CN108334488A - A kind of work order classification processing method and server - Google Patents
A kind of work order classification processing method and server Download PDFInfo
- Publication number
- CN108334488A CN108334488A CN201710040034.7A CN201710040034A CN108334488A CN 108334488 A CN108334488 A CN 108334488A CN 201710040034 A CN201710040034 A CN 201710040034A CN 108334488 A CN108334488 A CN 108334488A
- Authority
- CN
- China
- Prior art keywords
- work order
- probability
- generic
- sorted
- characteristic attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
Abstract
A kind of work order classification processing method of offer of the embodiment of the present invention and server, the method includes:Corresponding first probability of each generic of sample work order is calculated, the first probability is the ratio between the statistics summation of the statistical number and all generics of each generic;Corresponding second probability of each characteristic attribute in generic is calculated, the second probability is the ratio between the statistical number of each characteristic attribute in the generic and all characteristic attribute summations in the generic;According to the first probability, the characteristic attribute of the second probability and work order to be sorted, the corresponding third probability of work order generic to be sorted is calculated;Compare all third probability, and using the generic corresponding to the maximum value in the third probability as the class categories of work order to be sorted.The server executes the above method.Work order classification processing method and server provided in an embodiment of the present invention ensure that work order classification reasonability, and improve the efficiency of work order classification.
Description
Technical field
The present embodiments relate to information sorting technique fields, and in particular to a kind of work order classification processing method and service
Device.
Background technology
With the development of information technology, many companies receive customer complaint, consulting, feedback opinion etc. by customer service system.
Company needs the work order corresponding to the numerous customer informations received to customer service system for the needs of customer account management
Classify, it is common that work order is filed manually by customer service staff, typing and reply.But manually carry out work order
Classification has the following disadvantages:(1) personal subjective experience is excessively relied on, some sorters simultaneously do not know about classifying rules, cause
Work order classification is not reasonable;(2) due to the carelessness of sorter, work order classification error is caused;(3) work order classification is manually carried out
Inefficiency.
Therefore, how drawbacks described above is avoided, to realize that work order is classified automatically, ensures work order classification reasonability, and improve
The efficiency of work order classification, becoming need solve the problems, such as.
Invention content
In view of the problems of the existing technology, a kind of work order classification processing method of offer of the embodiment of the present invention and server.
On the one hand, the embodiment of the present invention provides a kind of work order classification processing method, the method includes:
Corresponding first probability of each generic of sample work order is calculated, first probability is each described institute
Belong to the ratio between the statistics summation of the statistical number and all generics of classification;
Corresponding second probability of each characteristic attribute in generic is calculated, second probability is each described spy
Levy the ratio between statistical number of the attribute in the generic and all characteristic attribute summations in the generic;
According to first probability, the characteristic attribute of second probability and work order to be sorted, the work to be sorted is calculated
The corresponding third probability of single generic;
Compare all third probability, and the generic corresponding to the maximum value in the third probability is waited for as described in
The class categories for work order of classifying.
On the other hand, the embodiment of the present invention provides a kind of work order classification processing server, and the server includes:
First computing module, corresponding first probability of each generic for calculating sample work order, described first
Probability is the ratio between the statistics summation of the statistical number and all generics of each generic;
Second computing module, for calculating corresponding second probability of each characteristic attribute in generic, described second
Probability is the statistical number of each characteristic attribute in the generic and all characteristic attributes in the generic
The ratio between summation;
Third computing module is used for the characteristic attribute according to first probability, second probability and work order to be sorted,
Calculate the corresponding third probability of the work order generic to be sorted;
Comparison module is used for more all third probability, and will be belonging to corresponding to the maximum value in the third probability
Class categories of the classification as the work order to be sorted.
Work order classification processing method and server provided in an embodiment of the present invention, realize work order and classify automatically, ensure that
Work order classification reasonability, and improve the efficiency of work order classification.
Description of the drawings
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 technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow diagram of work order classification processing method of the embodiment of the present invention;
Fig. 2 is the structural schematic diagram of work order of embodiment of the present invention classification processing server;
Fig. 3 is server entity structural schematic diagram provided in an embodiment of the present invention.
