CN112685676B

CN112685676B - Information recommendation method and device and electronic equipment

Info

Publication number: CN112685676B
Application number: CN202011631562.8A
Authority: CN
Inventors: 王天雨
Original assignee: Huakong Tsingjiao Information Technology Beijing Co Ltd
Current assignee: Huakong Tsingjiao Information Technology Beijing Co Ltd
Priority date: 2020-12-30
Filing date: 2020-12-30
Publication date: 2023-12-15
Anticipated expiration: 2040-12-30
Also published as: CN112685676A

Abstract

The embodiment of the invention provides an information recommendation method, an information recommendation device and electronic equipment, wherein the method comprises the following steps: the ciphertext computing platform acquires user data of a common user in the supplier platform and user data of the common user in the demander platform, wherein the user data is ciphertext; carrying out data fusion on user data of the shared user on the basis of the ciphertext to generate a user tag of the shared user; acquiring supply information of a supplier platform and demand information of a demander platform; selecting a user tag of the target user from the user tags of the shared users based on the provisioning information on the basis of the ciphertext; judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext; if the demand information is matched with the user label of the target user and the supply information, recommending information for the target user in the supplier platform based on the demand information; and the accuracy of information recommendation can be improved on the premise of ensuring the safety of user data.

Description

Information recommendation method and device and electronic equipment

Technical Field

The present invention relates to the field of data processing, and in particular, to an information recommendation method, an apparatus, and an electronic device.

Background

Many platforms, such as video platforms, audio platforms, etc., provide some information display sites in their platform pages; merchants/businesses and the like can display information at the information display position by purchasing the information display position to realize propaganda.

Typically, the same user may use multiple platforms, such as multiple video platforms to view video, multiple audio platforms to play music, etc.; in order to ensure personal information safety of users, the platforms do not share user data. Because any platform only has part of user data of each user, the accuracy of information recommendation is lower when information recommendation is performed for the users in any platform. Therefore, how to improve the accuracy of information recommendation without revealing user information, so as to improve the propaganda effect of the information, and enable users in the platform to acquire interested information is one of the problems to be solved in the prior art.

Disclosure of Invention

The embodiment of the invention provides an information recommendation method, which is used for improving the accuracy of information recommendation under the condition of not revealing user information.

Correspondingly, the embodiment of the invention also provides an information recommending device and electronic equipment, which are used for guaranteeing the implementation and application of the method.

In order to solve the above problems, an embodiment of the present invention discloses an information recommendation method, which is applied to an information recommendation system, wherein the information recommendation system includes: ciphertext computing platform, supplier's platform and demand side's platform specifically include: the ciphertext computing platform acquires user data of a common user in the supplier platform and user data of a common user in the demander platform, wherein the user data is ciphertext, and the common user is a user owned by the supplier platform and the demander platform; carrying out data fusion on user data of a shared user on the basis of the ciphertext to generate a user tag of the shared user, wherein the user tag is the ciphertext; acquiring supply information of a supplier platform and demand information of a demander platform; selecting a user tag of the target user from the user tags of the common users based on the supply information on the basis of the ciphertext; judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext; and if the demand information is matched with the user tag and the supply information of the target user, recommending information for the target user in the provider platform based on the demand information.

Optionally, the user data of the common user includes a user identifier of the common user; the data fusion is carried out on the user data of the shared user on the basis of the ciphertext, so as to generate a user tag of the shared user, which comprises the following steps: acquiring service requirements; and carrying out at least one of the following analysis on the user data of the shared users on the basis of the ciphertext based on the service demand: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: a consumption category label, an interest label, and a payroll label; based on the ciphertext, based on at least one of the following tags of the sharing user: and generating a user tag of the common user by using the consumption type tag, the interest tag, the payroll tag and the user identifier of the common user.

Optionally, the common user is determined by the provider platform and the desirer platform based on privacy intersection techniques.

Optionally, the user data of the common user in the demand side platform includes: user identification and user characteristic information; the user data of the common user in the provider platform comprises: user identification and user behavior data.

Optionally, the user identification is a de-identification ID.

Optionally, the provisioning information includes: the user identification and the current browsing information of the corresponding user of each user identification; the user tag of the shared user includes: user identification and at least one of the following: a consumption category label, an interest label, and a payroll label; the selecting the user tag of the target user from the user tags of the common users based on the provisioning information on the basis of the ciphertext includes: selecting a user tag of a user with the same user identifier as the user identifier in the supply information from the user tags of the common users as a user tag of a target user; and updating the user tag of the target user based on the current browsing information of the target user on the basis of the ciphertext.

Optionally, the supply information further includes area information of an information display area, and the target user is a user corresponding to the information display area; the demand information comprises a user demand label and area demand information of an information display area; on the basis of the ciphertext, judging whether the demand information of the demand party is matched with the user tag and the supply information of the target user or not, comprising: matching the user tag of the target user with the user demand tag in the demand information on the basis of the ciphertext, and matching the region information in the supply information with the region demand information in the demand information on the basis of the ciphertext; if the user demand label in the demand information is matched with the user label of the target user and the region demand information in the demand information is matched with the region information in the supply information, determining that the demand information of the demand party is matched with the user label of the target user and the supply information of the supply party.

