CN107305677A - Product information method for pushing and device - Google Patents
Product information method for pushing and device Download PDFInfo
- Publication number
- CN107305677A CN107305677A CN201610262785.9A CN201610262785A CN107305677A CN 107305677 A CN107305677 A CN 107305677A CN 201610262785 A CN201610262785 A CN 201610262785A CN 107305677 A CN107305677 A CN 107305677A
- Authority
- CN
- China
- Prior art keywords
- product information
- user
- pushed
- attribute
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
This application discloses product information method for pushing and device.One embodiment of methods described includes：Obtain product information to be pushed and the product category belonging to the product information to be pushed；Obtain the attribute set of the product category；It is that the product information to be pushed generates primary vector of each property value using in the attribute set per attribute as component according to property value of the product information to be pushed in the attribute set under every attribute；To each user at least one candidate user, secondary vector of each property value using in the attribute set per attribute as component is generated；Calculate the primary vector and the cosine similarity of the secondary vector of each user and sequence at least one described candidate user；Predetermined number candidate user is chosen according to the descending order of cosine similarity be used as targeted customer from least one described candidate user；The product information to be pushed is pushed to the targeted customer.
Description
Technical field
The application is related to field of computer technology, and in particular to Internet technical field, especially relates to
And product information method for pushing and and device.
Background technology
It is that, by certain technical standard or agreement, pushing user to user needs that product information, which is pushed,
The product information wanted reduces a technology of information overload.Product information push technology passes through master
The dynamic product information that pushes is to user, it is possible to reduce the time spent in user searches for product information.
Existing product information is pushed generally realizes targetedly product letter by two ways
Breath is pushed：One is, from user perspective, identity identification is carried out to user, is pushed from candidate
User's product information interested is found in product information and is pushed to user；Another, be from
Product information angle is set out, and finds the product information targeted customer interested for treating push, will
Product information to be pushed is pushed to targeted customer.Pushed from the product information of user perspective
Method, exists and inaccurate defect is assert to user identity, be thus likely to result in user's body
Part assert mistake, and does not account for the product category and product attribute of product information to be pushed
Information, it is possible to pushed the uninterested product information of user to user；From product information angle
The product information method for pushing set out is spent, only from product information angle, use is not accounted for
The history at family accesses data, is thus likely to result in product information and has been pushed to the product information
Uninterested user, or treat to push product information user interested and do not receive and wait to push away
Send product information.Therefore, existing product information method for pushing has user's history and accesses number
According to, product information push shortage pin under-utilized with product category information and product attribute information
To property the problem of.
The content of the invention
The purpose of the application is to propose a kind of improved products information-pushing method and device, come
Solve the technical problem that background section above is mentioned.
In a first aspect, this application provides a kind of product information method for pushing, methods described includes：
Obtain product information to be pushed and the product category belonging to the product information to be pushed；Obtain institute
The attribute set of product category is stated, wherein, have at least one in the attribute set per attribute
Individual property value；According to the product information to be pushed in the attribute set per under attribute
Property value is the product information generation to be pushed with each per attribute in the attribute set
Individual property value is the primary vector of component；It is raw to each user at least one candidate user
Into each property value using in the attribute set per attribute as the secondary vector of component, wherein,
The value of the corresponding component of each property value in the attribute set per attribute is visited for the user
Ask that the number of times of the product page under the property value divided by the user access the product under the product category
The ratio of the number of times of the page；Calculate every in the primary vector and at least one described candidate user
The cosine similarity of the secondary vector of individual user and sequence；From at least one described candidate user
Predetermined number candidate user is chosen according to the descending order of cosine similarity to use as target
Family；The product information to be pushed is pushed to the targeted customer.
In certain embodiments, the value of each component of primary vector is：It is described to wait to push
The value of component corresponding to property value of the product information in the attribute set under every attribute
For the numerical value more than 0, the value of the component corresponding to remaining property value is 0.
In certain embodiments, at least one described candidate user is accessed institute in registered user
State the user of the product page under product category.
It is in certain embodiments, described to push the product information to be pushed to the targeted customer,
Including：The user profile of the targeted customer is obtained, wherein the user profile is included below extremely
One item missing：User's registration account, E-mail address and phone number；Used according to the target
The user profile at family, the product information to be pushed is pushed to the targeted customer.
In certain embodiments, methods described also includes：In the user's registration of the targeted customer
Account pushes the product information to be pushed in the form of web pages when logging in.
Second aspect, this application provides a kind of product information pusher, described device includes：
First acquisition unit, is configured to obtain product information to be pushed and the product information to be pushed
Affiliated product category；Second acquisition unit, is configured to obtain the attribute of the product category
Set, wherein, there is at least one property value in the attribute set per attribute；First to
Generation unit is measured, the product information to be pushed according to is configured to every in the attribute set
Property value under attribute is the product information generation to be pushed with every in the attribute set
Each property value of attribute is the primary vector of component；Secondary vector generation unit, configuration is used
Each user in at least one candidate user, generation is with every kind in the attribute set
Property each property value be component secondary vector, wherein, per attribute in the attribute set
The value of the corresponding component of each property value access the product page under the property value for the user
Number of times divided by the user access the ratio of the number of times of the product page under the product category；Calculate
Unit, is configured to calculate the primary vector with each being used at least one described candidate user
The cosine similarity of the secondary vector at family and sequence；Choose unit, be configured to from it is described at least
In one candidate user predetermined number candidate is chosen according to the descending order of cosine similarity
User is used as targeted customer；Push unit, be configured to the targeted customer push described in treat
Push product information.
