CN110519466A - A kind of express delivery number identification method, equipment and computer storage medium - Google Patents
A kind of express delivery number identification method, equipment and computer storage medium Download PDFInfo
- Publication number
- CN110519466A CN110519466A CN201910818614.3A CN201910818614A CN110519466A CN 110519466 A CN110519466 A CN 110519466A CN 201910818614 A CN201910818614 A CN 201910818614A CN 110519466 A CN110519466 A CN 110519466A
- Authority
- CN
- China
- Prior art keywords
- short message
- information
- call
- feature
- sample
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/36—Statistical metering, e.g. recording occasions when traffic exceeds capacity of trunks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42025—Calling or Called party identification service
- H04M3/42034—Calling party identification service
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
- H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of express delivery number identification method, equipment and computer storage mediums, comprising: obtains enquiry number；The singal reporting code information of the corresponding enquiry number is obtained according to the enquiry number；The enquiry number is identified according to the singal reporting code information using Number Reorganization model, obtains the Number Reorganization that the enquiry number is express delivery number or non-express delivery number as a result, using express delivery number for identification of the embodiment of the present invention.
Description
Technical field
The present invention relates to machine learning techniques field more particularly to a kind of express delivery number identification methods, equipment and computer
Storage medium.
Background technique
With being constantly progressive for society, the mobile terminals such as mobile phone become the electronic product of manpower indispensability, and usual people are logical
Cross the interaction of folding and unfolding short message or information of making a phone call to realize.With popularizing for electronic product, user needs often to face and do not save
The conversational communication of strange number in address list, but due to cannot quickly identify the identity of strange number, user usually can
The risk swindled or harassed is faced, and the session of legal communication also leads to user because of the unknown of number such as express delivery number
Between cannot trust other side easily, influence both sides' communication efficiency.Various types harassing call equally gives people's lives, work belt
To adversely affect.Therefore how accurately to identify that the type of telephone number becomes urgent problem to be solved.
Summary of the invention
The present invention provides a kind of express delivery number identification method, equipment and computer storage medium, for identification express delivery number.
One aspect of the present invention provides a kind of express delivery number identification method, comprising: obtains enquiry number；According to the query ID
Code obtains the singal reporting code information of the corresponding enquiry number；Using Number Reorganization model according to the singal reporting code information to institute
It states enquiry number to be identified, obtains the Number Reorganization result that the enquiry number is express delivery number or non-express delivery number.
In a kind of embodiment, the singal reporting code information includes call indication information and short message indication information；Phase
It answers, the singal reporting code information of the corresponding enquiry number is obtained according to the enquiry number, comprising: inquire the enquiry number
Corresponding call behavioural information and short message behavioural information；It unites respectively to the call behavioural information and short message behavioural information
Meter, obtains the corresponding conversational nature of the enquiry number and short message feature；Summarize the conversational nature and the short message feature, obtains
Obtain singal reporting code information.
In a kind of embodiment, the conversational nature includes at least one following feature: for evaluating the number
First conversational nature of related total call frequency, for evaluating the second conversational nature of incoming call call frequency, for evaluating exhalation
The third conversational nature of call frequency, for evaluating the 4th conversational nature of incoming call air time, when for evaluating outgoing call
Between the 5th conversational nature return for evaluating the 6th conversational nature of outbound calling information of home location for evaluating Inbound Calls
7th conversational nature of possession information, for evaluating the 8th call of incoming call, outbound calling ownership place call frequency accounting information
Feature；The short message feature includes at least one following feature: first for evaluating the related total short message frequency of the number is short
Believe feature, for evaluating the second short message feature of collection of letters frequency characteristic, for evaluating the third short message feature for transmitting frequency characteristic,
For evaluating the 4th short message feature for transmitting corresponding number attribution information, for evaluating corresponding number attribution information of collecting mail
5th short message feature.
In a kind of embodiment, summarize the conversational nature and the short message feature, obtains singal reporting code information, packet
It includes: based on feature Assessment of Important strategy, to the different conversational natures and the short message characteristic binding difference weight；It will connection
The conversational nature and short message feature for closing different weights summarize, and obtain singal reporting code information.
In a kind of embodiment, the method also includes: multiple number samples are obtained by express delivery list；According to institute
It states multiple number samples and obtains corresponding communication behavior message sample；The communication behavior message sample is counted, is obtained
Corresponding singal reporting code message sample；Model training is carried out according to the singal reporting code message sample, obtains the Number Reorganization
Model.
