CN108777848A

CN108777848A - For intercept information and the method for determining intercept information

Info

Publication number: CN108777848A
Application number: CN201810500993.7A
Authority: CN
Inventors: 徐学东
Original assignee: Shanghai Lianshang Network Technology Co Ltd
Current assignee: Shanghai Lianshang Network Technology Co Ltd
Priority date: 2018-05-23
Filing date: 2018-05-23
Publication date: 2018-11-09

Abstract

The embodiment of the present application is disclosed for intercept information and the method for determining intercept information.One specific implementation mode of this method includes：In response to being currently received short message, the transmission number and content of short message are obtained；According to the transmission number and content and active user's attribute of short message, it is determined whether intercept short message, wherein user property includes the key message for characterizing user's information of interest；Short message is intercepted in response to determining, short message is executed and intercepts operation.The embodiment can be according to active user's attribute of user, to determine whether to intercept short message.I.e. for same short message, the processing method to vary with each individual may be used, realize different handling results.

Description

For intercept information and the method for determining intercept information

Technical field

The invention relates to field of computer technology, and in particular to the side for intercept information and determining intercept information Method.

Background technology

With the fast development of mobile Internet, daily life increasingly be unable to do without mobile terminal.At the same time, Mobile terminal also receives many security threats.Such as various swindles, junk information are sent to user by some criminals.With Family often faces the harassing and wrecking of economic loss, individual privacy information leakage and daily life.

At present for the intercept process of junk information, typically cloud server comes according to the flag data of a large number of users Build data interception library.To analyze coming signal code and the information content, to determine whether to carry out intercept process.However, For different users, this intercept process mode is often unified.

Invention content

The embodiment of the present application is proposed for the method for intercept information and the method for determining intercept information.

In a first aspect, the embodiment of the present application proposes a kind of method for intercept information, this method is used for user equipment End, including：In response to being currently received short message, the transmission number and content of short message are obtained；According to the transmission number of short message and interior Hold and active user's attribute, it is determined whether intercept short message, wherein user property includes the information of interest for characterizing user Key message；Short message is intercepted in response to determining, short message is executed and intercepts operation.

In some embodiments, according to the transmission number and content of short message and active user's attribute, it is determined whether intercept Short message, including：Short message is sent into the information analysis model for including active user's attribute of number and content input currently, is obtained The analysis result of short message；And the analysis result according to short message, it is determined whether intercept short message；Wherein, analysis result includes short message It is/is not the content and active user's attributes match/mismatch of normal short message or short message.

In some embodiments, short message is sent into the information for including active user's attribute of number and content input currently Analysis model obtains the analysis result of short message, including：By the transmission number of short message and/or content in the data interception library to prestore In matched, wherein data interception in data interception library includes intercepting number and intercepting keyword；If in the content of short message Including there is the interception to match with the transmission number of short message in non-interception keyword or data interception library in data interception library Number, then it is normal short message to analyze determining short message not.

In some embodiments, short message is sent into the information for including active user's attribute of number and content input currently Analysis model obtains the analysis result of short message, including：Determine short message transmission number whether service to the public number；If it is determined that The transmission number is not public service number, then further determines that whether the length of the transmission number is preset length；If it is determined that The length of the transmission number is not preset length, then it is normal short message to analyze determining short message not；If it is determined that the length of the transmission number Degree is preset length, then further determines that whether the content of short message meets preset condition；It is preset if it is determined that the content of short message meets Condition, then it is normal short message to analyze determining short message not.

In some embodiments, short message is sent into the information for including active user's attribute of number and content input currently Analysis model obtains the analysis result of short message, further includes：By the transmission number of short message and/or content in the non-interception number to prestore According to being matched in library, wherein the non-data interception in non-data interception library includes non-interception number and non-interception keyword；If Do not include the non-interception keyword in non-data interception library in the content of short message, and is not present and short message in non-data interception library The non-interception number that number matches is sent, then it is normal short message to analyze determining short message not.

In some embodiments, according to the analysis result of short message, it is determined whether short message is intercepted, including：When short message is not general When logical short message, further analyze short message content whether with active user's attributes match；When short message is not normal short message, and short message Content and active user's attribute when mismatching, determine and intercept short message.

In some embodiments, when short message is not normal short message, whether the content for further analyzing short message is used with current Family attributes match, including：The content of short message is analyzed, the contents attribute for determining short message and/or the content for extracting short message are closed Key information；Analyze the contents attribute of short message and/or the matching degree of key content information and active user's attribute；When matching degree does not reach When to predetermined threshold value, determine that the content of short message is mismatched with active user's attribute.

In some embodiments, this method further includes：The historical operating data of user to periodically acquiring is analyzed, User property in fresh information analysis model and related data, wherein historical operating data includes the third-party application of installation Application message and user third-party application operation information；Using updated information analysis model as current information Analysis model, wherein the user property in current information analysis model is active user's attribute；Wherein, information analysis model It trains to obtain by following steps：Obtain sample set, wherein the sample in sample set includes sample of users attribute, sample short message And the sample of users attribute user that is referred to is to the handling result of sample short message；By the sample of users attribute of sample in sample set Input with sample short message as initial model executes following training step：Transmission number to the sample short message of input and/or Content is analyzed, and determines whether the sample short message is normal short message；In response to determining that the sample short message is not normal short message, into One step analyze the sample short message content whether with corresponding sample of users attributes match；If the content of the sample short message with it is corresponding Sample of users attribute mismatch, it is determined that intercept the sample short message；By the definitive result of the sample short message of input with it is corresponding Handling result is compared, and determines whether the definitive result of the sample short message of input is identical as corresponding handling result；According to than Compared with as a result, determining whether initial model trains completion；If it is determined that initial model training is completed, then the initial model completed training As information analysis model；If it is determined that initial model not complete by training, the relevant parameter in initial model is adjusted, after adjustment Initial model is as initial model, and continues to execute training step.

Second aspect, the embodiment of the present application propose a kind of device for intercept information, which is set to user and sets Standby end, including：Acquiring unit is configured in response to be currently received short message, obtains the transmission number and content of short message；First Determination unit is configured to transmission number and content and active user's attribute according to short message, it is determined whether short message is intercepted, In, user property includes the key message for characterizing user's information of interest；Interception unit is configured in response to determine Short message is intercepted, short message is executed and intercepts operation.

The third aspect, the embodiment of the present application propose a kind of method for determining intercept information, and this method is used for network Equipment end, including：It is currently received short message in response to user equipment end, receives the transmission number for the short message that user equipment end is sent And content；According to the transmission number and active user's attribute of content and target user of short message, it is determined whether short message is intercepted, In, target user is the user using user equipment end, and user property includes the key for characterizing user's information of interest Information；Definitive result is sent to user equipment end so that user equipment end definitive result indicate intercept short message when, to short message It executes and intercepts operation.