In certain embodiments, the value of each component of primary vector is：It is described to wait to push
The value of component corresponding to property value of the product information in the attribute set under every attribute
For the numerical value more than 0, the value of the component corresponding to remaining property value is 0.
In certain embodiments, at least one described candidate user is accessed institute in registered user
State the user of the product page under product category.
In certain embodiments, the push unit includes：Acquisition module, is configured to obtain
The user profile of the targeted customer, wherein the user profile is including at least one of following：With
Family register account number, E-mail address and phone number；First pushing module, is configured to root
According to the user profile of the targeted customer, push the product to be pushed to the targeted customer and believe
Breath.
In certain embodiments, the push unit also includes：Second pushing module, configuration is used
Pushed in the form of web pages when user's registration account login in the targeted customer and described wait to push
Product information.
Product information method for pushing and device that the application is provided, by being believed according to product to be pushed
Cease in attribute set per the property value under attribute for product information to be pushed generate first to
Amount, and the history access information of each user at least one candidate user generates the use
The secondary vector at family, then calculate primary vector and each user's at least one candidate user
The cosine similarity of secondary vector and sequence, are then selected according to cosine similarity descending order
Predetermined number candidate user is taken as targeted customer, most backward targeted customer, which pushes, to be waited to push production
Product information, so as to effectively combine the history access information of user and the attribute letter of information to be pushed
Breath, realizes higher targetedly product information and pushes.
Brief description of the drawings
Retouched by reading with reference to the detailed of being made to non-limiting example of being made of the following drawings
State, other features, objects and advantages will become more apparent upon：
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart of one embodiment of the product information method for pushing according to the application；
Fig. 3 a-3d are showing for an application scenarios of the product information method for pushing according to the application
It is intended to；
Fig. 4 is the flow of another embodiment of the product information method for pushing according to the application
Figure；
Fig. 5 is the structural representation of one embodiment of the product information pusher according to the application
Figure；
Fig. 6 is adapted for the structure of the computer system of the server for realizing the embodiment of the present application
Schematic diagram.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is appreciated that
, specific embodiment described herein is used only for explaining related invention, rather than to the hair
Bright restriction.It also should be noted that, illustrate only for the ease of description, in accompanying drawing with
About the related part of invention.
It should be noted that in the case where not conflicting, embodiment and embodiment in the application
In feature can be mutually combined.Describe this in detail below with reference to the accompanying drawings and in conjunction with the embodiments
Application.
Fig. 1, which is shown, to be pushed using the product information method for pushing or product information of the application
The exemplary system architecture 100 of the embodiment of device.
As shown in figure 1, system architecture 100 can include terminal device 101,102,103,
Network 104 and server 105.Network 104 is used in the and of terminal device 101,102,103
The medium of communication link is provided between server 105.Network 104 can include various connection classes
Type, such as wired, wireless communication link or fiber optic cables etc..
User can pass through network 104 and server 105 with using terminal equipment 101,102,103
Interaction, to receive or send message etc..It can be provided with terminal device 101,102,103
Various client applications, such as web browser applications, the application of shopping class, mailbox client.
Terminal device 101,102,103 can be the various electronic equipments with display screen, bag
Include but be not limited to smart mobile phone, tablet personal computer, E-book reader, MP3 player (Moving
Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio layer
Face 3), (Moving Picture Experts Group Audio Layer IV, dynamic image is special by MP4
Family's compression standard audio aspect 4) player, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, for example to terminal device 101,
102nd, the shopping class application shown on 103 provides the background server that content is supported.Background service
Device can carry out the processing such as analyzing to data such as the shopping class requests that receives, and by result
(such as product page data) feeds back to terminal device.
It should be noted that the product information method for pushing that is provided of the embodiment of the present application it is general by
Server 105 is performed, correspondingly, and product information pusher is generally positioned at server 105
In.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only signal
Property.According to needs are realized, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates one of the product information method for pushing according to the application
The flow 200 of embodiment.Described product information method for pushing, comprises the following steps：
Step 201, product information to be pushed and the product class belonging to product information to be pushed are obtained
Not.
In the present embodiment, product information method for pushing operation electronic equipment thereon is (for example
Server shown in Fig. 1) on can prestore and need to be pushed product information, so above-mentioned electricity
Sub- equipment can locally obtain product information to be pushed；Product information to be pushed can also be stored in
On other electronic equipments being remotely connected with above-mentioned electronic equipment, so above-mentioned electronic equipment also may be used
Remotely to obtain the product information to be pushed positioned at other electronic equipments.
In the present embodiment, the corresponding product of product information to be pushed can be tangible product,
For example, mobile phone, computer, clothes, furniture, household electrical appliances, food etc.；Can also be invisible clothes
Business class product, such as paying on behalf telephone expenses, moving service, beauty services, household services on the net.
In the present embodiment, above-mentioned long-range connection can be wired connection mode or wireless connection
Mode.It is pointed out that above-mentioned radio connection can include but is not limited to 3G/4G companies
Connect, WiFi connections, bluetooth connection, WiMAX connections, Zigbee connections, UWB (ultra
Wideband) connection and other currently known or exploitation in the future radio connections.
In the present embodiment, above-mentioned electronic equipment can import above-mentioned product information to be pushed pre-
The product category model first trained is matched to obtain the product class belonging to product information to be pushed
Not.Here, it can utilize machine learning method to set up product category model, based on building in advance
Vertical product information set and product category set, training obtains product category model.For example,
After the newest listing of black mobile phone of so-and-so brand, corresponding product information is proposed, this waits to push
Product information can be classified into the product category of " mobile phone ".
