CN117009662A

CN117009662A - Feature generation method and device for recommendation, medium and electronic equipment

Info

Publication number: CN117009662A
Application number: CN202310945236.1A
Authority: CN
Inventors: 张晓亮; 郑思琦; 蓝京杭
Original assignee: Beijing Volcano Engine Technology Co Ltd
Current assignee: Beijing Volcano Engine Technology Co Ltd
Priority date: 2023-07-28
Filing date: 2023-07-28
Publication date: 2023-11-07

Abstract

The disclosure relates to a feature generation method, a device, a medium and an electronic device for recommendation, wherein the feature generation method comprises the following steps: displaying a configuration interface, wherein the configuration interface comprises a feature configuration area; determining target dependence hit by the target operation in response to the target operation aiming at the feature configuration area, wherein the target dependence comprises a feature which is built completely and/or a feature original value for feature construction; and generating target features based on the target dependencies in response to the generating operation. The feature generation is realized based on the visual interface, so that the feature generation efficiency is improved, and the error rate of manually writing codes to obtain the features is reduced.

Description

Feature generation method and device for recommendation, medium and electronic equipment

Technical Field

The disclosure relates to the field of recommendation, and in particular relates to a feature generation method, device, medium and electronic equipment for recommendation.

Background

In a recommendation system, the quality of data basically determines the upper limit of the recommendation effect, and the generation of features also serves as one of the key factors for determining the quality of data.

In the related art, features are defined in a code configuration manner. In general, one feature corresponds to a row of configuration codes, so that the larger the number of features to be created, the more corresponding codes to be configured, and the lower the manual writing efficiency; in addition, the greater the encoding effort, the more error prone the encoding process.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, the present disclosure provides a feature generation method for recommendation, including:

displaying a configuration interface, wherein the configuration interface comprises a feature configuration area;

determining target dependence hit by the target operation in response to the target operation aiming at the feature configuration area, wherein the target dependence comprises a feature which is built completely and/or a feature original value for feature construction;

and generating target features based on the target dependencies in response to the generating operation.

In a second aspect, the present disclosure provides a feature generation apparatus for recommendation, comprising:

the first display module is used for displaying a configuration interface, and the configuration interface comprises a feature configuration area;

a first response module, configured to determine a target dependency hit by the target operation in response to the target operation for the feature configuration area, where the target dependency includes a feature that has been completely constructed and/or a feature original value for feature construction;

and the second response module is used for responding to the generation operation and generating target characteristics based on the target dependence.

In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing device, implements the steps of the above-described feature generation method.

In a fourth aspect, the present disclosure provides an electronic device comprising:

a storage device having a computer program stored thereon;

processing means for executing the computer program in the storage means to implement the steps of the above feature generation method.

Through the technical scheme, a configuration interface is displayed, and the configuration interface comprises a feature configuration area; determining target dependence of target operation hit in response to target operation aiming at the feature configuration area, wherein the target dependence comprises the feature which is built completely and/or a feature original value for feature construction; and responding to the generating operation, generating target features based on target dependence, providing a visual interface without manually writing codes, obtaining corresponding target features based on target dependence hit by the target operation, improving the efficiency of feature generation, and simultaneously reducing the error rate of obtaining the features by manually writing codes.

Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale. In the drawings:

FIG. 1 is a flow chart illustrating a feature generation method for recommendation, according to an exemplary embodiment.

FIG. 2 is a schematic diagram of a visualization interface of a feature configuration area, shown in accordance with an exemplary embodiment.

FIG. 3 is a schematic diagram illustrating a visual interface for performing a second target operation, according to an example embodiment.

FIG. 4 is a schematic diagram illustrating a batch generation of target features according to an example embodiment.

FIG. 5 is a block diagram illustrating a feature generation apparatus for recommendation, according to an example embodiment.

Fig. 6 is a schematic diagram of an electronic device according to an exemplary embodiment.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.

