CN110472145B - Content recommendation method and electronic equipment - Google Patents

Abstract

The invention provides a content recommendation method and electronic equipment, and relates to the technical field of internet. Wherein, the method comprises the following steps: acquiring content to be recommended and at least two target user figures corresponding to target users; respectively determining a target weight coefficient of each target user portrait and a matching coefficient between each target user portrait and the content to be recommended; determining a recommendation index corresponding to the target user according to the matching coefficient and the target weight coefficient corresponding to each target user portrait; and when the recommendation index meets a preset recommendation condition, pushing the content to be recommended to the target user. According to the method and the device, the target user figures of the target user in different fields can be determined, and whether the content to be recommended which is cross-field but related to the fields of the target user figures is pushed to the target user or not is determined based on the target weight coefficients of the different target user figures and the matching degree of the target user figures and the content to be recommended, so that personalized content recommendation can be performed on the target user in a new field.

Description

A content recommendation method and electronic device

technical field

The invention relates to the technical field of the Internet, in particular to a content recommendation method and electronic equipment.

Background technique

With the rapid development of Internet technology, users' demand for content from the Internet is becoming more and more extensive, which also prompts many software products to focus on the original single-field products and expand products in a large number of peripheral fields. To meet the cross-domain content acquisition needs of users.

However, in practical applications, when users acquire content, there is usually a need for personalized content recommendation, and many software products cannot provide personalized content recommendation for different users in new areas.

Contents of the invention

The present invention provides a content recommendation method and an electronic device to solve the problem that cross-field recommended content cannot meet the personalized needs of users.

In order to solve the problems of the technologies described above, the present invention is achieved in that:

In the first aspect, the embodiment of the present invention provides a content recommendation method applied to electronic devices, including:

Obtaining the content to be recommended, and at least two target user portraits corresponding to the target user; wherein, the different target user portraits have different domain attributes;

Respectively determining target weight coefficients corresponding to the at least two target user portraits, and matching coefficients between the at least two target user portraits and the content to be recommended;

determining the recommendation index corresponding to the target user according to the matching coefficient and the target weight coefficient corresponding to each target user portrait;

When the recommendation index satisfies a preset recommendation condition, the content to be recommended is pushed to the target user.

In a second aspect, an embodiment of the present invention also provides an electronic device, including:

An acquisition module, configured to acquire content to be recommended and at least two target user portraits corresponding to the target user; wherein, different target user portraits have different domain attributes;

A first determination module, configured to respectively determine target weight coefficients corresponding to the at least two target user portraits, and a matching coefficient between the at least two target user portraits and the content to be recommended;

The second determination module is used to determine the recommendation index corresponding to the target user according to the matching coefficient and target weight coefficient corresponding to each target user portrait;

A push module, configured to push the content to be recommended to the target user when the recommendation index satisfies a preset recommendation condition.

In the third aspect, the embodiment of the present invention also provides an electronic device, the electronic device includes a processor, a memory, and a computer program stored in the memory and operable on the processor, the computer program is controlled by the The steps for implementing the content recommendation method of the present invention are implemented when the processor executes.

In a fourth aspect, the embodiment of the present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the content recommendation method described in the present invention are implemented.

In the embodiment of the present invention, the electronic device can first obtain the content to be recommended and at least two target user portraits corresponding to the target user, wherein different target user portraits have different domain attributes, and the domain attributes of the target user portraits are the same as the domain attributes to be recommended. The domain attribute of the recommended content is associated. Then the electronic device may respectively determine a target weight coefficient corresponding to each of the at least two target user portraits, and a matching coefficient between each of the at least two target user portraits and the content to be recommended, and According to the matching coefficient and target weight coefficient corresponding to each target user portrait, the recommendation index corresponding to the target user is determined. When the recommendation index meets the preset recommendation conditions, the content to be recommended can be pushed to the target user. In the embodiment of the present invention, the electronic device can determine target user portraits corresponding to different fields, and based on the target weight coefficients corresponding to different target user portraits, and the matching degree between each target user portrait and the content to be recommended, determine whether to Push cross-domain but related content to be recommended to target users, so that personalized content recommendations can be made to target users in new areas.

Description of drawings

FIG. 1 shows a flowchart of a content recommendation method in Embodiment 1 of the present invention;

FIG. 2 shows a flow chart of a content recommendation method in Embodiment 2 of the present invention;

FIG. 3 shows a structural block diagram of an electronic device in Embodiment 3 of the present invention;

FIG. 4 shows a structural block diagram of another electronic device in Embodiment 3 of the present invention;

Fig. 5 shows a schematic diagram of a hardware structure of an electronic device in various embodiments of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Embodiment one

Referring to FIG. 1 , it shows a flowchart of a content recommendation method in Embodiment 1 of the present invention, which may specifically include the following steps:

Step 101, acquire the content to be recommended and at least two target user portraits corresponding to the target user; wherein, different target user portraits have different domain attributes.

