CN109684475A - Processing method, device, equipment and the storage medium of complaint - Google Patents
Processing method, device, equipment and the storage medium of complaint Download PDFInfo
- Publication number
- CN109684475A CN109684475A CN201811389160.4A CN201811389160A CN109684475A CN 109684475 A CN109684475 A CN 109684475A CN 201811389160 A CN201811389160 A CN 201811389160A CN 109684475 A CN109684475 A CN 109684475A
- Authority
- CN
- China
- Prior art keywords
- complaint
- classification
- text
- textual
- complains
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the present invention provides processing method, device, equipment and the storage medium of a kind of complaint.The processing method that the present invention complains, text is complained by obtain reporting of user first, the complaint textual classification model that the first complaint text input is obtained in advance, obtaining described first complains the first of text to complain classification, and complain classification according to described first and reply corpus, the answer content that Xiang Suoshu user's push complains text to described first.The Fast Classification to customer complaint content is realized, and can timely and effectively complaint content be positioned and be solved.
Description
Technical field
The present embodiments relate to automotive field more particularly to a kind of processing method of complaint, device, equipment and storages
Medium.
Background technique
With the development of the times, internet and smart machine have incorporated the every aspect of our lives, and user is for producing
The complaint coverage area of product is increasing, and the channel of complaint is also more and more.And coming into operation with intelligent locomotive function, needle
The customer complaint of the function can also be emerged in multitude, and user complained by intelligent locomotive terminal it is also more convenient.
In the prior art, classification is carried out to the complaint of client and depends on artificial treatment, or simple simple pattra leaves
This classification is in the majority.
However, the scheme classification effectiveness of the prior art is low, and the accuracy classified is not also high, for customer complaint cannot and
When effectively position and solve.
Summary of the invention
The embodiment of the present invention provides processing method, device, equipment and the storage medium of a kind of complaint, compared to existing skill
Being unable to Accurate classification and the low problem of classification effectiveness, this programme for customer complaint in art realizes the standard to customer complaint
Really classification, and then can timely and effectively solve the problems, such as complaint.
In a first aspect, the embodiment of the present invention provides a kind of processing method of complaint, comprising:
Obtain reporting of user first complains text；
The complaint textual classification model that the first complaint text input is obtained in advance, obtains described first and complains text
First complain classification；
Classification is complained according to described first and replies corpus, and Xiang Suoshu user's push complains text to described first
Reply content.
Wherein, described to complain textual classification model for the classification for obtaining complaint text based on Recognition with Recurrent Neural Network training
Model includes the corresponding answer content of each complaint classification in the answer corpus.
In a kind of concrete implementation mode, before the first complaint text for obtaining reporting of user, the method is also
Include:
Sample set is complained in acquisition, includes multiple complaint samples of text and each complaint in the complaint sample set
The corresponding complaint classification of samples of text；
According to the complaint sample set, the complaint textual classification model is obtained using Recognition with Recurrent Neural Network training.
Further, the method also includes:
Feasibility verifying is carried out to the complaint textual classification model according to the test set obtained in advance；Wherein, the survey
The complaint classification of each complaint texts including multiple complaint texts and calibration is concentrated in examination；
If described complain textual classification model to be higher than preset value to the accuracy of the multiple classification results for complaining text,
Then determine that the complaint textual classification model is feasible.
In a kind of concrete implementation mode, the complaint text point that the first complaint text input is obtained in advance
Class model obtains described first and complains the first of text to complain classification, comprising:
Textual classification model will be complained described in the first complaint text input, obtains the first instruction information；Described first
Instruction information instruction to can not to it is described first complaint text classify；
New complaint classification is established, the new complaint classification is added in the first complaint text, described first complains
Classification is the new complaint classification.
In a kind of concrete implementation mode, the method also includes:
For the new complaint classification, the complaint textual classification model is updated.
Second aspect, the embodiment of the present invention provide a kind of processing unit of complaint, comprising:
Module is obtained, first for obtaining reporting of user complains text；
Classification processing module, the complaint textual classification model for obtaining the first complaint text input in advance, is obtained
Described first is taken to complain the first of text to complain classification；
Processing module is replied, for complaining classification according to described first and replying corpus, Xiang Suoshu user's push pair
Described first complains the answer content of text.
Wherein, described to complain textual classification model for the classification for obtaining complaint text based on Recognition with Recurrent Neural Network training
Model includes the corresponding answer content of each complaint classification in the answer corpus.