In some embodiments, according to the transmission number and active user's attribute of content and target user of short message, really It is fixed whether to intercept short message, including：Obtain the information analysis model of current active user's attribute including target user；By short message Transmission number and content input current information analysis model, obtain the analysis result of short message；And point according to institute's short message Analyse result, it is determined whether intercept short message；Wherein, analysis result, which includes short message, is/is not the content of normal short message or short message and work as Preceding user property match/mismatch.

In some embodiments, the transmission number and content of short message are inputted into current information analysis model, obtains short message Analysis knot, including：The transmission number of short message and/or content are matched in the data interception library to prestore, wherein intercept Data interception in database includes intercepting number and interception keyword；If including blocking in data interception library in the content of short message The interception number for existing in keyword or data interception library and matching with the transmission number of short message is cut, then analyzes determining short message It is not normal short message.

In some embodiments, the transmission number and content of short message are inputted into current information analysis model, obtains short message Analysis knot, including：Determine short message transmission number whether service to the public number；If it is determined that the transmission number is not public's clothes Business number, then further determine that whether the length of the transmission number is preset length；If it is determined that the length of the transmission number is not Preset length, then it is normal short message to analyze determining short message not；If it is determined that the length of the transmission number is preset length, then further Determine whether the content of short message meets preset condition；If it is determined that the content of short message meets preset condition, then determining short message is analyzed not It is normal short message.

In some embodiments, the transmission number and content of short message are inputted into current information analysis model, obtains short message Analysis knot, further include：In the non-data interception library group to prestore, non-data interception library corresponding with target user is chosen, In, the non-data interception in non-data interception library includes non-interception number and non-interception keyword；By the transmission number of short message and/ Or content is matched in the non-data interception library of selection；If not including in the content of short message in the non-data interception library chosen Non- interception keyword, and there is no the non-interceptions number to match with the transmission number of short message in the non-data interception library chosen Code, then it is normal short message to analyze determining short message not.

In some embodiments, this method further includes：Periodically obtain history of the target user on user equipment end Operation data, wherein historical operating data includes the application message and mesh for the third-party application being mounted on user equipment end Operation information of the mark user in third-party application；The historical operating data of acquisition is analyzed, update is corresponding with target user Information analysis model in user property and related data；Using updated information analysis model as current information analysis Model, wherein the user property in current information analysis model is active user's attribute；Wherein, information analysis model passes through Following steps train to obtain：Obtain sample set, wherein the sample in sample set include sample of users attribute, sample short message and Handling result of the user that sample of users attribute is referred to sample short message；By the sample of users attribute and sample of sample in sample set Input of this short message as initial model, executes following training step：To the transmission number and/or content of the sample short message of input It is analyzed, determines whether the sample short message is normal short message；In response to determining that the sample short message is not normal short message, further Analyze the sample short message content whether with corresponding sample of users attributes match；If the content of the sample short message and corresponding sample This user property mismatches, it is determined that intercepts the sample short message；By the definitive result of the sample short message of input and corresponding processing As a result it is compared, determines whether the definitive result of the sample short message of input is identical as corresponding handling result；It is tied according to comparing Fruit, determines whether initial model trains completion；If it is determined that initial model training complete, then will training complete initial model as Information analysis model；If it is determined that initial model not complete by training, the relevant parameter in initial model is adjusted, it will be initial after adjustment Model is as initial model, and continues to execute training step.

Fourth aspect, the embodiment of the present application propose a kind of device for determining intercept information, which is set to net Network equipment end, including：Receiving unit is configured in response to user equipment end and is currently received short message, receives user equipment end The transmission number and content of the short message of transmission；Second determination unit, be configured to according to the transmission number and content of short message and Active user's attribute of target user, it is determined whether intercept short message, wherein target user is the user using user equipment end, User property includes the key message for characterizing user's information of interest；Transmission unit is configured to send out definitive result User equipment end is given, so that user equipment end executes short message and intercept operation when definitive result indicates to intercept short message.

5th aspect, the embodiment of the present application propose a kind of electronic equipment, including：One or more processors；Storage dress It sets, is stored thereon with one or more programs；When one or more programs are executed by one or more processors so that one or Multiple processors realize the method as described in any embodiment in above-mentioned first aspect and the third aspect.

6th aspect, the embodiment of the present application propose a kind of computer-readable medium, are stored thereon with computer program, In, it is realized as described in any embodiment in above-mentioned first aspect and the third aspect when which is executed by processor Method.

The method for intercept information and determining intercept information that the embodiment of the present application proposes, listens at user equipment end When being currently received short message, the transmission number and content of short message can be obtained.Later, according to the transmission number of short message and content with And active user's attribute, user equipment end or network equipment end may determine whether to intercept the short message.Active user is belonged to Property indicated by user for, if to the short message execute intercept operation.Wherein, user property may include for characterizing user The key message of information of interest.In the case where determining the interception short message, user equipment end can execute interception to short message Operation.That is, the method in the present embodiment can be according to active user's attribute of user, to determine whether to carry out short message It intercepts.I.e. for same short message, the processing method to vary with each individual may be used, realize different handling results.

Description of the drawings

By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other Feature, objects and advantages will become more apparent upon：

Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein；

Fig. 2 is the flow chart according to one embodiment of the method for intercept information of the application；

Fig. 3 is the flow chart according to another embodiment of the method for intercept information of the application；

Fig. 4 is the flow chart according to one embodiment of the method for determining intercept information of the application；

Fig. 5 is the schematic diagram of an application scenarios of the method for determining intercept information according to Fig.4,；

Fig. 6 is adapted for the structural schematic diagram of the computer system of the electronic equipment for realizing the embodiment of the present application.

Specific implementation mode

The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to Convenient for description, is illustrated only in attached drawing and invent relevant part with related.

It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

Fig. 1 is shown can be using the embodiment of the present application for the method for intercept information or for determining intercept information The exemplary system architecture 100 of method.

As shown in Figure 1, system architecture 100 may include terminal (i.e. user equipment end) 101,102,103,104 He of network Server (i.e. network equipment end) 105.Network 104 can be logical to be provided between terminal 101,102,103 and server 105 Believe the medium of link.Network 104 may include various connection types, such as wired, wireless communication link or fiber optic cables etc. Deng.

User can be interacted with using terminal 101,102,103 by network 104 and server 105, to receive or send out Send message etc..Various client applications can be installed in terminal 101,102,103, for example, web browser, the application of shopping class, Class of managing money matters application, short message application and immediate communication tool etc..

Terminal 101,102,103 can monitor the current short message that whether receives and broadcast in real time.If receiving short message broadcast, eventually End 101,102,103 can obtain the transmission number and content of the indicated short message of short message broadcast.And then it can be to the letter of acquisition Breath is analyzed, to determine whether to intercept short message.If it is determined that intercepting short message, then short message can be executed and intercept operation.If it is determined that Short message is not intercepted, then the short message application installed thereon can be made to receive and store short message.Meanwhile it can be joined according to the setting of user Number sends new information to user and reminds.Here short message may include general short message (SMS, Short Message Service) With multimedia message (MMS, Multimedia Messaging Service).