In the embodiment of the present invention, the domain attribute of the target user portrait is associated with the domain attribute of the content to be recommended, and the content to be recommended may be the content configured in the electronic device by the software product party according to its own business needs or customer business needs. The device may be a server or a server group corresponding to the software product, which is not specifically limited in this embodiment of the present invention. The content to be recommended may specifically include advertisements, functions, products, UGC (User-generated Content, user-generated content) and PGC (Professionally-generated Content, professionally produced content), etc., which are not specifically limited in this embodiment of the present invention.

The target user is also one of the potential users to be judged whether to push the content to be recommended. The target user can be any user who has an account registered in the software product or its associated products, where the associated product of the software product can log in and use the software product through the same account as the software product, such as mobile phone number, WeChat Signals, etc., so that the electronic device can identify the user portraits accumulated by the same user in different software according to the same account. Of course, the target user may also be one of the users selected by the electronic device based on a preset policy, for example, one of the member users, which is not specifically limited in this embodiment of the present invention.

In practical applications, the electronic device may also be a server device corresponding to an associated product of the software product, or the electronic device may receive user data sent by a server device corresponding to another associated product. Correspondingly, at least two A target user portrait may be selected by the electronic device from user data collected and stored by itself, or may be sent to the electronic device by other server devices, which is not specifically limited in this embodiment of the present invention.

Among them, any target user portrait corresponding to the target user is the personal information, habits, preferences and other data of the target user in a certain field, for example, it can be the user's work field, leisure field, travel field, driving field, home field, etc. Habits and preference data in different fields such as health, sports, consulting, financial management, education, and consumption are not specifically limited in this embodiment of the present invention.

Different target user portraits corresponding to the target user have different domain attributes, and the domain attributes of each user portrait are associated with the domain attributes of the content to be recommended. For example, the domain attribute of the first target user portrait corresponding to the target user may be listening to songs, that is, the first target user portrait is the habit and preference data of the target user in the field of listening to music, and the second target user portrait corresponding to the target user is The domain attribute can be entertainment consumption, that is, the second target user profile is the habit and preference data of the target user in the entertainment consumption field, and the domain attribute of the content to be recommended can be music/concert. Therefore, the electronic device can determine whether to push to the target user, based on the target user portraits of the target user corresponding to different fields, content to be recommended that crosses fields but is associated with the field to which each target user portrait belongs.

It should be noted that the embodiment of the present invention does not specifically limit the acquisition order of at least two target user portraits corresponding to the content to be recommended and the target user.

Step 102, respectively determine the target weight coefficients corresponding to at least two target user portraits, and the matching coefficients between the at least two target user portraits and the content to be recommended.

In the embodiment of the present invention, since target user portraits in different fields have different degrees of association with the content to be recommended and different degrees of influence on the content to be recommended, the target weight coefficient corresponding to each target user portrait can be set in advance and stored Alternatively, in the electronic device, a target weight coefficient corresponding to each target user profile may be set based on feedback results from a small number of users, which is not specifically limited in this embodiment of the present invention. After acquiring at least two target user portraits corresponding to the target user, the electronic device may determine a target weight coefficient set for each target user portrait.

In addition, the matching coefficient between the target user portrait and the content to be recommended can represent the degree of correlation between the target user portrait and the content to be recommended. For example, if the target user portrait includes the residence information of the target user, and the content to be recommended involves location, when the target user’s residence information is the same as the location in the content to be recommended, the matching coefficient between the target user portrait and the content to be recommended is relatively large, and when the target user’s residence information is consistent with the location in the content to be recommended When the location of the target user is located in the same province, the matching coefficient between the target user portrait and the content to be recommended is second compared to the first case above. The matching coefficient between the portrait and the content to be recommended is next to that of the second case above.

It should be noted that, the embodiment of the present invention does not specifically limit the order of determining the target weight coefficient and the matching coefficient.

Step 103: Determine the recommendation index corresponding to the target user according to the matching coefficient and target weight coefficient corresponding to each target user profile.

In the embodiment of the present invention, the electronic device may weight and sum the matching coefficients corresponding to each target user portrait according to the target weight coefficient corresponding to each target user portrait of the target user, so as to obtain the recommendation index corresponding to the target user. When the recommendation index corresponding to the target user is large, the target user is a powerful recommendation object that can push the content to be recommended.

Step 104, when the recommendation index satisfies the preset recommendation condition, push the content to be recommended to the target user.

In the embodiment of the present invention, a preset recommendation condition can be set in the electronic device in advance, and when the recommendation index corresponding to the target user meets the preset recommendation condition, the content to be recommended can be pushed to the target user.

In the embodiment of the present invention, the electronic device can first obtain the content to be recommended and at least two target user portraits corresponding to the target user, wherein different target user portraits have different domain attributes, and the domain attributes of the target user portraits are the same as the domain attributes to be recommended. The domain attribute of the recommended content is associated. Then the electronic device may respectively determine a target weight coefficient corresponding to each of the at least two target user portraits, and a matching coefficient between each of the at least two target user portraits and the content to be recommended, and According to the matching coefficient and target weight coefficient corresponding to each target user portrait, the recommendation index corresponding to the target user is determined. When the recommendation index meets the preset recommendation conditions, the content to be recommended can be pushed to the target user. In the embodiment of the present invention, the electronic device can determine target user portraits corresponding to different fields, and based on the target weight coefficients corresponding to different target user portraits, and the matching degree between each target user portrait and the content to be recommended, determine whether to Push cross-domain but related content to be recommended to target users, so that personalized content recommendations can be made to target users in new areas.

