CN108595448A - Information-pushing method and device - Google Patents
Information-pushing method and device Download PDFInfo
- Publication number
- CN108595448A CN108595448A CN201710159136.0A CN201710159136A CN108595448A CN 108595448 A CN108595448 A CN 108595448A CN 201710159136 A CN201710159136 A CN 201710159136A CN 108595448 A CN108595448 A CN 108595448A
- Authority
- CN
- China
- Prior art keywords
- property value
- current property
- abnormal
- value
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 230000002159 abnormal effect Effects 0.000 claims abstract description 83
- 230000004044 response Effects 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 24
- 238000003062 neural network model Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000012512 characterization method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 230000014759 maintenance of location Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 230000006854 communication Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000008676 import Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application discloses information-pushing methods and device.One specific implementation mode of this method includes:Obtain the current property value and related information of target item, wherein the related information includes at least one of following:The order of Item Information including the target item in historical status value, predetermined amount of time;Based on the current property value and the related information, determine whether the current property value is abnormal;In response to determining that the current property value is abnormal, the prompt message for prompting current property value exception is pushed.The embodiment realizes abundant in content information push.
Description
Technical field
This application involves field of computer technology, and in particular to Internet technical field more particularly to information-pushing method
And device.
Background technology
Information pushes, and is to pass through the information of push user's needs on the internet by certain technical standard or agreement
To reduce a technology of information overload.
However, the information category that existing information push mode is pushed is limited, the information that accordingly, there are push is not rich
Rich problem.
Invention content
The purpose of the application is to propose a kind of improved information-pushing method and device, to solve background above technology department
Divide the technical issues of mentioning.
In a first aspect, the embodiment of the present application provides a kind of information-pushing method, the above method includes:Obtain target item
Current property value and related information, wherein above-mentioned related information includes at least one of following:Historical status value, pre- timing
Between in section the Item Information including above-mentioned target item order;Based on above-mentioned current property value and above-mentioned related information, determine
Whether above-mentioned current property value is abnormal;It is abnormal in response to the above-mentioned current property value of determination, it pushes for prompting above-mentioned current attribute
It is worth abnormal prompt message.
In some embodiments, above-mentioned to be based on above-mentioned current property value and above-mentioned related information, determine above-mentioned current attribute
Whether value is abnormal, including:The object of above-mentioned target item in the quantity on order and/or acquired order of order acquired in determining
Product total quantity;According to the above order quantity and/or above-mentioned total number of items amount, determine whether above-mentioned current property value is abnormal.
In some embodiments, above-mentioned according to the above order quantity and/or above-mentioned total number of items amount, determine above-mentioned current category
Property value it is whether abnormal, further include:The contact information of consignee in the acquired order of extraction, and the connection for being extracted
It is each contact information in mode information, determines the account by the contact method registration indicated by the contact information
Number account quantity;According to identified account quantity, determine whether above-mentioned current property value is abnormal.
In some embodiments, account quantity determined by above-mentioned basis determines whether above-mentioned current property value is abnormal, packet
It includes:Using abnormal point method of determining and calculating, determination includes the property value set of acquired historical status value and above-mentioned current property value
In exceptional value;Include above-mentioned current property value in response to exceptional value determined by determination, determines that above-mentioned current property value is abnormal.
In some embodiments, above-mentioned to be based on above-mentioned current property value and above-mentioned related information, determine above-mentioned current attribute
Whether value is abnormal, including:Above-mentioned current property value and above-mentioned related information are imported into identification model trained in advance, are used for
Indicate the whether abnormal instruction information of above-mentioned current property value, wherein above-mentioned identification model is for characterization attributes value, related information
Correspondence between the two and instruction information.
In some embodiments, the above method further includes the steps that trained identification model, wherein above-mentioned trained identification model
The step of, including:Based on elite retention strategy, initial neural network model is adjusted using genetic algorithm;Determine training sample,
Wherein, above-mentioned training sample includes attribute value, related information and is used to indicate the whether abnormal instruction information of above-mentioned attribute value;
Using identified training sample, the adjusted initial neural network model of training obtains above-mentioned identification model.
In some embodiments, above-mentioned that above-mentioned current property value and above-mentioned related information are imported into identification mould trained in advance
Type:According to the historical status value of above-mentioned target item, knowledge corresponding with the attribute value section belonging to above-mentioned historical status value is searched
Other model;Above-mentioned current property value and above-mentioned related information are imported into the identification model found out.
Second aspect, the embodiment of the present application provide a kind of information push-delivery apparatus, and above-mentioned apparatus includes:Acquiring unit is used
In the current property value and related information that obtain target item, wherein above-mentioned related information includes at least one of following:History
The order of Item Information including above-mentioned target item in attribute value, predetermined amount of time;Determination unit, for based on above-mentioned current
Attribute value and above-mentioned related information determine whether above-mentioned current property value is abnormal;Push unit, for working as in response to determination is above-mentioned
Preceding attribute value is abnormal, pushes the prompt message for prompting above-mentioned current property value exception.