Another aspect of the present invention provides a kind of express delivery Number Reorganization equipment, comprising: module is obtained, for obtaining query ID
Code；Module is obtained, for obtaining the singal reporting code information of the corresponding enquiry number according to the enquiry number；Identification module,
For identifying according to the singal reporting code information to the enquiry number using Number Reorganization model, the query ID is obtained
Code is the Number Reorganization result of express delivery number or non-express delivery number.
In a kind of embodiment, the singal reporting code information includes call indication information and short message indication information；Phase
It answers, the acquisition module, comprising: inquiry submodule, for inquiring the corresponding call behavioural information of the enquiry number and short
Believe behavioural information；Statistic submodule obtains institute for counting respectively to the call behavioural information and short message behavioural information
State the corresponding conversational nature of enquiry number and short message feature；Collects submodule, for summarizing the conversational nature and the short message
Feature obtains singal reporting code information.
In a kind of embodiment, the collects submodule is specifically used for: feature Assessment of Important strategy is based on, to not
The same conversational nature and the short message characteristic binding difference weight；The conversational nature and short message feature of different weights will be combined
Summarize, obtains singal reporting code information.
In a kind of embodiment, the equipment further include: sample obtains module, more for obtaining by express delivery list
A number sample；Sample respective modules, for obtaining corresponding communication behavior message sample according to the multiple number sample；Sample
This statistical module obtains corresponding singal reporting code message sample for counting to the communication behavior message sample；Sample
Training module obtains the Number Reorganization model for carrying out model training according to the singal reporting code message sample.
Another aspect of the present invention provides a kind of computer storage medium, and it is executable that computer is stored in the storage medium
Instruction, when executed for executing express delivery number identification method described in any one of above-mentioned embodiment.
A kind of express delivery number identification method, equipment and computer storage medium provided in an embodiment of the present invention, by looking into
The singal reporting code information for asking number is identified whether identification enquiry number belongs to the number of courier.
Detailed description of the invention
Fig. 1 shows the flow diagram of express delivery number identification method of the embodiment of the present invention；
Fig. 2 shows the flow diagrams that singal reporting code information is obtained in present invention method；
Fig. 3 shows the flow diagram for summarizing feature in present invention method；
Fig. 4 shows the flow diagram of training pattern in present invention method；
Fig. 5 shows the module diagram of express delivery Number Reorganization equipment of the embodiment of the present invention.
Specific embodiment
To keep the purpose of the present invention, feature, advantage more obvious and understandable, 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 only
It is only a part of the embodiment of the present invention, and not all embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Fig. 1 shows the flow diagram of express delivery number identification method of the embodiment of the present invention.
Referring to Fig. 1, on the one hand the embodiment of the present invention provides a kind of express delivery number identification method, comprising: step 101, obtains
Enquiry number；Step 102, the singal reporting code information of corresponding enquiry number is obtained according to enquiry number；Step 103, number is utilized
Identification model identifies that obtaining enquiry number is express delivery number or non-express delivery number according to singal reporting code information to enquiry number
Number Reorganization result.
Express delivery number identification method provided in an embodiment of the present invention is known by the singal reporting code information to enquiry number
Not, whether identification enquiry number belongs to the number of courier.This method can be applied to equipment having data processing function, can also
Applied to server having data processing function.
Specifically, this method obtains enquiry number first, which includes cell-phone number, home Tel and any other
With communications identities mark number it is any one or more.According to equipment applied by the number identification method, enquiry number
Acquisition pattern equally can also such as be incuded by equipment by equipment by database crawl acquisition enquiry number to be a variety of
Input content obtains enquiry number, can also make to receive inquiry using the equipment of this method by other equipment by communications
Number.
After equipment obtains enquiry number, the singal reporting code information of corresponding enquiry number is obtained according to enquiry number.
Singal reporting code information is obtained at least through the call behavioural information and short message behavioural information of the corresponding enquiry number.Its
In, call behavioural information is enquiry number related total air time and/or frequency, the time of incoming call call and/or the frequency, exhalation
The ratio of the time of call and the/frequency, incoming call air time and/or the frequency and outgoing call time and/or the frequency, incoming call call
The ratio of time and/or the frequency and total air time and/or the frequency, outgoing call time and/or the frequency and total air time and/
Or the frequency ratio and other enquiry numbers it is one or more in the information that communication process can generate.Short message behavior
Information is the related total short message frequency of enquiry number, and the collection of letters frequency transmits frequency characteristic and other enquiry numbers in short message mistake
The information that journey can generate it is one or more.