Step 202, the attribute set of product category is obtained.
In the present embodiment, above-mentioned electronic equipment can be previously stored with the category of each product category
Property set, so, the product class that above-mentioned electronic equipment can be obtained locally in obtaining step 201
Other attribute set；Certainly, the attribute set of each product category can also be remotely stored in
On other electronic equipments being remotely connected with above-mentioned electronic equipment, so above-mentioned electronic equipment also may be used
Remotely to obtain the attribute set of each product category positioned at other electronic equipments, so as to obtain
Take the attribute set of the product category obtained in step 201.For example, for " mobile phone " product
The attribute set of classification can be included as properties：Brand, color, camera pixel, screen are big
It is small etc.；And the attribute set for being directed to " computer " product category can be included as properties：Brand,
Color, central processing unit dominant frequency, hard disk size, memory size, display sizes etc..
In the present embodiment, there is at least one property value in attribute set per attribute.For example,
It can include property value for " brand " attribute in the attribute set of " mobile phone " product category：
A brands, B brands, C brands；" color " attribute can include property value：Black, white,
It is golden；" camera pixel " attribute can include property value：5000000 pixels, 8,000,000 pixels,
13000000 pixels；" screen size " attribute can include property value：4 cun, 4.5 cun, 5 cun.
Step 203, for product information to be pushed generate with attribute set per attribute each
Property value is the primary vector of component.
In the present embodiment, above-mentioned electronic equipment can be according to product information to be pushed in above-mentioned category
Property set in per the property value under attribute, be that product information to be pushed is generated with attribute set
Per attribute each property value be component primary vector, wherein the value of each component according to
Following principle is determined：Product information to be pushed is in above-mentioned attribute set under every attribute
The value of component corresponding to property value is larger numerical value, the component corresponding to remaining property value
Value be less value.The principle of so value is in order to which subsequent step calculates cosine similarity
Prepare.
In some optional implementations of the present embodiment, product information to be pushed is in above-mentioned category
Property set in per the value of the component corresponding to the property value under attribute be the numerical value more than 0
(for example, it may be 1), the value of the component corresponding to remaining property value is 0.As an example,
For having " brand " and " color " two attributes, " brand " category under " mobile phone " product category
Property include property value：A brands, B brands, C brands；" color " attribute includes property value：
Black, white, gold；Include " mobile phone " of " A brands " and " gold " for one
The product information to be pushed of classification, can for the product information generation with " A brands, B brands,
C brands, black, white is golden " it is that the value of component is " 1,0,0,0,0,1 "
Primary vector.
In some optional implementations of the present embodiment, above-mentioned electronic equipment will can also be treated
Product information is pushed in above-mentioned attribute set per the component corresponding to the property value under attribute
Value set it is different be more than 0 numerical value, be that the value of component corresponding to remaining property value is set
It is set to 0.For example, to point corresponding to the property value under the important attribute in above-mentioned attribute set
The value of amount is set than larger value, and under the hardly important attribute in above-mentioned attribute set
The value of component corresponding to property value sets smaller value, and 0 is set to remaining property value.
For example, for having " brand ", " color " and " screen size " under " mobile phone " product category
Three attributes, " brand " attribute includes property value：A brands, B brands, C brands；" face
Color " attribute includes property value：Black, white, gold, " screen size " attribute include attribute
Value：4 cun, 4.5 cun, 5 cun." brand " attribute is most important, three of corresponding brand generic
Property value, if product information to be pushed belongs to wherein which property value, the property value is corresponding
The value of component could be arranged to 2, and " color " attribute is important, corresponding " color "
Three property values of attribute, if product information to be pushed belongs to wherein which property value, the category
The value of the property corresponding component of value could be arranged to 1, and " screen size " attribute is inessential,
Three property values of corresponding " screen size " attribute, if product information to be pushed belongs to it
In which property value, the value of the corresponding component of the property value could be arranged to 0.5, for remaining
The property value that is all not belonging to of product information to be pushed, the value of the corresponding component of the property value can
To be set to 0.For example, including the " hand of " A brands ", " gold " and " 4 cun " for one
The product information to be pushed of machine " classification can be product information generation with " A brands, B
Brand, C brands, black, white is golden, 4 cun, 4.5 cun, 5 cun " it is component value
For " 2,0,0,0,0,1,0.5,0,0 " primary vector.
Step 204, to each user at least one candidate user, generate with attribute set
In per attribute each property value be component secondary vector.
In the present embodiment, above-mentioned electronic equipment can by attribute set per attribute each
The value of the corresponding component of property value is set to time that the user accesses the product page under the property value
Number divided by the user access the ratio of the number of times of the product page under the said goods classification.Here,
The product page can be Webpage or picture, icon or text with web page interlinkage
Word etc..As an example, for having " brand " and " color " two under " mobile phone " product category
Individual attribute, " brand " attribute includes property value：A brands, B brands, C brands；" color "
Attribute includes property value：Black, white, gold；User A accessed all " mobile phones " production
The other product page of category 100 times, accessed " mobile phone " of A brands, B brands and C brands
The number of times of the category product page is 20 times, 30 times and 50 times respectively, accesses black, white
Number of times with the product page of golden " mobile phone " product category is 15,25 and 60 respectively,
The so corresponding attribute set " brand " and " face that " mobile phone " product category is directed to for user A
Each attribute value generation in color " with " A brands, B brands, C brands, black, white,
It is golden " it is that the value of component is " 0.2,0.3,0.5,0.15,0.25,0.6 " secondary vector.