In some embodiments, above-mentioned determination unit, is additionally operable to:Determine quantity on order and/or the institute of acquired order
The total number of items amount of above-mentioned target item in the order of acquisition;According to the above order quantity and/or above-mentioned total number of items amount, determine
Whether above-mentioned current property value is abnormal.
In some embodiments, above-mentioned determination unit, is additionally operable to:The correspondent party of consignee in the acquired order of extraction
Formula information, and each contact information in the contact information for being extracted determine and pass through the contact information
The account quantity of the account of indicated contact method registration;According to identified account quantity, above-mentioned current property value is determined
It is whether abnormal.
In some embodiments, above-mentioned determination unit, is additionally operable to:Using abnormal point method of determining and calculating, determine to include acquired
Historical status value and above-mentioned current property value property value set in exceptional value;In response to exceptional value packet determined by determination
Above-mentioned current property value is included, determines that above-mentioned current property value is abnormal.
In some embodiments, above-mentioned determination unit, is additionally operable to:Above-mentioned current property value and above-mentioned related information are imported
Identification model trained in advance, obtain being used to indicate above-mentioned current property value whether abnormal instruction information, wherein above-mentioned identification
Model is for the correspondence between both characterization attributes value, related information and instruction information.
In some embodiments, above-mentioned determination unit, is additionally operable to:Based on elite retention strategy, adjusted using genetic algorithm
Initial neural network model;Determine training sample, wherein above-mentioned training sample includes attribute value, related information and is used for
Indicate the whether abnormal instruction information of above-mentioned attribute value;Utilize identified training sample, the adjusted initial nerve net of training
Network model obtains above-mentioned identification model.
In some embodiments, above-mentioned determination unit, is additionally operable to:According to the historical status value of above-mentioned target item, search
Identification model corresponding with the attribute value section belonging to above-mentioned historical status value;By above-mentioned current property value and above-mentioned related information
Import the identification model found out.
The third aspect, the embodiment of the present application provide server, and above-mentioned server includes:One or more processors;It deposits
Storage device, for storing one or more programs, when said one or multiple programs are executed by said one or multiple processors,
So that said one or multiple processors realize the method such as first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence realizes the method such as first aspect when the program is executed by processor.
Information-pushing method and device provided by the embodiments of the present application, by the current property value for obtaining target item first
And related information;Then, it is based on above-mentioned current property value and above-mentioned related information, determines whether above-mentioned current property value is different
Often;Finally, abnormal in response to the above-mentioned current property value of determination, it pushes for prompting the prompt of above-mentioned current property value exception to believe
Breath realizes abundant in content information push.
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 this application can be applied to exemplary system architecture figures therein;
Fig. 2 is the flow chart according to one embodiment of the information-pushing method of the application;
Fig. 3 is the schematic diagram according to an application scenarios of the information-pushing method of the application;
Fig. 4 is the flow chart according to another embodiment of the information-pushing method of the application;
Fig. 5 is the structural schematic diagram according to one embodiment of the information push-delivery apparatus of the application;
Fig. 6 is adapted for the structural schematic diagram of the computer system of the server 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 shows the exemplary system of the embodiment of the information-pushing method or information push-delivery apparatus that can apply the application
System framework 100.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 104 with server 105 with using terminal equipment 101,102,103, to receive or send out
Send message etc..Various telecommunication customer end applications, such as warehousing management class, purchase can be installed on terminal device 101,102,103
Species application, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture Experts
Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture
Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) it is player, on knee portable
Computer and desktop computer etc..
Server 105 can be to provide the server of various services, for example, various information are analyzed and obtain and wait for
The server of pushed information.Server can carry out the processing such as analyzing to the data such as the attribute value of article received, and
Handling result (such as prompt message) is fed back into terminal device.
It should be noted that the information-pushing method that the embodiment of the present application is provided generally is executed by server 105, accordingly
Ground, information push-delivery apparatus are generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the flows 200 according to one embodiment of the information-pushing method of the application.On
The information-pushing method stated, includes the following steps:
Step 201, the current property value and related information of target item are obtained.
In the present embodiment, the electronic equipment (such as server shown in FIG. 1) of information-pushing method operation thereon can
To obtain the current property value and related information of target item from local or from other electronic equipments.Herein, above-mentioned association
Information includes but not limited to:Historical status value, in the predetermined time including above-mentioned target item Item Information order.