Here terminal 101,102,103 can be hardware, can also be software.When terminal 101,102,103 is hardware When, can be the various electronic equipments with short message receive capabilities, including but not limited to smart mobile phone, tablet computer, wearable Equipment, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic Image expert's compression standard audio level 3), pocket computer on knee and desktop computer etc..When terminal 101,102,103 For software when, may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or software module (such as For providing Distributed Services), single software or software module can also be implemented as.It is not specifically limited herein.

Server 105 can be to provide the server of various services, such as can be to being installed in terminal 101,102,103 Various applications provide support background server.Background server can analyze user using upper operation behavior Processing, and corresponding response message is sent to user according to handling result.Meanwhile background server can also be to the operation of user Behavior carries out record storage.

For another example server 105 can also be the Analysis server analyzed the information of short message.At this point, terminal 101,102,103 in the case where listening to short message broadcast, and the short message of acquisition can be broadcasted to the transmission number of indicated short message Code and content are sent to Analysis server.In this way, Analysis server can analyze these data, to determine whether to intercept Short message, and definitive result can be sent to terminal 101,102,103.And then when definitive result indicates to intercept short message, terminal 101,102,103 interception operation can be executed to short message.

Here server 105 can be equally hardware, can also be software.When server 105 is hardware, Ke Yishi The distributed server cluster of ready-made multiple server compositions, can also be implemented as individual server.When server 105 is software When, multiple softwares or software module (such as providing Distributed Services) may be implemented into, single software can also be implemented as Or software module.It is not specifically limited herein.

It should be noted that the method for intercept information that is provided of the embodiment of the present application generally by terminal 101,102, 103 execute.And the method for determining intercept information that the embodiment of the present application is provided generally is executed by server 105.

It should be understood that the number of the terminal, network and server in Fig. 1 is only schematical.It, can according to needs are realized With with any number of terminal, network and server.

With continued reference to Fig. 2, it illustrates the flows according to one embodiment of the method for intercept information of the application 200.The method for being used for intercept information may comprise steps of：

Step 201, in response to being currently received short message, the transmission number and content of short message are obtained.

In the present embodiment, be used for intercept information method executive agent (such as terminal shown in FIG. 1 101,102, 103) in the case where being currently received short message, the transmission number and content of short message can be obtained.Wherein, short message may include one As short message (SMS, Short Message Service) and multimedia message (MMS, Multimedia Messaging Service).

In the present embodiment, the transmission number of short message generally refers to addresser's number, that is, the user for sending the short message is made Number.Here transmission number may include (but not limited to) phone number and network virtual number etc..The content of short message Can be any information that can be sent by short message (general short message and multimedia message), such as word, number, image, link.

It is understood that in order to realize SMS interception, the short message mentioned here that receives is typically on executive agent Short message is received before the short message application installed receives short message.Such as executive agent can be in call operation system API (application programming interfaces, Application Program Interface), to make operating system execute short message monitor Program.In the case where operating system listens to short message event, system can send a broadcast.At this point, pre- in executive agent The broadcast recipients first defined can receive this broadcast, and can obtain broadcasting the relevant information of indicated short message, Such as send number, content and time.

Step 202, according to the transmission number and content of short message and active user's attribute, it is determined whether intercept short message.

In the present embodiment, executive agent can be according to the active user's attribute for the user for using executive agent, Yi Jibu The transmission number and content of the short message obtained in rapid 201, to determine whether to intercept short message.Wherein, user property may include using In the key message of characterization user's information of interest.Such as user property may include for describing the liking of user, occupation Etc. personal information keyword etc..And active user's attribute can be same user each user property in newest user belong to Property.That is, analyzed by transmission number to active user's attribute, short message and content, come determine the short message for Whether it is refuse messages for user indicated by active user's attribute.If it is determined that the short message is refuse messages, then can intercept The short message, to avoid short message application from receiving the short message.If it is determined that the short message is not refuse messages, then it is short can not to intercept this Breath, to make short message application normally receive the short message.Herein, refuse messages generally refer to send with intention user without user User be unwilling short message that the short message or user received cannot reject according to the wish of oneself.

Herein, executive agent can determine whether to intercept short message by a variety of methods.Some in the present embodiment can In selection of land realization method, first, executive agent can carry out the transmission number of short message in pre-set interception number library Matching.Wherein, the short message that number library can be the required interception of the user's mark indicated by active user's attribute is intercepted It sends number and generates.That is, it includes the transmission number that the user needs the short message intercepted to intercept number library.If The interception number existed in number library with the transmission numbers match (such as identical) of the short message is intercepted, then executive agent can determine Intercept the short message.If intercepted in number library, there is no the interception numbers with the transmission numbers match of the short message, hold later Row main body can determine whether the transmission number is cell-phone number.The correlation that specific determination process may refer in Fig. 3 embodiments is retouched It states, details are not described herein again.

Then, if it is determined that the transmission number is not cell-phone number, then the transmission number is probably network virtual number Code.Illustrate that the short message may be the advertisement SMS that other people (such as businessmans) is sent by internet.At this point, executive agent can be into Analyze to one step the short message content whether with active user's attributes match, come finally determine whether to intercept the short message.It is specific true Determine process and equally may refer to associated description in Fig. 3 embodiments, details are not described herein again.If it is determined that the two mismatches, then say The bright short message may be refuse messages for the user.So executive agent, which can determine, intercepts the short message.In this way, for Certain is received for the first time and sends the short message that number is sent, and can also realize effectively intercept process.

Optionally, in order to improve the accuracy of intercept process, executive agent can also be by the transmission number and content of short message In the current information analysis model including active user's attribute of input, to obtain the analysis result of short message.It in turn, can basis The analysis result of short message, to determine whether to intercept short message.Wherein, information analysis model can be used for analyzing short message, mould It may include user attribute data in type.Current information analysis model generally refers to the information comprising latest data point in model Analyse model, i.e., newest information analysis model.Herein, analysis result, which may include short message, is/is not normal short message or short message Content and user property match/mismatch.For example, if analysis result indicates that short message is not the interior of normal short message or short message Hold and mismatched with active user's attribute, it may be said that bright short message for the user may be the short breath of rubbish, then executive agent It can determine and intercept the short message.

It should be noted that normal short message generally refers to the short message sent between user in daily life, as red-letter day blessing is short Communication short message etc. between letter, commercial affairs contacts short message, kith and kin.And above- mentioned information analysis model can be obtained by a variety of training methods It arrives.Such as associated description in Fig. 3 embodiments is may refer to, details are not described herein again.In addition, being replaced using information analysis model The operating system of executive agent carrys out process part data, it is possible to reduce the live load of executive agent helps to improve operation effect Rate.