The embodiment of the invention also discloses an information recommendation device which is applied to an information recommendation system, wherein the information recommendation system comprises: ciphertext computing platform, supplier's platform and demand side's platform, the device dispose in ciphertext computing platform, specifically include: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring user data of a common user in a provider platform and user data of a common user in a demand side platform, wherein the user data is ciphertext, and the common user is a user owned by the provider platform and the demand side platform together; the fusion module is used for carrying out data fusion on the user data of the shared user on the basis of the ciphertext to generate a user tag of the shared user, wherein the user tag is the ciphertext; the second acquisition module is used for acquiring the supply information of the supplier platform and the demand information of the demander platform; the selecting module is used for selecting the user tag of the target user from the user tags of the common users based on the supply information on the basis of the ciphertext; the matching module is used for judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext; and the information recommendation module is used for recommending information to the target user in the provider platform based on the requirement information if the requirement information is matched with the user tag and the supply information of the target user.

Optionally, the user data of the common user includes a user identifier of the common user; the fusion module comprises: the service demand acquisition sub-module is used for acquiring service demands; and the data fusion sub-module is used for carrying out at least one of the following analysis on the user data of the shared users on the basis of the ciphertext based on the service demand: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: a consumption category label, an interest label, and a payroll label; the label generation sub-module is used for generating at least one label based on the shared user on the basis of the ciphertext: and generating a user tag of the common user by using the consumption type tag, the interest tag, the payroll tag and the user identifier of the common user.

Optionally, the user identification is a de-identification ID.

Optionally, the provisioning information includes: the user identification and the current browsing information of the corresponding user of each user identification; the user tag of the shared user includes: user identification and at least one of the following: a consumption category label, an interest label, and a payroll label; the selecting module comprises: the label selecting sub-module is used for selecting the user label of the user with the same user identification as the user identification in the supply information from the user labels of the common users as the user label of the target user; and the updating sub-module is used for updating the user tag of the target user based on the current browsing information of the target user on the basis of the ciphertext.

Optionally, the supply information further includes area information of an information display area, and the target user is a user corresponding to the information display area; the demand information comprises a user demand label and area demand information of an information display area; the matching module is used for matching the user tag of the target user with the user demand tag in the demand information on the basis of the ciphertext and matching the region information in the supply information with the region demand information in the demand information on the basis of the ciphertext; if the user demand label in the demand information is matched with the user label of the target user and the region demand information in the demand information is matched with the region information in the supply information, determining that the demand information of the demand party is matched with the user label of the target user and the supply information of the supply party.

The embodiment of the invention also discloses a readable medium, which enables the electronic device to execute the information recommendation method according to one or more of the embodiments of the invention when the instructions in the storage medium are executed by the processor of the electronic device.

The embodiment of the invention also discloses an electronic device, which comprises: one or more processors; and one or more readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform the information recommendation method as described in one or more of the embodiments of the invention described above.

Compared with the prior art, the embodiment of the invention has the following advantages:

in the embodiment of the invention, the ciphertext computing platform can respectively acquire the ciphertext of the user data of the common user in the supplier platform and the requester platform, and perform data fusion on the user data of the common user on the basis of the ciphertext to generate the user tag of the common user; the safety of user data in the supplier platform and the demander platform can be further ensured; then, after obtaining the supply information of the supplier platform and the demand information of the demander platform, selecting a user tag of a target user from user tags of the common users based on the supply information on the basis of ciphertext; judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext, and if the demand information is matched with the user tag and the supply information of the target user, recommending information for the target user in a provider platform on the basis of the demand information; and the accuracy of information recommendation is improved by performing information recommendation based on the fusion data of the users commonly owned by the provider platform and the requester platform.

Drawings

FIG. 1A is a block diagram of an embodiment of an information recommendation system of the present invention;

FIG. 1B is a flowchart illustrating steps of an embodiment of an information recommendation method of the present invention;

FIG. 2 is a flow chart of steps of an alternative embodiment of an information recommendation method of the present invention;

FIG. 3 is a block diagram of an embodiment of an information recommendation device of the present invention;

FIG. 4 is a block diagram of an alternative embodiment of an information recommendation device of the present invention;

fig. 5 schematically shows a block diagram of an electronic device for performing the method according to the invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

The information recommendation method of the embodiment of the invention can be applied to an information recommendation system, as shown in FIG. 1A. The information recommendation system may include: ciphertext computing platform, supplier platform and demand side platform. Wherein, the provider platform may refer to a platform of a provider, and the provider may be a video company, an audio company, a search company, etc., and the provider platform may be a video portal, an audio portal, a search website, etc.; the provider may publish information in the provider platform. The provider platform may provide an information presentation area that may be used to present information that may be recommended by the consumer, which may include a variety of information such as text, images, video, audio, etc., as embodiments of the invention are not limited in this respect. The provider platform can be used by users, and the users can browse and use the information issued by the provider and the information displayed in the information display area in the provider platform. The demander platform may refer to a demander's platform, which may refer to a user, such as an enterprise, a merchant, etc., who needs to present information of a desired recommendation in an information presentation area of the supplier platform. The demand side platform can refer to an enterprise official website, a merchant network shop and the like; the embodiments of the present invention are not limited in this regard; the requestor may publish information in a requestor platform. The demand side platform can also be used by users, and the users can browse and use the information issued by the demand side in the demand side platform. The ciphertext computing platform may be a platform capable of ciphertext operations; the information recommendation method of the embodiment of the invention can be executed by the ciphertext computing platform to recommend the information required by the demander platform to the user in the supplier platform.

One of the core ideas of the embodiment of the invention is that the ciphertext computing platform performs data fusion on the user data of the user in the supplier platform and the user data of the user in the demander platform on the basis of ciphertext; then, based on the fused data, determining a target user to be subjected to information recommendation in the provider platform, and recommending information required to be recommended by the demander for the target user; and further, accurate information recommendation can be realized, and the accuracy of information recommendation is improved, so that the propaganda effect can be improved, and the user in the platform can acquire interested information.