In the present embodiment, above-mentioned target item can be the article for having physical entity, can also be virtual objects, example
Such as, the virtual objects of the instruction physical entity in electric business website or the virtual objects of instruction service.
In the present embodiment, above-mentioned attribute value can be indicated for the value of the attribute of article, and the attribute of article can wrap
The size, color, price etc. for including but being not limited to article, attribute value can include but is not limited to size value, price, be used to indicate object
The value etc. of product color.It should be noted that the type of the attribute of different articles is there may be difference, there may be the articles for article
Some specific attributes.As an example, if article is camera, the attribute value of camera may include price, maximum resolution
Rate, screen size, valid pixel number etc..
In the present embodiment, above-mentioned historical status value can be the target item of the historical juncture before current time
Attribute value.The above-mentioned historical juncture can be one or more.
In the present embodiment, the Item Information of above-mentioned target item can be the title of target item, can be for referring to
Show the article mark of above-mentioned target item.Herein, including the order of above-mentioned Item Information can have subscribed above-mentioned object
The order of product.
In some optional realization methods of the present embodiment, above-mentioned related information can also include being obtained based on the above order
The order relevant information arrived, order relevant information can include but is not limited to:It is the quantity on order of acquired order, acquired
The total number of items amount, account quantity of above-mentioned target item in order.Above-mentioned account quantity can be determining in the following manner:
The contact information of consignee in the acquired order of extraction, and it is each in the contact information for being extracted
It is mode information, determines the account quantity of the account by the contact method registration indicated by the contact information.Herein,
Contact information can include but is not limited to phone number, base number, Email Accounts etc..
Step 202, it is based on current property value and related information, determines whether current property value is abnormal.
In the present embodiment, above-mentioned electronic equipment can be based on current property value and related information, by various modes, really
Whether abnormal determine current property value.
In some optional realization methods of the present embodiment, step 202 can be accomplished by the following way:Determination is obtained
The quantity on order of the order taken;According to the above order quantity, determine whether above-mentioned current property value is abnormal.As an example, can be with
The above order quantity is determined whether in preset quantity on order numberical range, in response to determining the above order quantity not default
Numberical range in, determine that above-mentioned current property value is abnormal.As an example, the above order quantity can also be imported to training in advance
Identification model, obtain being used to indicate current characteristic value whether abnormal instruction information, wherein identification model is current for characterizing
The correspondence of both attribute value, quantity on order and instruction information.
In some optional realization methods of the present embodiment, step 202 can be accomplished by the following way:Determination is obtained
The total number of items amount of above-mentioned target item in the order taken;According to above-mentioned total number of items amount, whether above-mentioned current property value is determined
It is abnormal.As an example, above-mentioned total number of items amount can be determined whether within the scope of preset total number of items numerical quantity, in response to true
Fixed above-mentioned total number of items amount determines that above-mentioned current property value is abnormal not within the scope of preset total number of items numerical quantity.
In some optional realization methods of the present embodiment, step 202 can be accomplished by the following way:Extraction is obtained
The contact information of consignee in the order taken, and each contact method letter in the contact information for being extracted
Breath determines the account quantity of the account by the contact method registration indicated by the contact information;According to identified account
Number amount determines whether above-mentioned current property value is abnormal.As an example, it is preset to determine whether above-mentioned account quantity is more than
Account amount threshold is more than preset account amount threshold in response to the above-mentioned total number of items amount of determination, determines above-mentioned current attribute
Value is abnormal.
In some optional realization methods of the present embodiment, step 202 can be accomplished by the following way:Determination is obtained
The ratio of the historical status value and above-mentioned current property value that take;In response to the above-mentioned ratio of determination not in preset ratio numberical range
It is interior, determine that above-mentioned current property value is abnormal.
In some optional realization methods of the present embodiment, step 202 can be accomplished by the following way:Utilize exception
Point detection algorithm, determination include the exceptional value in the property value set of acquired historical status value and above-mentioned current property value;
Include above-mentioned current property value in response to exceptional value determined by determination, determines that above-mentioned current property value is abnormal.Herein, abnormal
Point detection algorithm itself is known in those skilled in the art, and details are not described herein.
In some optional realization methods of the present embodiment, step 202 can be accomplished by the following way:According to above-mentioned
Whether the above-mentioned current property value of one or more determinations in quantity on order, total number of items amount, account quantity, historical status value is different
Often.
In some optional realization methods of the present embodiment, can work as quantity on order, total number of items amount, account quantity,
When historical status value is satisfied by respective exception determining condition, determine that above-mentioned current property value is abnormal.Herein, current order
Abnormal determining condition can be quantity on order not in preset quantity on order numberical range.The determining item of exception of total number of items amount
Part can be total number of items amount within the scope of preset total number of items numerical quantity.The determining condition of exception of account quantity can be account
Number amount is more than preset account amount threshold.The determining condition of exception about historical status value can be acquired history category
Property value and above-mentioned current property value ratio not in preset ratio numberical range.The determining condition of exception about historical status value
It can also be that the current property value according to historical status value and the determination of abnormal point method of determining and calculating is exceptional value.
