CN111914188A - Method, system, device and storage medium for selecting recommendation target user - Google Patents
Method, system, device and storage medium for selecting recommendation target user Download PDFInfo
- Publication number
- CN111914188A CN111914188A CN202010834920.9A CN202010834920A CN111914188A CN 111914188 A CN111914188 A CN 111914188A CN 202010834920 A CN202010834920 A CN 202010834920A CN 111914188 A CN111914188 A CN 111914188A
- Authority
- CN
- China
- Prior art keywords
- target user
- user
- recommended
- item
- alternative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Recommending goods or services
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Circuits Of Receivers In General (AREA)
Abstract
The invention provides a selection method, a system, equipment and a storage medium of a recommendation target user, wherein the method comprises the following steps: acquiring information of an article to be recommended; acquiring a related user of a recommender from a social platform, taking the related user as an alternative target user for recommending the article, and acquiring user information of the alternative target user; selecting a recommendation target user of an article to be recommended from the alternative target users according to the article information to be recommended and the user information of the alternative target users; and pushing the recommendation target user information to the user terminal of the recommender. According to the method and the device, when the articles are recommended based on the social platform, the recommenders who have high probability of accepting the articles are selected, the recommendation conversion rate is improved, and the recommenders are prevented from receiving too much useless information.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, a system, a device, and a storage medium for selecting a recommendation target user.
Background
In order to increase the shipping volume, merchants are generally willing to give more favorable prices to stimulate purchases for consumers with large purchases. The existing group purchase of consumers is mostly limited by regions, and often neighbors of the same cell or colleagues of the same company purchase together to obtain a group purchase price; with the development of networks and logistics, some shopping platforms can also provide the function of online group opening and list combination, can directly join group buying ranks from the networks, and can be respectively distributed to different areas, so that the limitation of the areas is broken.
For example, in the prior art, in order to successfully improve the shipment volume and also assist the consumer to successfully obtain the group purchase price and increase the dependency on the platform, the shopping platform fuses the e-commerce and the social contact, so that the user can send the selection of the recommendation target user to family and friends through the social contact platform to group together and purchase the commodity with a preferential price.
However, if the general user does not have individual inquiry, he or she cannot know whether the recommended goods are needed by family or friend, if the recommendation information is widely sent to obtain the group purchase price, the unwanted goods information will be received by most recommenders, and too many useless recommendations may cause troubles to friends, even affect the recommenders' evaluation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a selection method, a system, equipment and a storage medium for recommending target users, which are used for selecting a recommended person who has high probability of accepting articles when articles are recommended on the basis of a social platform, so that the recommendation conversion rate is improved, and the recommended person is prevented from receiving too much useless information.
The embodiment of the invention provides a selection method of a recommendation target user, which comprises the following steps:
acquiring information of an article to be recommended;
acquiring a related user of a recommender from a social platform, taking the related user as an alternative target user for recommending the article, and acquiring user information of the alternative target user;
selecting a recommendation target user of an article to be recommended from the alternative target users according to the article information to be recommended and the user information of the alternative target users;
and pushing the recommendation target user information to the user terminal of the recommender.
Optionally, determining a recommendation target user of the item to be recommended according to the item information to be recommended and the user information of the alternative target user, including the following steps:
acquiring a historical behavior log of each alternative target user on a shopping platform;
and determining whether the alternative target user is a recommendation target user of the item to be recommended or not according to the historical behavior log of the alternative target user.
Optionally, determining whether the alternative target user is a recommendation target user of the item to be recommended according to the historical behavior log of the alternative target user, including the following steps:
determining the associated articles of the alternative target users according to the historical behavior logs of the alternative target users;
judging whether the item to be recommended belongs to the associated item of the alternative target user;
if so, the alternative target user is the recommendation target user of the item to be recommended.
Optionally, determining whether the alternative target user is a recommendation target user of the item to be recommended according to the historical behavior log of the alternative target user, including the following steps:
determining the associated articles of the alternative target users according to the historical behavior logs of the alternative target users;
querying similar items of the associated items in an item model according to the associated items, wherein the item model is configured to store the similar items of each item;
judging whether the item to be recommended belongs to the associated item of the alternative target user or a similar item of the associated item;
if so, the alternative target user is the recommendation target user of the item to be recommended.