It is to be understood that the locating week of call behavioural information and short message behavioural information that different numbers can be got
It is had differences between phase, i.e. the possible available call behavioural information and short message behavioural information in 1 year of portion numbers, portion
Branch code may can only get call behavioural information and short message behavioural information in half a year, and portion numbers may can only be got
Call behavioural information and short message behavioural information in one month, remaining situation do not repeat them here.Based on the above reasons, the present invention is implemented
The call behavioural information and short message behavioural information chosen in example can be the call behavioural information and short message row of setting same period
For information, it is also possible to the average value of the call behavioural information that can be obtained and short message behavioural information.For example, as the present invention
The call behavioural information and short message behavioural information chosen in embodiment can be the setting call behavioural information of same period and short
Believe behavioural information when, setting the period be adjusted as needed, be such as set as one day, one month, three months, 1 year or other
Meaning duration.The setting period is longer, and the singal reporting code information obtained within the setting period is more, keeps recognition result more accurate.It is logical
Believe that indication information is obtained at least through call behavioural information and short message behavioural information.When in the embodiment of the present invention using average value as
When the call behavioural information and short message behavioural information of acquisition, set average period, according to the data that will acquire average period into
Row conversion, can according to need and is set, be such as set as one day, one month, three months, 1 year or any other average period
Duration.For example, working as call behavioural information and the short message behavioural information that enquiry number can be got is intraday call behavior
Information and short message behavioural information, average period is 30 days, by the call behavioural information and short message behavioural information data multiplied by three
Ten, it can be obtained the call behavioural information and short message behavioural information in average period.When the call that enquiry number can be got
Behavioural information and short message behavioural information are call behavioural information and short message behavioural information in 1 year, and average period is one month,
By the call behavioural information and short message behavioural information data divided by 12, can be obtained call behavioural information in average period and
Short message behavioural information.As needed, above-mentioned call behavioural information and short message behavioural information excessively calculate and obtain singal reporting code
Information.
After obtaining singal reporting code information, enquiry number is known according to singal reporting code information using Number Reorganization model
Not, the Number Reorganization result that enquiry number is express delivery number or non-express delivery number is obtained.Number Reorganization model can be selected as arbitrarily
The model obtained by singal reporting code message sample corresponding with singal reporting code information training.By Number Reorganization model to communication
Indication information is identified, the corresponding recognition result of singal reporting code information can be obtained, i.e., acquisition enquiry number is corresponding logical
Believe recognition result corresponding to indication information, realizes the identification checked numbers.
For convenience of the understanding of the above method, the embodiment of the present invention, which also provides a kind of specific implementation scene and carries out concrete application, to be said
It is bright.
In the application scenarios, which is applied to mobile phone, for being made whether incoming number for express delivery
The identification of number.When mobile phone receives incoming number, the call behavior letter of the incoming number is transferred from operator database
Breath and short message behavioural information, and call behavioural information and short message behavioural information are obtained into singal reporting code information by calculating.
By in the singal reporting code information input Number Reorganization model of the incoming number, which is XGB model,
XGB model has already passed through the training of singal reporting code information corresponding to the express delivery number marked in database, can be to express delivery
Number is identified.It is identified by singal reporting code information of the Number Reorganization model to incoming number, obtains the logical of input
Whether the recognition result for believing indication information, i.e., be express delivery number, when the singal reporting code information of input is express delivery number, that is, is judged
Incoming number is express delivery number.The number can be labeled, to remind user.When the non-express delivery number of singal reporting code information of input
When code, that is, judge the non-express delivery number of the incoming number.
Fig. 2 shows the flow diagrams that singal reporting code information is obtained in present invention method.
Referring to fig. 2, in embodiments of the present invention, singal reporting code information includes call indication information and short message indication information；
Correspondingly, step 102, the singal reporting code information of corresponding enquiry number is obtained according to enquiry number, comprising: step 1021, inquiry
The corresponding call behavioural information of enquiry number and short message behavioural information；Step 1022, respectively to call behavioural information and short message row
It is counted for information, obtains the corresponding conversational nature of enquiry number and short message feature；Step 1023, summarize conversational nature and short
Believe feature, obtains singal reporting code information.