Specific implementation mode
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
The every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the flow diagram of work order classification processing method of the embodiment of the present invention, as shown in Figure 1, the present embodiment provides
A kind of work order classification processing method, include the following steps:
S1:Corresponding first probability of each generic of sample work order is calculated, first probability is described each
The ratio between the statistics summation of the statistical number of a generic and all generics.
Specifically, server calculates corresponding first probability of each generic of sample work order, first probability
For the ratio between the statistics summation of the statistical number and all generics of each generic.It should be noted that:Sample work
List can be extracted from the work order of known features attribute and generic in advance, generic can by manually determine, simultaneously
The classification of work order can be accurately reflected, can be classified as " complaining " according to work order different business, " consulting " etc., but do not make specific
It limits.The calculated example of first probability is described as follows:Category set C={ y1, y2, y3 ... yn }, the statistics of all generics
Summation is 1000, the statistical number of classification y1 " complaint " is 300, then classify the corresponding first probability P (y of y1 " complaint "1) it is 300/
1000=0.3.
S2:Corresponding second probability of each characteristic attribute in generic is calculated, second probability is described each
The ratio between statistical number of a characteristic attribute in the generic and all characteristic attribute summations in the generic.
Specifically, server calculates corresponding second probability of each characteristic attribute in generic, second probability
For all characteristic attribute summations in statistical number of each the described characteristic attribute in the generic and the generic
The ratio between.It should be noted that:aiIt is characterized attribute, Ke Yishi:a1It is client, a2It is reflection etc..Such as:The y1=that classifies " is thrown
Tell " in, all characteristic attribute summations of sample work order are 100, and the statistical number of a characteristic attribute " reflection " is 30, then feature category
Property for the probability that " reflection " correspondence " complaint " is classified be P (" reflection " | " complaint ")=30/100=0.3, i.e. characteristic attribute a2It is right
The the second probability P (a answered2|y1) it is 0.3.
S3:According to first probability, the characteristic attribute of second probability and work order to be sorted, calculate described to be sorted
The corresponding third probability of work order generic.
Specifically, server is calculated according to first probability, the characteristic attribute of second probability and work order to be sorted
The corresponding third probability of the work order generic to be sorted.In order to briefly explain, only consider that the characteristic attribute in classification y1 is
The case where " client " and " reflection ", such as:Classify in y1=" complaint ", all characteristic attribute summations of sample work order are 100, one
The statistical number of a characteristic attribute " client " is 70, then it is P (" client " that characteristic attribute, which is the probability of " client " correspondence " complaint " classification,
| " complaint ")=70/100=0.7, i.e. characteristic attribute a1Corresponding second probability P (a1|y1) it is 0.7.According to the meter of third probability
It calculates public
S4:Compare all third probability, and using the generic corresponding to the maximum value in the third probability as institute
State the class categories of work order to be sorted.
Specifically, more all third probability of server, and will be belonging to corresponding to the maximum value in the third probability
Class categories of the classification as the work order to be sorted.In order to briefly explain, only consider that the generic in classification set C is
The case where " complaint " and " consulting ", such as:Category set C={ y1, y2, y3 ... yn }, the statistics summation of all generics are
1000, the statistical number of classification y2 " consulting " is 700, then classify the corresponding first probability P (y of y2 " consulting "2) it is 700/1000=
0.7.Characteristic attribute is that the probability of " client " correspondence " consulting " classification is P (a1|y2)=P (" client " | " consulting ")=120/200
=0.6 (repeating no more), characteristic attribute are that the probability of " reflection " correspondence " consulting " classification is P (a2|y2)=P (" reflection " | " is consulted
Ask ")=80/200=0.4 (repeating no more).
According to the calculation formula of third probability:
Have:
Compare the above-mentioned corresponding third probability P (y of classification y1 " complaint "1| x), it can be deduced that:P(y1| x) < P (y2| x),
Therefore, work order x to be sorted is classified as y2 " consulting ".
Work order classification processing method provided in an embodiment of the present invention, realizes work order and classifies automatically, ensure that work order is classified
Reasonability, and improve the efficiency of work order classification.
On the basis of the above embodiments, the method further includes:
Sample work order is imported for the generic.
