CN107305677A - Product information method for pushing and device - Google Patents

Abstract

This application discloses a product information push method and device. A specific implementation of the method includes: acquiring the product information to be pushed and the product category to which the product information to be pushed belongs; acquiring the attribute set of the product category; attribute values under each attribute, generate a first vector with components of each attribute value of each attribute in the attribute set for the product information to be pushed; for each user in at least one candidate user, generate a first vector with the Each attribute value of each attribute in the attribute set is a second vector of components; calculate and sort the cosine similarity between the first vector and the second vector of each user in the at least one candidate user; from the at least one Selecting a predetermined number of candidate users as target users from the candidate users in descending order of cosine similarity; pushing the product information to be pushed to the target users.

Description

Product information pushing method and device

technical field

The present application relates to the field of computer technology, specifically to the field of Internet technology, especially to a method and device for pushing product information.

Background technique

Product information push is a technology that pushes the product information that users need to reduce information overload through certain technical standards or protocols. Product information push technology can reduce the time spent by users searching for product information by proactively pushing product information to users.

Existing product information push usually implements targeted product information push in two ways: first, from the perspective of the user, identify the user’s identity, find out the product information that the user is interested in from the candidate push product information, and push it to users; the other one is to start from the perspective of product information, find target users who are interested in the product information to be pushed, and push the product information to be pushed to the target users. The product information push method from the perspective of the user has the defect of inaccurate identification of the user's identity, which may cause a wrong identification of the user's identity, and does not take into account the product category and product attribute information of the product information to be pushed, which may be sent to the The user pushes product information that the user is not interested in; the product information push method from the perspective of product information only starts from the perspective of product information, without considering the user's historical access data, which may cause product information to be pushed to the product. Users who are not interested in the information, or users who are interested in the product information to be pushed do not receive the product information to be pushed. Therefore, the existing method for pushing product information has the problems of insufficient utilization of user historical access data, product category information, and product attribute information, and lack of pertinence in pushing product information.

Contents of the invention

The purpose of this application is to propose an improved method and device for pushing product information to solve the technical problems mentioned in the background technology section above.

In a first aspect, the present application provides a method for pushing product information, the method comprising: acquiring product information to be pushed and the product category to which the product information to be pushed belongs; acquiring an attribute set of the product category, wherein the Each attribute in the attribute set has at least one attribute value; according to the attribute value of the product information to be pushed under each attribute in the attribute set, each attribute in the attribute set is generated for the product information to be pushed Each attribute value of is a first vector with components; for each user in at least one candidate user, generate a second vector with each attribute value of each attribute in the attribute set as a component, wherein, in the attribute set The value of the component corresponding to each attribute value of each attribute is the ratio of the number of times the user visits the product page under the attribute value divided by the number of times the user visits the product page under the product category; calculate the first vector and The cosine similarity of the second vector of each user in the at least one candidate user is sorted; from the at least one candidate user, a predetermined number of candidate users are selected as the target user according to the order of the cosine similarity from large to small; The target user pushes the product information to be pushed.

In some embodiments, the value of each component of the first vector is: the value of the component corresponding to the attribute value of each attribute in the attribute set of the product information to be pushed is greater than 0, The values of the components corresponding to the remaining attribute values are 0.

In some embodiments, the at least one candidate user is a registered user who has visited a product page under the product category.

In some embodiments, the pushing the product information to be pushed to the target user includes: obtaining user information of the target user, wherein the user information includes at least one of the following: user registration account, email address and mobile phone number; according to the user information of the target user, push the product information to be pushed to the target user.

In some embodiments, the method further includes: pushing the product information to be pushed in the form of a web page when the target user logs in with a user registration account.

In a second aspect, the present application provides a device for pushing product information, the device comprising: a first acquiring unit configured to acquire product information to be pushed and the product category to which the product information to be pushed belongs; a second acquiring unit, Configured to obtain the attribute set of the product category, wherein each attribute in the attribute set has at least one attribute value; the first vector generation unit is configured to obtain the attribute set in the attribute set according to the product information to be pushed The attribute value under each attribute is to generate a first vector with each attribute value of each attribute in the attribute set as a component for the product information to be pushed; the second vector generating unit is configured for at least one candidate user For each user in , generate a second vector with each attribute value of each attribute in the attribute set as a component, wherein the value of the component corresponding to each attribute value of each attribute in the attribute set is the user The ratio of the number of visits to the product page under the attribute value divided by the number of times the user visits the product page under the product category; the calculation unit is configured to calculate the first vector and each user in the at least one candidate user The cosine similarity of the second vector of the second vector is sorted; the selection unit is configured to select a predetermined number of candidate users as target users from the at least one candidate user according to the order of cosine similarity from large to small; the push unit is configured to use to push the product information to be pushed to the target user.