For example, in response to receiving an active request from a user, a prompt is sent to the user to explicitly prompt the user that the operation it is requesting to perform will require personal information to be obtained and used with the user. Thus, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application program, a server or a storage medium for executing the operation of the technical scheme of the present disclosure according to the prompt information.

As an alternative but non-limiting implementation, in response to receiving an active request from a user, the manner in which the prompt information is sent to the user may be, for example, a popup, in which the prompt information may be presented in a text manner. In addition, a selection control for the user to select to provide personal information to the electronic device in a 'consent' or 'disagreement' manner can be carried in the popup window.

It will be appreciated that the above-described notification and user authorization process is merely illustrative and not limiting of the implementations of the present disclosure, and that other ways of satisfying relevant legal regulations may be applied to the implementations of the present disclosure.

Meanwhile, it can be understood that the data (including but not limited to the data itself, the acquisition or the use of the data) related to the technical scheme should conform to the requirements of the corresponding laws and regulations and related regulations.

In a recommendation system, the quality of data basically determines the upper limit of the recommendation effect, and feature construction is one of important factors for determining the quality of data. Taking the information flow recommending scene as an example, the content pushed to the user can accord with the preference of the user, so that the preference degree of the user on the content can be measured through clicking, praying, forwarding, collecting and other data of the user on the content, and the content recommendation is realized according to the measurement result.

Taking clicking as an example, whether the content user pushed to the user is willing to click is generally related to factors such as inherent attributes of the user, historical interactions of the user, environment where the user is located, content itself and the like, besides the original user, the content itself and environment features, some cross features can be constructed by combining business understanding, namely, new features are obtained by combining features and features.

However, in the related art, the features are defined by adopting a code configuration mode, the larger the number of features to be created, the more corresponding codes to be configured, the larger the workload of coding, the less efficient the feature generation, and the more error is prone to the coding process.

In view of this, the embodiments of the present disclosure provide a feature generating method, apparatus, medium and electronic device for recommendation.

Embodiments of the present disclosure are explained and illustrated below with reference to the drawings.

FIG. 1 is a flowchart illustrating a feature generation method for recommendation, which may be performed by an electronic device such as a mobile terminal or a server, according to an exemplary embodiment, as shown in FIG. 1, the feature generation method for recommendation may include the steps of:

step 110, displaying a configuration interface, wherein the configuration interface comprises a feature configuration area.

The electronic device can respond to the configuration instruction to display the configuration interface. The feature configuration area is used for providing a visual interface and supporting a user to select target dependence, and then the corresponding target feature is generated based on the selection of the target dependence.

It is noted that the target dependency comprises features that are processed from feature raw values associated with the features and can be used directly for model processing, such as hash processing.

In step 120, in response to the target operation for the feature configuration region, a target dependency of the target operation hit is determined.

It is worth noting that the target dependency may include the feature that has been built and/or the feature original value used for feature building. Therefore, a feature that can be directly input as a model may be used as a target dependency, a feature original value that can define the feature may be used as a target dependency, or a feature and a feature original value that are different from the feature original value that defines the feature may be used together as a target dependency.

In response to the generating operation, a target feature is generated based on the target dependency, step 130.

Where a feature is targeted for dependence, the targeted feature may be a different feature than the feature.

In the case of taking the original value of the feature as the target dependency, the target feature may be a feature defined according to the original value of the feature, or may be a feature different from the defined feature.

According to the technical scheme, the code is not required to be manually written, a visual interface is provided, the corresponding target characteristics are obtained based on target dependence of target operation hit, the characteristic generation efficiency is improved, and meanwhile, the error rate of the characteristics obtained by manually writing the code is also reduced.