Optionally, after obtaining the historical behavior log of each candidate target user on the shopping platform, the method further includes the following steps:
if the historical behavior log of the alternative target user is not acquired or the historical behavior log of the alternative target user does not accord with a preset log analysis condition, inquiring similar users of the alternative target user according to a user model, wherein the user model is configured to store the similar users of all users;
querying related items of similar users of the alternative target users;
judging whether the item to be recommended belongs to the associated item of the similar user of the alternative target user;
if so, the alternative target user is the recommendation target user of the item to be recommended.
Optionally, determining the associated item of the alternative target user according to the historical behavior log of the alternative target user includes the following steps:
when the alternative target user is a group, acquiring historical behavior logs of all single users in the group;
and determining the associated articles of the group according to the historical behavior logs of all the single users in the group as the associated articles of the group.
Optionally, the method further comprises the steps of:
after sending the item recommendation information to the recommendation target user, acquiring feedback data of the recommendation target user;
and adjusting the associated item corresponding to the recommendation target user according to the feedback data.
The embodiment of the invention also provides a selection system of a recommendation target user, which is used for realizing the selection method of the recommendation target user and is characterized in that the system comprises the following components:
the article information acquisition module is used for acquiring article information to be recommended;
the alternative user acquisition module is used for acquiring the associated user of the recommender from the social platform, taking the associated user as an alternative target user for recommending the article, and acquiring the user information of the alternative target user;
the target user selection module is used for selecting a recommendation target user of the item to be recommended from the alternative target users according to the information of the item to be recommended and the user information of the alternative target users;
and the target user pushing module is used for pushing the recommended target user information to the user terminal of the recommender.
An embodiment of the present invention further provides a device for selecting a recommended target user, including:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the method of recommending target user selection via execution of the executable instructions.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the method for selecting a recommendation target user when executed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
The selection method, the system, the equipment and the storage medium of the recommendation target user have the following beneficial effects:
according to the method and the device, when the object is recommended based on the social platform, the target user for recommending the object is selected from the social platform friends of the recommender through the relevance between the user and the object, so that the recommender with high probability of receiving the object can be selected, the probability of recommending the wrong object is greatly reduced, the recommendation conversion rate is improved, the recommendation information received by the recommender is more interesting for the recommender with high probability, the recommender can be prevented from receiving too much useless information, the use experience of the user is improved, and the waste of the object recommendation flow is also avoided.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method of selecting a recommendation target user in accordance with an embodiment of the present invention;
FIG. 2 is an interface diagram of a recommended object selection interface according to an embodiment of the invention;
FIG. 3 is a flow diagram of selecting a recommendation target user in accordance with an embodiment of the present invention;
FIG. 4 is a block diagram of a system for recommending target user selections in accordance with an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a selection device for recommending a target user according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
As shown in fig. 1, an embodiment of the present invention provides a method for selecting a recommendation target user, including the following steps:
s100: acquiring information of an article to be recommended;
s200: acquiring a related user of a recommender from a social platform, taking the related user as an alternative target user for recommending the article, and acquiring user information of the alternative target user;
s300: selecting a recommendation target user of an article to be recommended from the alternative target users according to the article information to be recommended and the user information of the alternative target users;
s400: and pushing the recommendation target user information to the user terminal of the recommender.
In the method for selecting the recommended target user, firstly, the item information to be recommended and the user information of the candidate target user are obtained through the steps S100 and S200. In step S100, the item is a broad concept, and may be a product to be recommended, for example, a product selected by the user on the shopping platform is to be recommended to other friends, or may also be an activity to be recommended, a movie to be recommended, an article to be recommended, and the like. In step S200, the candidate target user is determined from the associated users of the recommenders in the social platform. Here, the social platform may include a social network platform such as WeChat, Payment treasures, etc., and the associated users of the recommender may include friends and groups of participants of the recommender on the social platform, etc.