In some embodiments, the value of each component of the first vector is: the value of the component corresponding to the attribute value of each attribute in the attribute set of the product information to be pushed is greater than 0, The values of the components corresponding to the remaining attribute values are 0.

In some embodiments, the at least one candidate user is a registered user who has visited a product page under the product category.

In some embodiments, the push unit includes: an acquisition module configured to acquire user information of the target user, wherein the user information includes at least one of the following: user registration account, email address and mobile phone number; A push module, configured to push the product information to be pushed to the target user according to the user information of the target user.

In some embodiments, the push unit further includes: a second push module configured to push the product information to be pushed in the form of a webpage when the target user logs in with a user registration account.

The product information push method and device provided in this application generate a first vector for the product information to be pushed according to the attribute value of the product information to be pushed under each attribute in the attribute set, and generate the first vector according to each user in at least one candidate user The historical access information generates the second vector of the user, and then calculates and sorts the cosine similarity between the first vector and the second vector of each user in at least one candidate user, and then selects a predetermined number according to the order of cosine similarity from large to small Candidate users are used as target users, and finally push the product information to be pushed to the target users, thereby effectively combining the user's historical access information and attribute information of the information to be pushed, and realizing more targeted product information push.

Description of drawings

Other characteristics, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;

FIG. 2 is a flow chart of an embodiment of a method for pushing product information according to the present application;

3a-3d are schematic diagrams of an application scenario of the product information push method according to the present application;

FIG. 4 is a flow chart of another embodiment of the method for pushing product information according to the present application;

Fig. 5 is a schematic structural diagram of an embodiment of a product information pushing device according to the present application;

Fig. 6 is a schematic structural diagram of a computer system suitable for implementing the server of the embodiment of the present application.

detailed description

The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

Fig. 1 shows an exemplary system architecture 100 to which embodiments of the method for pushing product information or the device for pushing product information of the present application can be applied.

As shown in FIG. 1 , a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like. Various client applications may be installed on the terminal devices 101, 102, and 103, such as web browser applications, shopping applications, email clients, and the like.

Terminal devices 101, 102, 103 can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, moving picture experts compress standard audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) player, laptop portable computer and desktop computer, etc.

The server 105 may be a server that provides various services, for example, a background server that provides content support for shopping applications displayed on the terminal devices 101 , 102 , and 103 . The background server can analyze and process the received data such as shopping requests, and feed back the processing results (such as product page data) to the terminal device.

It should be noted that the product information push method provided in the embodiment of the present application is generally executed by the server 105 , and correspondingly, the product information push device is generally set in the server 105 .

It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

Continue to refer to FIG. 2 , which shows a process 200 of an embodiment of a method for pushing product information according to the present application. The method for pushing product information includes the following steps:

Step 201, acquire the product information to be pushed and the product category to which the product information to be pushed belongs.

In this embodiment, the electronic device (such as the server shown in FIG. 1 ) on which the product information push method runs can pre-store the product information to be pushed, so that the above-mentioned electronic device can locally obtain the product information to be pushed; The information can also be stored on other electronic devices remotely connected to the above electronic devices, so that the above electronic devices can also remotely obtain the product information to be pushed located on other electronic devices.

In this embodiment, the products corresponding to the product information to be pushed can be tangible products, such as mobile phones, computers, clothes, furniture, home appliances, food, etc.; they can also be intangible service products, such as online bill payment, moving services, grooming services, housekeeping services, etc.

In this embodiment, the foregoing remote connection may be a wired connection or a wireless connection. It should be noted that the above wireless connection methods may include but not limited to 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultrawideband) connection, and other wireless connection methods known or developed in the future.