In some embodiments, the feature original values may include a window aggregation feature value, where the window aggregation feature value is used to characterize the number of target interactions performed by the user for different objects within a preset time window, and the step of generating the target feature based on the target dependency may be implemented by: responding to the generating operation, determining a target task for generating a window aggregation characteristic value, wherein the target task is used for counting the times of target interaction executed by a user aiming at different objects in a preset time window; acquiring an object corresponding to a target task based on the target task; and generating target features corresponding to the objects based on the window aggregation feature values and the objects, wherein the target features corresponding to the objects are used for representing the times of target interaction executed by a user aiming at the objects in a preset time window.

Wherein the object has the same physical meaning as the content in the description information flow recommendation scene, and the object can be an article such as soda, books, computers and the like. The target interactions described above may be, for example, purchase interactions, click interactions, collection interactions, and the like.

The target task of the window aggregation feature value may be referred to as a window aggregation task, where the target task is used to count the number of times of target interactions performed by the user for different objects in a preset time window.

The window aggregation characteristic value generated by the window aggregation task can aggregate user interaction into one according to the user and time. Because the window aggregation feature value aggregates user interactions together according to the user and the time, matching is needed to be performed with different objects (i.e., objects) based on the window aggregation feature value, so as to obtain features respectively corresponding to different objects, wherein the features are used for describing the times of executing target interactions on the objects by the user in a certain time period.

In the recommendation system, by adding the corresponding target features, the feature types in the sample are enhanced, so that the preference of the user can be better described.

According to the scheme, the target features corresponding to the objects are generated based on the window aggregation feature values and the objects, so that batch generation of the target features is realized.

In some embodiments, the target operation includes a first target operation, and the step of determining target dependence of the target operation hit in response to the target operation for the feature configuration region may be implemented by: responding to a first target operation aiming at the feature configuration area, and displaying candidate dependence hit by the first target operation; and determining the candidate dependency belonging to the first preset type as the target dependency.

In some embodiments, the first target operation may include a first sub-target operation and a second sub-target operation, the feature configuration area includes a filter by type control and a filter by data source control, and the step of displaying candidate dependencies hit by the first target operation in response to the first target operation of the feature configuration area may be implemented by: responding to a first sub-target operation aiming at a target control in a feature configuration area, displaying a feature selection area corresponding to the target control, wherein the target control is one of a type-based screening control and a data source-based screening control; in response to the second sub-target operation for the feature selection region, candidate dependencies for the second sub-target operation hit are displayed.

In this embodiment, both the first sub-target operation and the second sub-target operation are for screening candidate dependencies. The first sub-objective operation decides a way to filter candidate dependencies, and the second sub-objective operation filters candidate dependencies in a way that the first sub-objective operation decides to filter candidate dependencies. Specifically, after the first sub-target operation selects one of the type-by-type screening control and the data source-by-data source screening control, a feature selection area corresponding to the target control is displayed, and a second sub-target operation is further executed in the feature selection area.

FIG. 2 is a schematic diagram of a visualization interface of a feature configuration area, shown in accordance with an exemplary embodiment. As shown in fig. 2, the per-data-source screening control and the data source 1 are selected by a first target operation. For example, one of the type-by-type screening control and the data source-by-type screening control may be selected by a first sub-objective operation, the data source-by-type screening control is selected in FIG. 2, and in response to this selection, a feature selection region within the dashed box shown in FIG. 2 is displayed, and the data source 1 may be selected by a second sub-objective operation within the feature selection region, thereby displaying the list shown in FIG. 2 in which the field types, default extraction methods, parameters, and operations of sequence numbers 1-6 are displayed. The sequence numbers 1-6 represent candidate dependencies of hit, and the "operation" control corresponding to the sequence number shown in fig. 2 may be clicked, so that a function of configuring "parameters" shown in fig. 2, for example, a function of configuring "default extraction method" shown in fig. 2 may be implemented, for example, a function of deleting the corresponding sequence number from the list may be implemented. It should be noted that, the "default extraction method" is automatically configured according to the field type of the sequence number, and the sequence number corresponding to the extraction method of the Match type, for example, the field type of the window aggregation feature value.