Further, in the present invention, when recommending an item based on the social platform through step S300, a target user for recommending an item is selected from the social platform friends of the recommender through the relevance between the user and the item. After the target user is selected, the target user information is pushed to the user terminal of the recommender through step S400, and the recommender can directly operate the user terminal that recommends the item to the target user. The user terminal herein refers to a terminal device used by a user, including but not limited to a mobile phone, a tablet computer, a notebook computer, etc., where the target user information may be identification information such as an ID of the target user. For example, when a recommender selects a recommended item, a user terminal of the recommender jumps to an APP interface of a social platform selected by a user to select a recommended object, at this time, after a recommended target user is selected by adopting steps S100 to S300, information of the target user is pushed to the user terminal, and after the user terminal receives the information of the target user, a recommended object selection interface is displayed.
As shown in fig. 2, a schematic diagram of a recommended object selection interface J100 displayed in the user terminal in this embodiment is shown. The friend selection area of the recommendation object selection interface J100 may display a nickname or a remark name of each target user, and the recommender may directly select a recommendation object in the interface and send recommendation information. Specifically, the friend selection area may be divided into two parts: a selection area J110 of a recommendation target user and a selection area J120 of a non-recommendation target user. What is displayed in the selection area J110 is the recommendation target user selected through steps S100 to S300, and other friends of the recommender may be listed in the selection area J120. The two selection areas J110 and J120 may be identified in different ways, for example, in different background colors, in different selection icons, in different text formats, etc.
Therefore, the invention can select the recommended person with high probability of receiving articles, greatly reduce the chance of recommending wrong objects and improve the recommendation conversion rate, and for the recommended person, the recommended information received by the recommended person is more interesting by the recommended person with high probability, thereby preventing the recommended person from receiving too much useless information. According to the invention, the social platform is connected with the shopping platform (in other scenes, a movie platform, a movable platform, an electronic book platform and the like), the advantages of the social network are fully utilized on the basis of advertisement recommendation according to the characteristics of individual users, the targeted mutual recommendation among the users is realized, and the users can more conveniently know more interested commodity information under the condition of improving the advertisement flow conversion rate.
As shown in fig. 3, in this embodiment, in the step S300, determining a recommendation target user of the item to be recommended according to the item information to be recommended and the user information of the candidate target user, includes the following steps:
s310: acquiring a historical behavior log of each alternative target user on a shopping platform;
s320: and determining whether the alternative target user is a recommendation target user of the item to be recommended or not according to the historical behavior log of the alternative target user.
In this embodiment, the step S320: determining whether the alternative target user is a recommendation target user of the item to be recommended according to the historical behavior log of the alternative target user, comprising the following steps:
determining the associated articles of the alternative target users according to the historical behavior logs of the alternative target users;
judging whether the item to be recommended belongs to the associated item of the alternative target user;
if so, the alternative target user is the recommendation target user of the item to be recommended.
Therefore, the invention can analyze and obtain the associated articles of the target user by combining the historical behavior log of each user on the shopping platform, and select the recommended target user according to the associated articles, thereby selecting the proper recommended target user according to the historical operation behavior of the user and improving the pertinence of the target user selection.
In this embodiment, considering that the number of the user's historical behavior logs is limited, there is a great limitation in selecting the target user only by means of the associated item. Therefore, an item model can be built according to the association degree between the items, the range of the associated items is further expanded based on the item model, and similar items of the associated items are added to select the alternative target users.
The step S320: determining whether the alternative target user is a recommendation target user of the item to be recommended according to the historical behavior log of the alternative target user, comprising the following steps:
s321: determining the associated articles of the alternative target users according to the historical behavior logs of the alternative target users;
determining the associated items of the alternative target users, selecting according to the items browsed, clicked or purchased by the user in the historical behavior log, and calculating the score of the user for each item according to different operation types of the user, for example, the score of the item browsed by the user and having browsing time greater than a certain threshold is a, the score of the item clicked by the user is b, and so on, if the user rejects the recommendation of a certain item, the score of the item by the user is subtracted by a certain score, and finally selecting the item having the score higher than a certain score threshold as the associated item of the user;
s322: querying similar items of the associated items in an item model according to the associated items, wherein the item model is configured to store the similar items of each item;
s323: judging whether the item to be recommended belongs to the associated item of the alternative target user or a similar item of the associated item;
if so, then step S324 is continued: the alternative target user is a recommendation target user of the item to be recommended;
if not, continue with step S325: the alternative target user is not the recommendation target user of the item to be recommended.