Wherein, it should be noted that be different from call behavioural information and short message behavioural information, singal reporting code information are by leading to
It talks about behavioural information and short message behavioural information to obtain by counting statistics, singal reporting code information includes that call indication information and short message refer to
Information is marked, call indication information is obtained by call behavioural information counting statistics, short message is obtained by short message behavioural information counting statistics
Indication information.Specific acquisition pattern includes, call behavioural information corresponding to enquiry number first and short message behavioural information into
Row inquiry.The User behavior operator database or other can inquire call behavioural information and short message behavioural information number
It is carried out according in library.In another case, when enquiry number itself carries call behavioural information and short message behavioural information, lead to
It crosses to parse enquiry number and can equally directly obtain call behavioural information and short message behavioural information.
Indication information of conversing includes several conversational natures, and short message indication information includes several short message features, is being inquired
After the call behavioural information and short message behavioural information of number, unite to call behavioural information and short message behavioural information according to feature
Meter calculates, and can be obtained conversational nature and short message feature, conversational nature and short message feature are summarized, to obtain corresponding call row
For the singal reporting code information of information and short message behavioural information.
In embodiments of the present invention, conversational nature includes at least one following feature: for evaluating the related total call of number
First conversational nature of the frequency, for evaluating the second conversational nature of incoming call call frequency, for evaluating the outgoing call frequency
Third conversational nature, for evaluating the 4th conversational nature of incoming call air time, the 5th for evaluating the outgoing call time is logical
Feature is talked about, for evaluating the 6th conversational nature of outbound calling information of home location, for evaluating Inbound Calls information of home location
7th conversational nature, for evaluating the 8th conversational nature of incoming call, outbound calling ownership place call frequency accounting information；Short message is special
Sign includes at least one following feature: for evaluating the first short message feature of the related total short message frequency of number, being collected mail for evaluating
Second short message feature of frequency characteristic transmits corresponding number for evaluating for evaluating the third short message feature for transmitting frequency characteristic
4th short message feature of code information of home location, for evaluating the 5th short message feature of corresponding number attribution information of collecting mail.
As needed, the statistics that the embodiment of the present invention can carry out arbitrary characteristics to conversational nature and short message feature calculates,
Such as using the first conversational nature, the second conversational nature, third conversational nature as call indication information, by the first short message feature,
As short message indication information, summarizing acquisition includes the first conversational nature, the second call spy for second short message feature, third short message feature
Sign, third conversational nature, the first short message feature, the second short message feature, the singal reporting code information of third short message feature.According to need
It wants, the singal reporting code information calculated is according to requiring to be adjusted.It is to be appreciated that when the feature for being used to count is got over
More, obtaining Number Reorganization result can be more accurate, further, it should be clear that, feature includes corresponding inquiry text herein
The feature of training in the conversational nature and Number Reorganization model for including in this singal reporting code information.For example, when input mould
When the conversational nature of type is the first conversational nature, identification model is the identification mould for having already passed through the first conversational nature sample training and crossing
Type.It further, in the training process, can be to different weights be set between multiple feature samples, to mention according to training result
The accuracy of high Number Reorganization.Likewise, being carried out in enquiry number identification process by Number Reorganization model, according to training feelings
Condition, to conversational nature and the short message feature-set difference weight of enquiry number, to improve the accuracy of Number Reorganization.It should be noted that
, the above conversational nature and short message feature are non-fully enumerated, and according to the needs of Number Reorganization, singal reporting code information can also have
There are the 9th conversational nature, the tenth conversational nature ..., the 5th short message feature, the 6th short message feature ... are not repeated herein.
Fig. 3 shows the flow diagram for summarizing feature in present invention method.
Referring to Fig. 3, in embodiments of the present invention, step 1023, summarizes conversational nature and short message feature, obtain singal reporting code
Information, comprising: step 10231, it is based on feature Assessment of Important strategy, it is different with short message characteristic binding to different conversational natures
Weight；Step 10232, the conversational nature for combining different weights and short message feature are summarized, obtains singal reporting code information.
