Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method and an apparatus for sending information, which can accurately determine a user who needs to push information, and send information to a corresponding user in a targeted manner, so as to avoid pushing information to a user who does not need to push information, effectively reduce the load of a system during information sending, reduce the information sending cost, reduce the harassment of junk information to the user, reduce the occupancy rate of network resources, and improve the information sending efficiency; and the object matched with the user can be accurately mastered according to the historical behavior record of the user, so that the recommendation accuracy is improved.
To achieve the above object, according to one aspect of the embodiments of the present invention, there is provided a method for transmitting information, including:
acquiring historical behavior records of a plurality of users in a target time period, and determining characteristic information of the users according to the historical behavior records; the historical behavior record is operation data of a user on an object;
under the condition that the characteristic information of the user meets the preset condition, determining the user as the user to be matched;
for each user to be matched, determining a target object matched with the user to be matched according to the historical behavior record of the user to be matched, generating push information according to the target object, and sending the push information to the corresponding user to be matched.
Optionally, the historical behavior record includes a historical browsing record and a historical order record; the characteristic information comprises a characteristic attribute value;
Determining the characteristic information of the user according to the historical behavior record comprises the following steps: determining a characteristic attribute value of a user according to the history browsing record and the history order record;
in the case that the feature information of the user meets the preset condition, determining the user as the user to be matched comprises: and determining the user as the user to be matched under the condition that the characteristic attribute value of the user is larger than or equal to a preset threshold value.
Optionally, determining that the target object matched with the user to be matched comprises according to the historical behavior record of the user to be matched; constructing a corresponding object pool according to the history browsing record and the history order record of the user to be matched; and screening out target objects matched with the users to be matched from the object pool.
Optionally, constructing the corresponding object pool according to the history browsing record and the history order record of the user to be matched includes:
According to the historical browsing records and the historical order records of the users to be matched, determining objects browsed by the users to be matched and purchased objects;
Determining a first object similar to the object browsed by the user to be matched, a second object complementary to the object browsed by the user to be matched, a third object similar to the object purchased by the user to be matched and a fourth object complementary to the object purchased by the user to be matched;
and constructing a corresponding object pool based on the object browsed by the user to be matched, the purchased object, the second object, the first object, the third object and the fourth object.
Optionally, selecting the target object matched with the user to be matched from the object pool includes: and determining the score of each object according to the click passing rate of each object in the object pool and a preset sorting algorithm, and taking the object with the highest score as a target object.
To achieve the above object, according to another aspect of an embodiment of the present invention, there is provided an apparatus for transmitting information, including:
the characteristic determining module is used for acquiring historical behavior records of a plurality of users in a target time period and determining characteristic information of the users according to the historical behavior records; the historical behavior record is operation data of a user on an object;
The user selection module is used for determining the user as the user to be matched under the condition that the characteristic information of the user meets the preset condition;
the information sending module is used for determining an object matched with the user to be matched according to the historical behavior record of the user to be matched for each target user to be matched, generating push information according to the target object and sending the push information to the corresponding user to be matched.
Optionally, the historical behavior record includes a historical browsing record and a historical order record; the characteristic information comprises a characteristic attribute value;
the feature determination module is further configured to: determining a characteristic attribute value of a user according to the history browsing record and the history order record;
The user selection module is further configured to: and determining the user as the user to be matched under the condition that the characteristic attribute value of the user is larger than or equal to a preset threshold value.
Optionally, the information sending module is further used for; constructing a corresponding object pool according to the history browsing record and the history order record of the user to be matched; and screening out target objects matched with the users to be matched from the object pool.
Optionally, the information sending module is further configured to: according to the historical browsing records and the historical order records of the users to be matched, determining objects browsed by the users to be matched and purchased objects; determining a first object similar to the object browsed by the user to be matched, a second object complementary to the object browsed by the user to be matched, a third object similar to the object purchased by the user to be matched and a fourth object complementary to the object purchased by the user to be matched; and constructing a corresponding object pool based on the object browsed by the user to be matched, the purchased object, the first object, the second object, the third object and the fourth object.
Optionally, the information sending module is further configured to: and determining the score of each object according to the click passing rate of each object in the object pool and a preset sorting algorithm, and taking the object with the highest score as a target object.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic device including: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the information sending method of the embodiment of the invention.
To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a method of information transmission of the embodiments of the present invention.