Herein, executive agent can determine that the user of user (user for using executive agent) belongs to by a variety of methods Property.The present embodiment some optionally in realization method, executive agent can obtain answering for the third-party application installed thereon Use information.And then the application message of acquisition can be analyzed, to determine the user property of user.Wherein, application message can For the function and usage of description application.Such as shopping class application is mounted on executive agent, the use of user can be determined at this time Family attribute is shopping intelligent.

Optionally, in order to keep determining user property more accurate, third party of the executive agent in addition to installation can be obtained Outside the application message of application, can also obtain user third-party application operation information.And then the application of acquisition can be believed Breath and operation information are for statistical analysis, to determine the user property of user.Here operation information can be that user is using Generated any information during third-party application, such as use duration, search content, click browsing content.Herein, It is not intended to limit in this application using the statistical of duration.Such as using duration can be time duration in certain period of time or Average duration.

As an example, being mounted with the application of shopping class on executive agent, reading class application and GT grand touring application.Wherein, it does shopping It is about 6 hours using duration that class, which is applied in nearly one month,；It is about 3 small using duration to read class and apply in nearly one month When；And it is about 0.5 hour using duration that GT grand touring, which is applied in nearly one month,.Since first two application is opposite using duration It is longer, and GT grand touring is applied almost without using, it is possible to determine that the user property of the user is shopping intelligent, love reading. Further, executive agent can also obtain the commodity that user browses or buys in shopping class application, such as glasses.At this time should The user property of user can also include glasses control.For another example method of weighting may be used in executive agent, to these applications into Row scoring.And then it can determine the user property of user according to higher application is scored.

It should be noted that executive agent can obtain above application information and operation information from local；It can also be from answering Background server (such as server 105 shown in FIG. 1) obtains these information.In addition, in order to make user property can be with User's relevant information of interest in the recent period is more accurately described, executive agent can periodically obtain above- mentioned information (application Information and operation information), to be continuously updated user property.Here acquisition cycle duration is not intended to limit in this application, such as Can be daily, weekly etc..

Further, executive agent can also be according to self-assessment input by user or description information, to analyze determining use The user property at family.Here input mode may include the input of (but not limited to) voice, keyboard input or be executed by selection The alternate item that main body provides inputs.

Step 203, short message is intercepted in response to determining, short message is executed and intercepts operation.

In the present embodiment, if executive agent determines in step 202 intercepts short message, short message can be executed and is blocked Cut operation.For example, executive agent can store short message to predeterminated position, and new information will not be sent to user and reminded.Its In, predeterminated position can be any position in addition to the storage location that short message is applied.For another example executive agent can also delete it is short Letter.

Method provided in this embodiment for intercept information, when user equipment end listens to and is currently received short message, The transmission number and content of short message can be obtained.It later, can according to the transmission number and content of short message and active user's attribute To determine whether to intercept the short message.I.e. for the user indicated by active user's attribute, if execute interception to the short message Operation.Wherein, user property may include the key message for characterizing user's information of interest.The short message is intercepted determining In the case of, short message can be executed and intercept operation.That is, the method in the present embodiment can be according to the current use of user Family attribute, to determine whether to intercept short message.I.e. for same short message, the processing method to vary with each individual may be used, it is real Existing different handling result.

With further reference to Fig. 3, it illustrates according to another embodiment of the method for intercept information of the application Flow 300.The method for being used for intercept information may comprise steps of：

Step 301, in response to being currently received short message, the transmission number and content of short message are obtained.

In the present embodiment, be used for intercept information method executive agent (such as terminal shown in FIG. 1 101,102, 103) in the case where being currently received short message, the transmission number and content of short message can be obtained.It is specific to may refer to Fig. 2 implementations Associated description in the step 201 of example, details are not described herein again.

Step 302, short message is sent into the information analysis mould for including active user's attribute of number and content input currently Type obtains the analysis result of short message.

In the present embodiment, the transmission number and content of short message can be inputted current information analysis model by executive agent In, to analyze short message, to obtain the analysis result of short message.Herein, current information analysis model includes using Active user's attribute at family.Wherein, analysis result may include short message be/be not the content of normal short message or short message with it is current User property match/mismatch.For details, reference can be made to the associated descriptions in the step 202 of Fig. 2 embodiments, and details are not described herein again.

The present embodiment some optionally in realization method, executive agent can be by model by the transmission number of short message And/or content is matched in the data interception library to prestore.Wherein, the data interception in data interception library may include intercepting Number and interception keyword.If including in interception keyword or the data interception library in data interception library in the content of short message In the presence of the interception number that the transmission number with short message matches, then executive agent, which can be analyzed, determines that the short message is not common short Letter.

It should be noted that above-mentioned data interception library can be the transmission number of the short message intercepted according to a large number of users And/or content and generate；It can also be the transmission number for the short message that the user indicated by active user's attribute is intercepted And/or content and generate.

Optionally, executive agent can determine whether the length of the transmission number of short message is preset length in a model.If Determine that the length of the transmission number is not preset length, then it is normal short message that can analyze determining short message not.

Herein, preset length is usually phone number length (i.e. 11).It determines and sends whether number is cell-phone number Code.In order to improve the accuracy of definitive result, executive agent can also determine send number preset length position whether include Preset characters.Wherein, preset length position generally refers to the front three of phone number.Preset characters generally refer to phone number Front three character, such as 188,159.In addition, preset length can also be the phone number length for including area code (such as+86 or 86) (i.e. 14 or 13).In this way, while determining the length for sending number, can also determine if to include area code.

It is understood that due to the fast development of Internet technology, most of businessmans are sent using network technology A large amount of advertising information.Therefore, if it is determined that the transmission number of short message is not phone number, then it is general that can determine the short message not Logical short message.

In order to improve the accuracy of definitive result, in the case where it is preset length to determine the length of the transmission number, also The content of short message can further be analyzed, you can to determine whether the content of short message meets preset condition.If met default Condition, it may be said that bright short message is not normal short message.

Here it is not normal short message that preset condition, which can be used for characterizing short message,.As an example, preset condition can be short It include predetermined keyword (such as special price, quick-fried money, panic buying) in the content of letter.It is pre- that preset condition can also be that the content of short message meets If format.Wherein, preset condition can be arranged according to actual conditions.Predetermined keyword (can be not limited to use to hold according to user The user of row main body) content of short message of required interception of label is arranged.Preset format can be by a large amount of non-general Logical short message (such as advertising information, financing category information, fraud information) is for statistical analysis to be arranged.

Further, before whether the length for the transmission number for determining short message is preset length, executive agent can be with In a model determine the transmission number whether service to the public number.Wherein, public service number generally refers to known to the public National number, such as operator's service calls, bank's service calls.In the case where not being public service number, Ke Yijin Determine its length to one step.It can cause to intercept to avoid to some notice category informations in this way, help to further improve determination As a result accuracy.