Further, since express delivery phone and general harassing call have a large amount of exhalation Content of Communication.It is fast in order to distinguish
Pass phone and general harassing call, according to the characteristic of express delivery phone, the embodiment of the present invention when choosing words feature and short message feature,
By with phone home higher weight in conjunction with related feature in singal reporting code information, the category feature is improved to recognition result
Influence, by singal reporting code information in conjunction with call frequency or the short message frequency lower weight, reduce the category feature to being to be tied
The influence of fruit.For example, to the 6th conversational nature for evaluating outbound calling information of home location, for evaluating Inbound Calls ownership
7th conversational nature of ground information, the first weight is arranged in the 8th conversational nature for evaluating outbound calling information of home location, right
For evaluating the first conversational nature of the related total call frequency of number, for evaluating the second conversational nature of incoming call call frequency,
For evaluating the third conversational nature of the outgoing call frequency, for evaluating the 4th conversational nature of incoming call air time, for commenting
The second weight is arranged in the 5th conversational nature of valence outgoing call time, wherein the first weight is greater than the second weight, is used in evaluation
6th conversational nature of outbound calling information of home location is used for evaluating the 7th conversational nature of Inbound Calls information of home location
It is greater than in evaluating influence of the 8th conversational nature of outbound calling information of home location to recognition result for evaluating number correlation
First conversational nature of total call frequency, for evaluating the second conversational nature of incoming call call frequency, for evaluating outgoing call
The third conversational nature of the frequency, for evaluating the 4th conversational nature of incoming call air time, for evaluating the outgoing call time
Influence of 5th conversational nature to recognition result, to keep recognition result more accurate.It should be noted that according to express delivery
Property, evaluation method Yi Qu, town or the mode in street of number attribution information are concluded, i.e., by the same area, town or street
The number in road is concluded to same home on the ground.In this way, by setting different weights between multiple conversational natures and short message feature,
To improve the accuracy of Number Reorganization.Likewise, during carrying out number sample training by Number Reorganization model, to training
Sample equally sets different weights, is checked numbers the accuracy of identification with improving model.To combining the conversational nature for having different weights
Summarized with short message feature, to obtain singal reporting code information.
Fig. 4 shows the flow diagram of training pattern in present invention method；
Referring to fig. 4, in embodiments of the present invention, method further include: step 401, obtain multiple numbers by express delivery list
Sample；Step 402, corresponding communication behavior message sample is obtained according to multiple number samples；Step 403, communication behavior is believed
Breath sample is counted, and corresponding singal reporting code message sample is obtained；Step 404, mould is carried out according to singal reporting code message sample
Type training obtains Number Reorganization model.
The Number Reorganization model of application of the embodiment of the present invention is by being trained acquisition to singal reporting code message sample.Its
In, what model can be selected as in XGB model, decision-tree model and Logic Regression Models any is trained it.The present invention
Embodiment is preferably trained XGB model.The training sample of model is obtained by express delivery list, wherein with express delivery list
In number correspond to the number sample that the embodiment of the present invention is referred to, the singal reporting code message sample conduct of corresponding number sample
Training sample is trained model, until it is express delivery singal reporting code that model, which can differentiate the corresponding recognition result of singal reporting code information,
Information or non-express delivery communicate indication information, and the corresponding number to corresponding singal reporting code information is express delivery number or non-express delivery number
Code.
Specifically, obtaining express delivery list by database first, database is network data base when carrying out model training
And/or operator database.Using the express delivery number in express delivery list obtained as number sample, according to number sample in number
According to being searched in library, the communication behavior message sample of corresponding number sample, similarly, communication behavior message sample herein are obtained
Including call behavioural information sample and short message behavioural information sample.By to call behavioural information sample and short message behavioural information sample
This carries out statistics calculating, obtains the conversational nature sample and corresponding short message behavioural information sample of corresponding call behavioural information sample respectively
This short message feature samples.It should be noted that the conversational nature of corresponding enquiry number and the conversational nature of corresponding number sample
The direction that sample is evaluated is identical.I.e. when in conversational nature including the first conversational nature, equally include in conversational nature sample
The first conversational nature sample identical with the first conversational nature evaluation content, remaining conversational nature similarly, do not repeat them here below.It is short
Letter feature and the relationship of short message feature samples do not repeat them here equally with the relationship of above-mentioned conversational nature and conversational nature sample.In
After obtaining conversational nature sample and short message feature samples, summarizes conversational nature sample and short message feature samples can be obtained correspondence
Singal reporting code message sample.Model training is carried out according to singal reporting code message sample later, obtains Number Reorganization model.It needs
Supplement, during carrying out model training by singal reporting code message sample, different conversational nature samples and short message are special
It levies sample and different weights is arranged according to its influence to recognition result accuracy.
For convenience of further understanding for above embodiment, a kind of scene embodiment presented below is illustrated.
It in this scenario, include Number Reorganization equipment using number identification method, Number Reorganization equipment is mobile phone, is needed
The type of number to be identified is express delivery number.