In some optional realization methods of the present embodiment, the exception about each related information can also be pre-set
Detection ordering is determined the whether abnormal flow of current property value.Determine that current property value is different using preceding related information
Chang Shi, it is determined that current property value is abnormal.When determining that current property value is normal using preceding related information, then utilize rear
Related information determine whether current property value abnormal.
As an example, quantity on order can be determined first whether in preset quantity on order numberical range, in response to true
Quantity on order is determined in preset quantity on order numberical range, determines that current property value is normal;Then, it is determined that total number of items amount is
It is no in preset total number of items numerical quantity range, in response to determining total number of items amount in preset total number of items numerical quantity range,
Determine that current property value is normal;After again, determine whether current property value is abnormal according to historical status value.It should be noted that different
Normal detection ordering can there are many, the sequence that should not be limited as in example.The related information utilized can be involved by the application
And whole related informations or partial association information, involved related information should not be limited as in this example.
In some optional realization methods of the present embodiment, according to the above order quantity, total number of items amount, account number
Whether the above-mentioned current property value of one or more determinations in amount, historical status value is abnormal, can be by above-mentioned current property value
And the knowledge that one or more importings in the above order quantity, total number of items amount, account quantity, historical status value are trained in advance
In other model, obtain being used to indicate current property value whether abnormal instruction information.Herein, identification model is used for characterization attributes
The correspondence of both value, related information and instruction information.
Step 203, it in response to determining that current property value is abnormal, pushes for prompting the prompt of current property value exception to believe
Breath.
In the present embodiment, above-mentioned electronic equipment can be in response to determining that current property value is abnormal, and push is worked as prompting
The prompt message of preceding attribute value exception.
As an example, being A type computer in target item, current property value is the feelings of the present price of this computer
Under condition, prompt message can be the information " A type computer-price-exception " for the present price exception for indicating this computer.
As an example, the prompt message can push at least one terminal device, the use of the terminal device pushed to
Family can be the user that the attribute value is uploaded to server, can also be the net that browsing includes the Item Information of the target item
The user of page.
It is a schematic diagram according to the application scenarios of the information-pushing method of the present embodiment with continued reference to Fig. 3, Fig. 3.
In the application scenarios of Fig. 3, first, server can obtain the current property value and related information of target item from the background, as
Example, target item can be A type computers, and 300 yuan of current property value price, related information can be historical price
3000 yuan and/or include the order of " A type computer " this Item Information;Then, above-mentioned server can be based on current belong to
Property value (300 yuan of price) and related information (3000 yuan of historical price and/or including " A type computer " this Item Information
Order), determine whether current property value (300 yuan of price) is abnormal;Finally, above-mentioned server can be in response to determining current attribute
It is worth (300 yuan of price) exception, prompt message (" -300 yuan of A type computer-is abnormal ") is pushed to user.
The method that above-described embodiment of the application provides, by the current property value and the association that obtain target item first
Information;Then, it is based on above-mentioned current property value and above-mentioned related information, determines whether above-mentioned current property value is abnormal;Finally, it rings
It should push the prompt message for prompting above-mentioned current property value exception in determining that above-mentioned current property value is abnormal, realize interior
Hold abundant information push.
With further reference to Fig. 4, it illustrates the flows 400 of another embodiment of information-pushing method.The information pushes
The flow 400 of method, includes the following steps:
Step 401, the current property value and related information of target item are obtained.
In the present embodiment, the electronic equipment (such as server shown in FIG. 1) of information-pushing method operation thereon can
To obtain the current property value and related information of target item.
In the present embodiment, above-mentioned related information can include but is not limited to:Include in historical status value, predetermined amount of time
The order of the Item Information of above-mentioned target item.
In some optional realization methods of the present embodiment, above-mentioned related information can also include being obtained based on the above order
The order relevant information arrived, the above order relevant information can include but is not limited to:The quantity on order of acquired order is obtained
The total number of items amount, account quantity of above-mentioned target item in the order taken, wherein above-mentioned account quantity can be by with lower section
What formula determined:The contact information of consignee in the acquired order of extraction, and the contact information for being extracted
In each contact information, determine the account number of the account by the contact method registration indicated by the contact information
Amount.
Step 402, current property value related information is imported to identification model trained in advance, obtains being used to indicate current category
Property the whether abnormal instruction information of value.