Embodiment two

Referring to FIG. 2 , it shows a flowchart of a content recommendation method in Embodiment 2 of the present invention, which may specifically include the following steps:

Step 201, obtain the content to be recommended and at least two target user portraits corresponding to the target user; different target user portraits have different domain attributes, and the domain attributes of the target user portraits are associated with the domain attributes of the content to be recommended.

This step is similar to the implementation process of step 101 above, and will not be described in detail here.

For example, a traditional online music software originally only had related functions in the field of listening to songs, but now a new function has been introduced, that is, concerts and concert ticket sales functions. There is a certain understanding of preferences. Now, there is a cross-domain content to be recommended "X day-Shanghai-singer Zhang-sales of concert tickets at a price of Y" that you want to recommend to users. The domain attribute of the content to be recommended is "concert/concert tickets". For the target user, the music software can already collect the basic information user portrait and music user portrait corresponding to the target user, and the music software can log in through the account of another payment software. Therefore, the music software can also use the payment software The software collects the consumption ability portrait corresponding to the target user. The electronic device corresponding to the application software, that is, the server, can obtain the content to be recommended "X day-Shanghai-singer Zhang-sales of concert tickets at price Y", as well as the basic information corresponding to the target user User portrait, music user There are three target user portraits: portrait and consumption ability portrait. Referring to Table 1 below, it shows the user information included in each target user portrait, the corresponding field attributes, and the relevance to the content to be recommended.

Table 1

It should be noted that the embodiment of the present invention is only described by taking various target user portraits, user information and other data shown in Table 1 as an example, and each data shown in Table 1 does not limit the present invention.

Step 202, based on the pre-stored correspondence between user portraits and weight coefficients, determine target weight coefficients corresponding to each target user portrait.

In the embodiment of the present invention, before this step, the electronic device may also perform the following steps, specifically including: determining at least two initial weight coefficients corresponding to each target user portrait; Adjust the initial weight coefficients to obtain the target weight coefficients; store the corresponding relationship between each target user portrait and each target weight coefficient.

Specifically, for any target user portrait corresponding to the target user, the electronic device can first assign at least two initial weight coefficients to the target user portrait, and one initial weight coefficient can be used as a weight test strategy, so that at least two Weight testing strategy. Then the electronic device can randomly select users with a preset ratio from all candidate users to be recommended, and then group the selected users, and each group executes this method according to different weight test strategies to provide each selected user The user pushes the content to be recommended, and then according to the feedback results such as the user's click on the recommendation interface and the browsing time of the recommendation interface, the weight test strategy with the best user feedback can be selected from at least two weight test strategies.

Next, the electronic device can adjust the weight coefficient in the weight test strategy with the best user feedback. The adjustment principle can be: the weight coefficient corresponding to the target user portrait that is beneficial to the recommendation can be increased, and the target user that has no obvious impact on the recommendation The weight coefficient corresponding to the portrait can be adjusted down. Through different degrees of adjustment, at least two new weight coefficients can be obtained again, and then the electronic device can randomly select users with a preset ratio from the remaining candidate users, and then continue to repeat the above process until at least two new weight coefficients are selected. The weight test strategy with the best user feedback is selected again from the weight test strategy. This process can be repeated a preset number of times, and for the last selected user feedback optimal weight test strategy, the electronic device can determine each weight coefficient in the weight test strategy as the target weight coefficient corresponding to each target user portrait, and The corresponding relationship between each target user portrait and each target weight coefficient may be stored.

For example, the electronic device can determine four initial weight coefficients for each target user portrait, so that four weight test strategies of A, B, C, and D can be obtained, and then the electronic device can randomly select from all candidate users to be recommended 10% of users push, and each weight testing strategy can target 2.5% of users. According to the user feedback results, the electronic device can select the weight test strategy A with the best user feedback, and then on the basis of the weight test strategy A, the electronic device can increase the weight coefficient of the target user portrait that is beneficial to the recommendation, and will have no impact on the recommendation. The weight coefficient of the affected target user portrait is lowered. Through different degrees of adjustment, 4 new weight test strategies E, F, G, and H can be obtained again, and continue to be pushed to 10% of the remaining candidate users to obtain user feedback After the result, the electronic device can select the best weight test strategy F, and store the basic information user portrait and the target weight coefficient 0.20 corresponding to the basic information user portrait in the weight test strategy F, and store the music user portrait and weight The target weight coefficient 0.55 corresponding to the music user portrait in the test strategy F is stored correspondingly, and the consumption ability user portrait is correspondingly stored with the target weight coefficient 0.25 corresponding to the consumption ability user portrait in the weight test strategy F.

