, which represents, uses
The Feature Words of family demand, the accounting that the respective occurrence number of these Feature Words accounts for the occurrence number sum of these Feature Words is obtained,
And the accounting that each Feature Words obtain in current time period is determined, obtained with the historical time cycle before current time period
Accounting between difference.When the corresponding difference of Feature Words be more than preset difference value and it is inconsistent with default word when, judge in the recent period should
The related portfolio showed increased of Feature Words, distributes personal call passage for this feature word automatically, can so pass through distribution
Personal call passage actively provides the user the information of Feature Words related service, so as to improve the efficiency of phone interaction.
In one embodiment, there is provided a kind of computer equipment, including memory and processor, store in memory
Computer executable instructions, when computer executable instructions are executed by processor so that computing device following steps:Temporally
Cycle obtains the user voice data in history voice conversation;The session text obtained to identification user voice data segments to obtain
Feature word set;Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;It is determined that
The accounting that each Feature Words obtain in current time period, the accounting obtained with the historical time cycle before current time period
Between difference;Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;For the spy of selection
Levy word and distribute corresponding personal call passage.
In one embodiment, the session text obtained to identification user voice data segments to obtain feature word set, including:
The session text obtained to identification user voice data segments to obtain independent word;Semanteme is classified to independent word as belonging to independent word
To independent lexon collection;Selecting each individually lexon concentrates the independent word of occurrence number highest to obtain feature word set as Feature Words.Obtain
The accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words is taken, including:For Feature Words
Each Feature Words are concentrated, current signature word is obtained and selects the occurrence number sum that independent lexon certainly concentrates each individually word, as
The occurrence number of current signature word;Determine that the occurrence number of each Feature Words accounts for the accounting of the occurrence number sum of each Feature Words.
In one embodiment, when computer executable instructions are executed by processor, also to walk below computing device
Suddenly:Collect each history service data corresponding to mark of attending a banquet;It is determined that the history service data for mark of respectively attending a banquet and the spy chosen
Levy the degree of correlation between word;Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;It is the first from the mark of attending a banquet of sequence
Act the mark of attending a banquet for choosing preset ratio;Attending a banquet for selection is attended a banquet into terminal association to personal call passage corresponding to mark.
In one embodiment, when computer executable instructions are executed by processor, also to walk below computing device
Suddenly:Communication connection rear line terminal, which is established, with user terminal sends voice guidance message;Real-time reception user terminal is according to drawing
Lead the personal call passage of information selection;Establish between user terminal terminal of attending a banquet corresponding with the personal call passage of selection
Communication connection.
In one embodiment, when computer executable instructions are executed by processor, also to walk below computing device
Suddenly:It is determined that the type of service belonging to the Feature Words chosen;Professional knowledge is obtained from Service Database corresponding with type of service
Information;Response template corresponding with type of service is generated according to professional knowledge information;Response template is sent into attending a banquet to selection
Attended a banquet corresponding to mark terminal.
Above computer equipment, temporally user voice data of the cycle from user in history voice conversation, which is extracted, represents
The Feature Words of user's request, obtain these Feature Words respective occurrence numbers and account for the occurrence number sums of these Feature Words and account for
Than, and the accounting that each Feature Words obtain in current time period is determined, with the historical time cycle before current time period
Difference between the accounting of acquisition.When the corresponding difference of Feature Words be more than preset difference value and it is inconsistent with default word when, judge near
The related portfolio showed increased of phase this feature word, distributes personal call passage for this feature word automatically, so can be by dividing
The personal call passage matched somebody with somebody actively provides the user the information of Feature Words related service, so as to improve the efficiency of phone interaction.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, described program can be stored in a non-volatile computer and can be read
In storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage is situated between
Matter can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc..
Each technical characteristic of above example can be combined arbitrarily, to make description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, lance is not present in the combination of these technical characteristics
Shield, all it is considered to be the scope of this specification record.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of communicating data processing method, methods described include:
Temporally the cycle obtains the user voice data in history voice conversation;
To identifying that the session text that the user voice data obtains segments to obtain feature word set;
Obtain the accounting for the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words;
The accounting that each Feature Words obtain in current time period is determined, with the historical time week before current time period
Difference between the accounting that phase obtains;
Choose the difference that mutually should determine that and be more than preset difference value and the Feature Words inconsistent with default word;
Corresponding personal call passage is distributed for the Feature Words of selection.
2. according to the method for claim 1, it is characterised in that the session that the described pair of identification user voice data obtains
Text segments to obtain feature word set, including:
To identifying that the session text that the user voice data obtains segments to obtain independent word;
Semanteme classifies to obtain independent lexon collection to the individually word as belonging to the individually word;
Selecting each individually lexon concentrates the independent word of occurrence number highest to obtain feature word set as Feature Words;
The accounting for obtaining the occurrence number sum that Feature Words concentrate the occurrence number of each Feature Words to account for each Feature Words, including:
Each Feature Words are concentrated for Feature Words, current signature word is obtained and selects the appearance that independent lexon certainly concentrates each individually word
Number sum, the occurrence number as current signature word;
Determine that the occurrence number of each Feature Words accounts for the accounting of the occurrence number sum of each Feature Words.