In some optional implementations of the present embodiment, due to usual electronic commerce Net
The registered user stood is numerous, sometimes even up to hundreds of millions of, is calculated if each user
Secondary vector, meeting heavy system burden, therefore can select to access above-mentioned production in registered user
Category not under the user of the product page be used as at least one candidate user.Wait to push for example, working as
When product information is the information of " mobile phone " product category, once accessed in selection registered user
The user of the product information of " mobile phone " product category is used as at least one candidate user.
Step 205, the second of primary vector and each user at least one candidate user is calculated
The cosine similarity of vector and sequence.
In the present embodiment, above-mentioned electronic equipment can use equation below calculate primary vector with
The cosine similarity of the secondary vector of each user at least one candidate user：
Wherein, v1It is primary vector；v2It is secondary vector；N is positive integer, represents primary vector
Number of dimensions, be also the number of dimensions of secondary vector, while being also per kind in the said goods classification
The summation of each property value number of property；I is the positive integer from 1 to n；v1[i] is primary vector
The i-th component value；v2[i] is the value of the i-th component of secondary vector；Sim(v1,v2) it is to calculate
The primary vector of gained and the cosine similarity of secondary vector, Sim (v1,v2) the bigger expression first of value
Cosine similarity between vector sum secondary vector is higher.
In the present embodiment, above-mentioned electronic equipment can be by the result of calculation of above-mentioned cosine similarity
It is ranked up according to descending order.
Step 206, according to descending suitable of cosine similarity from least one candidate user
Sequence chooses predetermined number candidate user and is used as targeted customer.
In the present embodiment, above-mentioned electronic equipment can be based on the cosine phase obtained in step 205
Like the ranking results of degree, according to the order that similarity is descending from least one candidate user
Choose predetermined number candidate user and be used as targeted customer.Here, predetermined number can be acquiescence
Set, for example, 3,000,000；Predetermined number can also be according to product to be pushed by keeper
The content of information or the network load state of above-mentioned electronic equipment come customized, for example, working as
When the network load of above-mentioned electronic equipment is heavier, it is 2,000,000 to set predetermined number, when above-mentioned electricity
When the network load of sub- equipment is lighter, it is 4,000,000 to set predetermined number.
Step 207, product information to be pushed is pushed to targeted customer.
In the present embodiment, above-mentioned electronic equipment can be selected into step 206 in a variety of manners
Predetermined number targeted customer push above-mentioned product information to be pushed.
With continued reference to Fig. 3, Fig. 3 is the application of the product information method for pushing according to the present embodiment
One schematic diagram of scene.In Fig. 3 application scenarios, under " mobile phone " product category
Attribute set in have " brand " and " color " two attributes；" brand " attribute includes attribute
Value：A brands, B brands and C brands；" color " attribute includes property value：White, black
And gold；User include user 1, user 2 ... user 9 and user 10, altogether 10
User；Each property value using in attribute set per attribute of above-mentioned 10 users is component
Secondary vector is shown in fig. 3 a, for example, the secondary vector of user 1 is：
(0.4,0.2,0.4,0.2,0.6,0.2)；In addition, the computational methods of primary vector, take for waiting to push away
Corresponding point under the property value of " brand " and " color " two attributes of the product information sent
The value of amount is set to 1, and the value of the corresponding component of remaining property value is set to 0；Fig. 3 b show
The difference " brand " obtained according to the computational methods of above-mentioned primary vector and " color " category are gone out
The primary vector of the product information of " mobile phone " product category of property；Based on first shown in Fig. 3 a
Secondary vector shown in vector sum Fig. 3 b, according to the formula shown in step 205：The cosine similarity calculated is illustrated in Fig. 3 c
In；After the cosine similarity sequence in Fig. 3 c, 6 mesh are chosen from 10 candidate users
The part that the runic that mark user is illustrated in Fig. 3 d is represented.
The method that above-described embodiment of the application is provided is by calculating the first of product information to be pushed
Cosine similarity between vector and the secondary vector of each candidate user, according to cosine similarity from
Predetermined number targeted customer is chosen from candidate user carry out product information greatly to small order
Push, realize and be imbued with targetedly product information push.
With further reference to Fig. 4, it illustrates another embodiment of product information method for pushing
Flow 400.The flow 400 of the product information method for pushing, comprises the following steps：
Step 401, product information to be pushed and the product class belonging to product information to be pushed are obtained
Not.
In the present embodiment, product information method for pushing operation electronic equipment thereon is (for example
Server shown in Fig. 1) on can prestore and need to be pushed product information, so above-mentioned electricity
Sub- equipment can locally obtain product information to be pushed；Product information to be pushed can also be stored in
On other electronic equipments being remotely connected with above-mentioned electronic equipment, so above-mentioned electronic equipment also may be used
Remotely to obtain the product information to be pushed positioned at other electronic equipments.
Step 402, the attribute set of product category is obtained.
In the present embodiment, above-mentioned electronic equipment can be previously stored with the category of each product category
Property set, so, the product class that above-mentioned electronic equipment can be obtained locally in obtaining step 401
Other attribute set；Certainly, the attribute set of each product category can also be remotely stored in
On other electronic equipments being remotely connected with above-mentioned electronic equipment, so above-mentioned electronic equipment also may be used
Remotely to obtain the attribute set of each product category positioned at other electronic equipments, so as to obtain
Take the attribute set of the product category obtained in step 401.
In the present embodiment, there is at least one property value in attribute set per attribute.
Step 403, for product information to be pushed generate with attribute set per attribute each
Property value is the primary vector of component.