Specifically, server imports sample work order for the generic.It should be noted that:The step of this method, can
With before being placed in corresponding first probability of each generic of sample work order " calculate " step in above-described embodiment, sample
Work order can select large number of sample work order, to ensure the accuracy of work order classification results.Sample work order can pass through
Excel files import, the list content of sample work order may include work order serial number, work order title, work order detailed description, divide
Class.Work order category set is combined into C={ y1, y2, y3 ... yn }, is directed respectively into the sample work order data of the classification such as corresponding y1.Such as work
Single category set is combined into C={ " complaint ", " consulting " }, and such as " complaint " classifies, and imports the work order data of corresponding " complaint ".
The participle of the sample work order is extracted using mmseg4j segmenter.
Specifically, server by utilizing mmseg4j segmenter extracts the participle of the sample work order.Mmseg4j can be utilized
(Chinese word segmentation machine that mmseg4j is realized with the MMSeg algorithms of Chih-Hao Tsai) segmenter is realized to every work order in work order
Chinese word segmentation extraction.
It polymerize the participle of the sample work order, to obtain the characteristic attribute of the generic.
Specifically, server polymerize the participle of the sample work order, to obtain the characteristic attribute of the generic.Polymerization
The participle of the sample work order can be understood as:For all participle duplicate removals, and obtain the set being made of multiple characteristic attributes.Example
As characteristic attribute of { " client, reflection, the inspection " } participle as work order can be obtained in " complaint " work order.
Work order classification processing method provided in an embodiment of the present invention is protected by the characteristic attribute of the generic got
The realizability of work order classification is demonstrate,proved.
On the basis of the above embodiments, the third probability is calculated by the following formula acquisition:
Wherein, P (yi| x) it is third probability, P (aj|yi) it is the second probability, P (yi) be the first probability, P (x | yi) it is to exchange
The conditional probability corresponding to third probability, x after event are work order to be sorted, ajFor each characteristic attribute and x={ a of x1,
a2...am}、yiIt is characterized attribute sum for each work order class categories, m.
Specifically, server, which is calculated by the following formula, obtains third probability:
Wherein, P (yi| x) it is third probability, P (aj|yi) it is the second probability, P (yi) be the first probability, P (x | yi) it is to exchange
The conditional probability corresponding to third probability, x after event are work order to be sorted, ajFor each characteristic attribute and x={ a of x1,
a2...am}、yiIt is characterized attribute sum for each work order class categories, m.Above-described embodiment is can refer to, is repeated no more.
Work order classification processing method provided in an embodiment of the present invention, by the calculation formula of specific third probability, effectively
Ground realizes work order and classifies automatically, ensure that work order classification reasonability, and improve the efficiency of work order classification.
On the basis of the above embodiments, the acquisition of the characteristic attribute of the work order to be sorted, including:
Import work order data to be sorted.
Specifically, server imports work order data to be sorted.The embodiment that above-mentioned sample work order imports is can refer to, it is no longer superfluous
It states.
The Chinese word segmentation of every work order in the work order to be sorted is extracted.
Specifically, server extracts the Chinese word segmentation of every work order in the work order to be sorted.It can refer to above-mentioned
The embodiment of sample work order participle extraction, repeats no more.
If judgement knows that the Chinese word segmentation extracted is present in the characteristic attribute of the sample work order, it is added to be sorted
In the characteristic attribute of work order, or:If judgement knows that the Chinese word segmentation extracted is not present in the characteristic attribute of the sample work order
In, then give up.
Specifically, if server judgement knows that the Chinese word segmentation extracted is present in the characteristic attribute of the sample work order
In, then it is added in the characteristic attribute of work order to be sorted, or:If judgement knows that the Chinese word segmentation extracted is not present in the sample
In the characteristic attribute of work order, then give up.It should be noted that:The participle of extraction was compareed with the characteristic attribute of sample work order
Filter, can realize in the following way:
Foreach (string segments in and segments list)
{
Judge whether participle exists in sample work order characteristic attribute,
In the presence of the characteristic attribute list that work order to be sorted is then added, there is no then give up.
}
To generate the characteristic attribute set of work order to be sorted:X={ a1,a2...am}。
Such as the participle extracted is a1(client), a2(reflection), a3(fine), and " fine " in the spy of sample work order
It levies in attribute set, is then rejected, then x={ " client ", " reflection " }.
Work order classification processing method provided in an embodiment of the present invention, by the feature category for reasonably obtaining work order to be sorted
Property, to ensure that the reasonability of work order classification.