Of course, in practical applications, the target weight coefficient corresponding to each target user portrait can also be manually set, and the corresponding relationship between the target user portrait and the set target weight coefficient is stored in the electronic device. This is not specifically limited.

Correspondingly, the electronic device may determine the target weight coefficient corresponding to the current target user portrait from the pre-stored correspondence between the user portrait and the weight coefficient.

For example, the correspondence between the user profile and the weight coefficient pre-stored by the electronic device may be shown in Table 2 below, and the electronic device may respectively determine that the target weight coefficient corresponding to the basic information user profile is 0.20 from the correspondence shown in Table 2, The target weight coefficient corresponding to the music user portrait is 0.55, and the target weight coefficient corresponding to the consumption power user portrait is 0.25.

Table 2

User portrait weight factor Basic information User portrait 0.20 Music user portrait 0.55 Consumption ability user portrait 0.25

It should be noted that the embodiment of the present invention is only described by taking the correspondence between user portraits and weight coefficients shown in Table 2 above as an example, and Table 2 above does not limit the present invention.

Step 203, each target user portrait includes user information in at least one dimension; for each dimension, from at least one preset condition corresponding to the dimension, determine the target preset condition that the user information in this dimension meets; where , each preset condition is set based on the user information in the corresponding dimension and the content to be recommended.

In the embodiment of the present invention, each target user profile may include user information in at least one dimension, for example, the basic information user profile may include user information in dimensions such as gender, age, and residence. At least two preset conditions may be set for each dimension in advance according to the content to be recommended and user information in each dimension. Correspondingly, for any dimension, the electronic device may determine the target preset condition that the user information in this dimension meets from the preset conditions corresponding to the dimension.

For example, referring to the following Table 3, taking the user information of the residence dimension corresponding to the basic information user portrait as an example, the residence dimension is correspondingly set with 4 preset conditions, and the user information of the residence dimension can be Shanghai, that is, the target user's permanent residence is Shanghai. When the concert venue is located in Shanghai, the electronic device can determine the first preset condition "the target user's permanent residence and the concert venue are located in the same city". The target preset condition that the user information under the resident dimension meets.

table 3

It should be noted that the embodiment of the present invention is only described by taking the preset conditions and matching scores shown in Table 3 as an example, and the above Table 3 does not limit the present invention.

Step 204, respectively determine the matching score corresponding to each target preset condition.

In the embodiment of the present invention, the electronic device may respectively determine the matching score corresponding to each target preset condition from the correspondence relationship between the preset condition and the matching score.

For example, the electronic device may determine that the matching score corresponding to the target preset condition "the target user's permanent residence and the concert venue are located in the same city" is 3 from the correspondence between preset conditions and matching scores shown in Table 3 above. .

Step 205: Add the matching scores corresponding to each target preset condition in the same target user portrait to obtain the matching coefficient between each target user portrait and the content to be recommended.

In the embodiment of the present invention, the electronic device may add the matching scores corresponding to each target preset condition in the same target user portrait, so as to obtain the matching coefficient between each target user portrait and the content to be recommended.

For example, the electronic device may add the matching scores corresponding to each target preset condition in the basic information user profile, so as to obtain a matching coefficient of 6 between the basic information user profile and the content to be recommended. The electronic device can add the matching scores corresponding to each target preset condition in the music user portrait, so as to obtain a matching coefficient of 8 between the music user portrait and the content to be recommended. The electronic device can add the matching scores corresponding to each target preset condition in the consumption ability user portrait, so as to obtain a matching coefficient of 2 between the consumption ability user portrait and the content to be recommended.

Step 206: Determine the recommendation index corresponding to the target user according to the matching coefficient and target weight coefficient corresponding to each target user portrait.

In the embodiment of the present invention, this step can be specifically implemented in the following manner, including: multiplying the matching coefficient corresponding to the same target user portrait by the target weight coefficient to obtain the recommended value corresponding to each target user portrait; The recommendation values corresponding to the portraits are added to obtain the recommendation index corresponding to the target user.

Wherein, the electronic device may weight and sum the matching coefficients corresponding to each target user portrait according to the target weight coefficient corresponding to each target user portrait of the target user, so as to obtain the recommendation index corresponding to the target user. When the recommendation index corresponding to the target user is large, the target user is a powerful recommendation object that can push the content to be recommended. When the recommendation index corresponding to the target user is small, the possibility of the target user being the recommendation object of the content to be recommended is low.

In another implementation, the electronic device may also multiply the matching score corresponding to each target preset condition in each target user portrait by the target weight coefficient of the corresponding target user portrait to obtain each product, and then The products can be added together to obtain the recommendation index corresponding to the target user. The embodiment of the present invention does not specifically limit the specific implementation manner of determining the recommendation index corresponding to the target user.