In the present embodiment, above-mentioned current property value and above-mentioned related information can be imported instruction in advance by above-mentioned electronic equipment
Experienced identification model, obtain being used to indicate above-mentioned current property value whether abnormal instruction information.Herein, instruction information can be with
It is indicated for the instruction information of current property value exception.Instruction information can also be that being used to indicate current property value normally refers to
Show information.
In some optional realization methods of the present embodiment, before step 402, method provided in this embodiment may be used also
To include the steps that trained identification model.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can also train identification model, can be with
Identification model is trained by executing following steps:Obtain initial neural network model;Determine training sample, wherein above-mentioned instruction
Practice sample to include attribute value, related information and be used to indicate the whether abnormal instruction information of above-mentioned attribute value;Using determining
Training sample, the initial neural network model of training obtains above-mentioned identification model.
It should be noted that how to obtain initial neural network model be it is known in those skilled in the art, herein
It repeats no more.Identified training sample can be enormous amount.Initial neural network model can be convolutional neural networks
Model, backpropagation (Back Propagation, BP) neural network model.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment is also based on elite retention strategy,
Initial neural network model is adjusted using genetic algorithm;Then, using identified training sample, training is adjusted initial
Neural network model obtains above-mentioned identification model.How to adjust initial neural network model using genetic algorithm is this field
Well known to technical staff, details are not described herein.However, it is desirable to which explanation, elite retention strategy is applied to determine article
The whether abnormal identification model of attribute value, can go out to be adapted to determine that with rapid Optimum article attribute value whether abnormal identification mould
Type.
In some optional realization methods of the present embodiment, step 402 can also be accomplished by the following way:According to upper
The historical status value of target item is stated, identification model corresponding with the attribute value section belonging to above-mentioned historical status value is searched, it will
Above-mentioned current property value and above-mentioned related information import the identification model found out.It should be noted that can be according to attribute value
Train multiple identification models in section.It, can be according to price range (such as 0-50,50- as an example, attribute value can be price
200,200-1000,1000-3000,3000 or more) the multiple identification models of training.
In some optional realization methods of the present embodiment, step 402 can also be accomplished by the following way:According to upper
State the above-mentioned goods categories of target item, search identification model corresponding with above-mentioned goods categories, by above-mentioned current property value with
Above-mentioned related information imports the identification model found out.It should be noted that multiple knowledges can be trained previously according to goods categories
Other model, such as electronic product identification model, individual wash shield class identification model etc..
Step 403, it in response to the instruction information for obtaining being used to indicate current property value exception, pushes for prompting currently to belong to
The prompt message of property value exception.
In the present embodiment, above-mentioned electronic equipment can be abnormal in response to the above-mentioned current property value of determination, pushes for carrying
Show the prompt message of above-mentioned current property value exception.
The realization details of the present embodiment step 401 and step 403 can refer to the explanation in step 201 and step 203,
This is repeated no more.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the flow of the information-pushing method in the present embodiment
400 highlight using the identification model that pre-establishes determine above-mentioned current property value whether abnormal step.The present embodiment as a result,
The scheme of description can be more convenient and whether extremely to accurately determine above-mentioned current property value, to realize more effective information
Push.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides a kind of push of information to fill
The one embodiment set, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, which specifically can be applied to respectively
In kind electronic equipment.
As shown in figure 5, information push-delivery apparatus 500 provided in this embodiment includes:Acquiring unit 501,502 and of determination unit
Push unit 503.Wherein, acquiring unit 501, current property value and related information for obtaining target item, wherein on
It includes at least one of following to state related information:Include the Item Information of above-mentioned target item in historical status value, predetermined amount of time
Order;Determination unit 502 determines that above-mentioned current property value is for being based on above-mentioned current property value and above-mentioned related information
No exception;Push unit 503, for abnormal in response to the above-mentioned current property value of determination, push is for prompting above-mentioned current attribute
It is worth abnormal prompt message.
In the present embodiment, the acquiring unit 501, determination unit 502 of device 500 and the specific processing of push unit 503
Can with step 201, step 202 and the step 203 in 2 corresponding embodiment of reference chart, this this repeat no more.
In some optional realization methods of the present embodiment, above-mentioned determination unit is additionally operable to:Determine acquired order
Quantity on order and/or acquired order in above-mentioned target item total number of items amount;According to the above order quantity and/or on
Total number of items amount is stated, determines whether above-mentioned current property value is abnormal.
In some optional realization methods of the present embodiment, above-mentioned determination unit is additionally operable to:The acquired order of extraction
In consignee contact information, and each contact information in the contact information for being extracted determines
Pass through the account quantity for the account that the contact method indicated by the contact information is registered;According to identified account quantity,
Determine whether above-mentioned current property value is abnormal.