On the basis of the above embodiments, the method by mmseg4j segmenter to every in the work order to be sorted
The Chinese word segmentation of work order extracts.
Specifically, server by mmseg4j segmenter to the Chinese word segmentation of every work order in the work order to be sorted into
Row extraction.Since mmseg4j is higher to the extraction accuracy rate of Chinese word segmentation, treated using mmseg4j every in classification work order
The Chinese word segmentation of work order extracts.
Work order provided in an embodiment of the present invention is classified processing server, is reasonably obtained and is waited for point by mmseg4j segmenter
The characteristic attribute of class work order realizes effective acquisition of characteristic attribute.
Fig. 2 is the structural schematic diagram of work order of embodiment of the present invention classification processing server, as shown in Fig. 2, the present embodiment carries
A kind of work order classification processing server, including the first computing module 1, the second computing module 2, third computing module 3 and ratio are supplied
Compared with module 4, wherein:
Each generic corresponding first probability of first computing module 1 for calculating sample work order, described first
Probability is the ratio between the statistics summation of the statistical number and all generics of each generic, and the second computing module 2 is used
In calculating corresponding second probability of each characteristic attribute in generic, second probability is each described characteristic attribute
The ratio between all characteristic attribute summations in statistical number and the generic in the generic, third computing module 3 is used
In the characteristic attribute according to first probability, second probability and work order to be sorted, calculate belonging to the work order to be sorted
The corresponding third probability of classification, comparison module 4 are used for more all third probability, and by the maximum value institute in the third probability
Class categories of the corresponding generic as the work order to be sorted.
Specifically, the first computing module 1 is used to calculate corresponding first probability of each generic of sample work order, institute
The ratio between the statistics summation of statistical number and all generics that the first probability is each generic is stated, second calculates mould
Block 2 is each described spy for calculating corresponding second probability of each characteristic attribute in generic, second probability
The ratio between statistical number of the attribute in the generic and all characteristic attribute summations in the generic are levied, third calculates mould
Block 3 is used for the characteristic attribute according to first probability, second probability and work order to be sorted, calculates the work order to be sorted
The corresponding third probability of generic, comparison module 4 are used for more all third probability, and by the maximum in the third probability
Class categories of the corresponding generic of value as the work order to be sorted.
Work order classification processing server provided in an embodiment of the present invention, realizes work order and classifies automatically, ensure that work order point
Class reasonability, and improve the efficiency of work order classification.
On the basis of the above embodiments, the server further includes acquisition module 5, is specifically used for:
Sample work order is imported for the generic;The participle of the sample work order is extracted using mmseg4j segmenter;
It polymerize the participle of the sample work order, to obtain the characteristic attribute of the generic.
Specifically, acquisition module 5, is specifically used for:
Sample work order is imported for the generic;The participle of the sample work order is extracted using mmseg4j segmenter;
It polymerize the participle of the sample work order, to obtain the characteristic attribute of the generic.
Work order provided in an embodiment of the present invention is classified processing server, by the characteristic attribute of the generic got,
It ensure that the realizability of work order classification.
On the basis of the above embodiments, the third computing module 3 is specifically used for, and is calculated by the following formula and obtains institute
State third probability:
Wherein, P (yi| x) it is third probability, P (aj|yi) it is the second probability, P (yi) be the first probability, P (x | yi) it is to exchange
The conditional probability corresponding to third probability, x after event are work order to be sorted, ajFor each characteristic attribute and x={ a of x1,
a2...am}、yiIt is characterized attribute sum for each work order class categories, m.
Specifically, the third computing module 3 is specifically used for, it is calculated by the following formula and obtains the third probability:
Wherein, P (yi| x) it is third probability, P (aj|yi) it is the second probability, P (yi) be the first probability, P (x | yi) it is to exchange
The conditional probability corresponding to third probability, x after event are work order to be sorted, ajFor each characteristic attribute and x={ a of x1,
a2...am}、yiIt is characterized attribute sum for each work order class categories, m.
Work order classification processing server provided in an embodiment of the present invention has by the calculation formula of specific third probability
It realizes work order to effect automatically to classify, ensure that work order classification reasonability, and improve the efficiency of work order classification.