For example, the electronic device can multiply the matching coefficient 6 corresponding to the basic information user portrait by the target weight coefficient 0.20 to obtain the recommended value corresponding to the basic information user portrait 1.2; the electronic device can multiply the matching coefficient 8 corresponding to the music user portrait and the target weight coefficient Multiply the coefficient 0.55 to obtain the recommended value corresponding to the music user portrait as 4.4; the electronic device can multiply the matching coefficient 2 corresponding to the consumption ability user portrait with the target weight coefficient 0.25 to obtain the recommended value corresponding to the consumption ability user portrait 0.5. Then, the electronic device can add the recommended value 1.2 corresponding to the basic information user profile, the recommended value 4.4 corresponding to the music user profile, and the recommended value 0.5 corresponding to the consumption ability user profile, to obtain the recommendation index corresponding to the target user as 6.1.

Step 207, when the recommendation index satisfies the preset recommendation condition, push the content to be recommended to the target user.

In the embodiment of the present invention, when the recommendation index corresponding to the target user satisfies the preset recommendation condition, the electronic device may send the recommendation information corresponding to the content to be recommended to the terminal where the target user logs in through the software account. In a specific application, the recommendation information may be information in the form of text, image, video, voice, etc., which is not specifically limited in this embodiment of the present invention. Furthermore, the terminal corresponding to the target user can display the recommendation information, so that the target user can view it.

Optionally, this step can be specifically implemented in the following ways, including: when the recommendation index is greater than or equal to the preset value, pushing the content to be recommended to the target user; and/or, when the recommendation index is in the corresponding recommendation index of each pre-selected user The sorting ranking in is less than or equal to the preset ranking, and the content to be recommended is pushed to the target user; the recommendation index corresponding to each pre-selected user is arranged in descending order.

That is, the preset recommendation condition may be that the recommendation index is greater than or equal to a preset value, and/or, the ranking of the recommendation index in the recommendation index corresponding to each preselected user is less than or equal to the preset ranking. Wherein, each preselected user is all potential users to be judged whether to push the content to be recommended, and correspondingly, the target user is any one of each preselected user.

Among them, when the recommendation index corresponding to the target user is greater than or equal to the preset value, and/or the target user ranks high among the pre-selected users arranged in descending order of the recommendation index, it means that the content to be recommended is pushed to the target user. To a large extent, it may meet the individual needs of target users, and it is easier to obtain better user feedback.

For example, the recommendation index corresponding to the target user can be 6.1, which is greater than the preset value of 4.5, so that the electronic device can push the content to be recommended to the target user "X day-Shanghai-singer Zhang-sale of concert tickets at price Y".

In the embodiment of the present invention, the electronic device can first obtain the content to be recommended and at least two target user portraits corresponding to the target user, wherein different target user portraits have different domain attributes, and the domain attributes of the target user portraits are the same as the domain attributes to be recommended. The domain attribute of the recommended content is associated. Then the electronic device can respectively determine the target weight coefficient corresponding to each of the target user portraits in the at least two target user portraits, and determine the weight coefficient in each dimension from each preset condition corresponding to each dimension in the target user portrait. The target preset conditions that the user information meets, and then respectively determine the matching score corresponding to each target preset condition, and add the matching scores corresponding to each target preset condition in the same target user portrait to obtain each The matching coefficient between the target user portrait and the content to be recommended. After that, according to the matching coefficient and target weight coefficient corresponding to each target user portrait, the recommendation index corresponding to the target user can be determined. When the recommendation index meets the preset recommendation conditions, the content to be recommended can be pushed to the target user. In the embodiment of the present invention, the electronic device can determine the target user portraits corresponding to different fields of the target user, and based on the target weight coefficients corresponding to different target user portraits, perform a weighted calculation for the matching coefficient between each target user portrait and the content to be recommended. and, so as to obtain the recommendation index corresponding to the target user, and then when the recommendation index meets the preset recommendation conditions, it is determined that the content to be recommended that is cross-domain but associated with the field of each target user portrait can be pushed to the target user, so that it can be in The new field makes personalized content recommendations for target users.

Embodiment Three

Referring to FIG. 3 , it shows a structural block diagram of an electronic device 300 according to Embodiment 3 of the present invention, which may specifically include:

An acquisition module 301, configured to acquire content to be recommended and at least two target user portraits corresponding to the target user; wherein, different target user portraits have different domain attributes;

Specifically, the domain attribute of the target user portrait is associated with the domain attribute of the content to be recommended.

The first determination module 302 is configured to respectively determine the target weight coefficients corresponding to the at least two target user portraits, and the matching coefficient between the at least two target user portraits and the content to be recommended;

The second determination module 303 is configured to determine the recommendation index corresponding to the target user according to the matching coefficient and target weight coefficient corresponding to each target user portrait;

A push module 304, configured to push the content to be recommended to the target user when the recommendation index satisfies a preset recommendation condition.