Further, by clicking on "confirm batch generation" shown in fig. 2, a generation operation may be triggered.

In general, the data of the window aggregation feature value meets a certain requirement, so that the candidate dependency belonging to the first preset type can be further determined as the target dependency, and the first preset type is set according to the requirement that the data of the window aggregation feature value meets.

Through the technical scheme, the visual interface is provided for operators to perform relevant configuration, semantic information provided by the visual interface is rich, the operation is convenient, and the generation of the features can be completed without the need of having relevant code expertise by the operators.

In some embodiments, the above method may further comprise the steps of: and displaying the target feature and a prompt message corresponding to the target feature, wherein the prompt message is used for reflecting whether the object corresponding to the target feature is a defined feature or not.

It should be noted that some objects may not be defined as features, and thus, the target features corresponding to such objects may be misreported when in use, and thus, a prompt message of the target features may be generated and displayed.

Therefore, an operator can be provided to redefine the objects, and the error reporting caused by using the target characteristics corresponding to the objects is avoided.

In some embodiments, the target operation may further include a second target operation, the feature that has been completed to be constructed includes a first feature to be combined and a plurality of second features to be combined, and the step of determining target dependence on the target operation in the feature configuration area in response to the target operation further includes: responding to a second target operation aiming at candidate dependences belonging to a second preset type, and determining a plurality of second features to be combined, which are hit by the second target operation, wherein the candidate dependences belonging to the second preset type are first features to be combined; the plurality of second features to be combined and the first features to be combined are determined as target dependencies.

Wherein the first feature to be combined and the plurality of second features to be combined may be constructed features.

For the mode of combining the characteristics to obtain the target characteristics, the two characteristics for splicing have no implicit logic relationship, and are completely specified by operators, but the efficiency of defining the combined characteristics can be improved by improving the interaction form, so that the batch generation of the combined characteristics is realized.

FIG. 3 is a schematic diagram illustrating a visual interface for performing a second target operation, according to an example embodiment. As an example, the "operation" control shown in fig. 2 may be clicked, the interface shown in fig. 3 is displayed, further, based on the second target operation executed in fig. 3, multiple selections of "features" are implemented, multiple second features to be combined are determined based on multiple selections, and the feature corresponding to the serial number corresponding to the "operation" control shown in fig. 2 may be clicked as the first feature to be combined.

The second preset type may be an exponent group, and satisfies that the internal data of the exponent group is the ulong data type. As an example, the second feature to be combined also belongs to the second preset type of feature.

Referring to fig. 4, in fig. 4, listA is taken as a first feature to be combined, and ListB1, listB2, listB3, and ListB4 are taken as a plurality of second features to be combined. ListA is combined with ListB1, listB2, listB3, and ListB4, respectively, to yield a corresponding plurality of target features, namely ListA_ListB1_ combine, listA _ListB2_ combine, listA _ListB3_combination and LitA_ListB4_combination, as shown in FIG. 4.

For the combination manner of the second feature to be combined and the first feature to be combined, each element in the first feature to be combined may be combined with each element in the second feature to be combined. The second feature to be combined and the first feature to be combined are two different arrays, the output result is a new array, the values of the new array are obtained by crossing the values of two elements, one element is an element in the first feature to be combined, and the other element is an element in the second feature to be combined. Illustratively, the first feature to be combined is [ a, b ], the second feature to be combined is [ c, d ], and the result of the crossover is [ ac, ad, bc, bd ].

In some embodiments, the feature generation method for recommendation may further include: acquiring a target object, and acquiring preference characteristics corresponding to a target user, wherein the preference characteristics comprise target characteristics; based on the target object and the preference characteristics, whether the target object is pushed to a target terminal is determined, and the target terminal corresponds to a target user.