In some optional realization methods of the present embodiment, above-mentioned determination unit is additionally operable to:Calculated using abnormal point
Method, determination include the exceptional value in the property value set of acquired historical status value and above-mentioned current property value;In response to true
Exceptional value includes above-mentioned current property value determined by fixed, determines that above-mentioned current property value is abnormal.
In some optional realization methods of the present embodiment, above-mentioned determination unit is additionally operable to:By above-mentioned current property value
Import identification model trained in advance with above-mentioned related information, obtain being used to indicate above-mentioned current property value whether abnormal instruction
Information, wherein above-mentioned identification model is for the correspondence between both characterization attributes value, related information and instruction information.
In some optional realization methods of the present embodiment, above-mentioned determination unit is additionally operable to:Retain plan based on elite
Slightly, initial neural network model is adjusted using genetic algorithm;Determine training sample, wherein above-mentioned training sample includes attribute
Value, related information and it is used to indicate the whether abnormal instruction information of above-mentioned attribute value;Utilize identified training sample, training
Adjusted initial neural network model, obtains above-mentioned identification model.
In some optional realization methods of the present embodiment, above-mentioned determination unit is additionally operable to:According to above-mentioned target item
Historical status value, search corresponding with the attribute value section belonging to above-mentioned historical status value identification model;By above-mentioned current category
Property value and above-mentioned related information import the identification model that finds out.
The realization details and technique effect of each unit of the provided device of the present embodiment can refer to the other of the application
Explanation in embodiment, details are not described herein.
Below with reference to Fig. 6, it illustrates the computer systems 600 suitable for the server for realizing the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not be to the function and use scope band of the embodiment of the present application
Carry out any restrictions.
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:Importation 606 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.;Storage section 608 including hard disk etc.;
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 610, as needed in order to be read from thereon
Computer program be mounted into storage section 608 as needed.
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 above-mentioned computer-readable medium of the application can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two arbitrarily combines.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or arbitrary above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to:Electrical connection with one or more conducting wires, just
It takes formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type and may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In this application, can be any include computer readable storage medium or storage journey
The tangible medium of sequence, the program can be commanded the either device use or in connection of execution system, device.And at this
In application, 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 unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to:Wirelessly, electric wire, optical cable, RF etc. or above-mentioned
Any appropriate combination.
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, determination unit and push unit.Wherein, the title of these units is not constituted under certain conditions to the unit
Itself restriction, for example, acquiring unit is also described as " obtaining the current property value and related information of target item
Unit ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment;Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device so that should
Device:Obtain the current property value and related information of target item, wherein above-mentioned related information includes at least one of following:
The order of Item Information including above-mentioned target item in historical status value, predetermined amount of time;Based on above-mentioned current property value and
Above-mentioned related information determines whether above-mentioned current property value is abnormal;Abnormal in response to the above-mentioned current property value of determination, push is used for
Prompt the prompt message of above-mentioned current property value exception.
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 (10)
1. a kind of information-pushing method, which is characterized in that the method includes:
Obtain the current property value and related information of target item, wherein the related information includes at least one of following:It goes through
The order of Item Information including the target item in history attribute value, predetermined amount of time;
Based on the current property value and the related information, determine whether the current property value is abnormal;
It is abnormal in response to the determination current property value, push the prompt message for prompting the current property value exception.
2. according to the method described in claim 1, it is characterized in that, described be associated with letter based on the current property value with described
Breath determines whether the current property value is abnormal, including:
The total number of items amount of target item described in the quantity on order and/or acquired order of order acquired in determining;
According to the quantity on order and/or the total number of items amount, determine whether the current property value is abnormal.
3. according to the method described in claim 2, it is characterized in that, described total according to the quantity on order and/or the article
Quantity determines whether the current property value is abnormal, further includes:
The contact information of consignee in the acquired order of extraction, and it is every in the contact information for being extracted
A contact information determines the account quantity of the account by the contact method registration indicated by the contact information;
According to identified account quantity, determine whether the current property value is abnormal.
4. according to the method described in claim 3, it is characterized in that, account quantity determined by the basis, determine described in work as
Whether preceding attribute value is abnormal, including:
Using abnormal point method of determining and calculating, determination includes the property value set of acquired historical status value and the current property value
In exceptional value;
Include the current property value in response to exceptional value determined by determination, determines that the current property value is abnormal.
5. according to the method described in claim 1, it is characterized in that, described be associated with letter based on the current property value with described
Breath determines whether the current property value is abnormal, including:
The current property value and the related information are imported into identification model trained in advance, obtain being used to indicate described current
The whether abnormal instruction information of attribute value, wherein the identification model is believed for both characterization attributes value, related information and instruction
Correspondence between breath.