Firstly, determining the number sample for belonging to express delivery by the express delivery list obtained from operator database.Belong to determining
After the number sample of express delivery, in operator database, the communication behavior in the number sample one month, communication behavior are searched
It include call behavior and short message behavior.Statistics calculating is carried out according to the call behavior and short message behavior of searching acquisition, is counted
Number calling call frequency feature in one month, the ownership region quantative attribute of outgoing call in one month breathe out in one month
Most ownership place frequency characteristics of number, as conversational nature sample；It also counts number in one month and issues short message frequency spy
Sign, most ownership place frequency characteristics that the ownership region quantative attribute of short message is issued in one month, issues short message in one month, makees
For short message feature samples.Wherein, in one month outgoing call ownership region quantative attribute, refer to the number sample at one month
The distribution statistics of the ownership place quantity of the number of interior exhalation, for example, the number sample has been dialed in total belongs to five regional numbers
Code, then the ownership place quantative attribute of the number breathed out in one month are denoted as 5；Further, a number sample area wherein
Domain number of calls are most, and number is 100, then most ownership place frequency characteristics of outgoing call are denoted as 100 in one month.Short message
Feature samples similarly, do not repeat them here.
The conversational nature sample and short message feature samples that the corresponding statistics of each number sample obtains are aggregated into a file,
The corresponding singal reporting code message sample of each sample is obtained, above-mentioned singal reporting code message sample input model is subjected to model instruction
Practice, and input the weight of each feature samples according to importance, obtains the model that can identify express delivery number communication Behavior law,
The model can be used as express delivery Number Reorganization model.
When obtaining unknown number, when needing to identify the unknown number, pass through data base querying this unknown number first
Communication behavior in code one month, carries out statistics calculating according to communication behavior, counts number calling call frequency in one month
Feature, in one month outgoing call ownership region quantative attribute, in one month outgoing call most ownership place frequency characteristics,
As conversational nature；It also counts number in one month and issues short message frequency characteristic, the ownership region of short message is issued in one month
Quantative attribute, most ownership place frequency characteristics that short message is issued in one month, as short message feature.
Conversational nature and short message feature are aggregated into a file, the corresponding singal reporting code letter of the unknown number is obtained
Above-mentioned singal reporting code information input model is carried out model identification, identifies whether the singal reporting code information meets express delivery number by breath
Communication behavior rule, when meeting express delivery number communication Behavior law, can assert that the unknown number belongs to express delivery number.
Fig. 5 shows the module diagram of express delivery Number Reorganization equipment of the embodiment of the present invention.
Referring to Fig. 5, on the other hand the embodiment of the present invention provides a kind of express delivery Number Reorganization equipment, comprising: obtains module
501, for obtaining enquiry number；Module 502 is obtained, the singal reporting code for obtaining corresponding enquiry number according to enquiry number is believed
Breath；Identification module 503 is looked into for being identified according to singal reporting code information to enquiry number using Number Reorganization model
Ask the Number Reorganization result that number is express delivery number or non-express delivery number.
In embodiments of the present invention, singal reporting code information includes call indication information and short message indication information；Correspondingly, obtaining
Modulus block 502, comprising: inquiry submodule 5021, for inquiring the corresponding call behavioural information of enquiry number and short message behavior letter
Breath；Statistic submodule 5022 obtains enquiry number pair for counting respectively to call behavioural information and short message behavioural information
The conversational nature and short message feature answered；Collects submodule 5023 obtains singal reporting code for summarizing conversational nature and short message feature
Information.
In embodiments of the present invention, collects submodule 5023 is specifically used for: feature Assessment of Important strategy is based on, to difference
Conversational nature and short message characteristic binding difference weight；The conversational nature for combining different weights and short message feature are summarized, obtained
Singal reporting code information.
In embodiments of the present invention, equipment further include: sample obtains module 504, multiple for obtaining by express delivery list
Number sample；Sample respective modules 505, for obtaining corresponding communication behavior message sample according to multiple number samples；Sample
Statistical module 506 obtains corresponding singal reporting code message sample for counting to communication behavior message sample；Sample instruction
Practice module 507, for carrying out model training according to singal reporting code message sample, obtains Number Reorganization model.
On the other hand the embodiment of the present invention provides a kind of computer storage medium, computer is stored in storage medium to be held
Row instruction, when executed for executing any one of above-mentioned embodiment express delivery number identification method.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of express delivery number identification method characterized by comprising
Obtain enquiry number；
The singal reporting code information of the corresponding enquiry number is obtained according to the enquiry number；
The enquiry number is identified according to the singal reporting code information using Number Reorganization model, obtains the query ID
Code is the Number Reorganization result of express delivery number or non-express delivery number.