The target object is an object to be recommended, the target object has the same physical meaning as the content in the description information flow recommendation scene, and the target object can be an article, such as soda, books, computers and the like.

In this embodiment, whether the target object is pushed to the target terminal may be determined based on whether the target object is interested in the target object, which may be determined based on preference characteristics of the target object corresponding to the target user.

For example, taking click interaction as an example, a recommendation model can be trained in advance, preference characteristics corresponding to a target object and a target user are processed by using the recommendation model, the click rate of the target object by the target user is predicted, when the click rate is high, the target object is determined to be interested by the target user, and the target object is determined to be pushed to a target terminal; otherwise, when the click rate is low, the target user is determined to be not interested in the target object, and the target object is determined not to be pushed to the target terminal.

By the method, recommendation of the target object is achieved based on the obtained target characteristics.

Based on the same inventive concept, the embodiment of the disclosure also provides a feature generation device for recommendation. FIG. 5 is a block diagram illustrating a feature generation apparatus for recommendation, as shown in FIG. 5, according to an exemplary embodiment, the feature generation apparatus for recommendation 500 includes:

a first display module 501, configured to display a configuration interface, where the configuration interface includes a feature configuration area;

a first response module 502, configured to determine, in response to a target operation for the feature configuration area, a target dependency hit by the target operation, where the target dependency includes a feature that has been completely constructed and/or a feature original value for feature construction;

and a second response module 503, configured to generate a target feature based on the target dependency in response to the generating operation.

Optionally, the feature original value includes a window aggregation feature value, where the window aggregation feature value is used to characterize the number of times of target interaction performed by the user for different objects in a preset time window, and the second response module 503 includes:

the first response sub-module is used for responding to the generation operation, determining a target task for generating the window aggregation characteristic value, wherein the target task is used for counting the times of target interaction executed by a user in a preset time window aiming at different objects;

the first acquisition sub-module is used for acquiring an object corresponding to the target task based on the target task;

the first generation sub-module is used for generating target features corresponding to the objects based on the window aggregation feature values and the objects, and the target features corresponding to the objects are used for representing the times of target interaction executed by the user for the objects in a preset time window.

Optionally, the target operation includes a first target operation, and the first response module 502 includes:

a second response sub-module for responding to a first target operation aiming at the characteristic configuration area and displaying candidate dependence hit by the first target operation;

and the first determining submodule is used for determining the candidate dependency belonging to the first preset type as the target dependency.

Optionally, the apparatus 500 further includes:

and the second display module is used for displaying the target feature and a prompt message corresponding to the target feature, wherein the prompt message is used for reflecting whether an object corresponding to the target feature is a defined feature or not.

Optionally, the target operations further include a second target operation, the constructed feature includes a first feature to be combined and a plurality of second features to be combined, and the first response module 502 further includes:

a third response sub-module, configured to determine, in response to a second target operation for candidate dependencies belonging to a second preset type, a plurality of second features to be combined hit by the second target operation, where the candidate dependencies belonging to the second preset type are the first features to be combined;

and the second determining submodule is used for determining the plurality of second features to be combined and the first features to be combined as target dependence.

Optionally, the first target operation includes a first sub-target operation and a second sub-target operation, the feature configuration area includes a filtering control by type and a filtering control by data source, and the second response sub-module is specifically configured to:

responding to a first sub-target operation aiming at a target control in the feature configuration area, and displaying a feature selection area corresponding to the target control, wherein the target control is one of the type-based screening control and the data source-based screening control;

and responding to a second sub-target operation aiming at the characteristic selection area, and displaying candidate dependence hit by the second sub-target operation.

Optionally, the apparatus 500 further includes:

the acquisition module is used for acquiring a target object and acquiring preference characteristics corresponding to a target user, wherein the preference characteristics comprise target characteristics;

and the pushing module is used for determining whether to push the target object to a target terminal based on the target object and the preference characteristics, and the target terminal corresponds to the target user.