In this embodiment, the electronic device may import the product information to be pushed into a pre-trained product category model for matching to obtain the product category to which the product information to be pushed belongs. Here, establishing the product category model may be to use a machine learning method to train the product category model based on the pre-established product information set and product category set. For example, after a black mobile phone of a certain brand is newly launched, corresponding product information is released, and the product information to be pushed will be classified into the product category of "mobile phone".

Step 202, acquiring the attribute set of the product category.

In this embodiment, the above-mentioned electronic device may pre-store attribute sets of various product categories, so that the above-mentioned electronic device may locally acquire the attribute sets of product categories obtained in step 201; of course, the attribute sets of each product category may also be obtained remotely Stored on other electronic devices remotely connected to the above-mentioned electronic device, so that the above-mentioned electronic device can also remotely obtain attribute sets of various product categories located in other electronic devices, thereby obtaining the attribute sets of product categories acquired in step 201. For example, the attribute set for the "mobile phone" product category may include the following attributes: brand, color, camera pixels, screen size, etc.; while the attribute set for the "computer" product category may include the following attributes: brand, color, CPU main frequency, hard disk size, memory size, monitor size, etc.

In this embodiment, each attribute in the attribute set has at least one attribute value. For example, the "brand" attribute in the attribute collection for the "mobile phone" product category may include attribute values: brand A, brand B, brand C; the attribute "color" may include attribute values: black, white, gold; "camera pixel" The attribute may include attribute values: 5 million pixels, 8 million pixels, and 13 million pixels; the "screen size" attribute may include attribute values: 4 inches, 4.5 inches, and 5 inches.

Step 203, generating a first vector for the product information to be pushed, with each attribute value of each attribute in the attribute set as components.

In this embodiment, the above-mentioned electronic device can generate the first component of each attribute value of each attribute in the attribute set for the product information to be pushed according to the attribute value of the product information to be pushed under each attribute in the above-mentioned attribute set. Vector, where the values of each component are determined according to the following principle: the value of the component corresponding to the attribute value of each attribute in the above attribute set of the product information to be pushed is a larger value, and the value of the component corresponding to the other attribute values The value of the component is a smaller value. The principle of such a value is to prepare for the calculation of the cosine similarity in the subsequent steps.

In some optional implementations of this embodiment, the value of the component corresponding to the attribute value of each attribute in the above attribute set of the product information to be pushed is greater than 0 (for example, it may be 1), and the rest The value of the component corresponding to the attribute value is 0. As an example, there are two attributes of "brand" and "color" under the product category of "mobile phone", the attribute "brand" includes attribute values: brand A, brand B, brand C; the attribute "color" includes attribute values: black, white , gold; for a product information to be pushed in the category of "mobile phone" including "A brand" and "gold", it can be generated for the product information with "A brand, B brand, C brand, black, white, gold" as components The first vector with values "1, 0, 0, 0, 0, 1".

In some optional implementations of this embodiment, the above-mentioned electronic device may also set the value of the component corresponding to the attribute value of each attribute in the above-mentioned attribute set of the product information to be pushed to a different value greater than 0, The values of the components corresponding to the remaining attribute values are set to 0. For example, set a relatively large value for the value of the component corresponding to the attribute value under the important attribute in the above attribute set, and set the value of the component corresponding to the attribute value under the less important attribute in the above attribute set For smaller values, set it to 0 for the rest of the property values. For example, for the "mobile phone" product category, there are three attributes "brand", "color" and "screen size", the "brand" attribute includes attribute values: brand A, brand B, brand C; the attribute "color" includes attribute values : black, white, gold, the "screen size" attribute includes attribute values: 4 inches, 4.5 inches, 5 inches. The "brand" attribute is the most important. For the three attribute values of the corresponding brand attribute, if the product information to be pushed belongs to which attribute value, the value of the component corresponding to the attribute value can be set to 2, while the "color" attribute is more important. For the three attribute values of the corresponding "color" attribute, if the product information to be pushed belongs to which attribute value, the value of the component corresponding to the attribute value can be set to 1, and the "screen size" attribute is not important, the corresponding "screen Size" attribute, if the product information to be pushed belongs to one of the attribute values, the value of the component corresponding to the attribute value can be set to 0.5. For the attribute values that the rest of the product information does not belong to, this attribute The value of the component corresponding to the value can be set to 0. For example, for a piece of product information to be pushed in the category of "mobile phone" including "Brand A", "Golden" and "4 inches", the product information can be generated as "Brand A, Brand B, Brand C, Black, White, Gold, 4 inches, 4.5 inches, 5 inches" is the first vector whose component values are "2, 0, 0, 0, 0, 1, 0.5, 0, 0".