Optionally, referring to FIG. 4 , each of the target user portraits includes at least one dimension of user information; the first determining module 302 includes:

The first determination sub-module 3021 is configured to respectively determine the target weight coefficient corresponding to each of the target user portraits based on the pre-stored correspondence between the user portrait and the weight coefficient;

The second determination sub-module 3022 is used to determine, for each dimension, from at least one preset condition corresponding to the dimension, the target preset condition that the user information under the dimension meets; wherein, each preset The setting conditions are set based on the user information in the corresponding dimension and the content to be recommended;

The third determination sub-module 3023 is used to respectively determine the matching score corresponding to each of the target preset conditions;

The first adding sub-module 3024 is used to add the matching scores corresponding to each of the target preset conditions in the same target user portrait to obtain the relationship between each of the target user portraits and the content to be recommended matching coefficient.

Optionally, referring to FIG. 4, the second determining module 303 includes:

The multiplication sub-module 3031 is used to multiply the matching coefficient corresponding to the same target user portrait and the target weight coefficient to obtain the recommendation value corresponding to each target user portrait;

The second adding sub-module 3032 is configured to add the recommendation value corresponding to each target user portrait to obtain the recommendation index corresponding to the target user.

Optionally, referring to FIG. 4, the electronic device 300 further includes:

A third determination module 305, configured to determine at least two initial weight coefficients corresponding to each of the target user portraits;

An adjustment module 306, configured to adjust the at least two initial weight coefficients according to the A/B test strategy to obtain a target weight coefficient;

The storage module 307 is configured to store the corresponding relationship between each of the target user portraits and each of the target weight coefficients.

Optionally, referring to FIG. 4, the pushing module 304 includes:

The first push sub-module 3041 is configured to push the content to be recommended to the target user when the recommendation index is greater than or equal to a preset value;

and / or,

The second push sub-module 3042 is used to push the content to be recommended to the target user when the ranking ranking of the recommendation index in the recommendation index corresponding to each pre-selected user is less than or equal to the preset ranking; each pre-selected user The corresponding recommendation indexes are arranged in descending order.

The electronic device provided by the embodiment of the present invention can implement various processes implemented by the electronic device in the method embodiments in FIG. 1 and FIG. 2 , and details are not repeated here to avoid repetition.

In the embodiment of the present invention, the electronic device can first acquire the content to be recommended and at least two target user portraits corresponding to the target user through the acquisition module, wherein different target user portraits have different domain attributes, and the target user portraits The domain attribute is associated with the domain attribute of the content to be recommended. Then the electronic device can respectively determine the target weight coefficient corresponding to each target user portrait in the at least two target user portraits, and the relationship between each target user portrait in the at least two target user portraits and the content to be recommended through the first determination module. The matching coefficient between them, and through the second determination module, according to the matching coefficient and target weight coefficient corresponding to each target user portrait, the recommendation index corresponding to the target user can be determined. When the recommendation index meets the preset recommendation conditions, the push module can Push recommended content to target users. In the embodiment of the present invention, the electronic device can determine target user portraits corresponding to different fields, and based on the target weight coefficients corresponding to different target user portraits, and the matching degree between each target user portrait and the content to be recommended, determine whether to Push cross-field but related content to be recommended to target users, so that personalized content recommendations can be made to target users in new fields.

Embodiment four

FIG. 5 is a schematic diagram of a hardware structure of an electronic device implementing various embodiments of the present invention,

The electronic device 500 includes, but is not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, a processor 510, and Power supply 511 and other components. Those skilled in the art can understand that the structure of the electronic device shown in Figure 5 does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine some components, or different components layout. In the embodiment of the present invention, electronic devices include but are not limited to mobile phones, tablet computers, notebook computers, palmtop computers, vehicle-mounted terminals, wearable devices, and pedometers.

Wherein, the processor 510 is configured to obtain the content to be recommended and at least two target user portraits corresponding to the target user; wherein, the different target user portraits have different domain attributes; respectively determine the at least two target user portraits The target weight coefficient corresponding to the portrait, and the matching coefficient between the at least two target user portraits and the content to be recommended; according to the matching coefficient and target weight coefficient corresponding to each of the target user portraits, the target user is determined Corresponding recommendation index; when the recommendation index satisfies a preset recommendation condition, push the content to be recommended to the target user.

In the embodiment of the present invention, the electronic device can first obtain the content to be recommended and at least two target user portraits corresponding to the target user, wherein different target user portraits have different domain attributes, and the domain attributes of the target user portraits are the same as the domain attributes to be recommended. The domain attribute of the recommended content is associated. Then the electronic device may respectively determine a target weight coefficient corresponding to each of the at least two target user portraits, and a matching coefficient between each of the at least two target user portraits and the content to be recommended, and According to the matching coefficient and target weight coefficient corresponding to each target user portrait, the recommendation index corresponding to the target user is determined. When the recommendation index meets the preset recommendation conditions, the content to be recommended can be pushed to the target user. In the embodiment of the present invention, the electronic device can determine target user portraits corresponding to different fields, and based on the target weight coefficients corresponding to different target user portraits, and the matching degree between each target user portrait and the content to be recommended, determine whether to Push cross-domain but related content to be recommended to target users, so that personalized content recommendations can be made to target users in new areas.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 501 can be used for receiving and sending signals during sending and receiving information or during a call. Specifically, after receiving the downlink data from the base station, the processor 510 processes it; Uplink data is sent to the base station. Generally, the radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 501 can also communicate with the network and other devices through a wireless communication system.