3. according to the method for claim 1, it is characterised in that methods described also includes:
Collect each history service data corresponding to mark of attending a banquet;
It is determined that the degree of correlation between the history service data for mark of respectively attending a banquet and the Feature Words of selection;
Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;
The mark of attending a banquet of preset ratio is chosen from the mark of attending a banquet of sequence is the first;
Attending a banquet for selection is attended a banquet into terminal association to the personal call passage corresponding to mark.
4. according to the method for claim 3, it is characterised in that methods described also includes:
Established with user terminal after communication connection and send voice guidance message to the user terminal;
The personal call passage that user terminal described in real-time reception selects according to the guidance information;
The communication connection established between user terminal terminal of attending a banquet corresponding with the personal call passage of selection.
5. according to the method for claim 3, it is characterised in that methods described also includes:
It is determined that the type of service belonging to the Feature Words chosen;
Professional knowledge information is obtained from Service Database corresponding with the type of service;
Response template corresponding with the type of service is generated according to the professional knowledge information;
The response template is sent to terminal of being attended a banquet corresponding to mark of being attended a banquet described in selection.
6. a kind of communicating data processing unit, described device include:
First acquisition module, the user voice data in history voice conversation is obtained for the temporally cycle;
Word-dividing mode, for identifying that the session text that the user voice data obtains segments to obtain feature word set;
Second acquisition module, the occurrence number of each Feature Words is concentrated to account for the occurrence number sum of each Feature Words for obtaining Feature Words
Accounting;
Determining module, the accounting obtained for determining each Feature Words in current time period, with current time period it
Difference between the accounting that the preceding historical time cycle obtains;
Module is chosen, is more than preset difference value and the Feature Words inconsistent with default word for choosing the difference that mutually should determine that;
Distribute module, for distributing corresponding personal call passage for the Feature Words of selection.
7. device according to claim 6, it is characterised in that the word-dividing mode is additionally operable to identifying the user speech
The session text that data obtain segments to obtain independent word;Semanteme classifies to obtain individually to the individually word as belonging to the individually word
Lexon collection;Selecting each individually lexon concentrates the independent word of occurrence number highest to obtain feature word set as Feature Words;
Second acquisition module is additionally operable to concentrate each Feature Words for Feature Words, obtains current signature word and selects certainly independent
Lexon concentrates the occurrence number sum of each individually word, the occurrence number as current signature word;Determine each Feature Words goes out occurrence
Number accounts for the accounting of the occurrence number sum of each Feature Words.
8. device according to claim 6, it is characterised in that described device also includes:
Relating module, for collecting each history service data corresponding to mark of attending a banquet;It is determined that the history service for mark of respectively attending a banquet
The degree of correlation between data and the Feature Words of selection;Corresponding mark of attending a banquet is ranked up according to degree of correlation descending;From
The mark of attending a banquet of sequence is the first to act the mark of attending a banquet for choosing preset ratio;By the terminal association of being attended a banquet corresponding to mark of attending a banquet of selection
To the personal call passage.
9. a kind of computer-readable recording medium, it is characterised in that be stored with computer on the computer-readable recording medium
Executable instruction, when the computer executable instructions are executed by processor so that the computing device such as claim 1 to
The step of method any one of 5.
10. a kind of computer equipment, including memory and processor, computer executable instructions are stored in the memory,
When the computer executable instructions are by the computing device so that any in the computing device such as claim 1 to 5
Described in method the step of.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710612991.2A CN107800900B (en) | 2017-07-25 | 2017-07-25 | Call data processing method and device, storage medium and computer equipment |
PCT/CN2018/087327 WO2019019778A1 (en) | 2017-07-25 | 2018-05-17 | Method and apparatus for processing call data, storage medium and computer device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710612991.2A CN107800900B (en) | 2017-07-25 | 2017-07-25 | Call data processing method and device, storage medium and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107800900A true CN107800900A (en) | 2018-03-13 |
CN107800900B CN107800900B (en) | 2020-08-28 |
Family
ID=61531124
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710612991.2A Active CN107800900B (en) | 2017-07-25 | 2017-07-25 | Call data processing method and device, storage medium and computer equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107800900B (en) |