On the basis of the above embodiments, the acquisition module 5 is specifically used for:
Import work order data to be sorted;The Chinese word segmentation of every work order in the work order to be sorted is extracted;If sentencing
It is disconnected to know that the Chinese word segmentation extracted is present in the characteristic attribute of the sample work order, then the feature category of work order to be sorted is added
In property, or:If judgement knows that the Chinese word segmentation extracted is not present in the characteristic attribute of the sample work order, give up.
Specifically, the acquisition module 5 is specifically used for:
Import work order data to be sorted;The Chinese word segmentation of every work order in the work order to be sorted is extracted;If sentencing
It is disconnected to know that the Chinese word segmentation extracted is present in the characteristic attribute of the sample work order, then the feature category of work order to be sorted is added
In property, or:If judgement knows that the Chinese word segmentation extracted is not present in the characteristic attribute of the sample work order, give up.
Work order classification processing server provided in an embodiment of the present invention, by the feature category for reasonably obtaining work order to be sorted
Property, to ensure that the reasonability of work order classification.
On the basis of the above embodiments, the acquisition module 5 is specifically used for:It is waited for described by mmseg4j segmenter
The Chinese word segmentation of every work order extracts in classification work order.
Specifically, the acquisition module 5 is specifically used for:By mmseg4j segmenter to every in the work order to be sorted
The Chinese word segmentation of work order extracts.
Work order provided in an embodiment of the present invention is classified processing server, is reasonably obtained and is waited for point by mmseg4j segmenter
The characteristic attribute of class work order realizes effective acquisition of characteristic attribute.
Work order classification processing server provided in this embodiment specifically can be used for executing the place of above-mentioned each method embodiment
Flow is managed, details are not described herein for function, is referred to the detailed description of above method embodiment.
Fig. 3 is server entity structural schematic diagram provided in an embodiment of the present invention, as shown in figure 3, the server includes:
Processor (processor) 301, memory (memory) 302 and bus 303;
Wherein, the processor 301, memory 302 complete mutual communication by bus 303;
The processor 301 is used to call the program instruction in the memory 302, to execute above-mentioned each method embodiment
The method provided, such as including:Calculate corresponding first probability of each generic of sample work order, first probability
For the ratio between the statistics summation of the statistical number and all generics of each generic;Calculate each in generic
Corresponding second probability of characteristic attribute, second probability are the statistics of each characteristic attribute in the generic
The ratio between number and all characteristic attribute summations in the generic;According to first probability, second probability and to be sorted
The characteristic attribute of work order calculates the corresponding third probability of the work order generic to be sorted;Compare all third probability, and will
Class categories of the generic corresponding to maximum value as the work order to be sorted in the third probability.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including:Calculate the every of sample work order
Corresponding first probability of one generic, first probability be each generic statistical number with it is all affiliated
The ratio between statistics summation of classification;Corresponding second probability of each characteristic attribute in generic is calculated, second probability is
In statistical number of each the described characteristic attribute in the generic and the generic all characteristic attribute summations it
Than;According to first probability, the characteristic attribute of second probability and work order to be sorted, calculate belonging to the work order to be sorted
The corresponding third probability of classification;Compare all third probability, and by the affiliated class corresponding to the maximum value in the third probability
Class categories not as the work order to be sorted.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute the method that above-mentioned each method embodiment is provided, example
Such as include:Corresponding first probability of each generic of sample work order is calculated, first probability is each described institute
Belong to the ratio between the statistics summation of the statistical number and all generics of classification;It is corresponding to calculate each characteristic attribute in generic
Second probability, second probability are the statistical number of each characteristic attribute in the generic and the affiliated class
The ratio between all characteristic attribute summations in not;According to first probability, the characteristic attribute of second probability and work order to be sorted,
Calculate the corresponding third probability of the work order generic to be sorted;Compare all third probability, and will be in the third probability
Maximum value corresponding to class categories of the generic as the work order to be sorted.
One of ordinary skill in the art will appreciate that:Realize that all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer read/write memory medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes:ROM, RAM, magnetic disc or light
The various media that can store program code such as disk.
The embodiments such as server described above are only schematical, wherein the list illustrated as separating component
Member may or may not be physically separated, and the component shown as unit may or may not be physics
Unit, you can be located at a place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of module therein achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creation
In the case of the labour of property, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be expressed in the form of software products in other words, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally it should be noted that:The above various embodiments is only to illustrate the technical solution of the embodiment of the present invention rather than right
It is limited;Although the embodiment of the present invention is described in detail with reference to foregoing embodiments, the ordinary skill of this field
Personnel should understand that:It still can be with technical scheme described in the above embodiments is modified, or to which part
Or all technical features carries out equivalent replacement;And these modifications or replacements, it does not separate the essence of the corresponding technical solution
The range of each embodiment technical solution of the embodiment of the present invention.