In the present embodiment, above-mentioned electronic equipment can be according to product information to be pushed in above-mentioned category
Property set in per the property value under attribute, be that product information to be pushed is generated with attribute set
Per attribute each property value be component primary vector, wherein the value of each component according to
Following principle is determined：Product information to be pushed is in above-mentioned attribute set under every attribute
The value of component corresponding to property value is larger numerical value, the component corresponding to remaining property value
Value be less value.The principle of so value is in order to which subsequent step calculates cosine similarity
Prepare.
Step 404, to each user at least one candidate user, generate with attribute set
In per attribute each property value be component secondary vector.
In the present embodiment, above-mentioned electronic equipment can by attribute set per attribute each
The value of the corresponding component of property value is set to time that the user accesses the product page under the property value
Number divided by the user access the ratio of the number of times of the product page under the said goods classification.Here,
The product page can be Webpage or picture, icon or text with web page interlinkage
Word etc..
Step 405, the second of primary vector and each user at least one candidate user is calculated
The cosine similarity of vector and sequence.
In the present embodiment, above-mentioned electronic equipment can use equation below calculate primary vector with
The cosine similarity of the secondary vector of each user at least one candidate user：
Wherein, v1It is primary vector；v2It is secondary vector；N is positive integer, represents primary vector
Number of dimensions, be also the number of dimensions of secondary vector, while being also per kind in the said goods classification
The summation of each property value number of property；I is the positive integer from 1 to n；v1[i] is primary vector
The i-th component value；v2[i] is the value of the i-th component of secondary vector；Sim(v1,v2) it is to calculate
The primary vector of gained and the cosine similarity of secondary vector, Sim (v1,v2) the bigger expression first of value
Cosine similarity between vector sum secondary vector is higher.
In the present embodiment, above-mentioned electronic equipment can be by the result of calculation of above-mentioned cosine similarity
It is ranked up according to descending order.
Step 406, according to descending suitable of cosine similarity from least one candidate user
Sequence chooses predetermined number candidate user and is used as targeted customer.
In the present embodiment, above-mentioned electronic equipment can be based on the cosine phase obtained in step 205
Like the ranking results of degree, according to the order that similarity is descending from least one candidate user
Choose predetermined number candidate user and be used as targeted customer.
Step 407, the user profile of targeted customer is obtained.
In the present embodiment, above-mentioned electronic equipment can locally obtain the user profile of targeted customer；
Certainly, above-mentioned electronic equipment can also remotely from the user profile of the targeted customer that is stored with its
His electronic equipment obtains the user profile of targeted customer.Here, user profile include it is following at least
One：User's registration account, E-mail address and phone number.
Step 408, according to the user profile of targeted customer, pushed to targeted customer and wait to push production
Product information.
In the present embodiment, above-mentioned electronic equipment can be pushed to targeted customer in a variety of manners
State product information to be pushed.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be to above-mentioned
Sending short message by mobile phone specified by the phone number of targeted customer is believed to push above-mentioned product to be pushed
Breath.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can also be upward
The E-mail address for stating targeted customer sends Email to push above-mentioned product letter to be pushed
Breath.
Step 409, push and treat in the form of web pages when the user's registration account of targeted customer is logged in
Push product information.
In the present embodiment, above-mentioned electronic equipment can be stepped in the user's registration account of targeted customer
Product information to be pushed is pushed during record in the form of web pages.Form web page can with intuitive and convenient to
Content in the more product informations to be pushed of family displaying.For shopping class application, compare
Short message and the product information of mail push mode, and Web page push form can facilitate user directly to exist
See quick place an order purchase, especially the user's registration account in user during product information interested
Product information just is pushed to user during login, the time that user searches for other like products is reduced,
Improve the efficiency of user.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the production in the present embodiment
The step of flow 400 of product information-pushing method has had more the user profile for obtaining targeted customer
407 and targeted customer user's registration account log in when push product to be pushed in the form of web pages
The step 409 of information, and step 408 highlight the user profile according to targeted customer, to
Targeted customer pushes product information to be pushed.Thus, the scheme of the present embodiment description can be introduced
It is more that the mode of product information is pushed to targeted customer, so as to realize push mode more comprehensively and more
Effective product information is pushed.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, the application is provided
A kind of one embodiment of product information pusher, the device embodiment with shown in Fig. 2
Embodiment of the method is corresponding, and the device specifically can apply in various electronic equipments.
As shown in figure 5, the product information pusher 500 described in the present embodiment includes：First
Acquiring unit 501, second acquisition unit 502, primary vector generation unit 503, secondary vector
Generation unit 504, computing unit 505, selection unit 506 and push unit 507.Wherein,
First acquisition unit 501, is configured to obtain product information to be pushed and the product to be pushed
Product category belonging to information；Second acquisition unit 502, is configured to obtain the product class
Other attribute set, wherein, there is at least one property value in the attribute set per attribute；
Primary vector generation unit 503, is configured to according to the product information to be pushed in the category
Property set in per the property value under attribute, be that the product information to be pushed is generated with the category
Property set in per attribute each property value be component primary vector；Secondary vector generation is single
Member 504, is configured to, to each user at least one candidate user, generate with the category
Property set in per attribute each property value be component secondary vector, wherein, the attribute
The value of the corresponding component of each property value in set per attribute accesses the attribute for the user
The number of times of the lower product page of value divided by the user access time of the product page under the product category
Several ratio；Computing unit 505, is configured to calculate the primary vector and described at least one
The cosine similarity of the secondary vector of each user and sequence in individual candidate user；Choose unit
506, it is configured to descending according to cosine similarity from least one described candidate user
Order chooses predetermined number candidate user and is used as targeted customer；Push unit 506, configuration is used
In pushing the product information to be pushed to the targeted customer.In the present embodiment, product is believed
Cease first acquisition unit 501 in pusher 500, second acquisition unit 502, primary vector life
Into unit 503, secondary vector generation unit 504, computing unit 505, selection unit 506 and
The specific processing of push unit 507 and its beneficial effect brought can be implemented referring to Fig. 2 correspondences
Step 201, step 202, step 203, step 204, step 205, step 206 in example
With the associated description of the implementation of step 207, it will not be repeated here.