6. according to the method described in claim 5, it is characterized in that, the method further includes the steps that trained identification model,
In, the step of the trained identification model, including:
Based on elite retention strategy, initial neural network model is adjusted using genetic algorithm;
Determine training sample, wherein the training sample includes attribute value, related information and is used to indicate the attribute value and is
No abnormal instruction information;
Using identified training sample, the adjusted initial neural network model of training obtains the identification model.
7. according to the method described in claim 6, it is characterized in that, described lead the current property value and the related information
Enter identification model trained in advance:
According to the historical status value of the target item, knowledge corresponding with the attribute value section belonging to the historical status value is searched
Other model;
The current property value and the related information are imported into the identification model found out.
8. a kind of information push-delivery apparatus, which is characterized in that described device includes:
Acquiring unit, current property value and related information for obtaining target item, wherein the related information include with
It is at least one of lower:The order of Item Information including the target item in historical status value, predetermined amount of time;
Determination unit determines whether the current property value is abnormal for being based on the current property value and the related information;
Push unit, for abnormal in response to the determination current property value, push is for prompting the current property value abnormal
Prompt message.
9. a kind of server, which is characterized in that the server includes:
One or more processors;
Storage device, for storing 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 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710159136.0A CN108595448B (en) | 2017-03-17 | 2017-03-17 | Information pushing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710159136.0A CN108595448B (en) | 2017-03-17 | 2017-03-17 | Information pushing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108595448A true CN108595448A (en) | 2018-09-28 |
CN108595448B CN108595448B (en) | 2022-03-04 |
Family
ID=63632927
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710159136.0A Active CN108595448B (en) | 2017-03-17 | 2017-03-17 | Information pushing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108595448B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109388548A (en) * | 2018-09-29 | 2019-02-26 | 北京京东金融科技控股有限公司 | Method and apparatus for generating information |
CN111144430A (en) * | 2018-11-05 | 2020-05-12 | 中国移动通信集团广东有限公司 | Genetic algorithm-based card number identification method and device |
CN111414566A (en) * | 2019-01-04 | 2020-07-14 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
CN112633960A (en) * | 2019-09-24 | 2021-04-09 | 北京京东尚科信息技术有限公司 | Recommendation information pushing method and device and computer readable storage medium |
CN113095756A (en) * | 2021-04-14 | 2021-07-09 | 北京京东振世信息技术有限公司 | Abnormal waybill feature determination method, device, equipment and computer readable medium |
CN113781091A (en) * | 2021-04-14 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Method and device for monitoring article attribute value |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030138378A1 (en) * | 2001-11-19 | 2003-07-24 | Dune Medical Devices Ltd. | Method and apparatus for examining tissue for predefined target cells, particularly cancerous cells, and a probe useful in such method and apparatus |
CN1853193A (en) * | 2003-06-24 | 2006-10-25 | 传送金融集团股份有限公司 | Confidential block trading system and method |
CN101408961A (en) * | 2007-10-12 | 2009-04-15 | 纬创资通股份有限公司 | Method for indicating right merchantable product sale price for helping shopping websites |
JP2009168201A (en) * | 2008-01-18 | 2009-07-30 | Jtekt Corp | Clutch release bearing |
US20150096692A1 (en) * | 2013-10-04 | 2015-04-09 | Hunter Engineering Company | Robotic Tire Changer User Interaction Procedures For Safety and Convenience |
CN104636933A (en) * | 2015-02-11 | 2015-05-20 | 广州唯品会信息科技有限公司 | Method and device for positioning oversell reasons of e-commerce website |
CN105160568A (en) * | 2015-08-28 | 2015-12-16 | 小米科技有限责任公司 | Reminding method and apparatus |
CN105354284A (en) * | 2015-10-30 | 2016-02-24 | 小米科技有限责任公司 | Template processing method and apparatus and short message identification method and apparatus |
CN105631638A (en) * | 2016-03-25 | 2016-06-01 | 北京京东尚科信息技术有限公司 | Order re-checking method, device and system |
US20160154690A1 (en) * | 2014-12-01 | 2016-06-02 | Uptake, LLC | Subsystem Health Score |
CN105808655A (en) * | 2016-02-26 | 2016-07-27 | 广州品唯软件有限公司 | Processing method, device and system for mass data anomaly checking |
CN106485558A (en) * | 2015-08-14 | 2017-03-08 | 阿里巴巴集团控股有限公司 | Merchandise items presell information processing method and device |
-
2017