Step 204, for each user in the at least one candidate user, generate a second vector whose components are each attribute value of each attribute in the attribute set.

In this embodiment, the above-mentioned electronic device can set the value of the component corresponding to each attribute value of each attribute in the attribute set as the number of times the user visits the product page under the attribute value divided by the number of times the user visits the product category under the above-mentioned product category. Ratio of product page counts. Here, the product page may be a web page, or may be a picture, icon or text with a web link. As an example, there are two attributes of "brand" and "color" under the product category of "mobile phone", the attribute "brand" includes attribute values: brand A, brand B, brand C; the attribute "color" includes attribute values: black, white , Gold; User A has visited all the product pages of the "mobile phone" product category 100 times, and the number of visits to the product pages of the "mobile phone" category of brand A, brand B and brand C are 20, 30 and 50 times respectively. The number of product pages of the product category "Mobile Phone" in black, white and gold are 15, 25 and 60 respectively, then corresponding to each of the attribute sets "Brand" and "Color" of User A for the product category "Mobile Phone". The attribute value generates a second vector whose components are "0.2, 0.3, 0.5, 0.15, 0.25, 0.6" and whose components are "A brand, B brand, C brand, black, white, gold".

In some optional implementations of this embodiment, since there are usually a large number of registered users of a large-scale e-commerce website, sometimes even reaching hundreds of millions, if the second vector is calculated for each user, the system burden will be increased, so it can be A user who has visited a product page under the above product category among registered users is selected as at least one candidate user. For example, when the product information to be pushed is information of the "mobile phone" product category, a user who has visited the product information of the "mobile phone" product category among the registered users is selected as at least one candidate user.

Step 205, calculating and sorting the cosine similarity between the first vector and the second vector of each user in the at least one candidate user.

In this embodiment, the above-mentioned electronic device may use the following formula to calculate the cosine similarity between the first vector and the second vector of each user in at least one candidate user:

Among them, v ₁ is the first vector; v ₂ is the second vector; n is a positive integer, indicating the number of dimensions of the first vector, which is also the number of dimensions of the second vector, and also the number of each attribute value of each attribute in the above product category The sum of numbers; i is a positive integer from 1 to n; v ₁ [i] is the value of the i-th component of the first vector; v ₂ [i] is the value of the i-th component of the second vector; Sim( v ₁ , v ₂ ) is the calculated cosine similarity between the first vector and the second vector, and a larger value of Sim(v ₁ , v ₂ ) indicates a higher cosine similarity between the first vector and the second vector.

In this embodiment, the electronic device may sort the calculation results of the cosine similarity in descending order.

Step 206, selecting a predetermined number of candidate users from at least one candidate user in descending order of cosine similarity as target users.

In this embodiment, the electronic device may select a predetermined number of candidate users from at least one candidate user in descending order of similarity based on the cosine similarity ranking result obtained in step 205 as the target user. Here, the predetermined number can be set by default, for example, 3 million; the predetermined number can also be defined by the administrator according to the content of the product information to be pushed or the network load status of the above-mentioned electronic device, for example, when the network of the above-mentioned electronic device When the load is heavy, the predetermined number is set to 2 million, and when the network load of the above-mentioned electronic devices is light, the predetermined number is set to 4 million.

Step 207, push the product information to be pushed to the target user.

In this embodiment, the above-mentioned electronic device may push the above-mentioned product information to be pushed to the predetermined number of target users selected in step 206 in various forms.