Claims (10)
1. a kind of work order classification processing method, which is characterized in that including:
Corresponding first probability of each generic of sample work order is calculated, first probability is each described affiliated class
The ratio between the statistics summation of other statistical number and all generics;
Corresponding second probability of each characteristic attribute in generic is calculated, second probability is each described feature category
Property the ratio between statistical number in the generic and all characteristic attribute summations in the generic;
According to first probability, the characteristic attribute of second probability and work order to be sorted, the work order institute to be sorted is calculated
Belong to the corresponding third probability of classification;
Compare all third probability, and using the generic corresponding to the maximum value in the third probability as described to be sorted
The class categories of work order.
2. according to the method described in claim 1, it is characterized in that, the method further includes:
Sample work order is imported for the generic;
The participle of the sample work order is extracted using mmseg4j segmenter;
It polymerize the participle of the sample work order, to obtain the characteristic attribute of the generic.
3. according to the method described in claim 1, it is characterized in that, the third probability is calculated by the following formula acquisition:
Wherein, P (yi| x) it is third probability, P (aj|yi) it is the second probability, P (yi) be the first probability, P (x | yi) it is exchange event
The conditional probability corresponding to third probability afterwards, x are work order to be sorted, ajFor each characteristic attribute and x={ a of x1,
a2...am}、yiIt is characterized attribute sum for each work order class categories, m.
4. method according to claim 1 or 2 or 3, which is characterized in that the characteristic attribute of the work order to be sorted obtains
It takes, including:
Import work order data to be sorted;
The Chinese word segmentation of every work order in the work order to be sorted is extracted;
If judgement knows that the Chinese word segmentation extracted is present in the characteristic attribute of the sample work order, work order to be sorted is added
Characteristic attribute in, or:
If judgement knows that the Chinese word segmentation extracted is not present in the characteristic attribute of the sample work order, give up.
5. according to the method described in claim 4, it is characterized in that, by mmseg4j segmenter in the work order to be sorted
The Chinese word segmentation of every work order extracts.
The processing server 6. a kind of work order is classified, which is characterized in that including:
First computing module, corresponding first probability of each generic for calculating sample work order, first probability
For the ratio between the statistics summation of the statistical number and all generics of each generic;
Second computing module, for calculating corresponding second probability of each characteristic attribute in generic, second probability
For all characteristic attribute summations in statistical number of each the described characteristic attribute in the generic and the generic
The ratio between;
Third computing module is calculated for the characteristic attribute according to first probability, second probability and work order to be sorted
The corresponding third probability of the work order generic to be sorted;
Comparison module is used for more all third probability, and by the generic corresponding to the maximum value in the third probability
Class categories as the work order to be sorted.
7. server according to claim 6, which is characterized in that further include acquisition module, be specifically used for:
Sample work order is imported for the generic;
The participle of the sample work order is extracted using mmseg4j segmenter;
It polymerize the participle of the sample work order, to obtain the characteristic attribute of the generic.
8. server according to claim 6, which is characterized in that the third computing module is specifically used for, by following
Formula, which calculates, obtains the third probability:
Wherein, P (yi| x) it is third probability, P (aj|yi) it is the second probability, P (yi) be the first probability, P (x | yi) it is exchange event
The conditional probability corresponding to third probability afterwards, x are work order to be sorted, ajFor each characteristic attribute and x={ a of x1,
a2...am}、yiIt is characterized attribute sum for each work order class categories, m.
9. the server described according to claim 6 or 7 or 8, which is characterized in that the acquisition module is specifically used for:
Import work order data to be sorted;
The Chinese word segmentation of every work order in the work order to be sorted is extracted;
If judgement knows that the Chinese word segmentation extracted is present in the characteristic attribute of the sample work order, work order to be sorted is added
Characteristic attribute in, or:
If judgement knows that the Chinese word segmentation extracted is not present in the characteristic attribute of the sample work order, give up.