One embodiment of the above invention has the following advantages or benefits: acquiring historical behavior records of a plurality of users in a target time period, and determining characteristic information of the users according to the historical behavior records; the historical behavior record is operation data of a user on an object; under the condition that the characteristic information of the user meets the preset condition, determining the user as the user to be matched; for each user to be matched, determining a target object matched with the user to be matched according to the historical behavior record of the user to be matched, generating push information according to the target object and sending the push information to the corresponding user to be matched, so that the user needing to push the information can be accurately determined, the information can be sent to the corresponding user in a targeted manner, the information is prevented from being pushed to the user not needing to push the information, the load of a system in information sending is effectively reduced, the information sending cost is reduced, the harassment of junk information to the user is reduced, the occupancy rate of network resources is reduced, and the information sending efficiency is improved; and the object matched with the user can be accurately mastered according to the historical behavior record of the user, so that the recommendation accuracy is improved.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flow chart illustrating main steps of a method for transmitting information according to an embodiment of the present invention, as shown in fig. 1, the method includes:
Step S101: acquiring historical behavior records of a plurality of users in a target time period, and determining characteristic information of the users according to the historical behavior records; the historical behavior record is operation data of the user on the object.
In this step, the behavior mainly refers to the interactive behavior of the user on the object, including but not limited to the behavior of browsing, clicking, focusing, purchasing, commenting and the like of the user on the object. The object of this step may be an article or a commodity. The data resulting from the above-described behavior is divided into two categories in the present embodiment: a review record and a purchase record, wherein the review record includes data generated by review, click and attention actions, and the purchase record includes data generated by add-on and comment actions. Thus, the historical behavior record includes a user's historical browsing record and a historical order record. In this embodiment, the time of day may be divided into several segments, for example, one hour is a period, and the present invention is not limited herein. The target time period is a specified one of the time periods. The user's characteristic information is used to filter out specific, demand-satisfying users, and may be described using characteristic attribute values, as an example.
Wherein for each user, determining characteristic information of the user based on the historical behavior record of the user in the target time period comprises: and determining the characteristic attribute value of the user according to the history browsing record and the history order record.
Specifically, the process of determining the characteristic attribute value of the user may include:
determining an average number of orders based on the number of orders of each user in the target time period;
respectively calculating a first ratio of the number of orders of each user in a target time period to the average number of orders;
determining an average number of categories to which the order belongs based on the number of categories to which the order belongs for each user within the target time period;
Respectively calculating a second ratio of the number of the classes to which each user belongs to the order and the average number of the classes to which the order belongs in a target time period;
Taking the history browsing record and the history order record of each user as input data, and inputting a pre-trained scoring model to obtain the score of each user;
and determining the characteristic attribute value of the user according to the first ratio, the second ratio and the score.
The scoring model can be trained according to the following process: acquiring sample data, wherein the sample data is a historical browsing record and a historical order record of a user; marking the sample data, namely determining the score of each user; setting parameters of a machine learning model; and training according to the sample data, the corresponding scores and the parameters of the machine learning model to obtain a scoring model. The input data of the scoring model is a historical browsing record and a historical order record of the user, and the output data is the score of the user.
More specifically, the characteristic attribute value of the user can be determined according to the following formula (1):
Wherein pinScoreu denotes a characteristic attribute value of user u, ordu denotes the number of orders of user u in a target period, ordAvgall denotes an average number of orders of all users in the target period,Representing a first ratio, ordCateu representing the number of categories to which the order of user u belongs within the target time period, ordAvgCateu representing the average number of categories to which the order of all users within the target time period belongs,Representing a second ratio, sensitiveScoreu represents the score for user u.
In other alternative embodiments, weights may be set for the first ratio, the second ratio, and the score of the user, respectively, and then the product of the three may be used as the characteristic attribute value of the user. Specifically, the following formula (2) shows:
wherein β1,β2,β3 is the first ratio, the second ratio, and the scoring weight of the user, respectively, and their values may be flexibly set by the application scenario, which is not limited herein.
Step S102: and under the condition that the characteristic information of the user meets the preset condition, determining the user as the user to be matched.
Specifically, in the case that the characteristic attribute value of the user is greater than or equal to a preset threshold value, the user is determined to be the user to be matched. The preset threshold value can be flexibly set according to application requirements, and the invention is not limited herein.
In other alternative embodiments, the feature attribute values may be arranged in order from the top to the bottom, and then the users with the top ranking may be selected as the users to be matched, for example, the first 50% of the users are selected as the users to be matched.
Step S103: for each user to be matched, determining a target object matched with the user to be matched according to the historical behavior record of the user to be matched, generating push information according to the target object, and sending the push information to the corresponding user to be matched.
Specifically, the step may include:
constructing a corresponding object pool according to the history browsing record and the history order record of the user to be matched;
And screening out target objects matched with the users to be matched from the object pool.