Continue to refer to FIG. 3 , which is a schematic diagram of an application scenario of the method for pushing product information according to this embodiment. In the application scenario of Figure 3, there are two attributes of "brand" and "color" in the attribute set under the product category of "mobile phone"; the attribute of "brand" includes attribute values: brand A, brand B and brand C; "color""Attributes include attribute values: white, black and gold; users include user 1, user 2, ... user 9 and user 10, a total of 10 users; the attribute values of each attribute in the attribute set of the above 10 users are The second vector of the component is shown in Figure 3a. For example, the second vector of user 1 is: (0.4,0.2,0.4,0.2,0.6,0.2); in addition, the calculation method of the first vector is adopted for the product to be pushed The value of the corresponding component of the information under the attribute values of the two attributes of "brand" and "color" is set to 1, and the value of the component corresponding to the remaining attribute values is set to 0; Figure 3b shows that according to the above-mentioned first vector The first vector of the product information of the "mobile phone" product category of different "brand" and "color" attributes obtained by the calculation method; based on the first vector shown in Figure 3a and the second vector shown in Figure 3b, according to step 205 The formula shown in: The calculated cosine similarity is shown in Figure 3c; after sorting the cosine similarity in Figure 3c, 6 target users are selected from the 10 candidate users and shown in bold in Figure 3d.

The method provided by the above-mentioned embodiments of the present application calculates the cosine similarity between the first vector of the product information to be pushed and the second vector of each candidate user, and selects the predetermined A large number of target users push product information, realizing targeted product information push.

Further referring to FIG. 4 , it shows a flow 400 of another embodiment of the method for pushing product information. The process 400 of the method for pushing product information includes the following steps:

Step 401, acquire the product information to be pushed and the product category to which the product information to be pushed belongs.

In this embodiment, the electronic device (such as the server shown in FIG. 1 ) on which the product information push method runs can pre-store the product information to be pushed, so that the above-mentioned electronic device can locally obtain the product information to be pushed; The information can also be stored on other electronic devices remotely connected to the above electronic devices, so that the above electronic devices can also remotely obtain the product information to be pushed located on other electronic devices.

Step 402, acquiring the attribute set of the product category.

In this embodiment, the above-mentioned electronic device may pre-store attribute sets of various product categories, so that the above-mentioned electronic device may locally acquire the attribute sets of product categories acquired in step 401; of course, the attribute sets of each product category may also be obtained remotely Stored on other electronic devices that are remotely connected to the above-mentioned electronic device, so that the above-mentioned electronic device can also remotely obtain attribute sets of various product categories located in other electronic devices, thereby obtaining the attribute sets of product categories obtained in step 401.

In this embodiment, each attribute in the attribute set has at least one attribute value.

Step 403, generating a first vector for the product information to be pushed, with each attribute value of each attribute in the attribute set as components.

In this embodiment, the above-mentioned electronic device can generate the first component of each attribute value of each attribute in the attribute set for the product information to be pushed according to the attribute value of the product information to be pushed under each attribute in the above-mentioned attribute set. Vector, where the values of each component are determined according to the following principle: the value of the component corresponding to the attribute value of each attribute in the above attribute set of the product information to be pushed is a larger value, and the value of the component corresponding to the other attribute values The value of the component is a smaller value. The principle of such a value is to prepare for the calculation of the cosine similarity in the subsequent steps.

Step 404, for each user in the at least one candidate user, generate a second vector whose components are each attribute value of each attribute in the attribute set.

In this embodiment, the above-mentioned electronic device can set the value of the component corresponding to each attribute value of each attribute in the attribute set as the number of times the user visits the product page under the attribute value divided by the number of times the user visits the product category under the above-mentioned product category. Ratio of product page counts. Here, the product page may be a web page, or may be a picture, icon or text with a web link.

Step 405, calculating and sorting the cosine similarity between the first vector and the second vector of each user in the at least one candidate user.

In this embodiment, the above-mentioned electronic device may use the following formula to calculate the cosine similarity between the first vector and the second vector of each user in at least one candidate user:

Among them, v ₁ is the first vector; v ₂ is the second vector; n is a positive integer, indicating the number of dimensions of the first vector, which is also the number of dimensions of the second vector, and also the number of each attribute value of each attribute in the above product category The sum of numbers; i is a positive integer from 1 to n; v ₁ [i] is the value of the i-th component of the first vector; v ₂ [i] is the value of the i-th component of the second vector; Sim( v ₁ , v ₂ ) is the calculated cosine similarity between the first vector and the second vector, and a larger value of Sim(v ₁ , v ₂ ) indicates a higher cosine similarity between the first vector and the second vector.