In a kind of concrete implementation mode, described device further include:
Acquisition module complains sample set for acquiring, and includes multiple complaint samples of text in the complaint sample set,
And each complaint classification for complaining samples of text corresponding；
Training managing module, for obtaining the throwing using Recognition with Recurrent Neural Network training according to the complaint sample set
Tell textual classification model.
Further, described device further include:
Verification processing module, for carrying out feasibility to the complaint textual classification model according to the test set obtained in advance
Verifying；It wherein, include the complaint classification of multiple each complaint texts for complaining texts and calibration in the test set；
Judgment module, if for the complaint textual classification model to the accurate of the multiple classification results for complaining text
Degree is higher than preset value, it is determined that the complaint textual classification model is feasible.
In a kind of concrete implementation mode, the classification processing module is specifically used for complaining text input for described first
The complaint textual classification model obtains the first instruction information；It is described first instruction information instruction to can not to it is described first throw
Tell that text is classified；
New complaint classification is established, the new complaint classification is added in the first complaint text, described first complains
Classification is the new complaint classification.
In a kind of concrete implementation mode, described device further include:
Update module is updated the complaint textual classification model for being directed to the new complaint classification.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, comprising: processor, memory and computer journey
Sequence；
The memory stores computer executed instructions；
The processor executes the computer executed instructions of the memory storage, so that at least one described processor is held
The processing method of the row such as described in any item complaints of first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, the computer-readable storage medium
It is stored with computer executed instructions in matter, when processor executes the computer executed instructions, realizes as first aspect is any
The processing method of complaint described in.
Processing method, device, equipment and the storage medium of a kind of complaint provided in an embodiment of the present invention are used by obtaining
The first complaint text that family reports, and the complaint textual classification model that the first complaint text input is obtained in advance, obtain first
It complains the first of text to complain classification, complain classification further according to first and replies corpus, complained to user's push to first
The answer content of text, realizes the Fast Classification to customer complaint content, and can timely and effectively to complaint content into
Row positioning and solution.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of the processing method embodiment one of complaint provided in an embodiment of the present invention；
Fig. 2 is a kind of complaint textual classification model schematic diagram provided in this embodiment；
Fig. 3 is a kind of flow diagram of the processing method embodiment two of complaint provided in an embodiment of the present invention；
Fig. 4 is a kind of flow diagram of the processing method embodiment three of complaint provided in an embodiment of the present invention；
Fig. 5 is a kind of flow diagram of the processing method example IV of complaint provided in an embodiment of the present invention；
Fig. 6 is a kind of flow diagram of the processing method embodiment five of complaint provided in an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of the processing device embodiment one of complaint provided in an embodiment of the present invention；
Fig. 8 is a kind of structural schematic diagram of the processing device embodiment two of complaint provided in an embodiment of the present invention；
Fig. 9 is a kind of structural schematic diagram of the processing device embodiment three of complaint provided in an embodiment of the present invention；
Figure 10 is the hardware structural diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the prior art, classification is carried out to the complaint of client and depends on artificial treatment, or simple simple pattra leaves
This classification is in the majority.It is low so as to cause scheme classification effectiveness, and the accuracy classified is not also high, cannot have in time for customer complaint
The positioning and solution of effect.
In view of the above problems, the present invention proposes that processing method, device, equipment and the storage of a kind of complaint are situated between
Matter.It is generated by complaining textual classification model to classify the complaint text of user, and according to corpus Auto-matching is replied
Content is replied, the accuracy of classification is improved, to more timely and effectively position and solve the problems, such as the complaint of user.Below by
The program is described in detail in several specific embodiments.
Fig. 1 is a kind of flow diagram of the processing method embodiment one of complaint provided in an embodiment of the present invention, such as Fig. 1 institute
Show, the processing method of the complaint, comprising:
S101: obtain reporting of user first complains text.
In this step, the first of reporting of user is obtained first and complains text, and the complaint text is with then to user's transmitting
The basis classified of calling information, which includes the calling information of user's input, such as text, voices etc..
Optionally, it can receive the calling information that user is reported by voice, converted calling information by speech recognition
Text is complained for first；Alternatively, directly receive the input of user's text first complains text；Alternatively, according to user by phone,
Wechat, mail or be to be commented in client, or the calling information for complaining the modes such as interface to transmit passes through contact staff's record
It generates first and complains text.
S102: the complaint textual classification model that the first complaint text input is obtained in advance obtains first and complains text
First complains classification.