2. the method according to claim 1, wherein the singal reporting code information includes call indication information and short
Believe indication information；
Correspondingly, obtaining the singal reporting code information of the corresponding enquiry number according to the enquiry number, comprising:
Inquire the corresponding call behavioural information of the enquiry number and short message behavioural information；
The call behavioural information and short message behavioural information are counted respectively, it is special to obtain the corresponding call of the enquiry number
Short message of seeking peace feature；
Summarize the conversational nature and the short message feature, obtains singal reporting code information.
3. according to the method described in claim 2, it is characterized in that,
The conversational nature includes at least one following feature: for evaluating the first call of the related total call frequency of the number
Feature, for evaluating the third conversational nature of the outgoing call frequency, is used for evaluating the second conversational nature of incoming call call frequency
In the 4th conversational nature of evaluation incoming call air time, for evaluating the 5th conversational nature of outgoing call time, for evaluating
6th conversational nature of outbound calling information of home location is used for evaluating the 7th conversational nature of Inbound Calls information of home location
In evaluation incoming call, the 8th conversational nature of outbound calling ownership place call frequency accounting information；
The short message feature includes at least one following feature: for evaluating the first short message of the related total short message frequency of the number
Feature, for evaluating the third short message feature for transmitting frequency characteristic, is used for evaluating the second short message feature of collection of letters frequency characteristic
The 4th short message feature of corresponding number attribution information is transmitted in evaluation, for evaluate the of correspondence number attribution information of collecting mail
Five short message features.
4. according to the method described in claim 2, obtaining it is characterized in that, summarize the conversational nature and the short message feature
Singal reporting code information, comprising:
Based on feature Assessment of Important strategy, to the different conversational natures and the short message characteristic binding difference weight；
The conversational nature for combining different weights and short message feature are summarized, singal reporting code information is obtained.
5. method according to any one of claims 1 to 4, which is characterized in that the method also includes:
Multiple number samples are obtained by express delivery list；
Corresponding communication behavior message sample is obtained according to the multiple number sample；
The communication behavior message sample is counted, corresponding singal reporting code message sample is obtained；
Model training is carried out according to the singal reporting code message sample, obtains the Number Reorganization model.
6. a kind of express delivery Number Reorganization equipment characterized by comprising
Module is obtained, for obtaining enquiry number；
Module is obtained, for obtaining the singal reporting code information of the corresponding enquiry number according to the enquiry number；
Identification module, for being identified according to the singal reporting code information to the enquiry number using Number Reorganization model,
Obtain the Number Reorganization result that the enquiry number is express delivery number or non-express delivery number.
7. equipment according to claim 6, which is characterized in that the singal reporting code information includes call indication information and short
Believe indication information；
Correspondingly, the acquisition module, comprising:
Submodule is inquired, for inquiring the corresponding call behavioural information of the enquiry number and short message behavioural information；
Statistic submodule obtains the inquiry for counting respectively to the call behavioural information and short message behavioural information
The corresponding conversational nature of number and short message feature；
Collects submodule obtains singal reporting code information for summarizing the conversational nature and the short message feature.
8. equipment according to claim 7, which is characterized in that
The collects submodule is specifically used for: feature Assessment of Important strategy is based on, to the different conversational nature and described
Short message characteristic binding difference weight；The conversational nature for combining different weights and short message feature are summarized, singal reporting code information is obtained.
9. according to the described in any item equipment of claim 6 to 8, which is characterized in that the equipment further include:
Sample obtains module, for obtaining multiple number samples by express delivery list；
Sample respective modules, for obtaining corresponding communication behavior message sample according to the multiple number sample；
Sample statistics module obtains corresponding singal reporting code information sample for counting to the communication behavior message sample
This；
Sample training module obtains the Number Reorganization mould for carrying out model training according to the singal reporting code message sample
Type.