In this embodiment, the electronic device may sort the calculation results of the cosine similarity in descending order.

Step 406, selecting a predetermined number of candidate users from at least one candidate user in descending order of cosine similarity as target users.

In this embodiment, the electronic device may select a predetermined number of candidate users from at least one candidate user in descending order of similarity based on the cosine similarity ranking result obtained in step 205 as the target user.

Step 407, acquiring user information of the target user.

In this embodiment, the above-mentioned electronic device may obtain the user information of the target user locally; of course, the above-mentioned electronic device may also remotely obtain the user information of the target user from other electronic devices storing the user information of the target user. Here, the user information includes at least one of the following: user registration account, email address and mobile phone number.

Step 408, according to the user information of the target user, push the product information to be pushed to the target user.

In this embodiment, the above-mentioned electronic device may push the above-mentioned product information to be pushed to the target user in various forms.

In some optional implementation manners of this embodiment, the electronic device may send a short message to the mobile phone specified by the mobile phone number of the target user to push the product information to be pushed.

In some optional implementation manners of this embodiment, the electronic device may also send an email to the email address of the target user to push the product information to be pushed.

Step 409, push the product information to be pushed in the form of a webpage when the target user logs in with the user registration account.

In this embodiment, the above-mentioned electronic device may push the product information to be pushed in the form of a webpage when the target user logs in with a user registration account. The webpage form can intuitively and conveniently display more content in the product information to be pushed to the user. For shopping applications, compared with the product information push method of SMS and email, the web page push method can facilitate users to quickly place an order and purchase directly when they see the product information they are interested in, especially when the user registers and logs in to the user account. Users push product information, which reduces the time for users to search for other similar products and improves user efficiency.

It can be seen from FIG. 4 that, compared with the embodiment corresponding to FIG. 2 , the process 400 of the product information pushing method in this embodiment includes the step 407 of obtaining the user information of the target user and registering an account in the user of the target user. The step 409 of pushing the product information to be pushed in the form of a web page during login, and the step 408 highlights that the product information to be pushed is pushed to the target user according to the user information of the target user. Therefore, the solution described in this embodiment can introduce more ways to push product information to target users, so as to realize more comprehensive and effective product information pushing methods.

Further referring to FIG. 5 , as an implementation of the methods shown in the above figures, the present application provides an embodiment of a device for pushing product information. This device embodiment corresponds to the method embodiment shown in FIG. 2 , and the device specifically It can be applied to various electronic devices.

As shown in Figure 5, the product information push device 500 described in this embodiment includes: a first acquisition unit 501, a second acquisition unit 502, a first vector generation unit 503, a second vector generation unit 504, a calculation unit 505, a selection Unit 506 and push unit 507. Wherein, the first acquiring unit 501 is configured to acquire the product information to be pushed and the product category to which the product information to be pushed belongs; the second acquiring unit 502 is configured to acquire the attribute set of the product category, wherein the Each attribute in the attribute set has at least one attribute value; the first vector generating unit 503 is configured to, according to the attribute value of the product information to be pushed under each attribute in the attribute set, generate an attribute value for the product information to be pushed Generate a first vector with each attribute value of each attribute in the attribute set as a component; the second vector generating unit 504 is configured to, for each user in at least one candidate user, generate a vector with each attribute in the attribute set Each attribute value of an attribute is a second vector of components, wherein the value of the component corresponding to each attribute value of each attribute in the attribute set is divided by the number of times the user visits the product page under the attribute value divided by the user's visit The ratio of the number of product pages under the product category; the calculation unit 505 is configured to calculate and sort the cosine similarity between the first vector and the second vector of each user in the at least one candidate user; the selection unit 506, configured to select a predetermined number of candidate users as target users from the at least one candidate user in descending order of cosine similarity; the push unit 506 is configured to push the target user to the target user product information. In this embodiment, the first acquisition unit 501, the second acquisition unit 502, the first vector generation unit 503, the second vector generation unit 504, the calculation unit 505, the selection unit 506 and the push unit 507 in the product information pushing device 500 For the specific processing and the beneficial effects brought by it, please refer to the relevant description of the implementation of steps 201, 202, 203, 204, 205, 206 and 207 in the embodiment corresponding to FIG. repeat.