The electronic device provides users with wireless broadband Internet access through the network module 502, such as helping users send and receive emails, browse web pages, and access streaming media.

The audio output unit 503 may convert audio data received by the radio frequency unit 501 or the network module 502 or stored in the memory 509 into an audio signal and output as sound. Also, the audio output unit 503 may also provide audio output related to a specific function performed by the electronic device 500 (for example, call signal reception sound, message reception sound, etc.). The audio output unit 503 includes a speaker, a buzzer, a receiver and the like.

The input unit 504 is used for receiving audio or video signals. The input unit 504 may include a graphics processing unit (Graphics Processing Unit, GPU) 5041 and a microphone 5042, and the graphics processor 5041 is used for still pictures or video images obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The data is processed. The processed image frames may be displayed on the display unit 506 . The image frames processed by the graphics processor 5041 may be stored in the memory 509 (or other storage media) or sent via the radio frequency unit 501 or the network module 502 . The microphone 5042 can receive sound, and can process such sound into audio data. The processed audio data can be converted into a format that can be sent to a mobile communication base station via the radio frequency unit 501 for output in the case of a phone call mode.

The electronic device 500 also includes at least one sensor 505, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 5061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 5061 and the / or backlighting. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is still, and can be used to identify the posture of electronic equipment (such as horizontal and vertical screen switching, related games) , magnetometer attitude calibration), vibration recognition-related functions (such as pedometer, knocking), etc.; the sensor 505 can also include fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, Infrared sensors, etc., will not be repeated here.

The display unit 506 is used to display information input by the user or information provided to the user. The display unit 506 may include a display panel 5061, and the display panel 5061 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.

The user input unit 507 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 507 includes a touch panel 5071 and other input devices 5072 . The touch panel 5071, also referred to as a touch screen, can collect touch operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger or a stylus on the touch panel 5071 or near the touch panel 5071). operate). The touch panel 5071 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to the For the processor 510, receive the command sent by the processor 510 and execute it. In addition, the touch panel 5071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 5071 , the user input unit 507 may also include other input devices 5072 . Specifically, other input devices 5072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.

Furthermore, the touch panel 5071 can be covered on the display panel 5061, and when the touch panel 5071 detects a touch operation on or near it, it will be sent to the processor 510 to determine the type of the touch event, and then the processor 510 can The type of event provides a corresponding visual output on the display panel 5061 . Although in FIG. 5, the touch panel 5071 and the display panel 5061 are used as two independent components to realize the input and output functions of the electronic device, in some embodiments, the touch panel 5071 and the display panel 5061 can be integrated. The implementation of the input and output functions of the electronic device is not specifically limited here.

The interface unit 508 is an interface for connecting an external device to the electronic device 500 . For example, an external device may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, audio input/output (I/O) ports, video I/O ports, headphone ports, and more. The interface unit 508 can be used to receive input from an external device (for example, data information, power, etc.) transfer data between devices.

The memory 509 can be used to store software programs as well as various data. The memory 509 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.) etc.; Data created by the use of mobile phones (such as audio data, phonebook, etc.), etc. In addition, the memory 509 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

The processor 510 is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device, by running or executing software programs and/or modules stored in the memory 509, and calling data stored in the memory 509 , to perform various functions of the electronic equipment and process data, so as to monitor the electronic equipment as a whole. The processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem The processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 510 .

The electronic device 500 can also include a power supply 511 (such as a battery) for supplying power to various components. Preferably, the power supply 511 can be logically connected to the processor 510 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. and other functions.

In addition, the electronic device 500 includes some functional modules not shown, which will not be repeated here.

Preferably, the embodiment of the present invention also provides an electronic device, including a processor 510, a memory 509, and a computer program stored in the memory 509 and operable on the processor 510. When the computer program is executed by the processor 510 Each process of the above content recommendation method embodiment can be realized and the same technical effect can be achieved, so in order to avoid repetition, details are not repeated here.

The embodiment of the present invention also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the above content recommendation method embodiment is realized, and the same technology can be achieved. Effect, in order to avoid repetition, will not repeat them here. Wherein, the computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), a magnetic disk or an optical disk, and the like.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM/RAM, disk, CD) contains several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in various embodiments of the present invention.

Embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementations, and the above-mentioned specific implementations are only illustrative, rather than restrictive, and those of ordinary skill in the art will Under the enlightenment of the present invention, without departing from the gist of the present invention and the protection scope of the claims, many forms can also be made, all of which belong to the protection of the present invention.