10. a kind of computer storage medium, which is characterized in that computer executable instructions are stored in the storage medium, when
Described instruction, which is performed, requires any one of the 1-5 express delivery number identification method for perform claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910818614.3A CN110519466A (en) | 2019-08-30 | 2019-08-30 | A kind of express delivery number identification method, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910818614.3A CN110519466A (en) | 2019-08-30 | 2019-08-30 | A kind of express delivery number identification method, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110519466A true CN110519466A (en) | 2019-11-29 |
Family
ID=68629919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910818614.3A Pending CN110519466A (en) | 2019-08-30 | 2019-08-30 | A kind of express delivery number identification method, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110519466A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101854609A (en) * | 2010-05-17 | 2010-10-06 | 中兴通讯股份有限公司 | Short message monitoring system and method |
| CN103796207A (en) * | 2012-11-02 | 2014-05-14 | 中国移动通信集团上海有限公司 | Method and device for identifying false subscriber number |
| CN105611084A (en) * | 2016-01-29 | 2016-05-25 | 中国联合网络通信集团有限公司 | User fraud suspiciousness degree calculation method and suspiciousness degree calculation system |
| CN107343077A (en) * | 2016-04-28 | 2017-11-10 | 腾讯科技（深圳）有限公司 | Identify malicious call and establish the method, apparatus of identification model, equipment |
| CN108449482A (en) * | 2018-02-09 | 2018-08-24 | 北京泰迪熊移动科技有限公司 | The method and system of Number Reorganization |
| CN109274834A (en) * | 2018-09-27 | 2019-01-25 | 杭州东信北邮信息技术有限公司 | A kind of express delivery number identification method based on call behavior |
| CN110072017A (en) * | 2019-04-28 | 2019-07-30 | 济南大学 | Abnormal phone recognition methods and system based on feature selecting and integrated study |
-
2019
- 2019-08-30 CN CN201910818614.3A patent/CN110519466A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101854609A (en) * | 2010-05-17 | 2010-10-06 | 中兴通讯股份有限公司 | Short message monitoring system and method |
| CN103796207A (en) * | 2012-11-02 | 2014-05-14 | 中国移动通信集团上海有限公司 | Method and device for identifying false subscriber number |
| CN105611084A (en) * | 2016-01-29 | 2016-05-25 | 中国联合网络通信集团有限公司 | User fraud suspiciousness degree calculation method and suspiciousness degree calculation system |
| CN107343077A (en) * | 2016-04-28 | 2017-11-10 | 腾讯科技（深圳）有限公司 | Identify malicious call and establish the method, apparatus of identification model, equipment |
| CN108449482A (en) * | 2018-02-09 | 2018-08-24 | 北京泰迪熊移动科技有限公司 | The method and system of Number Reorganization |
| CN109274834A (en) * | 2018-09-27 | 2019-01-25 | 杭州东信北邮信息技术有限公司 | A kind of express delivery number identification method based on call behavior |
| CN110072017A (en) * | 2019-04-28 | 2019-07-30 | 济南大学 | Abnormal phone recognition methods and system based on feature selecting and integrated study |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102158879B (en) | Essential factor lost score data processing method and equipment | |
| CN105824813B (en) | A kind of method and device for excavating core customer | |
| CN105007171A (en) | User data analysis system and method based on big data in communication field | |
| CN109688275A (en) | Harassing call recognition methods, device and storage medium | |
| CN110337059A (en) | A kind of parser, server and the network system of subscriber household relationship | |
| CN109508825A (en) | Employee's image method for prewarning risk and relevant apparatus | |
| CN109640312A (en) | " black card " recognition methods, electronic equipment and computer program product | |
| CN103092863A (en) | Questionnaire data processing method | |
| CN107527240A (en) | A kind of operator's industry product Praise effect identification system and method | |
| CN108268477A (en) | A kind of customer relationship based on ticket determines method and apparatus | |
| CN110493476B (en) | Detection method, device, server and storage medium | |
| US7729483B2 (en) | Methods, systems, and computer programs for generating a billing statement from detailed usage file records | |
| CN115759640A (en) | Public service information processing system and method for smart city | |
| CN110113748B (en) | Crank call monitoring method and device | |
| KR20170006158A (en) | System and method for detecting fraud usage of message | |
| CN108076197A (en) | A kind of detection method and device of terminal network performance degradation | |
| CN109474755A (en) | Abnormal phone active predicting method and system based on sequence study and integrated study | |
| CN110519466A (en) | A kind of express delivery number identification method, equipment and computer storage medium | |
| CN101150625A (en) | A call record analysis method and device | |
| CN111459961A (en) | Method, device and equipment for updating service data and storage medium | |
| CN110611689A (en) | Information identification method and device and computer readable storage medium | |
| CN110505353A (en) | A kind of number identification method, equipment and computer storage medium | |
| CN110516046A (en) | A kind of negative lable number recognition methods, equipment and computer storage medium | |
| CN110113471B (en) | Number monitoring method and device | |
| CN109121137A (en) | The Subscriber Number usage type recognition methods of double-terminal 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191129 |