It is understood that in the case where it is public service number to determine the transmission number of short message, executive agent also may be used To continue to determine whether the content of short message meets preset condition.And then to usurp refuse messages transmitted by public service number or The partial information (such as bank financing short message) that public service number is sent effectively is intercepted, and intercept process effect is promoted.

In application scenes, executive agent can also by model by the transmission number and/or content of short message pre- It is matched in the non-data interception library deposited.Wherein, the non-data interception in non-data interception library may include non-interception number With non-interception keyword.If not including the non-interception keyword in non-data interception library in the content of short message, and non-data interception There is no the non-interception number that the transmission number with short message matches in library, then it is normal short message that can analyze determining short message not. It should be noted that non-data interception library here is typically not needing for the user's mark indicated by active user's attribute The transmission number and/or content of the short message of interception and generate.

It is understood that in order to improve the accuracy of definitive result, executive agent can also use above-mentioned in a model The mode that various methods are combined, to analyze whether determining short message is normal short message.

Step 303, according to the analysis result of short message, it is determined whether intercept short message.

In the present embodiment, executive agent can be according to the analysis result of the short message obtained in step 302, to determine whether Intercept the short message.If analysis result indicates that short message is normal short message, executive agent can execute step 304.If analysis result Indicate that short message is not normal short message, then executive agent can continue to execute step 305.

Step 304, if short message is normal short message, determination does not intercept the short message.

It in the present embodiment, can be with if executive agent determines that short message is normal short message by information analysis model analysis Determination does not intercept the short message.At this point, executive agent can store short message, store into the short message application installed thereon.

Optionally, executive agent can be according to the above-mentioned non-data interception library of transmission number and/or content update of short message.Example Such as using the transmission number of short message as the keyword in non-interception number, and/or extraction content as non-interception keyword, thus It stores into non-data interception library.In this way, when receiving the short message of transmission number transmission again, executive agent can not Intercept process is done, to avoid executing subsequent step, improves treatment effeciency.

Step 305, if short message is not normal short message, further analyze short message content whether with active user's attribute Match.

It in the present embodiment, can if it is normal short message that executive agent determines short message not by information analysis model analysis With further analyzed by model short message content whether with active user's attributes match.If it is determined that the content of short message is used with current Family attributes match, then executive agent can execute step 304.If it is determined that the content of short message is mismatched with active user's attribute, then Executive agent can continue to execute step 306.

The present embodiment some optionally in realization method, executive agent can analyze the content of short message by model Whether include same or similar keyword with active user's attribute.It for example analyzes again and whether there is subordinate relation between the two Or relevance.As an example, active user's attribute is shopping intelligent.And the teaser information that short message is certain electric business, at this time may be used To determine that the two matches.

Optionally, executive agent first can also be analyzed the content of short message by model, determine the content of short message Attribute and/or the key content information for extracting short message.Wherein, the contents attribute of short message can be used for characterizing the content class of short message Type, such as shopping class, GT grand touring, financing class.Key content information can be used for describing the main contents of short message, such as crucial Word, word or sentence etc..Later, the contents attribute of short message and/or of key content information and active user's attribute can be analyzed With degree.Then, the matching degree of the two and predetermined threshold value (such as 80%) can be compared.If the not up to default threshold of matching degree Value, it may be determined that the content of short message is mismatched with active user's attribute.If matching degree reaches predetermined threshold value, it may be determined that short message Content and active user's attributes match.

Step 306, short message is not normal short message, and the content of short message is mismatched with active user's attribute, determines that interception is short Letter.

In the present embodiment, if determining short message not by information analysis model and being normal short message, and the content of short message with Active user's attribute also mismatches, then can determine and intercept the short message.As an example, determining that short message is not normal short message in analysis In the case of, executive agent can also be generated by information analysis model and intercept instruction.In this way, intercepting short message or confirmation determining In the case of intercepting instruction, executive agent can execute short message and intercept operation.Specific the step of may refer to Fig. 2 embodiments Associated description in 203, details are not described herein again.

Optionally, in order to improve information processing efficiency and interception effect, executive agent can be according to the transmission number of short message The above-mentioned data interception library of content update and/or.Such as using the transmission number of short message as in interception number, and/or extraction content Keyword as intercept keyword, to store into data interception library.

In application scenes, in order to further promote intercept process effect, executive agent can periodically more User property in new above- mentioned information analysis model and related data (such as data interception library, public service number, non-data interception Library etc.), to make the intercept process result of short message change with the variation of user demand.

Specifically, it is possible, firstly, to which the historical operating data of the user to periodically acquiring is analyzed, fresh information analysis User property in model and related data.Wherein, historical operating data may include the application letter of the third-party application of installation Breath and user third-party application operation information.It later, can be using updated information analysis model as current letter Cease analysis model (i.e. newest information analysis model).Wherein, the user property in current information analysis model is as current User property.Here period can be fixed duration (as daily)；When can also be that predeterminable event occurs, will such as it receive short When letter (before input information analysis model)；When obtaining analysis result (the determining whether to intercept short message) of short message for another example.

It is understood that historical operating data can also include the short message operation behavior of user.Such as when the user clicks When access has intercepted short message, executive agent can update above-mentioned non-data interception library according to the transmission number of the short breath of the interception.This Sample one, when receiving the short message of transmission number transmission again, executive agent can not do intercept process to it.Again for example when User directly deletes and does not click on when not intercepting short message of access, and executive agent can not also intercept the transmission number of short message according to this Update above-mentioned data interception library.So, when receiving the short message of transmission number transmission again, executive agent can do it Intercept process.Feedback mechanism can be formed in this way, to promote intercept process effect.

That is, for same user, the method in the present embodiment can also be grasped according to the history of user's different times Make data, come data such as the user properties of current period that determines user, so that the intercept process result of short message meets use Demand of the family in current period.

Herein, above- mentioned information analysis model can be trained to obtain by following steps：

First, sample set is obtained.Wherein, the sample in sample set includes sample of users attribute, sample short message and sample Handling result of the user that user property is referred to sample short message.Handling result can be used for characterizing for sample of users attribute For the user for being referred to, if to be executed to sample short message and intercept operation.Such as the mark of sample short message can be set.Work as mark When knowledge is 0, expression does not intercept sample short message；When being identified as 1, indicate to intercept sample short message.

Then, using the sample of users attribute of sample in sample set and sample short message as the input of initial model, execute with Lower 1) -6) training step：

1) the transmission number and/or content of the sample short message of input are analyzed, determines whether the sample short message is general Logical short message.The associated description in step 302 is may refer to, details are not described herein again.

2) in response to determine the sample short message be not normal short message, further analyze the sample short message content whether with it is right The sample of users attributes match answered.The associated description in step 305 is may refer to, details are not described herein again.

If 3) content of the sample short message is mismatched with corresponding sample of users attribute, it is determined that intercept the sample short message.

4) definitive result of the sample short message of input is compared with corresponding handling result, determines that the sample of input is short Whether the definitive result of letter is identical as corresponding handling result.