In this embodiment, the item model may be constructed based on the degree of similarity between items. For each item, a feature vector of the item is constructed by means of attribute values of various attributes of the item, wherein the attributes of the item can comprise a name, a commodity category, an applicable group, a group feature for searching the item and the like. Then, the similarity of the two articles can be calculated according to the feature vectors of the two articles, and the similarity can be calculated by cosine similarity, Euclidean distance and other calculation methods. After the similarity sim (j, i) is calculated, an item matrix may be constructed, which includes, for n items, an array of similarity values for the ith item and the jth item. In addition, the similarity of two items can be further calculated by combining the search relevance of the users, for example, when a plurality of users search the item A and simultaneously search the item B, the item A and the item B can be considered to belong to similar items. The finally obtained article model may include a similar article collection n (u) of each article, and the similarity between the similar article and the article is greater than a preset similarity threshold.
For example, for a blood pressure meter, its similar collection of items n (u) may be found including blood glucose meters, electronic blood pressure meters, elderly health, electronic product agencies, intelligent electronic blood pressure meters, and so forth. After a user searches for a blood pressure meter, if a friend of the social platform has a recommendation of a blood glucose meter, the user who has searched for the blood pressure meter can also be used as a recommendation target user of the blood glucose meter.
In this embodiment, if the number of the historical behavior logs of a user in the shopping platform is small, the recommendation target user can be further selected by combining the constructed user model and the association degree between the users.
Specifically, the step S310: after the historical behavior logs of the candidate target users on the shopping platform are acquired, if the acquired historical behavior logs meet preset log analysis conditions, the step S320 is continued, where the preset log analysis conditions may be a preset log number, if the log number is too small, the preset log analysis conditions are not met, and if the log number meets the preset log number requirement, the step S320 may be continued.
If the historical behavior log of the alternative target user is not acquired or the historical behavior log of the alternative target user does not accord with the preset log analysis condition, continuing the following steps:
s331: inquiring similar users of the alternative target users according to a user model, wherein the user model is configured to store the similar users of all the users;
s332: querying the related items of the similar users of the alternative target user, wherein the range of the related items of the similar users can be further expanded according to the item model, and the similar items of the related items of the similar users are also used as the related items of the similar users;
s333: judging whether the item to be recommended belongs to the associated item of the similar user of the alternative target user;
if yes, continue the step S324: the alternative target user is a recommendation target user of the item to be recommended;
if not, the step S325 is continued: the alternative target user is not the recommendation target user of the item to be recommended.
The user model may be a model that collects a feature vector of each user in advance, finds a similar user set n (u) of each user according to a similarity of the feature vectors between every two users, and the similarity between each similar user in the similar user set and the user is greater than a preset similarity threshold. Specifically, the similarity between each two users may be cosine similarity, euclidean distance, or the like. And constructing a user matrix according to the similarity between the users, wherein the user matrix comprises the similarity between the ith user and the jth user. The feature vector of the user may be composed of attribute values of a plurality of attributes of the user, and the attributes of the user may include basic attributes, such as the age, sex, region to which the user belongs, and the like of the user, and may also include attributes obtained by analyzing the behavior habits of the user, such as the shopping frequency of the user, the consumption habits of the user, and the like.
The method for selecting the recommended target user is specifically described in an example of recommending a sphygmomanometer. When a user A wants to recommend a sphygmomanometer to friends of the user A, a friend behavior log of friends 1, 2 and 3 … … of the user A is obtained first, and then whether the friends 1, 2 and 3 … … browse or click related articles such as a electrocardiogram, a blood glucose meter and a sphygmomanometer in the operation of a shopping platform is judged, if yes, if the friends 1 browse the blood glucose meter once, the friends 1 are interested in the high probability of the sphygmomanometer because the blood glucose meter can be determined to be the similar article of the sphygmomanometer according to an article model, and the friends 1 are selected as recommendation target users.