Claims (8)

1. A content recommendation method applied to electronic equipment, characterized in that the method comprises: Obtain the content to be recommended, and at least two target user portraits corresponding to the target user; wherein, different target user portraits have different domain attributes, and the domain attributes are used to represent the characteristics described by the target user portrait. field, each of the target user portraits includes at least one dimension of user information; Respectively determining target weight coefficients corresponding to the at least two target user portraits, and matching coefficients between the at least two target user portraits and the content to be recommended; determining the recommendation index corresponding to the target user according to the matching coefficient and the target weight coefficient corresponding to each target user portrait; When the recommendation index satisfies a preset recommendation condition, push the content to be recommended to the target user; The step of respectively determining the target weight coefficients corresponding to the at least two target user portraits and the matching coefficient between the at least two target user portraits and the content to be recommended includes: Based on the correspondence between the pre-stored user portrait and the weight coefficient, respectively determine the target weight coefficient corresponding to each of the target user portraits; For each dimension, from at least one preset condition corresponding to the dimension, determine the target preset condition that the user information under the dimension meets; wherein, each of the preset conditions is based on the user information under the corresponding dimension and the setting of the content to be recommended; Respectively determine the matching score corresponding to each of the target preset conditions; adding matching scores corresponding to each of the target preset conditions in the same target user portrait to obtain a matching coefficient between each of the target user portraits and the content to be recommended; Before the step of respectively determining the target weight coefficients corresponding to the at least two target user portraits and the matching coefficient between the at least two target user portraits and the content to be recommended, it also includes: determining at least two initial weight coefficients corresponding to each of the target user portraits; According to the A/B test strategy, adjusting the at least two initial weight coefficients to obtain a target weight coefficient; The corresponding relationship between each of the target user portraits and each of the target weight coefficients is stored. 2. The method according to claim 1, wherein the step of determining the recommendation index corresponding to the target user according to the matching coefficient and target weight coefficient corresponding to each target user portrait includes: multiplying the matching coefficient and the target weight coefficient corresponding to the same target user portrait to obtain a recommendation value corresponding to each of the target user portraits; Adding the recommendation values corresponding to each of the target user portraits to obtain the recommendation index corresponding to the target user. 3. The method according to claim 1, wherein the step of pushing the content to be recommended to the target user when the recommendation index satisfies a preset recommendation condition comprises: When the recommendation index is greater than or equal to a preset value, push the content to be recommended to the target user; and / or, When the ranking of the recommendation index in the recommendation index corresponding to each pre-selected user is less than or equal to the preset ranking, push the content to be recommended to the target user; sorted in order. 4. An electronic device, characterized in that, comprising: An acquisition module, configured to acquire the content to be recommended, and at least two target user portraits corresponding to the target user; wherein, the different target user portraits have different domain attributes, and the domain attributes are used to characterize the target user portraits The field to which the described features belong, each of the target user portraits includes at least one dimension of user information; A first determination module, configured to respectively determine target weight coefficients corresponding to the at least two target user portraits, and a matching coefficient between the at least two target user portraits and the content to be recommended; The second determination module is used to determine the recommendation index corresponding to the target user according to the matching coefficient and target weight coefficient corresponding to each target user portrait; A push module, configured to push the content to be recommended to the target user when the recommendation index satisfies a preset recommendation condition; The first determination module includes: The first determination sub-module is configured to respectively determine the target weight coefficient corresponding to each of the target user portraits based on the pre-stored correspondence between the user portrait and the weight coefficient; The second determining submodule is used to determine, for each dimension, from at least one preset condition corresponding to the dimension, the target preset condition that the user information under the dimension meets; wherein, each of the preset The condition is set based on the user information in the corresponding dimension and the content to be recommended; The third determining submodule is used to respectively determine the matching score corresponding to each of the target preset conditions; The first adding submodule is used to add the matching scores corresponding to each of the target preset conditions in the same target user portrait to obtain the relationship between each of the target user portraits and the content to be recommended The matching coefficient; The electronic equipment also includes: A third determination module, configured to determine at least two initial weight coefficients corresponding to each of the target user portraits; An adjustment module, configured to adjust the at least two initial weight coefficients according to an A/B test strategy to obtain a target weight coefficient; A storage module, configured to store the correspondence between each of the target user portraits and each of the target weight coefficients. 5. The electronic device according to claim 4, wherein the second determining module comprises: The multiplication sub-module is used to multiply the matching coefficient corresponding to the same target user portrait and the target weight coefficient to obtain the recommendation value corresponding to each target user portrait; The second adding sub-module is used to add the recommendation value corresponding to each target user portrait to obtain the recommendation index corresponding to the target user. 6. The electronic device according to claim 4, wherein the push module comprises: The first push submodule is used to push the content to be recommended to the target user when the recommendation index is greater than or equal to a preset value; and / or, The second push submodule is used to push the content to be recommended to the target user when the ranking ranking of the recommendation index in the recommendation index corresponding to each pre-selected user is less than or equal to the preset ranking; The recommended indexes are arranged in descending order. 7. An electronic device, characterized by comprising a processor, a memory, and a computer program stored on the memory and operable on the processor, when the computer program is executed by the processor, the The steps of the content recommendation method described in any one of requirements 1 to 3. 8. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the content according to any one of claims 1 to 3 is realized Steps in the recommended method.

Images