In some optional implementations of the present embodiment, above-mentioned each component of primary vector
Value is：Property value of the above-mentioned product information to be pushed in above-mentioned attribute set under every attribute
The value of corresponding component is numerical value more than 0, and component corresponding to remaining property value takes
It is worth for 0.The specific beneficial effect for handling and its being brought can be referring to step in Fig. 2 correspondence embodiments
The associated description of rapid 203 implementation, will not be repeated here.
In some optional implementations of the present embodiment, at least one above-mentioned candidate user is
The user of the product page under the said goods classification was accessed in registered user.Specific processing and its
The beneficial effect brought can correspond to the phase of the implementation of step 204 in embodiment referring to Fig. 2
Description is closed, be will not be repeated here.
In some optional implementations of the present embodiment, in product information pusher 500
Push unit 507 can include：Acquisition module (not shown), is configured to obtain above-mentioned
The user profile of targeted customer, wherein above-mentioned user profile is including at least one of following：User notes
Volume account, E-mail address and phone number；First pushing module (not shown), matches somebody with somebody
Put for the user profile according to above-mentioned targeted customer, wait to push away to above-mentioned targeted customer push is above-mentioned
Send product information.The specific processing of acquisition module and the first pushing module and its brought it is beneficial
Effect can be related to the implementation of step 408 referring to step 407 in Fig. 4 correspondence embodiments
Description, will not be repeated here.
In some optional implementations of the present embodiment, in product information pusher 500
Push unit 507 can also include：Second pushing module (not shown), is configured to
The user's registration account of above-mentioned targeted customer pushes above-mentioned product to be pushed in the form of web pages when logging in
Information.The specific processing of second pushing module and its beneficial effect brought can be referring to Fig. 4 pairs
The associated description of the implementation of step 409 in embodiment is answered, be will not be repeated here.
Below with reference to Fig. 6, it illustrates suitable for for realizing the server of the embodiment of the present application
The structural representation of computer system 600.
As shown in figure 5, computer system 600 includes CPU (CPU) 601, its
Can according to the program being stored in read-only storage (ROM) 602 or from storage part 606
The program that is loaded into random access storage device (RAM) 603 and perform various appropriate actions
And processing.In RAM 603, the system that is also stored with 600 operates required various program sums
According to.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 bus 604.
I/O interfaces 605 are connected to lower component：Storage part 606 including hard disk etc.；And
The communications portion 607 of NIC including LAN card, modem etc..Communication
Part 607 performs communication process via the network of such as internet.Driver 608 is also according to need
It is connected to I/O interfaces 605.Detachable media 609, such as disk, CD, magneto-optic disk,
Semiconductor memory etc., is arranged on driver 608, in order to read from it as needed
The computer program gone out is mounted into storage part 606 as needed.
Especially, in accordance with an embodiment of the present disclosure, the process described above with reference to flow chart can be with
It is implemented as computer software programs.For example, embodiment of the disclosure includes a kind of computer journey
Sequence product, it includes being tangibly embodied in the computer program on machine readable media, the meter
Calculation machine program bag, which contains, is used for the program code of the method shown in execution flow chart.Implement such
In example, the computer program can be downloaded and installed by communications portion 607 from network,
And/or be mounted from detachable media 609.In the computer program by CPU
(CPU) during 601 execution, the above-mentioned functions limited in the present processes are performed.In accompanying drawing
Flow chart and block diagram, it is illustrated that according to the system, method and calculating of the various embodiments of the application
Architectural framework in the cards, function and the operation of machine program product.At this point, flow chart
Or each square frame in block diagram can represent a part for a module, program segment or code,
A part for the module, program segment or code is comprising one or more defined for realizing
The executable instruction of logic function.It should also be noted that in some realizations as replacement, side
The function of being marked in frame can also be with different from the order marked in accompanying drawing generation.For example,
Two square frames succeedingly represented can essentially be performed substantially in parallel, and they sometimes can also
Perform in the opposite order, this is depending on involved function.It is also noted that block diagram and/
Or the combination of each square frame in flow chart and the square frame in block diagram and/or flow chart, can be with
Realized with the special hardware based system of function or operation as defined in performing, or can be with
Realized with the combination of specialized hardware and computer instruction.
Being described in unit involved in the embodiment of the present application can be real by way of software
It is existing, it can also be realized by way of hardware.Described unit can also be arranged on processing
In device, for example, can be described as：A kind of processor includes first acquisition unit, the second acquisition
Unit, primary vector generation unit, secondary vector generation unit, computing unit, selection unit
And push unit.Wherein, the title of these units is not constituted to the unit under certain conditions
The restriction of itself, for example, first acquisition unit is also described as " obtaining product to be pushed
The unit of product category belonging to information and the product information to be pushed ".