If the friend 2 has no history behavior log or the data of the history behavior log is little, searching for similar users of the friend 2 according to the user model to obtain similar users B, similar users C and the like, and if the related articles of the similar users B have the sphygmomanometer, determining that the friend 2 is interested in the high probability of the sphygmomanometer, and selecting the friend 2 as a recommendation target user.
Therefore, in the embodiment, the friends can be classified into items to be recommended according to the user model and the item model, the items to be recommended have high probability of being interested or low probability of being interested, when the user needs to recommend the items, the user can preferentially select the recommendation target user with high probability of being interested, so that the situation that the uninteresting friends are interfered is avoided, the possibility that the user receives the meaningless uninteresting recommendation is reduced, and for the recommenders, the recommenders can receive related demands or favorite commodities or activities. The shopping platform can offer preferential prices to attract consumers to recommend commodities to other people, the activity sponsoring unit is to attract more participants, the movie platform is to attract more viewers, and the shopping platform is more willing to provide preferential/bonus/point and the like to attract the existing users to assist popularization. When recommending articles, the recommender can accurately find social friends with similar preferences, can accurately recommend commodities, activities and the like, and achieves the purpose of group purchase, so that the recommender and the referee can benefit.
In this embodiment, in step S321, determining the associated item of the alternative target user according to the historical behavior log of the alternative target user includes the following steps:
when the alternative target user is a group, acquiring historical behavior logs of all single users in the group;
and determining the associated articles of the group according to the historical behavior logs of all the single users in the group as the associated articles of the group. Specifically, the coincident associated items of all the single users in the group are searched for as the associated items of the group. For example, if substantially all users in a group have viewed an exercise product, the exercise item may be considered an associated item of the group.
In this embodiment, the method for selecting the recommendation target user further includes the following steps:
after sending the item recommendation information to the recommendation target user, obtaining feedback data of the recommendation target user, where the feedback data may include operations of browsing, clicking, purchasing and the like of the recommended item by the user, and may also include a rejection operation of the recommended item by the user;
and adjusting the associated articles corresponding to the recommendation target users according to the feedback data, namely performing weight reduction processing on the articles according to the rejection history condition of the users, and adding the articles into the associated articles of the users according to browsing, clicking, purchasing and other operations of the users on the recommended articles.
As shown in fig. 4, an embodiment of the present invention further provides a system for selecting a recommendation target user, which is used to implement the method for selecting a recommendation target user, where the system includes:
the article information acquisition module M100 is used for acquiring article information to be recommended;
the alternative user obtaining module M200 is used for obtaining an associated user of a recommender from a social platform, using the associated user as an alternative target user for recommending the article, and obtaining user information of the alternative target user;
a target user selection module M300, configured to select a recommendation target user of an item to be recommended from the alternative target users according to the item information to be recommended and the user information of the alternative target users;
and the target user pushing module M400 is used for pushing the recommendation target user information to the user terminal of the recommender.
The selection system of the recommendation target user firstly respectively acquires the information of the item to be recommended and the information of the alternative target users to be selected through the item information acquisition module M100 and the alternative user acquisition module M200, the target user selection module M300 selects the target user for recommending the item from the social platform friends of the recommender through the relevance between the user and the item, and pushes the target user information to the user terminal of the recommender through the target user push module M400, therefore, the recommenders who have high probability of accepting articles can be selected, the chance of recommending wrong objects is greatly reduced, the recommendation conversion rate is improved, and for the recommenders, the received recommendation information is interested in the probability, so that the fact that a recommended person receives too much useless information can be avoided, the use experience of a user is improved, and waste of item recommendation flow is avoided.
In the selection system of the recommendation target user of the present invention, the functions of each module may be implemented by using the specific implementation manner of the selection method of the recommendation target user as described above, which is not described herein again.
The embodiment of the invention also provides a selection device for recommending the target user, which comprises a processor; a memory having stored therein executable instructions of the processor; wherein the processor is configured to perform the steps of the method of recommending target user selection via execution of the executable instructions.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.
An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 5. The electronic device 600 shown in fig. 5 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 that connects the various system components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned recommendation target user selection method section of the present specification. For example, the processing unit 610 may perform the steps as shown in fig. 1.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the method for selecting a recommendation target user when executed. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the invention described in the above-mentioned method of selection of a recommendation target user section of this specification, when the program product is executed on the terminal device.