In this step, first will acquire complains text input to complain in textual classification model, complains text classification mould
Type will export the first complaint text corresponding first and complain classification.The complaint textual classification model is to be obtained in advance based on following
The model of the classification for obtaining complaint text of ring neural metwork training.
In a kind of concrete implementation mode, textual classification model is complained as shown in Fig. 2, Fig. 2 is provided in this embodiment
A kind of complaint textual classification model schematic diagram, classification of the model realization to text is complained including the following steps:
Step1: the first data for complaining text are read.
Step2: carrying out numeralization processing to the sentence being input in model, and each vocabulary in sentence is shown as a number
The term vector of value type.
Step3: for each word after numeralization, numerical value X0~Xn enters shot and long term memory network (Long Short-
Term Memory, LSTM) layer, a vector h0~hn for hiding LSTM neural unit of n obtained by a time series, this
A little vectors pass through mean pooling layers, after being averaging to characteristic point in neighborhood, an available vector h, then immediately
Be Softmax layers of distribution probability function, obtain a category distribution probability vector, take the maximum classification conduct of probability value
The classification results for the complaint text finally predicted, i.e., first complains classification.
S103: complaining classification according to first and reply corpus, in the answer for complaining text to first to user's push
Hold.
In this step, corresponding answer content is searched in replying corpus according to the first complaint classification, and by this
The one answer content push for complaining text corresponding is to the user, so as to be resolved in time the problem of user, if first throwing
It tells that text is unable to get classification or can not match answer content, then should believe comprising illustrative prompt in the answer pushed to user
The information such as breath and solution time, for example, " we are being that you are handled to your opinion to prompt user, would you please bear with, at the latest
It will be contacted in XX month XX day with you ".
Alternatively, searching multiple relevant answer contents in replying corpus according to the first complaint classification, and generate answer
Option will reply option list and push to give the user, and user is allowed to select immediate answer option according to option list is replied, and
According to the answer option that user selects, corresponding answer content is provided to the user.
Wherein, include the corresponding answer content of each complaint classification in the answer corpus, optionally, reply corpus
Including user's service manual, perhaps FAQs answer table or service manual etc. can provide help for client's use
Any data, this programme do not require this.
A kind of processing method of complaint provided in this embodiment complains text by obtaining the first of reporting of user, and will
The complaint textual classification model that first complaint text input obtains in advance obtains first and complains the first of text to complain classification, then
According to first complain classification and reply corpus, to user push to first complain text answer content, realize to
The Fast Classification of family complaint content, and can timely and effectively complaint content be positioned and be solved.
Fig. 3 is a kind of flow diagram of the processing method embodiment two of complaint provided in an embodiment of the present invention, such as Fig. 3 institute
Show, on the basis of embodiment shown in Fig. 1, before S101 step, the processing method of the complaint further include:
S201: sample set is complained in acquisition, and complaining includes multiple complaint samples of text and each complaint in sample set
The corresponding complaint classification of samples of text.
In this step, multiple samples for complaining text are acquired, the sample of the complaint text is to be labelled with correct complaint
The complaint text of classification, these complain the sample of text to constitute complaint sample set.
S202: it according to sample set is complained, obtains complaining textual classification model using Recognition with Recurrent Neural Network training.
In this step, after initializing to Recognition with Recurrent Neural Network, multiple complaint texts in sample set will be complained
Sample put into Recognition with Recurrent Neural Network respectively, obtain the complaint classification of each sample for complaining text, trained by being repeated several times
It obtains complaining textual classification model.Further, the complaint classification that will acquire is compared with the complaint classification marked in advance, is obtained
The accuracy of the complaint textual classification model is taken, and is constantly trained so that its accuracy reaches preset standard.
Optionally, the accuracy for complaining textual classification model includes recall rate and precision.Wherein, recall rate is correct obtains
The sample number of classification accounts for the ratio of all sample numbers of the category in test set, and which represent the specific gravity for correctly judging positive example；Precision
Correctly to obtain the ratio that the sample number of classification accounts for all sample numbers in set, which represent the specific gravity correctly judged.Wherein, it surveys
Examination collection is for verifying the set for complaining the test sample of textual classification model accuracy.
Optionally, quick training and the iteratively faster of model can be completed using python 3.0.
Fig. 4 is a kind of flow diagram of the processing method embodiment three of complaint provided in an embodiment of the present invention, such as Fig. 4 institute
Show, on the basis of Fig. 1 and embodiment illustrated in fig. 3, the processing method of the complaint further includes testing complaint textual classification model
Card method, comprising the following specific steps
S301: feasibility verifying is carried out to complaint textual classification model according to the test set obtained in advance.