In some optional implementations of this embodiment, the value of each component of the above-mentioned first vector is: the value of the component corresponding to the attribute value of each attribute in the above-mentioned attribute set of the product information to be pushed is greater than The value of 0, and the value of the components corresponding to the other attribute values is 0. For specific processing and beneficial effects brought about by it, reference may be made to the relevant description of the implementation manner of step 203 in the embodiment corresponding to FIG. 2 , which will not be repeated here.

In some optional implementation manners of this embodiment, the at least one candidate user is a registered user who has visited a product page under the above product category. For specific processing and beneficial effects brought about by it, reference may be made to the relevant description of the implementation manner of step 204 in the embodiment corresponding to FIG. 2 , and details are not repeated here.

In some optional implementations of this embodiment, the push unit 507 in the product information push device 500 may include: an acquisition module (not shown in the figure), configured to acquire the user information of the above-mentioned target user, wherein the above-mentioned user information Including at least one of the following: user registration account, email address and mobile phone number; a first push module (not shown in the figure), configured to push the above-mentioned product information to be pushed to the above-mentioned target user according to the user information of the above-mentioned target user . For the specific processing of the acquisition module and the first push module and the beneficial effects brought about by them, please refer to the relevant description of the implementation of step 407 and step 408 in the embodiment corresponding to FIG. 4 , which will not be repeated here.

In some optional implementations of this embodiment, the push unit 507 in the product information push device 500 may further include: a second push module (not shown in the figure), configured to log in with the user registration account of the target user The above-mentioned product information to be pushed is pushed in the form of a webpage from time to time. For the specific processing of the second push module and the beneficial effects brought by it, please refer to the relevant description of the implementation of step 409 in the embodiment corresponding to FIG. 4 , which will not be repeated here.

Referring now to FIG. 6 , it shows a schematic structural diagram of a computer system 600 suitable for implementing the server of the embodiment of the present application.

As shown in FIG. 5 , a computer system 600 includes a central processing unit (CPU) 601 that can execute programs according to programs stored in a read-only memory (ROM) 602 or loaded from a storage section 606 into a random-access memory (RAM) 603 Instead, various appropriate actions and processes are performed. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601 , ROM 602 , and RAM 603 are connected to each other via a bus 604 . An input/output (I/O) interface 605 is also connected to the bus 604 .

The following components are connected to the I/O interface 605: a storage section 606 including a hard disk and the like; and a communication section 607 including a network interface card such as a LAN card, a modem, and the like. The communication section 607 performs communication processing via a network such as the Internet. A drive 608 is also connected to the I/O interface 605 as needed. A removable medium 609, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is mounted on the drive 608 as necessary so that a computer program read therefrom is installed into the storage section 606 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product including a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 607 and/or installed from removable media 609 . When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the method of the present application are performed. The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logic devices for implementing the specified Executable instructions for a function. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments described in the present application may be implemented by means of software or by means of hardware. The described unit can also be set in the processor, for example, it can be described as: a processor includes a first acquisition unit, a second acquisition unit, a first vector generation unit, a second vector generation unit, a calculation unit, and a selection unit and push unit. Wherein, the names of these units do not constitute a limitation to the unit itself under certain circumstances. For example, the first obtaining unit can also be described as "acquiring the product information to be pushed and the product category to which the product information to be pushed belongs." unit".

As another aspect, the present application also provides a non-volatile computer storage medium, which may be the non-volatile computer storage medium contained in the device described in the above embodiments; It may be a non-volatile computer storage medium that exists independently and is not assembled into the terminal. The non-volatile computer storage medium stores one or more programs, and when the one or more programs are executed by a device, the device: acquires the product information to be pushed and the product category to which the product information to be pushed belongs ; Obtain the attribute set of the above-mentioned product category, wherein each attribute in the above-mentioned attribute set has at least one attribute value; according to the attribute value of the above-mentioned product information to be pushed under each attribute in the above-mentioned attribute set, generate the above-mentioned product information to be pushed A first vector with each attribute value of each attribute in the above attribute set as a component; for each user in at least one candidate user, generate a second vector with each attribute value of each attribute in the above attribute set as a component, Among them, the value of the component corresponding to each attribute value of each attribute in the above attribute set is the ratio of the number of times the user visits the product page under the attribute value divided by the number of times the user visits the product page under the above product category; The cosine similarity between the first vector and the second vector of each user in the at least one candidate user is sorted; a predetermined number of candidate users are selected from the at least one candidate user in descending order of cosine similarity as the target user ; Push the above-mentioned product information to be pushed to the above-mentioned target user.