Referring to fig. 6, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be executed on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In summary, by using the selection method, the system, the device and the storage medium for recommending the target user, when recommending the object based on the social platform, the target user for recommending the object is selected from the social platform friends of the recommender through the relevance between the user and the object, so that the recommended person who has a high probability of receiving the object can be selected, the probability of recommending a wrong object is greatly reduced, the recommendation conversion rate is improved, and the recommended person is interested in the received recommendation information with a high probability, so that the situation that the recommended person receives too much useless information can be avoided, the use experience of the user is improved, and the waste of the object recommendation flow is also avoided.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (10)
1. A selection method of a recommendation target user is characterized by comprising the following steps:
acquiring information of an article to be recommended;
acquiring a related user of a recommender from a social platform, taking the related user as an alternative target user for recommending the article, and acquiring user information of the alternative target user;
selecting a recommendation target user of an article to be recommended from the alternative target users according to the article information to be recommended and the user information of the alternative target users;
and pushing the recommendation target user information to the user terminal of the recommender.
2. The selection method of the recommendation target user according to claim 1, wherein the recommendation target user of the item to be recommended is determined according to the item information to be recommended and the user information of the alternative target user, comprising the steps of:
acquiring a historical behavior log of each alternative target user on a shopping platform;
and determining whether the alternative target user is a recommendation target user of the item to be recommended or not according to the historical behavior log of the alternative target user.
3. The method for selecting the recommended target user according to claim 2, wherein determining whether the alternative target user is the recommended target user of the item to be recommended according to the historical behavior log of the alternative target user comprises the following steps:
determining the associated articles of the alternative target users according to the historical behavior logs of the alternative target users;
judging whether the item to be recommended belongs to the associated item of the alternative target user;
if so, the alternative target user is the recommendation target user of the item to be recommended.
4. The method for selecting the recommended target user according to claim 2, wherein determining whether the alternative target user is the recommended target user of the item to be recommended according to the historical behavior log of the alternative target user comprises the following steps:
determining the associated articles of the alternative target users according to the historical behavior logs of the alternative target users;
querying similar items of the associated items in an item model according to the associated items, wherein the item model is configured to store the similar items of each item;
judging whether the item to be recommended belongs to the associated item of the alternative target user or a similar item of the associated item;
if so, the alternative target user is the recommendation target user of the item to be recommended.
5. The method for selecting recommended target users according to claim 2, wherein after obtaining the historical behavior log of each candidate target user on the shopping platform, the method further comprises the following steps:
if the historical behavior log of the alternative target user is not acquired or the historical behavior log of the alternative target user does not accord with a preset log analysis condition, inquiring similar users of the alternative target user according to a user model, wherein the user model is configured to store the similar users of all users;
querying related items of similar users of the alternative target users;
judging whether the item to be recommended belongs to the associated item of the similar user of the alternative target user;
if so, the alternative target user is the recommendation target user of the item to be recommended.
6. The selection method of the recommended target user according to claim 3 or 4, wherein the step of determining the associated item of the alternative target user according to the historical behavior log of the alternative target user comprises the following steps:
when the alternative target user is a group, acquiring historical behavior logs of all single users in the group;
and determining the associated articles of the group according to the historical behavior logs of all the single users in the group as the associated articles of the group.
7. The method for selecting a recommendation target user according to claim 3 or 4, further comprising the steps of:
after sending the item recommendation information to the recommendation target user, acquiring feedback data of the recommendation target user;
and adjusting the associated item corresponding to the recommendation target user according to the feedback data.
8. A selection system of a recommendation target user for implementing the selection method of the recommendation target user according to any one of claims 1 to 7, the system comprising:
the article information acquisition module is used for acquiring article information to be recommended;
the alternative user acquisition module is used for acquiring the associated user of the recommender from the social platform, taking the associated user as an alternative target user for recommending the article, and acquiring the user information of the alternative target user;
the target user selection module is used for selecting a recommendation target user of the item to be recommended from the alternative target users according to the information of the item to be recommended and the user information of the alternative target users;
and the target user pushing module is used for pushing the recommended target user information to the user terminal of the recommender.