Referring to fig. 1B, a flowchart illustrating steps of an embodiment of an information recommendation method according to the present invention may specifically include the following steps:

step 102, the ciphertext computing platform obtains user data of a common user in the supplier platform and user data of a common user in the demander platform, wherein the user data is ciphertext, and the common user is a user commonly owned by the supplier platform and the demander platform.

Because the same user can be a user in the provider platform or a user in the demander platform; therefore, the user data of the user in the provider platform and the user data in the demand side platform can be fused to acquire more comprehensive user data of the user; and further, accurate information recommendation can be performed for the user. Wherein, the users in the provider platform may refer to all users using the provider platform, such as registered users, and such as users who only browse but are not registered; for example, the provider platform is a video portal, and the users of the video portal may include registered users of the video portal, or may include users who are browsing videos using only the video portal but are unregistered. The client platform may refer to all users using the client platform, such as registered users, and such as users who only browse but are not registered; for example, the consumer platform is a shopping website, and the user in the consumer platform may be a member of the shopping website or may be a user who uses only the shopping website to browse goods but is not registered.

The same user may be a user in both the supplier platform and the demander platform; it is also possible that only users in the provider platform, and also only users in the demand side platform. Thus, the provider platform and the demander platform may predetermine users that are commonly owned by both; user data of commonly owned users may then be uploaded to the ciphertext computing platform, respectively. Among them, for convenience of the following description, a user commonly owned by the provider platform and the demander platform may be referred to as a common user. The user data may include data related to information recommendation, such as user characteristic information, user behavior data, and the like, to which embodiments of the present invention are not limited.

In order to ensure the safety of the user data of the common user in the provider platform and the safety of the user data of the common user in the requester platform, the provider platform and the requester platform can encrypt the user data of the common user in the respective platforms; and uploading the user data encrypted by the common user to the ciphertext computing platform. And the ciphertext computing platform can receive the ciphertext of the user data of the common user uploaded by the supplier platform and the ciphertext of the user data of the common user uploaded by the requester platform.

And 104, carrying out data fusion on user data of the shared users on the basis of the ciphertext to generate user tags of the shared users, wherein the user tags are the ciphertext.

And then the ciphertext computing platform can perform ciphertext operation on the user data of the shared user uploaded by the supplier platform and the user data of the shared user uploaded by the requester platform by adopting a multiparty secure computing protocol, so as to fuse the user data of the shared user uploaded by the supplier platform and the user data of the shared user uploaded by the requester platform and obtain a user tag of the shared user. The user tags are also ciphertext, and may include a variety of categories, such as tags for uniquely identifying users, tags for characterizing user interests, tags for characterizing user purchasing trends, tags for characterizing user revenue levels, and so forth; the embodiments of the present invention are not limited in this regard. One common user may have a plurality of user tags, and one common user may have a plurality of user tags of one category.

Wherein the multiparty secure computing protocol may include a variety of protocols such as secret sharing, homomorphic encryption, etc., as embodiments of the invention are not limited in this regard.

And 106, acquiring the supply information of the supplier platform and the demand information of the demander platform.

When the demand side needs to recommend information in the provider platform, the demand side can upload demand information to the ciphertext computing platform through the demand side platform; the requirement information can be used for representing requirements for information recommendation at the provider platform; such as the content of the information recommendation, the form, frequency, time period, etc., to which the embodiments of the present invention are not limited. And the ciphertext computing platform can acquire the demand information of the demand side platform.

In the process of browsing and using information provided by a provider, a user in the provider platform can upload the supply information which can be provided by the provider platform to the ciphertext computing platform; the provisioning information may include information related to information that needs to be recommended in the provider platform by the displaying of the demander, such as area information of an information display area, user characteristic information of a user who can view the information display area, and so on, to which embodiments of the present invention are not limited. The ciphertext computing platform can further acquire the supply information of the supplier platform; it may then be determined whether to be a user in the provider platform based on the supply information uploaded by the provider platform and the demand information uploaded by the demand platform, and the information required by the demand party may be pushed, referring to steps 108-112.

The demand information can be plaintext or ciphertext; the provisioning information may be ciphertext.

And 108, selecting the user tag of the target user from the user tags of the common users based on the provisioning information on the basis of the ciphertext.

And step 110, judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext.

And 112, if the demand information is matched with the user tag and the supply information of the target user, recommending information for the target user in the provider platform based on the demand information.

In the embodiment of the invention, the target user to be subjected to information recommendation can be selected from the provider platform; and then judging whether information recommendation is required to be performed for the target user, and performing information recommendation for the target user when the information recommendation is determined to be required to be performed for the target user.

One way to select the target user to be recommended from the provider platform may be to determine the target user based on the supply information uploaded by the provider platform on the basis of the ciphertext. And then selecting the user label of the target user from the user labels of the common users.

One way to determine whether information recommendation is required for the target user may be to determine, based on ciphertext, whether the demand information is matched with both the user tag and the supply information of the target user. That is, it is determined whether the demand of the demand side platform matches the information of the supply side platform. When the demand information is matched with the user tag and the supply information of the target user, recommendation information can be generated based on the demand information; recommending the recommendation information for the target user in the provider platform; the recommendation information may be presented, for example, in an information presentation area of the provider platform.