The above description is only a preferred embodiment of the present application and an illustration of the applied technical principle. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, but should also cover the technical solution formed by the above-mentioned technical features without departing from the inventive concept. Other technical solutions formed by any combination of or equivalent features thereof. For example, a technical solution formed by replacing the above-mentioned features with technical features with similar functions disclosed in (but not limited to) this application.

Claims (10)

1. A method for pushing product information, characterized in that the method comprises: Obtaining the product information to be pushed and the product category to which the product information to be pushed belongs; Obtaining an attribute set of the product category, wherein each attribute in the attribute set has at least one attribute value; According to the attribute value of the product information to be pushed under each attribute in the attribute set, generate a first vector with components of each attribute value of each attribute in the attribute set for the product information to be pushed; For each user in at least one candidate user, generate a second vector with components of each attribute value of each attribute in the attribute set, wherein the components corresponding to each attribute value of each attribute in the attribute set The value is the ratio of the number of times the user visits the product page under the attribute value divided by the number of times the user visits the product page under the product category; calculating and sorting the cosine similarity between the first vector and the second vector of each user in the at least one candidate user; Selecting a predetermined number of candidate users from the at least one candidate user in descending order of cosine similarity as target users; Pushing the product information to be pushed to the target user. 2. The method for pushing product information according to claim 1, wherein the value of each component of the first vector is determined by the attribute value of the product information to be pushed under each attribute in the attribute set The value of the corresponding component is a value greater than 0, and the value of the components corresponding to the other attribute values is 0. 3. The method for pushing product information according to claim 1, wherein the at least one candidate user is a registered user who has visited a product page under the product category. 4. The method for pushing product information according to claim 1, wherein the pushing the product information to be pushed to the target user comprises: Obtaining user information of the target user, wherein the user information includes at least one of the following: user registration account, email address and mobile phone number; Pushing the product information to be pushed to the target user according to the user information of the target user. 5. The method for pushing product information according to claim 4, characterized in that the method further comprises: The product information to be pushed is pushed in the form of a web page when the target user logs in with a user registration account. 6. A product information push device, characterized in that the device comprises: The first obtaining unit is configured to obtain the product information to be pushed and the product category to which the product information to be pushed belongs; The second obtaining unit is configured to obtain an attribute set of the product category, wherein each attribute in the attribute set has at least one attribute value; The first vector generating unit is configured to generate each attribute of each attribute in the attribute set for the product information to be pushed according to the attribute value of the product information to be pushed under each attribute in the attribute set the first vector whose values are components; The second vector generation unit is configured to, for each user in at least one candidate user, generate a second vector whose components are each attribute value of each attribute in the attribute set, wherein each attribute in the attribute set The value of the component corresponding to each attribute value of the attribute is the ratio of the number of times the user visits the product page under the attribute value divided by the number of times the user visits the product page under the product category; A calculation unit configured to calculate and sort the cosine similarity between the first vector and the second vector of each user in the at least one candidate user; The selection unit is configured to select a predetermined number of candidate users as target users from the at least one candidate user in descending order of cosine similarity; A push unit configured to push the product information to be pushed to the target user. 7. The product information pushing device according to claim 6, wherein the value of each component of the first vector is determined by the attribute value of the product information to be pushed under each attribute in the attribute set The value of the corresponding component is a value greater than 0, and the value of the components corresponding to the other attribute values is 0. 8. The device for pushing product information according to claim 6, wherein the at least one candidate user is a registered user who has visited a product page under the product category. 9. The product information pushing device according to claim 6, wherein the pushing unit comprises: An acquisition module configured to acquire user information of the target user, wherein the user information includes at least one of the following: user registration account, email address and mobile phone number; The first push module is configured to push the product information to be pushed to the target user according to the user information of the target user. 10. The product information pushing device according to claim 9, wherein the pushing unit further comprises: The second push module is configured to push the product information to be pushed in the form of a webpage when the target user logs in with a user registration account.