As on the other hand, present invention also provides a kind of nonvolatile computer storage media,
The nonvolatile computer storage media can be described in above-described embodiment included in device
Nonvolatile computer storage media；Can also be individualism, without non-in supplying terminal
Volatile computer storage medium.Above-mentioned nonvolatile computer storage media be stored with one or
The multiple programs of person, when one or more of programs are performed by an equipment so that described
Equipment：Obtain product information to be pushed and the product category belonging to above-mentioned product information to be pushed；
The attribute set of the said goods classification is obtained, wherein, have in above-mentioned attribute set per attribute
At least one property value；According to above-mentioned product information to be pushed in above-mentioned attribute set per kind
Property under property value, be above-mentioned product information to be pushed generation with above-mentioned attribute set per kind
Property each property value be component primary vector；To each use at least one candidate user
Family, generates secondary vector of each property value using in above-mentioned attribute set per attribute as component,
Wherein, the value of the corresponding component of each property value in above-mentioned attribute set per attribute is to be somebody's turn to do
User accesses the number of times of the product page divided by the user under the property value and accessed under the said goods classification
The product page number of times ratio；Above-mentioned primary vector is calculated to use with least one above-mentioned candidate
The cosine similarity of the secondary vector of each user and sequence in family；From at least one above-mentioned candidate
In user predetermined number candidate user conduct is chosen according to the descending order of cosine similarity
Targeted customer；Above-mentioned product information to be pushed is pushed to above-mentioned targeted customer.
Above description is only the preferred embodiment of the application and saying to institute's application technology principle
It is bright.It will be appreciated by those skilled in the art that invention scope involved in the application, is not limited
In the technical scheme of the particular combination of above-mentioned technical characteristic, do not departed from while should cover yet
In the case of the inventive concept, it is combined by above-mentioned technical characteristic or its equivalent feature
Formed by other technical schemes.Such as features described above and (but not limited to) disclosed herein
Technical characteristic with similar functions carries out technical scheme formed by replacement mutually.
Claims (10)
1. a kind of product information method for pushing, it is characterised in that methods described includes：
Obtain product information to be pushed and the product category belonging to the product information to be pushed；
The attribute set of the product category is obtained, wherein, per attribute in the attribute set
With at least one property value；
According to attribute of the product information to be pushed in the attribute set under every attribute
Value is the product information generation to be pushed with each category in the attribute set per attribute
Property value be component primary vector；
To each user at least one candidate user, generate with every kind of in the attribute set
Each property value of attribute is the secondary vector of component, wherein, per kind in the attribute set
Property the value of the corresponding component of each property value access the product page under the property value for the user
Number of times divided by the user access the product page under the product category number of times ratio；
Calculate second of each user in the primary vector and at least one described candidate user to
The cosine similarity of amount and sequence；
Chosen from least one described candidate user according to the descending order of cosine similarity
Predetermined number candidate user is used as targeted customer；
The product information to be pushed is pushed to the targeted customer.
2. product information method for pushing according to claim 1, it is characterised in that described
The value of each component of primary vector is：The product information to be pushed is in the attribute set
The value of the component corresponding to property value under per attribute is the numerical value more than 0, remaining attribute
The value of the corresponding component of value is 0.
3. product information method for pushing according to claim 1, it is characterised in that described
At least one candidate user is to access the product page under the product category in registered user
User.
4. product information method for pushing according to claim 1, it is characterised in that described
The product information to be pushed is pushed to the targeted customer, including：
Obtain the user profile of the targeted customer, wherein the user profile include it is following at least
One：User's registration account, E-mail address and phone number；
According to the user profile of the targeted customer, to the targeted customer push described in wait to push
Product information.
5. product information method for pushing according to claim 4, it is characterised in that described
Method also includes：
Wait to push away described in pushing in the form of web pages when the user's registration account of the targeted customer is logged in
Send product information.
6. a kind of product information pusher, it is characterised in that described device includes：
First acquisition unit, is configured to obtain product information to be pushed and the product to be pushed
Product category belonging to information；
Second acquisition unit, is configured to obtain the attribute set of the product category, wherein,
There is at least one property value in the attribute set per attribute；
Primary vector generation unit, is configured to according to the product information to be pushed in the category
Property set in per the property value under attribute, be that the product information to be pushed is generated with the category
Property set in per attribute each property value be component primary vector；
Secondary vector generation unit, is configured to each user at least one candidate user,
Secondary vector of each property value using in the attribute set per attribute as component is generated, its
In, the value of the corresponding component of each property value in the attribute set per attribute is the use
Family accesses the number of times of the product page divided by the user under the property value and accessed under the product category
The ratio of the number of times of the product page；
Computing unit, is configured to calculate the primary vector and at least one described candidate user
In each user secondary vector cosine similarity and sequence；
Unit is chosen, is configured to from least one described candidate user according to cosine similarity
Descending order chooses predetermined number candidate user and is used as targeted customer；
Push unit, is configured to push the product information to be pushed to the targeted customer.
7. product information pusher according to claim 6, it is characterised in that described
The value of each component of primary vector is：The product information to be pushed is in the attribute set
The value of the component corresponding to property value under per attribute is the numerical value more than 0, remaining attribute
The value of the corresponding component of value is 0.
8. product information pusher according to claim 6, it is characterised in that described
At least one candidate user is to access the product page under the product category in registered user
User.
9. product information pusher according to claim 6, it is characterised in that described
Push unit includes：
Acquisition module, is configured to obtain the user profile of the targeted customer, wherein described use
Family information includes at least one of following：User's registration account, E-mail address and phone number；
First pushing module, is configured to the user profile according to the targeted customer, to described
Targeted customer pushes the product information to be pushed.