In this step, multiple samples for complaining text are acquired in advance, and the sample of the complaint text is to be labelled with correctly
The complaint text of classification is complained, these complain the sample of text to constitute the test set for complaining sample.It will be multiple in test set
It complains the sample investment of text to complain textual classification model, obtains the complaint classification of each sample for complaining text, will acquire
It complains classification and the complaint classification of calibration to compare, obtains the accuracy of the complaint textual classification model, being determined by accuracy should
Complain whether textual classification model has feasibility.
Specifically, the accuracy for complaining textual classification model includes recall rate and precision.
S302: if textual classification model is complained to be higher than preset value to the accuracy of multiple classification results for complaining text,
It determines and complains textual classification model feasible.
In this step, if the complaint classification by the complaint classification and calibration of complaining textual classification model to obtain compares
Afterwards, accuracy is higher than preset accuracy, then can determine that the complaint textual classification model is feasible.
Wherein, recall rate is the ratio that the correct sample number for obtaining classification accounts for all sample numbers of the category in test set,
Represent the specific gravity for correctly judging positive example；Precision is the ratio that the correct sample number for obtaining classification accounts for all sample numbers in set,
Which represent the specific gravity correctly judged.Wherein, test set is for verifying the test sample for complaining textual classification model accuracy
Set.By obtaining accuracy after being weighted and averaged to recall rate and precision.
In a kind of concrete implementation mode, the default of accuracy is set to 80%, i.e., when accuracy is higher than 80%, it is believed that should
Complain textual classification model feasible.
Fig. 5 is a kind of flow diagram of the processing method example IV of complaint provided in an embodiment of the present invention, such as Fig. 5 institute
Show, on the basis of the above embodiments, the processing method of the complaint further include:
S401: it complains text input to complain textual classification model for first, obtains the first instruction information.
After the first of the user that will acquire complains text input to complain textual classification model, if the first complaint text is not
Belong to and complain any one of textual classification model classification, then can not obtain the corresponding complaint classification of the first complaint text,
The first instruction information will be obtained, instruction can not classify to the first complaint text.
S402: establishing new complaint classification, new complaint classification is added in the first complaint text, the first complaint classification is new
Complaint classification.
If complaining in textual classification model there is no complaint classification corresponding with the first complaint text, text point is being complained
It complains the problem of including in text or semanteme to establish new complaint classification according to first in class model, and complains text for first
The new complaint classification is added, correspondingly, the first complaint classification is the new complaint classification.
Fig. 6 is a kind of flow diagram of the processing method embodiment five of complaint provided in an embodiment of the present invention, such as Fig. 6 institute
Show, on the basis of embodiment shown in Fig. 5, the processing method of the complaint further include:
S403: for new complaint classification, complaint textual classification model is updated.
It in this step, can be by complaining sample set, for the new complaint classification progress for complaining textual classification model
Training, and repetition training improves the accuracy for complaining textual classification model；It can be by the test set that obtains in advance, for complaining text
The new complaint classification of this disaggregated model carries out feasibility verifying.The above training and verification process and training above-mentioned and authentication
Method is similar, and details are not described herein again.
Fig. 7 is a kind of structural schematic diagram of the processing device embodiment one of complaint provided in an embodiment of the present invention, such as Fig. 7 institute
Show, the processing unit 10 of the complaint includes:
Obtain module 101: first for obtaining reporting of user complains text；
Classification processing module 102: the complaint textual classification model for obtaining the first complaint text input in advance,
Obtaining described first complains the first of text to complain classification；
Reply processing module 103: for complaining classification according to described first and replying corpus, Xiang Suoshu user's push
The answer content for complaining text to described first.
Wherein, described to complain textual classification model for the classification for obtaining complaint text based on Recognition with Recurrent Neural Network training
Model includes the corresponding answer content of each complaint classification in the answer corpus.
The processing unit of complaint provided in this embodiment, including obtain module, classification processing module and reply processing mould
Block complains text wherein obtaining module and being used to obtain the first of reporting of user；Classification processing module by described first for complaining
The complaint textual classification model that text input obtains in advance obtains described first and complains the first of text to complain classification；At answer
It manages module to be used to complain classification according to described first and reply corpus, Xiang Suoshu user's push complains text to described first
Answer content, realize the Fast Classification to customer complaint content, and can timely and effectively determine complaint content
Position and solution.