5) according to comparison result, determine whether initial model trains completion.Herein, if inputting multiple samples, In the case where the definitive result of each sample is with corresponding handling result all same, executive agent can determine that initial model is instructed Practice and completes.Alternatively, executive agent can count the sample that definitive result sample identical with corresponding handling result accounts for input Ratio.And when the ratio reaches preset ratio (such as 95%), it may be determined that initial model training is completed.

Wherein, initial model can be the existing various neural network models created based on machine learning techniques.It should Neural network model can have existing various neural network structures (such as DenseBox, VGGNet, ResNet, SegNet Deng).

6) if it is determined that initial model training is completed, then the initial model completed training is as information analysis model.

Finally, however, it is determined that initial model not complete by training, adjusts the relevant parameter in initial model.It is passed for example, by using reversed Broadcast the weight in each convolutional layer in technology modification initial model.And can using the initial model after adjustment as initial model, with And continue to execute above-mentioned training step.It should be noted that the sample of input initial model does not also limit in this application.Such as In the case where sample is concentrated with great amount of samples, executive agent can therefrom choose the sample not being entered.

It should be noted that above-mentioned sample set can be executive agent by wired connectivity method or radio connection, It is obtained from the data that database server or cloud server are stored.At this point, for the information analysis for making training obtain Model is more in line with the demand of the user using executive agent, and executive agent is in first pass information analysis model to the short of reception It, can will be in active user's attribute input information analysis model of user before letter is analyzed.Further, it is also possible to according to the use Related data in the existing historical operating data in family more new model.Certainly, above-mentioned sample set can also be that executive agent passes through The historical data of itself is collected and is generated.The information analysis model that training obtains in this way can be more in line with user's Demands of individuals.

Method provided in this embodiment for intercept information replaces executive agent by using information analysis model Operating system can improve the accuracy of analysis result to analyze short message.So that the intercept process knot of short message Fruit is more in line with user demand.Meanwhile being also beneficial to reduce the live load at user equipment end, help to improve its operation effect Rate.

Fig. 4 is referred to, it illustrates the streams of one embodiment of the method according to the application for determining intercept information Journey 400.The method for being used to determine intercept information may comprise steps of：

Step 401, it is currently received short message in response to user equipment end, receives the transmission for the short message that user equipment end is sent Number and content.

In the present embodiment, the executive agent (such as server 105 shown in FIG. 1) of the method for determining intercept information Can by wired connection mode or radio connection, come receive user equipment end (such as terminal shown in FIG. 1 101,102, 103) the transmission number and content of the short message sent.Wherein, short message is the currently received short message in user equipment end.

It is understood that in order to realize that SMS interception, user equipment mentioned here terminate the short message received and be typically The short message received before the short message application installed on user equipment end receives short message.Specifically it may refer to figure Associated description in the step 201 of 2 embodiments, details are not described herein again.

Step 402, according to the transmission number and active user's attribute of content and target user of short message, it is determined whether block Truncate letter.

In the present embodiment, executive agent can be received according in the active user's attribute and step 401 of target user Short message transmission number and content, come determine whether intercept short message.Wherein, target user can be to use user equipment end User；User property may include the key message for characterizing user's information of interest.Specifically it may refer to Fig. 2 embodiments Step 202 in associated description, details are not described herein again.

The present embodiment some optionally in realization method, it includes target user's that executive agent, which can obtain current, The information analysis model of active user's attribute；The transmission number and content of short message are inputted into current information analysis model, obtained The analysis result of short message；And the analysis result according to institute's short message, it may be determined that whether intercept short message；Wherein, analysis result can To include content and active user's attributes match/mismatch that short message is/is not normal short message or short message.

Herein, executive agent can obtain the analysis result of short message using a variety of methods by information analysis model, It may refer to the associated description in the step 302 of Fig. 3 embodiments.For example, executive agent can by the transmission number of short message and/or Content is matched in the data interception library to prestore, wherein the data interception in data interception library may include intercepting number With interception keyword；If including to exist in interception keyword or the data interception library in data interception library in the content of short message The interception number to match with the transmission number of short message, then it is normal short message that can analyze determining short message not.

Optionally, executive agent can determine short message transmission number whether service to the public number；If it is determined that the transmission Number is not public service number, then may further determine that whether the length of the transmission number is preset length；If it is determined that should The length for sending number is not preset length, then it is normal short message that can analyze determining short message not；If it is determined that the transmission number Length is preset length, then may further determine that whether the content of short message meets preset condition；If it is determined that the content of short message is full Sufficient preset condition, then it is normal short message that can analyze determining short message not.

Further, executive agent can be chosen corresponding with target user non-in the non-data interception library group to prestore Data interception library, wherein the non-data interception in non-data interception library includes non-interception number and non-interception keyword；By short message Transmission number and/or content matched in the non-data interception library of selection；If not including selection in the content of short message Non- interception keyword in non-data interception library, and there is no the transmission number phases with short message in the non-data interception library chosen The non-interception number matched, then it is normal short message that can analyze determining short message not.

In some embodiments, when short message is not normal short message, executive agent can by information analysis model, into One step analyze short message content whether with active user's attributes match.The correlation that may refer in the step 305 of Fig. 3 embodiments is retouched It states.When short message is not normal short message, and the content of short message is mismatched with active user's attribute, it may be determined that intercept short message.

As an example, it is possible, firstly, to the content to short message is analyzed, to determine contents attribute and/or the extraction of short message The key content information of short message；Later, the contents attribute and/or key content information and active user's attribute of short message can be analyzed Matching degree；If matching degree is not up to predetermined threshold value, it may be determined that the content of short message is mismatched with active user's attribute.

In addition, in order to ensure that the accuracy of analysis result, executive agent can periodically obtain target user in user Historical operating data in equipment end.Wherein, historical operating data includes the third-party application being mounted on user equipment end The operation information of application message and target user in third-party application.Then, the historical operating data of acquisition can be carried out Analysis, to update the user property and related data in information analysis model corresponding with target user.And it can will be after update Information analysis model as current information analysis model.Wherein, the user property in current information analysis model is to work as Preceding user property.

Herein, information analysis model can be trained to obtain by following steps：Obtain sample set, wherein in sample set Sample include processing knot of sample of users attribute, sample short message and sample of users the attribute user that is referred to sample short message Fruit；Using the sample of users attribute of sample in sample set and sample short message as the input of initial model, following training step is executed： The transmission number and/or content of the sample short message of input are analyzed, determine whether the sample short message is normal short message；Response In determining that the sample short message is not normal short message, further analyze the sample short message content whether with corresponding sample of users category Property matching；If the content of the sample short message is mismatched with corresponding sample of users attribute, it is determined that intercept the sample short message；It will be defeated The definitive result of the sample short message entered is compared with corresponding handling result, determine input sample short message definitive result with Whether corresponding handling result is identical；According to comparison result, determine whether initial model trains completion；If it is determined that initial model is instructed Practice and complete, then the initial model completed training is as information analysis model；If it is determined that initial model not complete by training, adjustment is just Relevant parameter in beginning model using the initial model after adjustment as initial model, and continues to execute training step.