9. A selection device that recommends a target user, comprising:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the method of recommending target user selection of any of claims 1-7 via execution of the executable instructions.
10. A computer-readable storage medium storing a program, wherein the program when executed implements the steps of the method of recommending a target user of any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010834920.9A CN111914188A (en) | 2020-08-19 | 2020-08-19 | Method, system, device and storage medium for selecting recommendation target user |
| TW109142961A TWI823036B (en) | 2020-08-19 | 2020-12-04 | Recommended target user selecting method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010834920.9A CN111914188A (en) | 2020-08-19 | 2020-08-19 | Method, system, device and storage medium for selecting recommendation target user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914188A true CN111914188A (en) | 2020-11-10 |
Family
ID=73279378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010834920.9A Pending CN111914188A (en) | 2020-08-19 | 2020-08-19 | Method, system, device and storage medium for selecting recommendation target user |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111914188A (en) |
| TW (1) | TWI823036B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158031A (en) * | 2021-03-15 | 2021-07-23 | 北京健康之家科技有限公司 | Method and device for determining user resource information, computer storage medium and terminal |
| CN113434762A (en) * | 2021-06-28 | 2021-09-24 | 平安银行股份有限公司 | Association pushing method, device and equipment based on user information and storage medium |
| CN113609386A (en) * | 2021-07-21 | 2021-11-05 | 深圳供电局有限公司 | Electricity price policy document pushing method and system and storage medium |
| CN113689233A (en) * | 2021-08-03 | 2021-11-23 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and corresponding device, equipment and medium thereof |
| CN113723733A (en) * | 2020-12-23 | 2021-11-30 | 北京沃东天骏信息技术有限公司 | Article information display method and device, electronic equipment and computer readable medium |
| CN113744018A (en) * | 2020-11-23 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Article information pushing method and device and computer-readable storage medium |
| CN115374365A (en) * | 2022-09-14 | 2022-11-22 | 康键信息技术（深圳）有限公司 | Information recommendation method and device, storage medium and computer equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI839706B (en) * | 2022-04-06 | 2024-04-21 | 精誠資訊股份有限公司 | Insurance product recommendation system and method for predicting policy preferences based on social platform data and policyholder characteristics |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160117595A1 (en) * | 2013-07-11 | 2016-04-28 | Huawei Technologies Co., Ltd. | Information recommendation method and apparatus in social media |
| CN106534984A (en) * | 2016-12-23 | 2017-03-22 | 深圳Tcl数字技术有限公司 | TV program pushing method and device |
| CN108320213A (en) * | 2018-01-31 | 2018-07-24 | 深圳春沐源控股有限公司 | Electric business Method of Commodity Recommendation and electric business Platform Server |
| CN109903127A (en) * | 2019-02-14 | 2019-06-18 | 广州视源电子科技股份有限公司 | Group recommendation method and device, storage medium and server |
| CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
| CN111475737A (en) * | 2020-03-23 | 2020-07-31 | 威比网络科技(上海)有限公司 | User recommendation method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2437158A1 (en) * | 2005-12-19 | 2012-04-04 | Apple Inc. | User-to-user recommender |
| CN106204144A (en) * | 2016-07-14 | 2016-12-07 | 乐视控股（北京）有限公司 | A kind of information-pushing method and information push-delivery apparatus |
| CN107862530A (en) * | 2016-09-19 | 2018-03-30 | 阿里巴巴集团控股有限公司 | Establish the method and device of user's interpersonal relationships information |
| CN108711075A (en) * | 2018-05-22 | 2018-10-26 | 阿里巴巴集团控股有限公司 | A kind of Products Show method and apparatus |
| CN111475741A (en) * | 2019-01-24 | 2020-07-31 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining user interest tags |
-
2020
- 2020-08-19 CN CN202010834920.9A patent/CN111914188A/en active Pending
- 2020-12-04 TW TW109142961A patent/TWI823036B/en active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160117595A1 (en) * | 2013-07-11 | 2016-04-28 | Huawei Technologies Co., Ltd. | Information recommendation method and apparatus in social media |
| CN106534984A (en) * | 2016-12-23 | 2017-03-22 | 深圳Tcl数字技术有限公司 | TV program pushing method and device |
| CN108320213A (en) * | 2018-01-31 | 2018-07-24 | 深圳春沐源控股有限公司 | Electric business Method of Commodity Recommendation and electric business Platform Server |