In a kind of concrete implementation mode, classification processing module 102 is specifically used for complaining text input for described first
The complaint textual classification model obtains the first instruction information；It is described first instruction information instruction to can not to it is described first throw
Tell that text is classified；New complaint classification is established, the first complaint text is added the new complaint classification, described the
One complains classification for the new complaint classification.
On the basis of the above embodiments, Fig. 8 is a kind of processing device embodiment of complaint provided in an embodiment of the present invention
Two structural schematic diagram, as shown in figure 8, the processing unit 10 of the complaint further include:
Verification processing module 104: the test set obtained in advance for basis can to complaint textual classification model progress
Row verifying；It wherein, include the complaint classification of multiple each complaint texts for complaining texts and calibration in the test set；
Judgment module 105: if for the complaint textual classification model to the multiple classification results for complaining text
Accuracy is higher than preset value, it is determined that the complaint textual classification model is feasible.
On the basis of the above embodiments, Fig. 9 is a kind of processing device embodiment of complaint provided in an embodiment of the present invention
Three structural schematic diagram, as shown in figure 9, the processing unit 10 of the complaint further include:
Update module 106 is updated the complaint textual classification model for being directed to the new complaint classification.
The processing unit of complaint provided in this embodiment can be used for executing the technical solution of any of the above-described embodiment of the method,
The realization principle and technical effect are similar, and details are not described herein again for the present embodiment.
Figure 10 is the hardware structural diagram of a kind of electronic equipment provided in an embodiment of the present invention.As shown in Figure 10, the electricity
Sub- equipment 20 includes: processor 201 and memory 202；Wherein
Memory 202, for storing computer executed instructions；
Processor 201, for executing the computer executed instructions of memory storage, to realize, terminal is set in above-described embodiment
Standby performed each step.It specifically may refer to the associated description in preceding method embodiment.
Optionally, memory 202 can also be integrated with processor 201 either independent.
When memory 202 is independently arranged, which further includes bus 203, for connecting 202 He of memory
Processor 201.
The embodiment of the present invention also provides a kind of computer readable storage medium, stores in the computer readable storage medium
There are computer executed instructions, when processor executes the computer executed instructions, realizes the processing side complained as described above
Method.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the module, only
Only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple modules can combine or
It is desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed it is mutual it
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of device or module
It connects, can be electrical property, mechanical or other forms.
The module as illustrated by the separation member may or may not be physically separated, aobvious as module
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.Some or all of the modules therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
It, can also be in addition, each functional module in each embodiment of the present invention can integrate in one processing unit
It is that modules physically exist alone, can also be integrated in one unit with two or more modules.Above-mentioned module at
Unit 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 module realized in the form of software function module, can store and computer-readable deposit at one
In storage media.Above-mentioned software function module is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this Shen
Please each embodiment the method part steps.
It should be understood that above-mentioned processor can be central processing unit (English: Central Processing Unit, letter
Claim: CPU), can also be other general processors, digital signal processor (English: Digital Signal Processor,
Referred to as: DSP), specific integrated circuit (English: Application Specific Integrated Circuit, referred to as:
ASIC) etc..General processor can be microprocessor or the processor is also possible to any conventional processor etc..In conjunction with hair
The step of bright disclosed method, can be embodied directly in hardware processor and execute completion, or with hardware in processor and soft
Part block combiner executes completion.
Memory may include high speed RAM memory, it is also possible to and it further include non-volatile memories NVM, for example, at least one
Magnetic disk storage can also be USB flash disk, mobile hard disk, read-only memory, disk or CD etc..
Bus can be industry standard architecture (Industry Standard Architecture, ISA) bus, outer
Portion's apparatus interconnection (Peripheral Component, PCI) bus or extended industry-standard architecture (Extended
Industry Standard Architecture, EISA) bus etc..Bus can be divided into address bus, data/address bus, control
Bus etc..For convenient for indicating, the bus in illustrations does not limit only a bus or a type of bus.
Above-mentioned storage medium can be by any kind of volatibility or non-volatile memory device or their combination
It realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable
Read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory,
Disk or CD.Storage medium can be any usable medium that general or specialized computer can access.