The objects in the object pool comprise objects browsed by users to be matched and purchased objects, and are objects interested by the users to be matched. As an example, the object of interest to the user to be recommended may be determined according to the following procedure: respectively determining the category to which the object purchased, searched, browsed and purchased in the historical behavior record of the user belongs, then determining the preference degree of the user for all the categories according to each category, and sorting according to the preference degree; if the preference degree is the same, sorting is carried out according to the object quality, and the objects interested by the user are selected by combining time factors and the like. The time factor refers to the time of purchasing, searching, browsing, and purchasing objects by the user, and is used as a feature, including whether it is holiday, weekday, weekend, time period division (early, middle, late), and the like. The object of interest to the user is obtained through the above process.
When the target object is screened from the object pool, a screening rule can be preset. As an example, the score of each object may be determined according to the click through rate of each object in the object pool and a preset sorting algorithm, and the object with the highest score is taken as the target object.
The preset sorting algorithm generally considers a CTR (Click-Through-Rate) index, and uses a classification model to score according to the behavior of a user on an object and the statistical characteristics of the user on commodity image subdivision, and after the relative order of the objects is obtained, the object with the forefront sorting is taken as a target object. Statistical characteristics refer to statistics of object behaviors (i.e., browsing behaviors, searching behaviors, purchasing behaviors) by a user over a period of time, such as browsing several times a day, clicking several times.
Training of the classification model is also required before scoring the object using the classification model. Firstly, defining the problem during training, namely, after pushing a message to a user, the user points out something, so that the problem is abstracted into a classification problem; then constructing data according to the historical behavior of the user on the object, wherein the data patterns are user characteristics, namely whether the user clicks, so that the data can be used for training a model through classification algorithms (LR (Logistic Regression, logistic regression analysis), GBDT (Gradient Boosting Decision Tree, gradient lifting tree), lightGBM (LightGBM is a gradient Boosting framework), deep learning and other methods); after the classification model is obtained, scoring the objects (probability values between 0 and 1), and finally selecting the object with the highest ranking to push according to the obtained scoring ranking.
In an alternative embodiment, the objects in the object pool may include objects browsed by the user to be matched and purchased, may further include objects similar to browsed objects and complementary objects, and may further include objects similar to purchased objects and complementary objects. As shown in fig. 2, this step may include:
step S201: according to the historical browsing records and the historical order records of the users to be matched, determining objects browsed by the users to be matched and purchased objects;
Step S202: determining a first object similar to the object browsed by the user to be matched, a second object complementary to the object browsed by the user to be matched, a third object similar to the object purchased by the user to be matched and a fourth object complementary to the object purchased by the user to be matched;
Step S203: and constructing a corresponding object pool based on the object browsed by the user to be matched, the purchased object, the first object, the second object, the third object and the fourth object.
In this embodiment, the object pool is constructed for the object browsed by the user and the purchased object (i.e. the user obtains the object and the similar object which are complementary to the object of interest based on the object complementary model and the object similar model, so that the object pool is constructed by the object of interest, the object similar to the object of interest and the object complementary to the object of interest, wherein the object complementary means that there is a certain consumption dependency relationship between two objects, i.e. the consumption of one object must match the consumption of the other object, such as table tennis and racket, automobile and gasoline.
The information sending method of the embodiment of the invention can accurately determine the users needing to push information, and can send the information to the corresponding users in a targeted manner, thereby avoiding pushing the information to the users not needing to push the information, effectively reducing the load of a system when the recommended information is sent, reducing the information sending cost, reducing the harassment of junk information to the users, reducing the occupancy rate of network resources and improving the information sending efficiency; according to the historical behavior record of the user, the object matched with the user can be accurately mastered, so that the recommendation accuracy is improved; the method can push the interested articles to the active users, increase the exposure of the articles, improve the browsing and purchasing conversion rate of the articles, and push the interested article messages to the inactive users to increase daily activity without affecting the experience of the inactive users.
Fig. 3 is a schematic diagram of main modules of an apparatus 300 for transmitting information according to an embodiment of the present invention, and as shown in fig. 3, the apparatus 300 includes:
The feature determining module 301 is configured to obtain historical behavior records of a plurality of users in a target period, and determine feature information of the users according to the historical behavior records; the historical behavior record is operation data of a user on an object;
a user selection module 302, configured to determine a user as a user to be matched if the feature information of the user meets a preset condition;
the information sending module 303 is configured to determine, for each user to be matched, a target object that is matched with the user to be matched according to the historical behavior record of the user to be matched, and generate push information according to the target object, and send the push information to the corresponding user to be matched.