10. server according to claim 9, which is characterized in that the acquisition module is specifically used for:Pass through mmseg4j
Segmenter extracts the Chinese word segmentation of every work order in the work order to be sorted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710040034.7A CN108334488A (en) | 2017-01-18 | 2017-01-18 | A kind of work order classification processing method and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710040034.7A CN108334488A (en) | 2017-01-18 | 2017-01-18 | A kind of work order classification processing method and server |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108334488A true CN108334488A (en) | 2018-07-27 |
Family
ID=62922733
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710040034.7A Pending CN108334488A (en) | 2017-01-18 | 2017-01-18 | A kind of work order classification processing method and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108334488A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111080148A (en) * | 2019-12-20 | 2020-04-28 | Oppo(重庆)智能科技有限公司 | Net value calculation method and device of ERP system, electronic equipment and storage medium |
CN111988807A (en) * | 2019-05-21 | 2020-11-24 | 中国移动通信集团湖北有限公司 | Network problem positioning method and device based on big data and computing equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268134A (en) * | 2014-09-28 | 2015-01-07 | 苏州大学 | Subjective and objective classifier building method and system |
US20150332156A1 (en) * | 2014-05-15 | 2015-11-19 | Cellco Partnership D/B/A Verizon Wireless | Predictive Modeling Based on Summary Data and Modeling User's Age at Line Level |
CN105183808A (en) * | 2015-08-26 | 2015-12-23 | 苏州大学张家港工业技术研究院 | Problem classification method and apparatus |
-
2017
- 2017-01-18 CN CN201710040034.7A patent/CN108334488A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150332156A1 (en) * | 2014-05-15 | 2015-11-19 | Cellco Partnership D/B/A Verizon Wireless | Predictive Modeling Based on Summary Data and Modeling User's Age at Line Level |
CN104268134A (en) * | 2014-09-28 | 2015-01-07 | 苏州大学 | Subjective and objective classifier building method and system |
CN105183808A (en) * | 2015-08-26 | 2015-12-23 | 苏州大学张家港工业技术研究院 | Problem classification method and apparatus |
Non-Patent Citations (1)
Title |
---|
陈宁俊: "电信用户投诉分类及管理系统的设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111988807A (en) * | 2019-05-21 | 2020-11-24 | 中国移动通信集团湖北有限公司 | Network problem positioning method and device based on big data and computing equipment |
CN111080148A (en) * | 2019-12-20 | 2020-04-28 | Oppo(重庆)智能科技有限公司 | Net value calculation method and device of ERP system, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dahiya et al. | Customer churn analysis in telecom industry | |
CN108256691A (en) | Refund Probabilistic Prediction Model construction method and device | |
CN106844407B (en) | Tag network generation method and system based on data set correlation | |
US10521748B2 (en) | Retention risk determiner | |
CN111291816A (en) | Method and device for carrying out feature processing aiming at user classification model | |
CN111932130B (en) | Service type identification method and device | |
CN107169768A (en) | The acquisition methods and device of abnormal transaction data | |
CN106067091A (en) | Enterprise Institutions checking system and method | |
CN110390584A (en) | A kind of recognition methods of abnormal user, identification device and readable storage medium storing program for executing | |
CN105574544A (en) | Data processing method and device | |
CN108062306A (en) | A kind of index system establishment system and method for business environment evaluation | |
CN114510735B (en) | Role management-based intelligent shared financial management method and platform | |
CN111985937A (en) | Method, system, storage medium and computer equipment for evaluating value information of transaction traders | |
CN108228622A (en) | The sorting technique and device of traffic issues | |
TAN et al. | Evaluation and improvement of procurement process with data analytics | |
CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
CN109960719A (en) | A kind of document handling method and relevant apparatus | |
CN110930218A (en) | Method and device for identifying fraudulent customer and electronic equipment | |
CN108776857A (en) | NPS short messages method of investigation and study, system, computer equipment and storage medium | |
CN108334488A (en) | A kind of work order classification processing method and server | |
CN111460315A (en) | Social portrait construction method, device and equipment and storage medium | |
Johny et al. | Customer churn prediction: A survey | |
CN105991574A (en) | Risk behavior monitoring method and apparatus thereof | |
CN111967521A (en) | Cross-border active user identification method and device | |
CN109711984A (en) | Risk monitoring and control method and device before a kind of loan based on collection |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180727 |