The embodiments of each module in the above apparatus may refer to the above related embodiments, which are not described herein.

Based on the same inventive concept, the embodiments of the present disclosure also provide a computer-readable medium having stored thereon a computer program which, when executed by a processing device, implements the steps of the above-described feature generation method.

Based on the same inventive concept, the embodiments of the present disclosure further provide an electronic device, including:

a storage device having a computer program stored thereon;

Referring now to fig. 6, a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 6 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 6, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

In general, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

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 non-transitory 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 communication means 609, or from storage means 608, or from ROM 602. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 601.

It should be noted that the computer readable medium described in the present disclosure 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 disclosure, 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 disclosure, 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: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the electronic device may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: displaying a configuration interface, wherein the configuration interface comprises a feature configuration area; determining target dependence hit by the target operation in response to the target operation aiming at the feature configuration area, wherein the target dependence comprises a feature which is built completely and/or a feature original value for feature construction; and generating target features based on the target dependencies in response to the generating operation.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ 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 computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

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 disclosure. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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 described in the embodiments of the present disclosure may be implemented in software or hardware. The name of a module does not in some cases define the module itself.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims. The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

Claims

1. A feature generation method for recommendation, comprising:

2. The feature generation method according to claim 1, wherein the feature original values include window aggregation feature values for characterizing a number of target interactions performed by a user for different objects within a preset time window, the response generation operation generating a target feature based on the target dependency, comprising:

responding to the generating operation, determining a target task for generating the window aggregation characteristic value, wherein the target task is used for counting the times of target interaction executed by a user aiming at different objects in a preset time window;

acquiring an object corresponding to the target task based on the target task;

and generating target features corresponding to the objects based on the window aggregation feature values and the objects, wherein the target features corresponding to the objects are used for representing the times of target interaction executed by the user for the objects in a preset time window.

3. The feature generation method according to claim 2, wherein the target operation includes a first target operation, the responding to the target operation for the feature configuration area determining a target dependency on which the target operation hits, comprising:

responding to a first target operation aiming at the characteristic configuration area, and displaying candidate dependence hit by the first target operation;

and determining the candidate dependency belonging to the first preset type as the target dependency.

4. The feature generation method according to claim 2, characterized in that the method further comprises:

and displaying the target feature and a prompt message corresponding to the target feature, wherein the prompt message is used for reflecting whether an object corresponding to the target feature is a defined feature or not.

5. The feature generation method of claim 3, wherein the target operations further comprise a second target operation, the completed features comprise a first feature to be combined and a plurality of second features to be combined, the responding to the target operation of the feature configuration area, determining a target dependency hit by the target operation, further comprising:

responding to a second target operation aiming at candidate dependences belonging to a second preset type, and determining a plurality of second features to be combined hit by the second target operation, wherein the candidate dependences belonging to the second preset type are the first features to be combined;

and determining the plurality of second features to be combined and the first features to be combined as target dependencies.

6. The feature generation method of claim 3, wherein the first target operation comprises a first sub-target operation and a second sub-target operation, the feature configuration region comprises a per-type filter control and a per-data source filter control, the responding to the first target operation for the feature configuration region displays a dependent feature hit by the first target operation, comprising:

7. The feature generation method according to any one of claims 1 to 6, characterized by further comprising:

acquiring a target object and acquiring preference characteristics corresponding to a target user, wherein the preference characteristics comprise target characteristics;

and determining whether to push the target object to a target terminal based on the target object and the preference characteristics, wherein the target terminal corresponds to the target user.

8. A feature generation apparatus for recommendation, comprising:

9. A computer readable medium on which a computer program is stored, characterized in that the program, when being executed by a processing means, carries out the steps of the feature generation method of any one of claims 1-7.

10. An electronic device, comprising:

a storage device having a computer program stored thereon;

processing means for executing said computer program in said storage means to carry out the steps of the feature generation method of any one of claims 1 to 7.