In an alternative embodiment, the historical behavior record includes a historical browsing record and a historical order record; the characteristic information comprises a characteristic attribute value;
the feature determination module 301 is further configured to: determining a characteristic attribute value of a user according to the history browsing record and the history order record;
the user selection module 302 is further configured to: and determining the user as the user to be matched under the condition that the characteristic attribute value of the user is larger than or equal to a preset threshold value.
In an alternative embodiment, the information sending module 303 is further configured to; constructing a corresponding object pool according to the history browsing record and the history order record of the user to be matched; and screening out target objects matched with the users to be matched from the object pool.
In an alternative embodiment, the information sending module 303 is further configured to:
According to the historical browsing records and the historical order records of the users to be matched, determining objects browsed by the users to be matched and purchased objects;
Determining a first object similar to the object browsed by the user to be matched, a second object complementary to the object browsed by the user to be matched, a third object similar to the object purchased by the user to be matched and a fourth object complementary to the object purchased by the user to be matched;
And constructing a corresponding object pool based on the object browsed by the user to be matched, the purchased object, the first object, the third object and the fourth object.
In an alternative embodiment, the information sending module 303 is further configured to: and determining the score of each object according to the click passing rate of each object in the object pool and a preset sorting algorithm, and taking the object with the highest score as a target object.
According to the information sending device, the historical behavior records of a plurality of users in a target time period are obtained, and the characteristic information of the users is determined according to the historical behavior records; the historical behavior record is operation data of a user on an object; under the condition that the characteristic information of the user meets the preset condition, determining the user as the user to be matched; for each user to be matched, determining a target object matched with the user to be matched according to the historical behavior record of the user to be matched, generating push information according to the target object and sending the push information to the corresponding user to be matched, so that the user needing to push the information can be accurately determined, the information can be sent to the corresponding user in a targeted manner, the information is prevented from being pushed to the user not needing to push the information, the load of a system in information sending is effectively reduced, the information sending cost is reduced, the harassment of junk information to the user is reduced, the occupancy rate of network resources is reduced, and the information sending efficiency is improved; and the object matched with the user can be accurately mastered according to the historical behavior record of the user, so that the recommendation accuracy is improved.
Fig. 4 illustrates an exemplary system architecture 400 of a method of information transmission or an apparatus of information transmission to which embodiments of the present invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 is used as a medium to provide communication links between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 405 via the network 404 using the terminal devices 401, 402, 403 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc., may be installed on the terminal devices 401, 402, 403.
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 405 may be a server providing various services, such as a background management server providing support for shopping-type websites browsed by the user using the terminal devices 401, 402, 403. The background management server can analyze and other processing on the received data such as the product information inquiry request and the like, and feed back processing results (such as target push information and product information) to the terminal equipment.
It should be noted that, the method for sending information provided in the embodiment of the present invention is generally executed by the server 405, and accordingly, the device for sending information is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 500 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 509, and/or installed from the removable media 511. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 501.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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. In the context of this document, a computer 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. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer 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 computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes a sending module, an obtaining module, a determining module, and a first processing module. The names of these modules do not constitute a limitation on the unit itself in some cases, and for example, the transmitting module may also be described as "a module that transmits a picture acquisition request to a connected server".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include:
acquiring historical behavior records of a plurality of users in a target time period, and determining characteristic information of the users according to the historical behavior records; the historical behavior record is operation data of a user on an object;
under the condition that the characteristic information of the user meets the preset condition, determining the user as the user to be matched;
for each user to be matched, determining a target object matched with the user to be matched according to the historical behavior record of the user to be matched, generating push information according to the target object, and sending the push information to the corresponding user to be matched.
According to the technical scheme, the historical behavior records of a plurality of users in a target time period are obtained, and the characteristic information of the users is determined according to the historical behavior records; the historical behavior record is operation data of a user on an object; under the condition that the characteristic information of the user meets the preset condition, determining the user as the user to be matched; for each user to be matched, determining an object matched with the user to be matched according to the historical behavior record of the user to be matched, accurately determining the user needing to push information, and sending the information to the corresponding user in a targeted manner, so that the information is prevented from being pushed to the user needing not to push information, the load of a system in the process of sending the recommended information is effectively reduced, the information sending cost is reduced, the harassment of junk information to the user is reduced, the occupancy rate of network resources is reduced, and the information sending efficiency is improved; and the object matched with the user can be accurately mastered according to the historical behavior record of the user, so that the recommendation accuracy is improved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.