A kind of illustrative storage medium is coupled to processor, believes to enable a processor to read from the storage medium
Breath, and information can be written to the storage medium.Certainly, storage medium is also possible to the component part of processor.It processor and deposits
Storage media can be located at specific integrated circuit (Application Specific Integrated Circuits, referred to as:
ASIC in).Certainly, pocessor and storage media can also be used as discrete assembly and be present in electronic equipment or main control device.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (12)
1. a kind of processing method of complaint characterized by comprising
Obtain reporting of user first complains text；
By the complaint textual classification model that obtains in advance of the first complaint text input, obtain described first complain text the
One complains classification；
Classification is complained according to described first and replies corpus, the answer that Xiang Suoshu user's push complains text to described first
Content；
Wherein, the mould of the classification for complaining textual classification model to complain text for the acquisition based on Recognition with Recurrent Neural Network training
Type includes the corresponding answer content of each complaint classification in the answer corpus.
2. the method according to claim 1, wherein it is described obtain reporting of user first complain text before,
The method also includes:
Sample set is complained in acquisition, includes multiple complaint samples of text and each complaint text in the complaint sample set
The corresponding complaint classification of sample；
According to the complaint sample set, the complaint textual classification model is obtained using Recognition with Recurrent Neural Network training.
3. method according to claim 1 or 2, which is characterized in that the method also includes:
Feasibility verifying is carried out to the complaint textual classification model according to the test set obtained in advance；Wherein, the test set
In include it is multiple complaint texts and calibration each complaint texts complaint classification；
If described complain textual classification model to be higher than preset value to the accuracy of the multiple classification results for complaining text, really
The fixed complaint textual classification model is feasible.
4. method according to claim 1 or 2, which is characterized in that described to obtain the first complaint text input in advance
The complaint textual classification model taken obtains described first and complains the first of text to complain classification, comprising:
Textual classification model will be complained described in the first complaint text input, obtains the first instruction information；First instruction
Information instruction can not classify to the first complaint text；
New complaint classification is established, the new complaint classification is added in the first complaint text, described first complains classification
For the new complaint classification.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
For the new complaint classification, the complaint textual classification model is updated.
6. a kind of processing unit of complaint characterized by comprising
Module is obtained, first for obtaining reporting of user complains text；
Classification processing module, the complaint textual classification model for obtaining the first complaint text input in advance, obtains institute
State the first complaint text first complains classification；
Processing module is replied, for complaining classification according to described first and replying corpus, Xiang Suoshu user is pushed to described
First complains the answer content of text；
Wherein, the mould of the classification for complaining textual classification model to complain text for the acquisition based on Recognition with Recurrent Neural Network training
Type includes the corresponding answer content of each complaint classification in the answer corpus.
7. device according to claim 6, which is characterized in that described device further include:
Acquisition module complains sample set for acquiring, and includes multiple complaint samples of text in the complaint sample set, and
Each complaint classification for complaining samples of text corresponding；
Training managing module, for obtaining the complaint text using Recognition with Recurrent Neural Network training according to the complaint sample set
This disaggregated model.
8. device according to claim 6 or 7, which is characterized in that described device further include:
Verification processing module is tested for carrying out feasibility to the complaint textual classification model according to the test set obtained in advance
Card；It wherein, include the complaint classification of multiple each complaint texts for complaining texts and calibration in the test set；
Judgment module, if high for accuracy of the complaint textual classification model to the multiple classification results for complaining text
In preset value, it is determined that the complaint textual classification model is feasible.
9. device according to claim 6 or 7, which is characterized in that the classification processing module is specifically used for described the
Textual classification model is complained described in one complaint text input, obtains the first instruction information；The first instruction information instruction is to nothing
Method classifies to the first complaint text；
New complaint classification is established, the new complaint classification is added in the first complaint text, described first complains classification
For the new complaint classification.
10. device according to claim 8, which is characterized in that described device further include:
Update module is updated the complaint textual classification model for being directed to the new complaint classification.
11. a kind of electronic equipment characterized by comprising processor, memory and computer program；
The memory stores computer executed instructions；
The processor executes the computer executed instructions of the memory storage, so that at least one described processor executes such as
The processing method of complaint described in any one of claim 1 to 5.
12. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
It executes instruction, when processor executes the computer executed instructions, realizes such as complaint described in any one of claim 1 to 5
Processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811389160.4A CN109684475B (en) | 2018-11-21 | 2018-11-21 | Complaint processing method, complaint processing device, complaint processing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811389160.4A CN109684475B (en) | 2018-11-21 | 2018-11-21 | Complaint processing method, complaint processing device, complaint processing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109684475A true CN109684475A (en) | 2019-04-26 |
| CN109684475B CN109684475B (en) | 2021-03-30 |
Family
ID=66185418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811389160.4A Active CN109684475B (en) | 2018-11-21 | 2018-11-21 | Complaint processing method, complaint processing device, complaint processing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109684475B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110347840A (en) * | 2019-07-18 | 2019-10-18 | 携程计算机技术（上海）有限公司 | Complain prediction technique, system, equipment and the storage medium of text categories |
| CN110704619A (en) * | 2019-09-24 | 2020-01-17 | 支付宝(杭州)信息技术有限公司 | Text classification method and device and electronic equipment |
| CN111429157A (en) * | 2020-03-27 | 2020-07-17 | 上海东普信息科技有限公司 | Method, device and equipment for evaluating and processing complaint work order and storage medium |
| CN111695360A (en) * | 2020-06-15 | 2020-09-22 | 深圳追一科技有限公司 | Semantic analysis method and device, electronic equipment and storage medium |
| CN112115240A (en) * | 2019-06-21 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Classification processing method, classification processing device, server and storage medium |
| CN112288446A (en) * | 2020-10-28 | 2021-01-29 | 中国联合网络通信集团有限公司 | Method and device for calculating complaint and claim |
| CN112529584A (en) * | 2020-12-08 | 2021-03-19 | 支付宝(杭州)信息技术有限公司 | Transaction dispute data processing method, device, equipment and storage medium |
| CN112732918A (en) * | 2021-01-13 | 2021-04-30 | 国网山东省电力公司日照供电公司 | Complaint work order intelligent classification system |
| CN112766290A (en) * | 2019-10-18 | 2021-05-07 | 普天信息技术有限公司 | Complaint data processing method and device |
| WO2021119949A1 (en) * | 2019-12-16 | 2021-06-24 | 深圳市欢太科技有限公司 | Text classification model training method, text classification method and apparatus, and electronic device |
| CN113672732A (en) * | 2021-08-19 | 2021-11-19 | 胜斗士(上海)科技技术发展有限公司 | Method and device for classifying business data |
| US20230334246A1 (en) * | 2022-04-14 | 2023-10-19 | Dell Products, L.P. | Determining indications of visual abnormalities in an unstructured data stream |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133817A (en) * | 2013-05-02 | 2014-11-05 | 深圳市世纪光速信息技术有限公司 | Online community interaction method and device and online community platform |
| CN104281615A (en) * | 2013-07-08 | 2015-01-14 | 中国移动通信集团甘肃有限公司 | Complaint handling method and system |
| US9552548B1 (en) * | 2016-07-01 | 2017-01-24 | Intraspexion Inc. | Using classified text and deep learning algorithms to identify risk and provide early warning |
| CN106649561A (en) * | 2016-11-10 | 2017-05-10 | 复旦大学 | Intelligent question-answering system for tax consultation service |
| CN107844559A (en) * | 2017-10-31 | 2018-03-27 | 国信优易数据有限公司 | A kind of file classifying method, device and electronic equipment |
| CN108170818A (en) * | 2017-12-29 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of file classification method, server and computer-readable medium |
| CN108563791A (en) * | 2018-04-29 | 2018-09-21 | 华中科技大学 | A kind of construction quality complains the method and system of text classification |
-
2018
- 2018-11-21 CN CN201811389160.4A patent/CN109684475B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133817A (en) * | 2013-05-02 | 2014-11-05 | 深圳市世纪光速信息技术有限公司 | Online community interaction method and device and online community platform |
| CN104281615A (en) * | 2013-07-08 | 2015-01-14 | 中国移动通信集团甘肃有限公司 | Complaint handling method and system |
| US9552548B1 (en) * | 2016-07-01 | 2017-01-24 | Intraspexion Inc. | Using classified text and deep learning algorithms to identify risk and provide early warning |
| CN106649561A (en) * | 2016-11-10 | 2017-05-10 | 复旦大学 | Intelligent question-answering system for tax consultation service |
| CN107844559A (en) * | 2017-10-31 | 2018-03-27 | 国信优易数据有限公司 | A kind of file classifying method, device and electronic equipment |
| CN108170818A (en) * | 2017-12-29 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of file classification method, server and computer-readable medium |
| CN108563791A (en) * | 2018-04-29 | 2018-09-21 | 华中科技大学 | A kind of construction quality complains the method and system of text classification |
Non-Patent Citations (1)
| Title |
|---|