- 2017-03-17 CN CN201710159136.0A patent/CN108595448B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030138378A1 (en) * | 2001-11-19 | 2003-07-24 | Dune Medical Devices Ltd. | Method and apparatus for examining tissue for predefined target cells, particularly cancerous cells, and a probe useful in such method and apparatus |
CN1853193A (en) * | 2003-06-24 | 2006-10-25 | 传送金融集团股份有限公司 | Confidential block trading system and method |
CN101408961A (en) * | 2007-10-12 | 2009-04-15 | 纬创资通股份有限公司 | Method for indicating right merchantable product sale price for helping shopping websites |
JP2009168201A (en) * | 2008-01-18 | 2009-07-30 | Jtekt Corp | Clutch release bearing |
US20150096692A1 (en) * | 2013-10-04 | 2015-04-09 | Hunter Engineering Company | Robotic Tire Changer User Interaction Procedures For Safety and Convenience |
US20160154690A1 (en) * | 2014-12-01 | 2016-06-02 | Uptake, LLC | Subsystem Health Score |
CN104636933A (en) * | 2015-02-11 | 2015-05-20 | 广州唯品会信息科技有限公司 | Method and device for positioning oversell reasons of e-commerce website |
CN106485558A (en) * | 2015-08-14 | 2017-03-08 | 阿里巴巴集团控股有限公司 | Merchandise items presell information processing method and device |
CN105160568A (en) * | 2015-08-28 | 2015-12-16 | 小米科技有限责任公司 | Reminding method and apparatus |
CN105354284A (en) * | 2015-10-30 | 2016-02-24 | 小米科技有限责任公司 | Template processing method and apparatus and short message identification method and apparatus |
CN105808655A (en) * | 2016-02-26 | 2016-07-27 | 广州品唯软件有限公司 | Processing method, device and system for mass data anomaly checking |
CN105631638A (en) * | 2016-03-25 | 2016-06-01 | 北京京东尚科信息技术有限公司 | Order re-checking method, device and system |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109388548A (en) * | 2018-09-29 | 2019-02-26 | 北京京东金融科技控股有限公司 | Method and apparatus for generating information |
CN109388548B (en) * | 2018-09-29 | 2020-12-22 | 京东数字科技控股有限公司 | Method and apparatus for generating information |
CN111144430A (en) * | 2018-11-05 | 2020-05-12 | 中国移动通信集团广东有限公司 | Genetic algorithm-based card number identification method and device |
CN111144430B (en) * | 2018-11-05 | 2023-08-01 | 中国移动通信集团广东有限公司 | Card-keeping number identification method and device based on genetic algorithm |
CN111414566A (en) * | 2019-01-04 | 2020-07-14 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
CN112633960A (en) * | 2019-09-24 | 2021-04-09 | 北京京东尚科信息技术有限公司 | Recommendation information pushing method and device and computer readable storage medium |
CN112633960B (en) * | 2019-09-24 | 2024-05-24 | 北京京东尚科信息技术有限公司 | Recommendation information pushing method and device and computer readable storage medium |
CN113095756A (en) * | 2021-04-14 | 2021-07-09 | 北京京东振世信息技术有限公司 | Abnormal waybill feature determination method, device, equipment and computer readable medium |
CN113781091A (en) * | 2021-04-14 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Method and device for monitoring article attribute value |
CN113095756B (en) * | 2021-04-14 | 2024-01-12 | 北京京东振世信息技术有限公司 | Abnormal waybill feature determination method, device, equipment and computer readable medium |
Also Published As
Publication number | Publication date |
---|---|
CN108595448B (en) | 2022-03-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108595448A (en) | Information-pushing method and device | |
CN108805594A (en) | Information-pushing method and device | |
CN108595628A (en) | Method and apparatus for pushed information | |
CN107908666A (en) | A kind of method and apparatus of identification equipment mark | |
CN108776692A (en) | Method and apparatus for handling information | |
CN107944481A (en) | Method and apparatus for generating information | |
CN107426328A (en) | Information-pushing method and device | |
CN110020162B (en) | User identification method and device | |
CN109255337A (en) | Face critical point detection method and apparatus | |
CN107911449A (en) | Method and apparatus for pushed information | |
CN109711508A (en) | Image processing method and device | |
CN109711917A (en) | Information-pushing method and device | |
CN108540508A (en) | Method, apparatus and equipment for pushed information | |
CN107517251A (en) | Information-pushing method and device | |
CN109214501A (en) | The method and apparatus of information for identification | |
CN107330091A (en) | Information processing method and device | |
CN109087139A (en) | Advertisement placement method and device for feed stream | |
CN108573054A (en) | Method and apparatus for pushed information | |
CN109492687A (en) | Method and apparatus for handling information | |
CN109885564A (en) | Method and apparatus for sending information | |
CN109446379A (en) | Method and apparatus for handling information | |
CN108921792A (en) | Method and apparatus for handling picture | |
CN109840724A (en) | Method and apparatus for output information | |
CN109255563A (en) | The determination method and apparatus in the storage space region of article | |
CN109614603A (en) | Method and apparatus for generating information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TG01 | Patent term adjustment |