It should be noted that executive agent can utilize different target user sample set, come be respectively trained to obtain with respectively The corresponding information analysis model of target user.Certainly, executive agent can also utilize the sample set of a large number of users, to train to obtain One general information analysis model.Later, the related data of different target user can be inputted to the general information analysis In model, to obtain information analysis model corresponding with each target user.

Step 403, definitive result is sent to user equipment end.

In the present embodiment, the definitive result in step 402 can be sent to user equipment end by executive agent.In this way, When definitive result indicates to intercept short message, user equipment end can execute short message and intercept operation.It intercepts operation and may refer to Fig. 2 Associated description in the step 203 of embodiment, details are not described herein again.

It is an applied field according to the method for determining intercept information of Fig. 4 embodiments with further reference to Fig. 5, Fig. 5 The schematic diagram of scape.In the application scenarios of Fig. 5, user can install various applications in the terminal 101 that it is used, and and these Using interacting.Terminal 101 can periodically acquire historical operating data of the user in terminal 101, and can will adopt The data of collection are uploaded to Cloud Server 105.The data that Cloud Server 105 can be acquired according to terminal 101 are somebody's turn to do to determine to use Active user's attribute of the user of terminal 101.

In addition, in the case where terminal 101 listens to short message broadcast event, the transmission number of short message and interior can be obtained Hold, and these information of acquisition can be sent to Cloud Server 105.In this way, Cloud Server 105 can be according to the transmission of short message Active user's attribute of number and content and the user, to determine whether to intercept the short message.Meanwhile Cloud Server 105 can be with Definitive result is sent to terminal 101.

In this way, terminal 101 can analyze definitive result.And when definitive result indicates to intercept the short message, terminal 101 can execute the short message indicated by short message broadcast event interception operation, to realize SMS interception function.And it is tied when determining When fruit instruction does not intercept the short message, terminal 101 can not do intercept process to the short message indicated by short message broadcast event, thus will The short message is stored into short message application.It is reminded at this point, terminal 101 can send new information to user, it should to remind user to consult Short message.

The method for determining intercept information in the present embodiment, its current reception sent by receiving user equipment end Short message transmission number and content, according to these information for receiving and the target user at the user equipment end can be used Active user's attribute, come determine whether intercept short message.I.e. for target user, if executed to the short message and intercept behaviour Make.Wherein, user property may include the key message for characterizing user's information of interest.And it can be by definitive result It is sent to user equipment end.And then when definitive result indicates to intercept short message, user's equipment end can be made to execute interception to short message Operation.In this way can according to active user's attribute of different target user, to determine whether to carry out intercept process to short message, to Realize different handling results.

Referring to Fig. 6, it illustrates suitable for for realizing that the electronic equipment of the embodiment of the present application is (such as shown in FIG. 1 Terminal 101,102,103 or server 105) computer system 600 structural schematic diagram.Electronic equipment shown in Fig. 6 is only It is an example, any restrictions should not be brought to the function and use scope of the embodiment of the present application.

As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and Execute various actions appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data. CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always Line 604.

It is connected to I/O interfaces 605 with lower component：Include the importation of touch screen, keyboard, microphone, camera etc. 606；Output par, c 607 including cathode-ray tube (CRT) and/or liquid crystal display (LCD) etc. and loud speaker etc.；Packet Include the storage section 608 of hard disk etc.；And the communications portion of the network interface card including LAN card, modem etc. 609.Communications portion 609 executes communication process via the network of such as internet.Driver 610 is also according to needing to be connected to I/O Interface 605.Detachable media 611, such as disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on drive as needed On dynamic device 610, in order to be mounted into storage section 608 as needed from the computer program read thereon.

Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium On computer program, which includes the program code for method shown in execution flow chart.In such reality It applies in example, which can be downloaded and installed by communications portion 609 from network, and/or from detachable media 611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes Above-mentioned function.It should be noted that the computer-readable medium of the application can be computer-readable signal media or calculating Machine readable storage medium storing program for executing either the two arbitrarily combines.Computer readable storage medium for example can be --- but it is unlimited In --- electricity, system, device or the device of magnetic, optical, electromagnetic, infrared ray or semiconductor, or the arbitrary above combination.It calculates The more specific example of machine readable storage medium storing program for executing can include but is not limited to：Being electrically connected, be portable with one or more conducting wires Formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or The above-mentioned any appropriate combination of person.In this application, can be any include computer-readable medium or storage program has Shape medium, the program can be commanded the either device use or in connection of execution system, device.And in the application In, computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated, wherein Carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but not limited to electric Magnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable and deposit Any computer-readable medium other than storage media, the computer-readable medium can send, propagate or transmit for by referring to Enable execution system, device either device use or program in connection.The program for including on computer-readable medium Code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc. or above-mentioned times The suitable combination of meaning.

Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction Combination realize.

Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet Include acquiring unit, the first determination unit and interception unit.For another example can also be described as：A kind of processor include receiving unit, Second determination unit and transmission unit.Wherein, the title of these units is not constituted to the unit itself under certain conditions It limits, for example, acquiring unit is also described as " in response to being currently received short message, obtaining the transmission number of short message and interior The unit of appearance ".

As on the other hand, present invention also provides a kind of computer-readable medium, which can be Included in electronic equipment described in above-described embodiment；Can also be individualism, and without be incorporated the electronic equipment in. For example, above computer readable medium carries one or more program, when said one or multiple programs are by the electronics When equipment executes so that the electronic equipment：In response to being currently received short message, the transmission number and content of short message are obtained；According to The transmission number and content and the user property of prediction of short message, it is determined whether intercept short message, wherein user property is for characterizing The relevant information of user's concern；Short message is intercepted in response to determining, short message is executed and intercepts operation.

For another example when said one or multiple programs are executed by the electronic equipment, it is also possible that the electronic equipment： It is currently received short message in response to user equipment end, receives the transmission number and content of the short message that user equipment end is sent；According to The transmission number and active user's attribute of content and target user of short message, it is determined whether intercept short message, wherein target user Include the key message for characterizing user's information of interest to use the user at user equipment end, user property；It will determine As a result it is sent to user equipment end, so that user equipment end executes short message and intercept behaviour when definitive result indicates to intercept short message Make.

Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein Can technical characteristic replaced mutually and the technical solution that is formed.

Claims

1. a kind of method for intercept information, the method is used for user equipment end, including：

In response to being currently received short message, the transmission number and content of the short message are obtained；

According to the transmission number and content and active user's attribute of the short message, it is determined whether intercept the short message, wherein use Family attribute includes the key message for characterizing user's information of interest；

The short message is intercepted in response to determining, the short message is executed and intercepts operation.