| 曾谁飞等: "基于神经网络的文本表示模型新方法", 《通信学报》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115240A (en) * | 2019-06-21 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Classification processing method, classification processing device, server and storage medium |
| CN110347840B (en) * | 2019-07-18 | 2023-06-13 | 携程计算机技术（上海）有限公司 | Prediction method, system, equipment and storage medium for complaint text category |
| CN110347840A (en) * | 2019-07-18 | 2019-10-18 | 携程计算机技术（上海）有限公司 | Complain prediction technique, system, equipment and the storage medium of text categories |
| CN110704619A (en) * | 2019-09-24 | 2020-01-17 | 支付宝(杭州)信息技术有限公司 | Text classification method and device and electronic equipment |
| CN112766290A (en) * | 2019-10-18 | 2021-05-07 | 普天信息技术有限公司 | Complaint data processing method and device |
| WO2021119949A1 (en) * | 2019-12-16 | 2021-06-24 | 深圳市欢太科技有限公司 | Text classification model training method, text classification method and apparatus, and electronic device |
| CN111429157A (en) * | 2020-03-27 | 2020-07-17 | 上海东普信息科技有限公司 | Method, device and equipment for evaluating and processing complaint work order and storage medium |
| CN111695360A (en) * | 2020-06-15 | 2020-09-22 | 深圳追一科技有限公司 | Semantic analysis method and device, electronic equipment and storage medium |
| CN111695360B (en) * | 2020-06-15 | 2023-10-27 | 深圳追一科技有限公司 | Semantic analysis method, semantic analysis device, electronic equipment and storage medium |
| CN112288446A (en) * | 2020-10-28 | 2021-01-29 | 中国联合网络通信集团有限公司 | Method and device for calculating complaint and claim |
| CN112288446B (en) * | 2020-10-28 | 2023-06-06 | 中国联合网络通信集团有限公司 | Calculation method and device for complaint and claim payment |
| CN112529584A (en) * | 2020-12-08 | 2021-03-19 | 支付宝(杭州)信息技术有限公司 | Transaction dispute data processing method, device, equipment and storage medium |
| CN112732918A (en) * | 2021-01-13 | 2021-04-30 | 国网山东省电力公司日照供电公司 | Complaint work order intelligent classification system |
| CN113672732A (en) * | 2021-08-19 | 2021-11-19 | 胜斗士(上海)科技技术发展有限公司 | Method and device for classifying business data |
| CN113672732B (en) * | 2021-08-19 | 2024-04-26 | 胜斗士(上海)科技技术发展有限公司 | Method and device for classifying service data |
| US20230334246A1 (en) * | 2022-04-14 | 2023-10-19 | Dell Products, L.P. | Determining indications of visual abnormalities in an unstructured data stream |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109684475B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109684475A (en) | Processing method, device, equipment and the storage medium of complaint | |
| CN110442790B (en) | Method, device, server and storage medium for recommending multimedia data | |
| CN110297912A (en) | Cheat recognition methods, device, equipment and computer readable storage medium | |
| CN109976997B (en) | Test method and device | |
| CN109062802A (en) | A kind of method for testing software, computer readable storage medium and terminal device | |
| CN109739985A (en) | Automatic document classification method, equipment and storage medium | |
| CN110348471B (en) | Abnormal object identification method, device, medium and electronic equipment | |
| CN110349039A (en) | Complaint risk appraisal procedure, system, computer equipment and readable storage medium storing program for executing | |
| CN111445928A (en) | Voice quality inspection method, device, equipment and storage medium | |
| CN111882140A (en) | Risk evaluation method, model training method, device, equipment and storage medium | |
| CN110033120A (en) | For providing the method and device that risk profile energizes service for trade company | |
| CN110009480A (en) | The recommended method in judicial collection path, device, medium, electronic equipment | |
| CN109753436A (en) | Test method, device and the storage medium of intelligent customer service system | |
| CN107992484A (en) | A kind of method, equipment and the storage medium of the performance for evaluating and testing OCR system | |
| CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
| CN114782123A (en) | Credit assessment method and system | |
| CN109684198A (en) | Data capture method to be tested, device, medium, electronic equipment | |
| CN114116801A (en) | Data list checking method and device | |
| CN111373395A (en) | Artificial intelligence system and method based on hierarchical clustering | |
| CN110648213A (en) | Address verification method, device, equipment and computer readable medium | |
| CN113935788B (en) | Model evaluation method, device, equipment and computer readable storage medium | |
| CN113032514B (en) | Method and device for processing point of interest data | |
| CN113450208A (en) | Loan risk change early warning and model training method and device | |
| CN113379464A (en) | Block chain-based site selection method, device, equipment and storage medium | |
| CN113743435A (en) | Business data classification model training method and device, and business data classification method and device |
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 |