In summary, in the embodiment of the invention, the ciphertext computing platform can respectively acquire ciphertext of user data of a common user in the supplier platform and the requester platform, and perform data fusion on the user data of the common user on the basis of the ciphertext to generate a user tag of the common user; the safety of user data in the supplier platform and the demander platform can be further ensured; then, after obtaining the supply information of the supplier platform and the demand information of the demander platform, selecting a user tag of a target user from user tags of the common users based on the supply information on the basis of ciphertext; judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext, and if the demand information is matched with the user tag and the supply information of the target user, recommending information for the target user in a provider platform on the basis of the demand information; and the accuracy of information recommendation is improved by performing information recommendation based on the fusion data of the users commonly owned by the provider platform and the requester platform.

The following describes how the supplier platform and the demander platform determine a co-user.

In the embodiment of the invention, in order to ensure the personal information safety of the users in the provider platform and the demand side platform, the personal information of the users in the provider platform and the demand side platform can be subjected to de-identification processing to obtain the corresponding de-identification ID of each user; the de-identification ID may be used to uniquely represent the user. Here, de-identification may refer to a process of making it impossible to associate or identify a personal information body by processing the personal information without additional information. Based on the individual user, the technology such as pseudonym, encryption, hash function and the like can be adopted to replace the identification of personal information.

In one example of the present invention, the provider platform may de-identify the personal information of the user therein to obtain a corresponding de-identified ID; and the user data of the user can be de-identified by the demand side platform to obtain a corresponding de-identification ID. The provider platform and the demander platform can cooperatively establish a unified de-identification scheme to cooperatively de-identify personal information of users in the respective platforms; and the de-identification IDs of the same user on the supplier platform and the demander platform are the same.

Of course, the supplier platform and the demander platform can cooperate to de-identify the personal information of the user in the respective platforms without establishing a unified de-identification scheme; and the de-identification IDs of the same user on the supplier platform and the demander platform are different. At this time, the provider platform and the requester platform hold the de-identification ID and the ciphertext of the corresponding relationship of the user in the respective platforms; the correspondence may refer to a relationship between the de-identification IDs of the same user in the provider platform and the demander platform.

In one example of the invention, the provider platform and the demander platform upload personal information of the user therein to the de-identification platform; and then the de-identification platform can respectively de-identify the personal information of the user in the provider platform to obtain the corresponding de-identification ID. And the de-identification platform is used for de-identifying the personal information of the user in the demand side platform respectively to obtain the corresponding de-identification ID. The de-identification platform can use a unified de-identification scheme to de-identify users in the provider platform and the demander platform respectively; at this time, the de-identification ID of the same user in the provider platform and the demander platform is the same. The de-identification platform may then return the de-identification ID of the user in the provider platform to the provider platform and the de-identification ID of the user in the consumer platform to the consumer platform. Of course, the de-identification platform can also use a non-uniform de-identification scheme to de-identify the users in the provider platform and the demander platform respectively; the de-identification ID of the same user in the provider platform and the demander platform are not identical. At this time, the de-identification platform may hold the de-identification ID of each user in the supplier platform and the demander platform, and the correspondence relationship of the de-identification IDs; the de-identification ID of the user in the supplier platform may then be returned to the supplier platform in a corresponding relationship, and the de-identification ID of the user in the demander platform may be returned to the demander platform in a corresponding relationship.

The personal information may include various information such as a device identification number, a device fingerprint, a browser fingerprint, a cookie (data stored on a local terminal of the user) and the like which are indirectly associated with the user, and information such as a personal identification card, a telephone number, a social network account and the like which are directly associated with the user; the service requirement of the demander can be specifically determined, and the embodiment of the invention is not limited to this.

In an alternative embodiment of the present invention, the common user is determined by the provider platform and the demander platform based on privacy intersection techniques. When the de-identification IDs of the same user in the demand side platform and the supply side platform are the same, and the demand side platform and the supply side platform do not obtain the de-identification IDs of the shared user, the supply side platform and the demand side platform can determine intersection sets of the respectively held de-identification IDs based on a privacy intersection technology to obtain intersection sets. The intersection set comprises a plurality of de-identification IDs, and one de-identification ID corresponds to one common user. When the de-identification IDs of the same user in the demand side platform and the supply side platform are the same, but the de-identification IDs of the common user are obtained, the demand side platform and the supply side platform each hold a juncture set of the de-identification IDs of the common user. At this time, when the de-identification ID of the user in the demand side platform or the supply side platform is updated, the supply side platform and the demand side platform determine the intersection of the de-identification IDs held by the demand side platform and the supply side platform based on the privacy intersection technology, so as to obtain an intersection set.

When the de-identification IDs of the same user in the demand side platform and the supply side platform are different, the supply side platform and the demand side platform can cooperate with ciphertext based on the corresponding relation to calculate an intersection of the de-identification IDs, and an intersection set of the de-identification IDs is obtained. In one example, the intersection set includes the de-identification IDs of the common users and the corresponding relationships. In one example, the intersection set obtained by the supplier platform may include the de-identification ID of the common user in the present platform, and the intersection set obtained by the demander platform may include the de-identification ID of the common user in the present platform.

Referring to fig. 2, a flowchart of steps of an alternative embodiment of an information recommendation method of the present invention is shown.

Step 202, a ciphertext computing platform acquires user data of a common user in a provider platform and user data of a common user in a demand side platform, wherein the user data is ciphertext, and the common user is a user commonly owned by the provider platform and the demand side platform.

In the embodiment of the present invention, the user data of the common user in the demand side platform may include: user identification and user characteristic information. The user identifier may be used to uniquely identify a user, and may be an identifier ID, and the user feature information may include information describing a user feature, such as age, gender, occupation, region, learning, specialty, wedding, login terminal, social circle, search record, browse record, purchase interaction, and focus on a subject (such as celebrity, entertainment, sports, and financing, etc.), which is not limited in the embodiment of the present invention.

In the embodiment of the present invention, the user data of the common user in the provider platform includes: user identification and user behavior data. The user identifier may be used to uniquely identify the user, and may be an identifier ID, and the user behavior data may be used to describe a behavior of the user in the provider platform, such as click information, browse duration, share information, comment information, and so on, where the browse information may include browse information for the recommended information displayed in the information display area, and the click information may include click information for the recommended information displayed in the information display area, and so on.

The user identification of the common user in the supplier platform and the user identification of the common user in the demander platform can be the same or different; the method is specifically determined according to the manner of de-identifying personal information in the provider platform and the requester platform, and the embodiment of the invention is not limited thereto.

Then the ciphertext computing platform can fuse the user data of the common user uploaded by the supplier platform and the user data uploaded by the demander platform; reference may be made to steps 204-208.

Step 204, obtaining the service requirement.

Step 206, based on the service requirement, at least one of the following analysis is performed on the user data of the shared user on the basis of the ciphertext: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: consumer category labels, interest labels, payroll labels.

Step 208, based on the ciphertext, based on at least one of the following of the sharing user: and generating a user tag of the common user by using the consumption type tag, the interest tag, the payroll tag and the user identifier of the common user.

In the embodiment of the invention, the ciphertext computing platform can acquire the service requirement of the requiring party, such as service type, service-oriented object and the like; and then based on the service requirement of the requiring party, fusing the user data of the common user uploaded by the provider platform and the user data uploaded by the requiring party platform on the basis of the ciphertext.

In the embodiment of the invention, various types of labels, such as a consumption category label, an interest label and a payroll label, can be preset. Wherein the consumption category label may be used to characterize a user's purchasing propensity; a variety of consumer category labels may be preset, such as: infant products, luxury products, travel, educational training, financial management products, pets, health products, real estate, automobiles, and the like. The interest tag can be used for representing the interests of a user, and various interest tags such as games, job hunting, various kinds of products, marriage, fashion, entertainment, training, financial, education, insurance, job stadium, insurance, endowment, health care, medical treatment and the like can be preset. The salary tag may be used to characterize the income level of the user, and various salary tags may be preset, such as high salary, medium salary, low salary, etc., which are not limited by the embodiment of the present invention.

The ciphertext computing platform may then perform at least one of the following analyses on the user data of the shared user based on the ciphertext: interest analysis, consumption category analysis and salary analysis; that is, analyzing interests, consumption categories, salary levels, etc. of the sharing users; correspondingly, at least one of the following labels of the shared user can be obtained: consumer category labels, interest labels, payroll labels. Wherein, according to the analysis result of the consumption category analysis, the consumption category of which the consumption frequency of the common user is more than the frequency threshold value can be determined; and taking the consumption class label corresponding to the consumption class of which the consumption frequency of the common user is larger than the frequency threshold value as the consumption class label of the common user. Wherein, the frequency threshold may be set according to requirements, which is not limited by the embodiment of the present invention. The consumer category labels of the shared users may include one or more of the consumer category labels described above. According to the analysis result of interest analysis, determining the interests with the common user interest degree higher than an interest degree threshold; and taking the interest label corresponding to the interest with the interest degree higher than the interest degree threshold value of the common user as the interest label of the common user. The interestingness threshold may be set as required, which is not limited by the embodiment of the present invention. The common user's interest tags may include one or more of the interest tags described above. And determining the section to which the common user salary belongs according to the analysis result of interest analysis; and the salary label corresponding to the interval to which the shared user salary belongs is used as the salary label of the shared user. The payroll labels of the shared users may include one or more of the payroll labels described above.

One or two kinds of analysis can be performed on the user data of the shared user on the basis of the ciphertext according to the service requirement; all of the above analyses may also be performed; and in particular, may be determined according to service requirements, which is not limited by embodiments of the present invention.

Any of the above analyses may be ciphertext-based clustering, classification, or the like; the embodiments of the present invention are not limited in this regard.

At least one of the consumption category label, the interest label, and the payroll label, and the user identification of the shared user may then be employed to generate a user label of the shared user.

Step 210, obtaining the supply information of the supplier platform and the demand information of the demander platform.

In the embodiment of the invention, when the demander needs to make information recommendation in the information display area of the supplier platform, the demander platform can determine the requirement of the demander information recommendation for the user and determine the requirement of the demander information recommendation for the information display area. Then, a user demand label can be generated based on the user-oriented requirement of the information recommendation, and region demand information can be generated based on the requirement of the information recommendation on the information display region; and generating the demand information based on the user demand label and the regional demand information. In one example, the demand information may include a user demand label and area demand information. The user demand label may include any one or more of the consumer category labels described above, and/or any one or more of the interest labels, and/or any one or more of the salary labels.

In the embodiment of the invention, when determining that the information recommendation can be performed for the user, the provider platform can determine the area information of the information display area capable of performing the information recommendation, the user corresponding to the information display area capable of performing the information recommendation, and the current browsing information of the user corresponding to the information display area capable of performing the information recommendation. The user corresponding to the information display area capable of performing information recommendation may be a user who can browse the recommended information displayed in the information display area capable of performing information recommendation when the information display area capable of performing information recommendation displays recommended information. And then the provider platform can generate and upload the supply information to the ciphertext computing platform based on the area information of the information display area, the user identification of the user corresponding to the information display area and the current browsing information of the user corresponding to the information display area. Wherein the provisioning information may include: the information display area comprises area information of the information display area, user identifiers and current browsing information of corresponding users of the user identifiers.

Then, the ciphertext computing platform may select the user tag of the target user from the user tags of the shared users based on the provisioning information, and may refer to steps 212 to 214:

Step 212, selecting the user tag of the user with the same user identification as the user identification in the provisioning information from the user tags of the common users as the user tag of the target user.

Step 214, updating the user tag of the target user based on the current browsing information of the target user on the basis of the ciphertext.

In the embodiment of the invention, the user tag of the shared user comprises a user identifier, and the supply information comprises the user identifier; and the user identification in the supply information can be compared with the user identification included in the user label of the common user. Then, the user identification in the user tag is the same as the user identification in the supply information, and the user is determined to be the target user; and then the user label of the target user can be selected from the user labels of the shared users.

In the embodiment of the invention, based on the current browsing information of the target user and the user data of the target user in the provider platform and the user data of the target user in the demand platform, at least one of the following analysis can be performed again: interest analysis, consumption category analysis and salary analysis; determining at least one of the following tags of the target user: consumer category labels, interest labels, payroll labels. And then judging whether the label determined based on the current browsing information of the target user is the same as the label of the target user determined in the steps 204-208. If the tag determined based on the current browsing information of the target user is the same as the tag of the target user determined in the above steps 204 to 208, the user tag of the target user may not need to be updated. If the tag determined based on the current browsing information of the target user is different from the tag of the target user determined in the above steps 204 to 208, the tag determined based on the current browsing information of the target user may be used to update the user tag of the target user determined in the above steps 204 to 208. And further, more accurate user labels of the target users can be determined.

Then, referring to steps 216 to 218, it may be determined whether the demand information of the demand party is matched with the user tag and the supply information of the target user; and further judging whether recommendation information corresponding to the requirement information of the requirement party needs to be recommended to the target user.

Step 216, matching the user tag of the target user with the user demand tag in the demand information on the basis of the ciphertext, and matching the region information in the supply information with the region demand information in the demand information on the basis of the ciphertext.

Step 218, if the user requirement label in the requirement information is matched with the user label of the target user, and the region requirement information in the requirement information is matched with the region information in the supply information, recommending information for the target user in the supplier platform based on the requirement information.

In the embodiment of the invention, the user tag of the target user except the user identifier can be matched with the user demand tag in the demand information on the basis of the ciphertext, and the region information in the supply information can be matched with the region demand information in the demand information on the basis of the ciphertext. If the user label of the target user comprises all user demand labels in the demand information; or the user demand label with the preset ratio in the demand information is contained, the user demand label in the demand information can be determined to be matched with the user label of the target user; otherwise, it may be determined that the user requirement label in the requirement information does not match the user label of the target user. The preset ratio may be set according to requirements, such as 80%, which is not limited in the embodiment of the present invention. The matching degree of the region information in the supply information and the region demand information in the demand information can be calculated on the basis of the ciphertext; when the matching degree of the regional information in the supply information and the regional requirement information in the requirement information is larger than a matching degree threshold value, the regional requirement information in the requirement information and the regional information in the supply information can be determined to be matched; otherwise, determining that the region demand information in the demand information does not match the region information in the supply information.

When the user demand label in the demand information is matched with the user label of the target user, and the region demand information in the demand information is matched with the region information in the supply information, the demand information of the demand party can be determined to be matched with the user label of the target user and the supply information of the supply party; at this time, the recommended information corresponding to the requirement information can be obtained, and then when the information display area corresponding to the regional information in the supply information is displayed by the supplier platform, the recommended information is displayed in the information display area.

The requirement information can include recommendation information, and then the ciphertext computing platform can directly acquire the recommendation information from the requirement information. When the requirement information does not include the recommendation information, the ciphertext computing platform can generate corresponding recommendation information based on the requirement information; the ciphertext computing platform can also send the demand information to other platforms, and the other platforms generate the recommendation information based on the demand information and return the recommendation information to the ciphertext computing platform; the embodiments of the present invention are not limited in this regard.

In summary, in the embodiment of the invention, the service requirement can be acquired; and then, based on the service requirement, carrying out at least one of the following analysis on the user data of the shared user on the basis of the ciphertext: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: a consumption category label, an interest label, and a payroll label; based on the ciphertext, at least one of the following labels of the shared user is based on: the method comprises the steps of generating a user label of a common user by using a consumption category label, an interest label, a payroll label and a user identifier of the common user; and then can generate user's label based on the business demand of demand side to follow-up demand that can be better laminating demand side carries out information recommendation, improves information recommendation's accuracy.

Secondly, in the embodiment of the invention, the user tag of the target user can be matched with the user demand tag in the demand information on the basis of the ciphertext, and the region information in the supply information can be matched with the region demand information in the demand information on the basis of the ciphertext; when a user demand label in demand information is matched with a user label of a target user, and region demand information in demand information is matched with region information in supply information, information recommendation is carried out for the target user in a supplier platform based on the demand information; further, when the regional information of the information display region in the supplier platform and the user of the information display region are matched with the requirements of the demander platform, information recommendation is performed; therefore, the information recommendation effect can be maximized, the information of interest can be recommended to the user, and the user experience is improved.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

The embodiment of the invention also provides an information recommendation device, which is applied to an information recommendation system, wherein the information recommendation system comprises: the device comprises a ciphertext computing platform, a supplier platform and a demander platform, wherein the device is deployed in the ciphertext computing platform.

Referring to fig. 3, a block diagram of an embodiment of an information recommendation device according to the present invention is shown, which may specifically include the following modules:

the first obtaining module 302 is configured to obtain user data of a common user in the provider platform and user data of a common user in the requester platform, where the user data is ciphertext, and the common user is a user owned by the provider platform and the requester platform;

the fusion module 304 is configured to perform data fusion on user data of a common user on the basis of the ciphertext, and generate a user tag of the common user, where the user tag is the ciphertext;

a second obtaining module 306, configured to obtain supply information of the supplier platform and demand information of the demander platform;

a selecting module 308, configured to select a user tag of a target user from user tags of the common users based on the provisioning information on the basis of the ciphertext;

a matching module 310, configured to determine, based on the ciphertext, whether the demand information is matched with the user tag and the supply information of the target user;

And the information recommending module 312 is configured to recommend information to the target user in the provider platform based on the requirement information if the requirement information is matched with the user tag and the supply information of the target user.

Referring to fig. 4, a block diagram of an alternative embodiment of an information recommendation device of the present invention is shown.

In an optional embodiment of the present invention, the user data of the common user includes a user identifier of the common user; the fusion module 304 includes:

a service requirement acquisition sub-module 3042, configured to acquire a service requirement;

the data fusion submodule 3044 is configured to perform at least one of the following analysis on user data of the shared user on the basis of the ciphertext based on the service requirement: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: a consumption category label, an interest label, and a payroll label;

a tag generation sub-module 3046 for generating, based on the ciphertext, at least one of the following tags for the sharing user: and generating a user tag of the common user by using the consumption type tag, the interest tag, the payroll tag and the user identifier of the common user.

In an alternative embodiment of the present invention, the common user is determined by the provider platform and the demander platform based on privacy intersection techniques.

In an optional embodiment of the present invention, the user data of the common user in the demand side platform includes: user identification and user characteristic information; the user data of the common user in the provider platform comprises: user identification and user behavior data.

In an alternative embodiment of the present invention, the user identifier is a de-identifier ID.

In an alternative embodiment of the present invention, the provisioning information includes: the user identification and the current browsing information of the corresponding user of each user identification; the user tag of the shared user includes: user identification and at least one of the following: a consumption category label, an interest label, and a payroll label; the selecting module 308 includes:

the tag selection submodule 3082 is used for selecting the user tag of the user with the same user identifier as the user identifier in the supply information from the user tags of the shared users as the user tag of the target user;

and an updating sub-module 3084, configured to update the user tag of the target user based on the current browsing information of the target user on the basis of the ciphertext.

In an optional embodiment of the present invention, the provisioning information further includes area information of an information display area, and the target user is a user corresponding to the information display area;

The demand information comprises a user demand label and area demand information of an information display area;

the matching module 310 is configured to match a user tag of the target user with a user demand tag in demand information on the basis of ciphertext, and match region information in supply information with region demand information in demand information on the basis of ciphertext; if the user demand label in the demand information is matched with the user label of the target user and the region demand information in the demand information is matched with the region information in the supply information, determining that the demand information of the demand party is matched with the user label of the target user and the supply information of the supply party.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The embodiment of the invention also provides a readable medium, which enables the electronic device to execute the information recommendation method according to one or more of the embodiments of the invention when the instructions in the storage medium are executed by the processor of the electronic device.

The embodiment of the invention also provides electronic equipment, which comprises: one or more processors; and one or more readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform the information recommendation method as described in one or more of the embodiments of the invention described above.

In an example of an embodiment of the present invention, an electronic device, such as a server, fig. 5 shows that a server according to the present invention may be implemented, such as a management server, a storage server, an application server, a cloud control service, a server cluster, etc. The server conventionally comprises a processor 510 and a computer program product or computer readable medium in the form of a memory 520. The memory 520 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 520 has a memory space 530 for program code 531 for performing any of the method steps described above. For example, the memory space 530 for the program code may include respective program code 531 for implementing the respective steps in the above method, respectively. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such computer program products are typically portable or fixed storage units. The storage unit may have a memory segment, a memory space, or the like arranged similarly to the memory 520 in the server of fig. 5. The program code may be compressed, for example, in a suitable form. Typically, the storage unit comprises computer readable code, i.e. code that can be read by a processor such as 510, for example, which when executed by a server causes the server to perform the steps in the method described above.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.

The above description of an information recommendation method, an information recommendation device and an electronic device provided by the present invention applies specific examples to illustrate the principles and embodiments of the present invention, and the above description of the examples is only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. An information recommendation method is applied to an information recommendation system, and the information recommendation system comprises: the system comprises a ciphertext computing platform, a supplier platform and a demander platform, wherein the demander is a user who needs to display required recommendation information in an information display area of the supplier platform, and the method comprises the following steps:

the ciphertext computing platform obtains user data of a common user in the supplier platform and user data of a common user in the requester platform, wherein the user data is ciphertext, the common user is a user commonly owned by the supplier platform and the requester platform, and the user data of the common user in the requester platform comprises: user identification and user characteristic information, wherein the user data of the common user in the provider platform comprises: user identification and user behavior data;

carrying out data fusion on user data of a shared user on the basis of the ciphertext to generate a user tag of the shared user, wherein the user tag is the ciphertext;

acquiring supply information of a supplier platform and demand information of a demander platform; wherein the provisioning information includes: the user identification and the current browsing information of the corresponding user of each user identification;

Selecting a user tag of the target user from the user tags of the common users based on the supply information on the basis of the ciphertext;

judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext;

and if the demand information is matched with the user tag and the supply information of the target user, recommending information for the target user in the provider platform based on the demand information.

2. The method of claim 1, wherein the user data of the common user comprises a user identification of the common user; the data fusion is carried out on the user data of the shared user on the basis of the ciphertext, so as to generate a user tag of the shared user, which comprises the following steps:

acquiring service requirements;

and carrying out at least one of the following analysis on the user data of the shared users on the basis of the ciphertext based on the service demand: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: a consumption category label, an interest label, and a payroll label;

based on the ciphertext, based on at least one of the following tags of the sharing user: and generating a user tag of the common user by using the consumption type tag, the interest tag, the payroll tag and the user identifier of the common user.

3. The method of claim 1, wherein the common user is determined by a provider platform and a requester platform based on a privacy trading technique.

4. The method of claim 1, wherein the user identification is a de-identification ID.

5. The method of claim 1, wherein the step of determining the position of the substrate comprises,

the user tag of the shared user includes: user identification and at least one of the following: a consumption category label, an interest label, and a payroll label;

the selecting the user tag of the target user from the user tags of the common users based on the provisioning information on the basis of the ciphertext includes:

selecting a user tag of a user with the same user identifier as the user identifier in the supply information from the user tags of the common users as a user tag of a target user;

and updating the user tag of the target user based on the current browsing information of the target user on the basis of the ciphertext.

6. The method of claim 1, wherein the provisioning information further comprises area information for an information presentation area, the target user being a user corresponding to the information presentation area;

On the basis of the ciphertext, judging whether the demand information of the demand party is matched with the user tag and the supply information of the target user or not, comprising:

matching the user tag of the target user with the user demand tag in the demand information on the basis of the ciphertext, and matching the region information in the supply information with the region demand information in the demand information on the basis of the ciphertext;

if the user demand label in the demand information is matched with the user label of the target user and the region demand information in the demand information is matched with the region information in the supply information, determining that the demand information of the demand party is matched with the user label of the target user and the supply information of the supply party.

7. An information recommendation device, which is applied to an information recommendation system, the information recommendation system comprising: the device is deployed in the ciphertext computing platform, the demander is a user who needs to display the required recommendation information in the information display area of the supplier platform, and the device comprises:

the first acquisition module is configured to acquire user data of a common user in a provider platform and user data of a common user in a requester platform, where the user data is ciphertext, the common user is a user commonly owned by the provider platform and the requester platform, and the user data of the common user in the requester platform includes: user identification and user characteristic information, wherein the user data of the common user in the provider platform comprises: user identification and user behavior data;

The fusion module is used for carrying out data fusion on the user data of the shared user on the basis of the ciphertext to generate a user tag of the shared user, wherein the user tag is the ciphertext;

the second acquisition module is used for acquiring the supply information of the supplier platform and the demand information of the demander platform; wherein the provisioning information includes: the user identification and the current browsing information of the corresponding user of each user identification;

the selecting module is used for selecting the user tag of the target user from the user tags of the common users based on the supply information on the basis of the ciphertext;

the matching module is used for judging whether the demand information is matched with the user tag and the supply information of the target user or not on the basis of the ciphertext;

and the information recommendation module is used for recommending information to the target user in the provider platform based on the requirement information if the requirement information is matched with the user tag and the supply information of the target user.

8. The apparatus of claim 7, wherein the user data of the common user comprises a user identification of the common user;

the fusion module comprises:

the service demand acquisition sub-module is used for acquiring service demands;

And the data fusion sub-module is used for carrying out at least one of the following analysis on the user data of the shared users on the basis of the ciphertext based on the service demand: interest analysis, consumption category analysis and salary analysis to obtain at least one of the following labels for the sharing user: a consumption category label, an interest label, and a payroll label;

the label generation sub-module is used for generating at least one label based on the shared user on the basis of the ciphertext: and generating a user tag of the common user by using the consumption type tag, the interest tag, the payroll tag and the user identifier of the common user.

9. The apparatus of claim 7, wherein the common user is determined by the provider platform and the requester platform based on a privacy trading technique.

10. The apparatus of claim 7, wherein the user identification is a de-identification ID.

11. The apparatus of claim 7, wherein the device comprises a plurality of sensors,

the selecting module comprises:

the label selecting sub-module is used for selecting the user label of the user with the same user identification as the user identification in the supply information from the user labels of the common users as the user label of the target user;

And the updating sub-module is used for updating the user tag of the target user based on the current browsing information of the target user on the basis of the ciphertext.

12. The apparatus of claim 11, wherein the device comprises a plurality of sensors,

the supply information further comprises area information of an information display area, and the target user is a user corresponding to the information display area;

the matching module is used for matching the user tag of the target user with the user demand tag in the demand information on the basis of the ciphertext and matching the region information in the supply information with the region demand information in the demand information on the basis of the ciphertext; if the user demand label in the demand information is matched with the user label of the target user and the region demand information in the demand information is matched with the region information in the supply information, determining that the demand information of the demand party is matched with the user label of the target user and the supply information of the supply party.

13. A readable medium, characterized in that instructions in the readable medium, when executed by a processor of an electronic device, enable the electronic device to perform the information recommendation method according to any of the method claims 1-6.

14. An electronic device, comprising:

one or more processors; and

one or more readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform the information recommendation method of any of claims 1-6.