2. according to the method described in claim 1, wherein, the transmission number and content according to the short message and current use Family attribute, it is determined whether the short message is intercepted, including：

The short message is sent into the information analysis model for including active user's attribute of number and content input currently, obtains institute State the analysis result of short message；And

According to the analysis result of the short message, it is determined whether intercept the short message；

Wherein, the analysis result include short message be/be not the content of normal short message or short message and active user's attributes match/ It mismatches.

3. described that the transmission number and content of the short message are inputted current packet according to the method described in claim 2, wherein The information analysis model for including active user's attribute obtains the analysis result of the short message, including：

The transmission number of the short message and/or content are matched in the data interception library to prestore, wherein the interception number Include intercepting number and interception keyword according to the data interception in library；

If including to be deposited in interception keyword or the data interception library in the data interception library in the content of the short message In the interception number that the transmission number with the short message matches, then analyzes and determine that the short message is not normal short message.

4. described that the transmission number and content of the short message are inputted current packet according to the method described in claim 2, wherein The information analysis model for including active user's attribute obtains the analysis result of the short message, including：

Determine the short message transmission number whether service to the public number；If it is determined that the transmission number is not public service number Code, then further determine that whether the length of the transmission number is preset length；

If it is determined that the length of the transmission number is not preset length, then analyzes and determine that the short message is not normal short message；If it is determined that The length of the transmission number is preset length, then further determines that whether the content of the short message meets preset condition；If it is determined that The content of the short message meets preset condition, then analyzes and determine that the short message is not normal short message.

5. described that the transmission number and content of the short message are inputted current packet according to the method described in claim 2, wherein The information analysis model for including active user's attribute, obtains the analysis result of the short message, further includes：

The transmission number of the short message and/or content are matched in the non-data interception library to prestore, wherein described non-to block The non-data interception cut in database includes non-interception number and non-interception keyword；

If not including the non-interception keyword in the non-data interception library in the content of the short message, and the non-data interception There is no the non-interception number that the transmission number with the short message matches in library, then analyzes and determine that the short message is not common short Letter.

6. according to the method described in claim 2, wherein, the analysis result according to the short message, it is determined whether intercept institute Short message is stated, including：

When the short message is not normal short message, further analyze the short message content whether with active user's attributes match；

When the short message is not normal short message, and the content of the short message is mismatched with active user's attribute, determines and intercept institute State short message.

7. it is described when the short message is not normal short message according to the method described in claim 6, wherein, further analyze institute State short message content whether with active user's attributes match, including：

The content of the short message is analyzed, the content of the contents attribute and/or the extraction short message that determine the short message is closed Key information；

Analyze the contents attribute of the short message and/or the matching degree of key content information and active user's attribute；

When matching degree is not up to predetermined threshold value, determine that the content of the short message is mismatched with active user's attribute.

8. according to the method described in one of claim 2-7, wherein the method further includes：

The historical operating data of user to periodically acquiring is analyzed, the user property in fresh information analysis model and phase Close data, wherein the historical operating data includes that the application message of the third-party application of installation and user answer in third party Operation information；

Using updated information analysis model as current information analysis model, wherein in current information analysis model User property is active user's attribute；

Wherein, information analysis model trains to obtain by following steps：

Obtain sample set, wherein the sample in the sample set includes sample of users attribute, sample short message and sample of users category Handling result of the user that property is referred to sample short message；

Using the sample of users attribute of sample in sample set and sample short message as the input of initial model, following training step is executed Suddenly：The transmission number and/or content of the sample short message of input are analyzed, determine whether the sample short message is normal short message； In response to determining that the sample short message is not normal short message, whether the content for further analyzing the sample short message is used with corresponding sample Family attributes match；If the content of the sample short message is mismatched with corresponding sample of users attribute, it is determined that intercept the sample short message；

The definitive result of the sample short message of input is compared with corresponding handling result, determines the sample short message of input really It is whether identical as corresponding handling result to determine result；According to comparison result, determine whether initial model trains completion；If it is determined that just Beginning model training is completed, then the initial model completed training is as information analysis model；

If it is determined that initial model training complete, adjust initial model in relevant parameter, using the initial model after adjustment as Initial model, and continue to execute the training step.

9. a kind of method for determining intercept information, the method is used for network equipment end, including：

It is currently received short message in response to user equipment end, receives the transmission number for the short message that the user equipment end is sent And content；

According to the transmission number and active user's attribute of content and target user of the short message, it is determined whether intercept described short Letter, wherein the target user is the user using the user equipment end, and user property includes of interest for characterizing user Information key message；

Definitive result is sent to the user equipment end, so that the user equipment end indicates to intercept institute in the definitive result When stating short message, the short message is executed and intercepts operation.

10. according to the method described in claim 9, wherein, the transmission number and content and target according to the short message Active user's attribute of user, it is determined whether the short message is intercepted, including：

Obtain the information analysis model of current active user's attribute including target user；

The transmission number and content of the short message are inputted into current information analysis model, obtain the analysis result of the short message； And

According to the analysis result of institute's short message, it is determined whether intercept the short message；

11. according to the method described in claim 10, wherein, it is described by the short message send number and content input is current Information analysis model obtains the analysis knot of the short message, including：

12. according to the method described in claim 10, wherein, it is described by the short message send number and content input is current Information analysis model obtains the analysis knot of the short message, including：

13. according to the method described in claim 10, wherein, it is described by the short message send number and content input is current Information analysis model obtains the analysis knot of the short message, further includes：

In the non-data interception library group to prestore, non-data interception library corresponding with target user is chosen, wherein the non-interception Non- data interception in database includes non-interception number and non-interception keyword；

The transmission number of the short message and/or content are matched in the non-data interception library of selection；

If the non-interception for not including the non-interception keyword in the non-data interception library chosen in the content of the short message, and choosing There is no the non-interception number that the transmission number with the short message matches in database, then analyzes and determine that the short message is not general Logical short message.

14. according to the method described in claim 10, wherein, the analysis result according to the short message, it is determined whether intercept The short message, including：

15. according to the method for claim 14, wherein it is described when the short message is not normal short message, further analyze The content of the short message whether with active user's attributes match, including：

16. according to the method described in one of claim 10-15, wherein the method further includes：

Periodically obtain historical operating data of the target user on the user equipment end, wherein the historical operation number According to the application message and target user for including the third-party application being mounted on the user equipment end in third-party application Operation information；

The historical operating data of acquisition is analyzed, the user property in information analysis model corresponding with target user is updated And related data；

Wherein, information analysis model trains to obtain by following steps：

17. a kind of electronic equipment, including：

One or more processors；

Storage device is stored thereon with one or more programs；

When one or more of programs are executed by one or more of processors so that one or more of processors are real The now method as described in any in claim 1-16.

18. a kind of computer-readable medium, is stored thereon with computer program, wherein the computer program is held by processor The method as described in any in claim 1-16 is realized when row.