10. product information pusher according to claim 9, it is characterised in that institute
Stating push unit also includes：
Second pushing module, is configured in the user's registration account login of the targeted customer
The product information to be pushed is pushed in the form of web pages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610262785.9A CN107305677A (en) | 2016-04-25 | 2016-04-25 | Product information method for pushing and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610262785.9A CN107305677A (en) | 2016-04-25 | 2016-04-25 | Product information method for pushing and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107305677A true CN107305677A (en) | 2017-10-31 |
Family
ID=60150568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610262785.9A Pending CN107305677A (en) | 2016-04-25 | 2016-04-25 | Product information method for pushing and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107305677A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109309715A (en) * | 2018-09-20 | 2019-02-05 | 江苏满运软件科技有限公司 | Information block method for pushing, system, equipment and storage medium based on user group |
| CN110119477A (en) * | 2019-05-14 | 2019-08-13 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and storage medium |
| CN110827044A (en) * | 2018-08-07 | 2020-02-21 | 北京京东尚科信息技术有限公司 | Method and device for extracting user interest mode |
| WO2020098163A1 (en) * | 2018-11-12 | 2020-05-22 | 平安科技（深圳）有限公司 | Product data pushing method and device, and computer non-volatile readable storage medium |
| CN111881341A (en) * | 2020-06-15 | 2020-11-03 | 合肥美的电冰箱有限公司 | Diet information recommendation method and device, electronic equipment and medium |
| CN113674009A (en) * | 2020-05-15 | 2021-11-19 | 北京沃东天骏信息技术有限公司 | Method and device for determining target user |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101287082A (en) * | 2008-05-16 | 2008-10-15 | 华东师范大学 | Collaborative filtered recommendation method introducing hotness degree weight of program |
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN102411754A (en) * | 2011-11-29 | 2012-04-11 | 南京大学 | Personalized recommendation method based on commodity property entropy |
| EP2543014A4 (en) * | 2010-03-01 | 2014-12-24 | Opera Solutions Llc | Computer-implemented method for enhancing product sales |
| CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
| CN104866484A (en) * | 2014-02-21 | 2015-08-26 | 阿里巴巴集团控股有限公司 | Data processing method and device |
-
2016
- 2016-04-25 CN CN201610262785.9A patent/CN107305677A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101287082A (en) * | 2008-05-16 | 2008-10-15 | 华东师范大学 | Collaborative filtered recommendation method introducing hotness degree weight of program |
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| EP2543014A4 (en) * | 2010-03-01 | 2014-12-24 | Opera Solutions Llc | Computer-implemented method for enhancing product sales |
| CN102411754A (en) * | 2011-11-29 | 2012-04-11 | 南京大学 | Personalized recommendation method based on commodity property entropy |
| CN104866484A (en) * | 2014-02-21 | 2015-08-26 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827044A (en) * | 2018-08-07 | 2020-02-21 | 北京京东尚科信息技术有限公司 | Method and device for extracting user interest mode |
| CN109309715A (en) * | 2018-09-20 | 2019-02-05 | 江苏满运软件科技有限公司 | Information block method for pushing, system, equipment and storage medium based on user group |
| CN109309715B (en) * | 2018-09-20 | 2021-11-30 | 江苏满运软件科技有限公司 | Information grouping pushing method, system, equipment and storage medium based on user group |
| WO2020098163A1 (en) * | 2018-11-12 | 2020-05-22 | 平安科技（深圳）有限公司 | Product data pushing method and device, and computer non-volatile readable storage medium |
| CN110119477A (en) * | 2019-05-14 | 2019-08-13 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and storage medium |
| CN110119477B (en) * | 2019-05-14 | 2024-02-27 | 腾讯科技（深圳）有限公司 | Information pushing method, device and storage medium |
| CN113674009A (en) * | 2020-05-15 | 2021-11-19 | 北京沃东天骏信息技术有限公司 | Method and device for determining target user |
| CN111881341A (en) * | 2020-06-15 | 2020-11-03 | 合肥美的电冰箱有限公司 | Diet information recommendation method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107305677A (en) | Product information method for pushing and device | |
| CN105224623B (en) | The training method and device of data model | |
| Kim et al. | Can mobile and biometric payments replace cards in the Korean offline payments market? Consumer preference analysis for payment systems using a discrete choice model | |
| CN107220852A (en) | Method, device and server for determining target recommended user | |
| CN107105031A (en) | Information-pushing method and device | |
| CN106845999A (en) | Risk subscribers recognition methods, device and server | |
| CN107730389A (en) | Electronic installation, insurance products recommend method and computer-readable recording medium | |
| CN107247786A (en) | Method, device and server for determining similar users | |
| CN107944481A (en) | Method and apparatus for generating information | |
| CN107391680A (en) | Content recommendation method, device and equipment | |
| CN105893465A (en) | Automatic question answering method and device | |
| CN107203894A (en) | Information-pushing method and device | |
| CN107944956A (en) | Method and apparatus for generating information | |
| CN110084658B (en) | Method and device for matching articles | |
| CN107808314B (en) | User recommendation method and device | |
| CN107679217A (en) | Association method for extracting content and device based on data mining | |
| CN111915400B (en) | Personalized clothing recommendation method and device based on deep learning | |
| CN107426328A (en) | Information-pushing method and device | |
| CN107911449A (en) | Method and apparatus for pushed information | |
| CN108595448A (en) | Information-pushing method and device | |
| CN106776716A (en) | A kind of intelligent Matching marketing consultant and the method and apparatus of user | |
| CN107742128A (en) | Method and apparatus for output information | |
| CN107451869A (en) | Method and apparatus for pushed information | |
| CN107783962A (en) | Method and device for query statement | |
| CN108268450A (en) | For generating the method and apparatus of 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171031 |
|
| RJ01 | Rejection of invention patent application after publication |