| CN109903127A (en) * | 2019-02-14 | 2019-06-18 | 广州视源电子科技股份有限公司 | Group recommendation method and device, storage medium and server |
| CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
| CN111475737A (en) * | 2020-03-23 | 2020-07-31 | 威比网络科技(上海)有限公司 | User recommendation method and device, electronic equipment and storage medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113744018A (en) * | 2020-11-23 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Article information pushing method and device and computer-readable storage medium |
| CN113723733A (en) * | 2020-12-23 | 2021-11-30 | 北京沃东天骏信息技术有限公司 | Article information display method and device, electronic equipment and computer readable medium |
| CN113158031A (en) * | 2021-03-15 | 2021-07-23 | 北京健康之家科技有限公司 | Method and device for determining user resource information, computer storage medium and terminal |
| CN113158031B (en) * | 2021-03-15 | 2024-04-23 | 北京水滴科技集团有限公司 | Method and device for determining user resource information, computer storage medium and terminal |
| CN113434762A (en) * | 2021-06-28 | 2021-09-24 | 平安银行股份有限公司 | Association pushing method, device and equipment based on user information and storage medium |
| CN113609386A (en) * | 2021-07-21 | 2021-11-05 | 深圳供电局有限公司 | Electricity price policy document pushing method and system and storage medium |
| CN113689233A (en) * | 2021-08-03 | 2021-11-23 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and corresponding device, equipment and medium thereof |
| CN113689233B (en) * | 2021-08-03 | 2024-07-26 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and corresponding device, equipment and medium thereof |
| CN115374365A (en) * | 2022-09-14 | 2022-11-22 | 康键信息技术（深圳）有限公司 | Information recommendation method and device, storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202209220A (en) | 2022-03-01 |
| TWI823036B (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111914188A (en) | Method, system, device and storage medium for selecting recommendation target user | |
| US10664888B2 (en) | Method and system for attribute extraction from product titles using sequence labeling algorithms | |
| US20230089850A1 (en) | Real-time product environmental impact scoring | |
| CN111310046B (en) | Object recommendation method and device | |
| US20190019203A1 (en) | Method for providing marketing management data for optimization of distribution and logistics and apparatus for the same | |
| CN111523976A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN113139115B (en) | Information recommendation method, search method, device, client, medium and equipment | |
| US10853424B1 (en) | Content delivery using persona segments for multiple users | |
| US20090077081A1 (en) | Attribute-Based Item Similarity Using Collaborative Filtering Techniques | |
| CN113781149B (en) | Information recommendation method and device, computer readable storage medium and electronic equipment | |
| CN112561581A (en) | Recommendation method and device, electronic equipment and storage medium | |
| CN111754278A (en) | Item recommendation method, apparatus, computer storage medium and electronic device | |
| CN113837843A (en) | Product recommendation method, device, medium and electronic equipment | |
| CN115511546A (en) | Behavior analysis method, system, equipment and readable medium for E-commerce users | |
| US12354147B2 (en) | Systems and methods for determining price bands and user price affinity predictions using machine learning architectures and techniques | |
| CN111209351A (en) | Object relation prediction method and device, object recommendation method and device, electronic equipment and medium | |
| US20090077093A1 (en) | Feature Discretization and Cardinality Reduction Using Collaborative Filtering Techniques | |
| KR20210059000A (en) | Plug-in enable identification and display of alternative products for purchase | |
| US12412204B2 (en) | Systems and methods for determining price bands and user price affinity predictions using machine learning architectures and techniques | |
| CN113689257A (en) | User behavior buried point construction method and system | |
| CN113744002A (en) | Method, device, equipment and computer readable medium for pushing information | |
| JP5275531B1 (en) | Information providing apparatus, information providing method, information providing program, and computer-readable recording medium storing the program | |
| CN110390574A (en) | The determination method and apparatus of business object | |
| CN115618126A (en) | Search processing method, system, computer readable storage medium and computer device | |
| CN112949852A (en) | Method and device for training model, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201110 |