WO (1) | WO2019019778A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019019778A1 (en) * | 2017-07-25 | 2019-01-31 | 平安科技(深圳)有限公司 | Method and apparatus for processing call data, storage medium and computer device |
CN109543177A (en) * | 2018-10-19 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Message data processing method, device, computer equipment and storage medium |
CN111901554A (en) * | 2020-07-27 | 2020-11-06 | 中国平安人寿保险股份有限公司 | Call channel construction method and device based on semantic clustering and computer equipment |
CN113129866A (en) * | 2021-04-13 | 2021-07-16 | 重庆度小满优扬科技有限公司 | Voice processing method, device, storage medium and computer equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101094271A (en) * | 2007-07-20 | 2007-12-26 | 华为技术有限公司 | Method and device for creating menu of automatic voice responsion system |
WO2015047272A1 (en) * | 2013-09-26 | 2015-04-02 | Interactive Intelligence, Inc. | System and method for context based knowledge retrieval |
CN104598632A (en) * | 2015-02-05 | 2015-05-06 | 北京航空航天大学 | Hot event detection method and device |
US9036806B1 (en) * | 2014-08-27 | 2015-05-19 | Xerox Corporation | Predicting the class of future customer calls in a call center |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104375847B (en) * | 2013-08-14 | 2017-12-05 | 华为技术有限公司 | Identify the method and device of type of service |
CN107800900B (en) * | 2017-07-25 | 2020-08-28 | 平安科技(深圳)有限公司 | Call data processing method and device, storage medium and computer equipment |
-
2017
- 2017-07-25 CN CN201710612991.2A patent/CN107800900B/en active Active
-
2018
- 2018-05-17 WO PCT/CN2018/087327 patent/WO2019019778A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101094271A (en) * | 2007-07-20 | 2007-12-26 | 华为技术有限公司 | Method and device for creating menu of automatic voice responsion system |
WO2015047272A1 (en) * | 2013-09-26 | 2015-04-02 | Interactive Intelligence, Inc. | System and method for context based knowledge retrieval |
US9036806B1 (en) * | 2014-08-27 | 2015-05-19 | Xerox Corporation | Predicting the class of future customer calls in a call center |
CN104598632A (en) * | 2015-02-05 | 2015-05-06 | 北京航空航天大学 | Hot event detection method and device |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019019778A1 (en) * | 2017-07-25 | 2019-01-31 | 平安科技(深圳)有限公司 | Method and apparatus for processing call data, storage medium and computer device |
CN109543177A (en) * | 2018-10-19 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Message data processing method, device, computer equipment and storage medium |
CN109543177B (en) * | 2018-10-19 | 2022-04-12 | 中国平安人寿保险股份有限公司 | Message data processing method and device, computer equipment and storage medium |
CN111901554A (en) * | 2020-07-27 | 2020-11-06 | 中国平安人寿保险股份有限公司 | Call channel construction method and device based on semantic clustering and computer equipment |
CN111901554B (en) * | 2020-07-27 | 2022-11-11 | 中国平安人寿保险股份有限公司 | Call channel construction method and device based on semantic clustering and computer equipment |
CN113129866A (en) * | 2021-04-13 | 2021-07-16 | 重庆度小满优扬科技有限公司 | Voice processing method, device, storage medium and computer equipment |
CN113129866B (en) * | 2021-04-13 | 2022-08-02 | 重庆度小满优扬科技有限公司 | Voice processing method, device, storage medium and computer equipment |
Also Published As
Publication number | Publication date |
---|---|
WO2019019778A1 (en) | 2019-01-31 |
CN107800900B (en) | 2020-08-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11425254B2 (en) | Systems and methods for chatbot generation | |
CN107800900A (en) | Communicating data processing method, device, storage medium and computer equipment | |
US6937705B1 (en) | Apparatus and method for visually representing events in calls handled by an automated response system | |
US6823054B1 (en) | Apparatus and method for analyzing an automated response system | |
CN108521525A (en) | Intelligent robot customer service marketing method and system based on user tag system | |
CN108764649A (en) | Insurance sales method for real-time monitoring, device, equipment and storage medium | |
US8774372B2 (en) | Telephone call inbox | |
CN112346567A (en) | Virtual interaction model generation method and device based on AI (Artificial Intelligence) and computer equipment | |
CN111625632A (en) | Question-answer pair recommendation method, device, equipment and storage medium | |
CN106095834A (en) | Intelligent dialogue method and system based on topic | |
CN104375847B (en) | Identify the method and device of type of service | |
JP2009528614A (en) | General recommendation word and advertisement recommendation word automatic completion method and system | |
CN106378781A (en) | Service robot guide system and method | |
CN106022708A (en) | Method for predicting employee resignation | |
CN106682137A (en) | Intelligent stock investment adviser questioning-answering interaction method and intelligent stock investment adviser questioning-answering interaction system | |
US20220366127A1 (en) | Legal Document Generation | |
WO2021031985A1 (en) | Intelligent dialing method, apparatus, device, and computer readable storage medium | |
CN112434501A (en) | Work order intelligent generation method and device, electronic equipment and medium | |
CN108257600A (en) | Method of speech processing and device | |
US8750476B2 (en) | Media optimization using transcription analysis | |
CN107562457A (en) | The generation method and device of navigation menu | |
CN113486166B (en) | Construction method, device and equipment of intelligent customer service robot and storage medium | |
CN110399473A (en) | The method and apparatus for determining answer for customer problem | |
JP2017010374A (en) | Business support information providing system and business support information providing method | |
CN111858874A (en) | Conversation service processing method, device, equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |