CN114119139A - Information recommendation method and device, storage medium and electronic equipment - Google Patents
Information recommendation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114119139A CN114119139A CN202111294011.1A CN202111294011A CN114119139A CN 114119139 A CN114119139 A CN 114119139A CN 202111294011 A CN202111294011 A CN 202111294011A CN 114119139 A CN114119139 A CN 114119139A
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation
- combinations
- determining
- information
- 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; CALCULATING OR 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—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The specification discloses an information recommendation method, an information recommendation device, a storage medium and electronic equipment, wherein a plurality of element types corresponding to a recommendation component can be determined in response to an event for showing the recommendation component to a user, and each element to be selected corresponding to each element type is determined according to user information of the user when the event is triggered. And then, determining a plurality of element combinations according to each element to be selected corresponding to each element type, screening a plurality of element combinations to be selected based on the predicted click rate corresponding to each element combination, and storing. After receiving an information recommendation request sent by a user, determining a target combination according to preset service indexes and various combinations to be selected, regenerating a recommendation component based on the target combination, and displaying recommendation to the user. The elements to be selected of each element type are combined, and the element combinations are screened to generate the recommendation components, so that the hit rate of the recommendation components and the richness of the recommendation components are improved, and the decision experience of a user is further improved.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to an information recommendation method and apparatus, a storage medium, and an electronic device.
Background
With the development of big data technology, more and more e-commerce platforms recommend merchants or commodities to users through recommendation systems so as to improve the decision-making experience of the users. For example, the merchant information is displayed to the user by means of page pop-up, or the commodity information is displayed at the banner position of the page.
Taking the recommendation of a merchant through a page popup as an example, a popup component of a page popup generally consists of multiple element types, such as a popup style, a merchant brand, a user's evaluation of the merchant, and a commodity image of the merchant. When the pop-up window assembly displayed to the user is generated, for each element type corresponding to the pop-up window assembly, the display element with the best element type is screened from a plurality of elements to be selected of the element type, and the pop-up window assembly is formed by combining the display elements of all the element types.
Assuming that the popup component comprises three element types of a merchant brand, a popup pattern and a commodity image of a merchant, the popup pattern with the highest click rate can be screened based on the historical click rate of each popup pattern to be selected, a plurality of merchants nearby the user can be recalled based on the real-time position of the user, and then the recommended merchants are screened according to the good-scoring scores of the merchants. Then, a product image of a recommended product is determined from the plurality of products offered by the merchant according to the sales volume of the product. And finally, combining the determined pop-up window style, the recommended merchant and the commodity image to form a pop-up window assembly to be displayed.
However, by independently screening each element type, influences among the element types are often ignored, so that the recommendation hit rate of the combined popup component is low, and the decision experience of a user is influenced.
Disclosure of Invention
The embodiment of the specification provides an information recommendation method, an information recommendation device, a storage medium and electronic equipment, which are used for partially solving the problems in the prior art.
The embodiment of the specification adopts the following technical scheme:
the information recommendation method provided by the specification comprises the following steps:
in response to an event that a recommended component is presented to a user, determining a plurality of element types corresponding to the recommended component;
determining each element to be selected corresponding to each element type according to the user information of the user when the event is triggered;
determining a plurality of element combinations according to each element to be selected corresponding to each element type, screening the plurality of combinations to be selected based on the predicted click rate corresponding to each element combination, and storing the plurality of combinations to be selected;
and after receiving an information recommendation request sent by the user, determining a target combination according to preset service indexes and stored combinations to be selected, and regenerating a recommendation component according to the target combination so as to display the recommendation component to the user.
Optionally, determining each element to be selected corresponding to each element type according to the user information of the user when the event is triggered, specifically including:
determining each element to be selected corresponding to each element type according to the position information of the user when the event is triggered; and/or
And determining each element to be selected corresponding to each element type according to the portrait information of the user when the event is triggered.
Optionally, screening a plurality of combinations to be selected based on the predicted click rate corresponding to each element combination specifically includes:
inputting each element combination into a click prediction model trained in advance, and determining a predicted click rate corresponding to the element combination; the click prediction model is obtained based on historical click rate training of recommended components generated by the user on each element combination;
and screening a plurality of element combinations from each element combination according to the sequence of the predicted click rate corresponding to each element combination to be used as a combination to be selected.
Optionally, before determining the target combination, the method further comprises:
and determining that the time interval between the two latest information recommendation requests sent by the user is less than a preset time.
Optionally, there is an association relationship between the at least some element types;
determining a plurality of element combinations according to each element to be selected corresponding to each element type, wherein the element combinations specifically comprise:
and determining a plurality of element combinations according to the incidence relation among the element types and the elements to be selected corresponding to each element type.
Optionally, determining a target combination according to a preset service index and each stored candidate combination, specifically including:
and determining a target combination from the stored combinations to be selected according to the portrait information of the user and a preset service index.
Optionally, the element types corresponding to the recommendation component include at least some types of style templates, merchants, goods, images, and documentaries.
The present specification provides an information recommendation apparatus including:
the first determination module is configured to respond to an event for showing the recommendation component to a user and determine a plurality of element types corresponding to the recommendation component;
the second determining module is configured to determine each element to be selected corresponding to each element type according to the user information of the user when the event is triggered;
the storage module is configured to determine a plurality of element combinations according to each element to be selected corresponding to each element type, screen the plurality of combinations to be selected based on the predicted click rate corresponding to each element combination, and store the plurality of combinations to be selected;
and the recommendation module is configured to determine a target combination according to preset service indexes and stored combinations to be selected after receiving an information recommendation request sent by the user, and regenerate a recommendation component according to the target combination so as to display the recommendation component to the user.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described information recommendation method.
The electronic device provided by the present specification includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the information recommendation method when executing the program.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:
in this specification, in response to an event that a recommendation component is presented to a user, a plurality of element types corresponding to the recommendation component may be determined, and each element to be selected corresponding to each element type may be determined according to user information of the user when the event is triggered. And then, determining a plurality of element combinations according to each element to be selected corresponding to each element type, screening a plurality of element combinations to be selected based on the predicted click rate corresponding to each element combination, and storing. After receiving an information recommendation request sent by a user, determining a target combination according to preset service indexes and various combinations to be selected, regenerating a recommendation component based on the target combination, and displaying recommendation to the user. The elements to be selected of each element type are combined, and the element combinations are screened to generate the recommendation components, so that the hit rate of the recommendation components and the richness of the recommendation components are improved, and the decision experience of a user is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic combination diagram of a combination of elements provided in an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of an information recommendation method provided in an embodiment of the present specification;
FIG. 3 is a schematic combination diagram of a combination of elements provided in an embodiment of the present disclosure;
fig. 4 is a schematic view of a pop-up window assembly provided in an embodiment of the present disclosure;
fig. 5 is a schematic view of a pop-up window assembly provided in an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a banner assembly as provided by embodiments of the present disclosure;
fig. 7 is a schematic structural diagram of an information recommendation device provided in an embodiment of the present specification;
fig. 8 is a schematic view of an electronic device implementing an information recommendation method provided in an embodiment of the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more apparent, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person skilled in the art without making any inventive step based on the embodiments in the description belong to the protection scope of the present application.
Generally, the e-commerce platform can recommend information to a user through a recommendation system, for example, merchant information is displayed in a page pop-up window mode, commodity information is displayed in a banner recommendation position of a home page, and the like.
Taking the display mode of the page popup as an example, when the popup component to be displayed is generated, the types of the elements forming the popup component, such as the style template of the popup, the merchant to be recommended, the brand image of the merchant to be displayed, and the like, may be determined first. And then determining the elements to be selected of each element type, and determining the popup component to be displayed based on the combination of the elements to be selected of each element type.
When the existing online recommendation system generates the pop-up window component, the element with the highest index ranking can be selected from various elements to be selected of the element type according to a preset screening index and aiming at each element type forming the pop-up window component, and the element is used as a display element. And generating the popup component by combining the display elements of the element types.
However, the method of independently screening each element type ignores the association relationship among the element types, so that the final combination result is not the best display effect, and the recommendation hit rate is low.
Therefore, in order to screen the optimal element combination, obtain the optimal recommendation effect and improve the richness of the displayed elements, all possible combination results can be determined based on each element to be selected of each element type, and then the combination with the highest click rate is selected from a large number of element combinations to generate the popup component.
As shown in fig. 1, assuming that the pop-up window module is composed of element types 1 to 3, where there are two types of elements to be selected in the element type 1, 3 types of elements to be selected in the element type 2, and 6 types of elements to be selected in the element type 3, cross-combination is performed, and 2 × 3 × 6 — 36 element combinations can be obtained.
However, since the online recommendation system is a user-oriented service, and needs to provide a real-time recommendation service in response to a user operation, the online recommendation system often cannot perform large-scale calculation in consideration of response time. The above-mentioned method of determining all possible combinations of elements and performing combined screening requires a lot of computing resources and a long computing time, and cannot be computed in real time from the online side.
When the time interval of the user accessing the same page twice is short, the position and preference of the user are small in change, and the contact ratio of information recalled twice is high. Therefore, the information recommendation method provided by the present specification may calculate, on the basis of each candidate element recalled when information recommendation is recently performed on the user, an element combination of each candidate element on the near-line side, perform preliminary screening on each element combination, and write a preliminary screening result into the cache, so that when information recommendation is performed on the user again, a pop-up window component displayed to the user may be generated on the basis of a preliminary screening result with a higher overlap ratio.
The near-line side of the recommendation system can acquire real-time data of the platform, real-time service is not required to be provided, the limitation of response time is avoided, large-scale calculation can be carried out on the real-time data, and calculation results are written into a cache for being read by the online service.
The present specification provides an information recommendation method, and the following describes technical solutions provided in embodiments of the present application in detail with reference to the accompanying drawings.
Fig. 2 is a schematic flow chart of an information recommendation method provided in an embodiment of this specification, which may specifically include the following steps:
s100: in response to an event that presents a recommended component to a user, a number of element types corresponding to the recommended component are determined.
When recommending information to a user, a common e-commerce platform can display the information in a recommendation component form, such as a pop-up window component of a page pop-up window, a banner component of a banner position of a home page, and the like. The recommended content displayed by the recommending component can be determined based on user information such as the real-time position and the real-time preference of the user.
For example, when a page popup mode is adopted to recommend merchants to a user, the displayed popup component is composed of a plurality of element types such as a style template, merchants, merchant brand images and the like, so that a plurality of nearby merchants can be recalled according to the real-time position of the user, and the popup component is obtained by combining the recalled merchants, the style template of the popup component and the brand images of each merchant so as to be displayed.
Based on the analysis, in the present specification, each candidate element recalled during recent recommendation may be determined based on recent information recommendation of the user, each element combination may be calculated on the near-line side, and each element combination may be preliminarily screened.
Specifically, in response to an event that historically presents a recommended component to a user, a number of element types corresponding to the recommended component may be determined first. The recommendation component may be a pop-up window component, a banner component in a page, or other components for displaying recommendation information, which is not limited in this specification and may be set as needed. The element types corresponding to the recommendation components comprise at least part of types of style templates, merchants, commodities, images and documents, and the documents can be user evaluation or recommendation slogans of the merchants and other information. The types of elements corresponding to different types of recommended components also differ, e.g., the types of elements required to compose the pop-up window component are not exactly the same as the types of elements required to compose the banner component.
Further, since the shorter the time interval for making information recommendation, the higher the degree of coincidence of recalled information, the subsequent steps may be performed in response to the event that the user was historically presented with the recommended component the last time.
It should be noted that the information recommendation method provided in this specification may be executed by a server executing the information recommendation service in the e-commerce platform, where the server may be a single server, or may be a system composed of multiple servers, such as a distributed server system, and may be a physical server device, or may be a cloud server, and this specification does not limit this, and may be set as needed.
The e-commerce platform can comprise an e-commerce platform such as a take-out platform and a fresh platform. For convenience of description, the e-commerce platform is taken as a takeout platform for illustration.
S102: and determining each element to be selected corresponding to each element type according to the user information of the user when the event is triggered.
S104: determining a plurality of element combinations according to each element to be selected corresponding to each element type, screening the plurality of combinations to be selected based on the predicted click rate corresponding to each element combination, and storing the plurality of combinations to be selected.
In this specification, the elements to be selected recalled for each element type may be determined based on user information in recent information recommendation to the user, and then combined based on each element to be selected. For convenience of description, the description is given by taking the recommendation component as a page popup in the present specification.
Specifically, first, each element to be selected corresponding to each element type constituting the popup component may be determined according to user information of a user when the event is triggered. The user information is carried in an information recommendation request sent by a user, and the user information at least comprises portrait information of the user, current position information of the user and the like. And then, combining the elements to be selected corresponding to each element type to determine a plurality of element combinations.
Suppose that the pop-up window component consists of three element types, a style template, a merchant, and a merchant brand image. And aiming at the pattern template, determining each template to be selected displayed to the user from a plurality of preset pattern templates according to the portrait information of the user. For the merchants, according to the position information in the information recommendation request sent by the user, a plurality of merchants in a nearby preset range can be recalled as merchants to be selected. And aiming at the brand images of the merchants, determining the brand images of the recalled merchants as images to be selected.
Further, in order to improve the richness of information recommendation, the popup component may also display contents such as a commodity image of a merchant and evaluation information of a user on the merchant, and because the commodity image and the evaluation information have an association relationship with the merchant, when there is an association relationship between each element type constituting the popup component, it is also necessary to determine a plurality of element combinations according to the association relationship between each element type and each element to be selected corresponding to each element type.
As shown in FIG. 3, assume that the pop-up window component consists of three element types, a style template, a merchant, and a merchandise image. The to-be-selected style template comprises a template 1 and a template 2, the to-be-selected merchants comprise a merchant A, a merchant B and a merchant C, the to-be-selected commodity images of the merchant A comprise a1 and a2, the to-be-selected commodity images of the merchant B comprise B1 and B2, and the to-be-selected commodity images of the merchant C comprise C1 and C2. Because the association relationship exists between the merchants and the commodity images, each merchant to be selected can only be combined with the commodity image of the merchant when the cross combination is carried out.
After rich element combinations are determined, preliminary screening can be performed on each element combination, so that preliminary screening results are written into a cache for online service reading.
In one or more embodiments of the present disclosure, the initial screening may be performed based on the click rate of each element combination, and for each element combination, the element combination may be input into a click prediction model trained in advance, so as to determine a predicted click rate corresponding to the element combination. The click prediction model can be obtained based on historical click rate training of recommended components generated by the user on each element combination. Then, according to the sequence of the predicted click rate corresponding to each element combination, a plurality of element combinations are screened from each element combination to be used as the combinations to be selected, and the screened combinations to be selected are stored. And when information recommendation is carried out subsequently, the recommendation component displayed for the user can be determined based on each candidate combination with higher contact ratio.
S106: and after receiving an information recommendation request sent by the user, determining a target combination according to preset service indexes and stored combinations to be selected, and regenerating a recommendation component according to the target combination so as to display the recommendation component to the user.
In this specification, if the online recommendation system receives the information recommendation request sent by the user again, the pop-up window component displayed to the user may be determined directly based on each combination to be selected stored in the cache.
Specifically, after receiving an information recommendation request sent by the user, the target combination can be determined from stored combinations to be selected according to preset service indexes. The service index may be a gain brought by recommending information to the user, such as a placing conversion rate of the user, a click rate of the user, an advertisement fee of a merchant, and the like. And then, regenerating the popup window component according to the target combination, and sending the popup window component to the user terminal for displaying.
Further, when the time interval for recommending information to the user is short, the contact degree of the two recalling information is high, and when the time interval is long, the real-time position of the user, the image information and the like may be changed, so that the contact degree of the recalling information is reduced.
Therefore, when the information recommendation request sent by the user is received again, whether the time interval between the two latest information recommendation requests sent by the user is less than the preset time length or not can be judged, if so, the contact ratio of the two recalling information is higher, and the displayed popup window component can be generated based on the combination of all elements in the cache. If the preset duration is exceeded, the contact ratio of the two-time recall information is low, and the prior art method can be still adopted to independently screen each element type respectively to generate the popup component. The preset time period can be set as required, such as 5 minutes, 1 hour, and the like.
Based on the information recommendation method shown in fig. 2, in response to an event that a recommendation component is presented to a user, a plurality of element types corresponding to the recommendation component may be determined first, and each element to be selected corresponding to each element type is determined according to user information of the user when the event is triggered. And then, determining a plurality of element combinations according to each element to be selected corresponding to each element type, screening a plurality of element combinations to be selected based on the predicted click rate corresponding to each element combination, and storing. After receiving an information recommendation request sent by a user, determining a target combination according to preset service indexes and various combinations to be selected, regenerating a recommendation component based on the target combination, and displaying recommendation to the user. The elements to be selected of each element type are combined, and the element combinations are screened to generate the recommendation components, so that the hit rate of the recommendation components and the richness of the recommendation components are improved, and the decision experience of a user is further improved.
In one embodiment of the present description, a popup component is presented to a user as shown in fig. 4, and the popup component contains a style template, a merchant, an image of a commodity, and four element types for user evaluation. Because only one merchant is recommended to be displayed in the pop-up window component, when the pop-up window component is generated, a target combination consisting of the pattern template 1, the merchant A, the commodity image a and the user evaluation content 1 can be determined from all element combinations based on preset service indexes.
In another embodiment of the present specification, a pop-up window component is shown in fig. 5, where the pop-up window component includes two element types of merchants and their brand images, and may be used to recommend to show 3 merchants at the same time, so when generating the pop-up window component, based on a preset business index, from element combinations of each candidate merchant and its brand image, target combinations of top 3 in the sequence may be determined, which are (merchant a, brand image a), (merchant B, brand image B), (merchant C, and brand image C), respectively. And then generating a displayed popup window assembly based on the determined target combinations.
In an embodiment of the present specification, the information recommendation method provided by the present specification can also be used to generate a banner component of the page, as shown in fig. 6, where the banner component includes three element types, namely, a merchant, a brand image, and a dish image, and can be switched by sliding left and right. When the banner component is generated, the sequencing of each element combination can be determined based on preset service indexes, and a plurality of target combinations to be displayed are determined according to the sequencing result. And then, adding each target combination into the task queue to be sequentially displayed according to the banner display sequence.
Further, in step S106 of this specification, when the online recommendation system performs real-time recommendation, a target combination may be determined from stored combinations to be selected in combination with portrait information of the user and a preset service index, so as to generate a pop-up window component. The portrait information of the user at least comprises historical behavior information of the user, such as merchants browsed by the user history, merchants ordered by the user history and the like.
Furthermore, although the information recalled by two adjacent recommendations has high overlap ratio, partial difference still exists, so when an information recommendation request sent by a user is received, the online recommendation system can also recall a plurality of nearby merchants based on the real-time position information of the user in the information recommendation request and roughly arrange the merchants according to preset indexes (sales volume, star level and the like). And then, carrying out fine ranking on each to-be-selected combination of the cache according to the coarse ranking result, and determining a target combination from the to-be-selected combinations.
For example, assuming that the result of the rough ranking is E merchant, F merchant, G merchant, and the ranking of the combinations to be selected determined according to the click-through rate is (F merchant, brand image F), (G merchant, brand image G), (M merchant, brand image M), the ranking of the two is combined to determine that the target combination to be displayed is (F merchant, brand image F).
Based on the information recommendation method shown in fig. 2, an embodiment of the present specification further provides a schematic structural diagram of an information recommendation apparatus, as shown in fig. 7.
Fig. 7 is a schematic structural diagram of an information recommendation apparatus provided in an embodiment of this specification, including:
the first determining module 200 is configured to determine a plurality of element types corresponding to the recommended components in response to an event that the recommended components are presented to a user;
a second determining module 202, configured to determine, according to the user information of the user when the event is triggered, each element to be selected corresponding to each element type;
the storage module 204 is configured to determine a plurality of element combinations according to each element to be selected corresponding to each element type, screen the plurality of combinations to be selected based on the predicted click rate corresponding to each element combination, and store the plurality of combinations to be selected;
and the recommending module 206 is configured to determine a target combination according to preset service indexes and stored combinations to be selected after receiving an information recommending request sent by the user, and regenerate a recommending component according to the target combination so as to show the recommending component to the user.
Optionally, the second determining module 202 is specifically configured to determine, according to the location information of the user when the event is triggered, each to-be-selected element corresponding to each element type; and/or determining each element to be selected corresponding to each element type according to the portrait information of the user when the event is triggered.
Optionally, the storage module 204 is specifically configured to, for each element combination, input the element combination into a click prediction model trained in advance, and determine a predicted click rate corresponding to the element combination; the click prediction model is obtained based on historical click rate training of recommended components generated by the user on each element combination, and a plurality of element combinations are screened from each element combination to serve as combinations to be selected according to the ranking of the predicted click rate corresponding to each element combination.
Optionally, the recommending module 206 is further configured to determine that a time interval between two latest times of sending information recommendation requests by the user is less than a preset time length.
Optionally, there is an association relationship between at least some of the element types, and the recommending module 206 is specifically configured to determine a plurality of element combinations according to the association relationship between the element types and each element to be selected corresponding to each element type.
Optionally, the recommending module 206 is specifically configured to determine a target combination from stored combinations to be selected according to the portrait information of the user and a preset service index.
Optionally, the element types corresponding to the recommendation component include at least some types of style templates, merchants, goods, images, and documentaries.
Embodiments of the present specification further provide a computer-readable storage medium, where the storage medium stores a computer program, and the computer program may be used to execute the information recommendation method provided in fig. 2.
According to an information recommendation method shown in fig. 2, an embodiment of the present specification further provides a schematic structural diagram of the electronic device shown in fig. 8. As shown in fig. 8, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the information recommendation method shown in fig. 2.
Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and create a dedicated integrated circuit chip. Furthermore, nowadays, instead of manually generating an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardbyscript Description Language (vhigh Description Language), and so on, which are currently used in the most popular languages. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. An information recommendation method, comprising:
in response to an event that a recommended component is presented to a user, determining a plurality of element types corresponding to the recommended component;
determining each element to be selected corresponding to each element type according to the user information of the user when the event is triggered;
determining a plurality of element combinations according to each element to be selected corresponding to each element type, screening the plurality of combinations to be selected based on the predicted click rate corresponding to each element combination, and storing the plurality of combinations to be selected;
and after receiving an information recommendation request sent by the user, determining a target combination according to preset service indexes and stored combinations to be selected, and regenerating a recommendation component according to the target combination so as to display the recommendation component to the user.
2. The method according to claim 1, wherein determining, according to the user information of the user when the event is triggered, each element to be selected corresponding to each element type specifically includes:
determining each element to be selected corresponding to each element type according to the position information of the user when the event is triggered; and/or
And determining each element to be selected corresponding to each element type according to the portrait information of the user when the event is triggered.
3. The method of claim 1, wherein screening a plurality of combinations to be selected based on the predicted click rate corresponding to each element combination specifically comprises:
inputting each element combination into a click prediction model trained in advance, and determining a predicted click rate corresponding to the element combination; the click prediction model is obtained based on historical click rate training of recommended components generated by the user on each element combination;
and screening a plurality of element combinations from each element combination according to the sequence of the predicted click rate corresponding to each element combination to be used as a combination to be selected.
4. The method of claim 1, wherein prior to determining the target combination, the method further comprises:
and determining that the time interval between the two latest information recommendation requests sent by the user is less than a preset time.
5. The method of claim 1, wherein there is an associative relationship between the at least some element types;
determining a plurality of element combinations according to each element to be selected corresponding to each element type, wherein the element combinations specifically comprise:
and determining a plurality of element combinations according to the incidence relation among the element types and the elements to be selected corresponding to each element type.
6. The method of claim 1, wherein determining the target combination according to the preset service index and each stored candidate combination specifically comprises:
and determining a target combination from the stored combinations to be selected according to the portrait information of the user and a preset service index.
7. The method of claim 1, wherein the element types corresponding to the recommendation component include at least some types of style templates, merchants, goods, images, and paperwork.
8. An information recommendation apparatus, comprising:
the first determination module is configured to respond to an event for showing the recommendation component to a user and determine a plurality of element types corresponding to the recommendation component;
the second determining module is configured to determine each element to be selected corresponding to each element type according to the user information of the user when the event is triggered;
the storage module is configured to determine a plurality of element combinations according to each element to be selected corresponding to each element type, screen the plurality of combinations to be selected based on the predicted click rate corresponding to each element combination, and store the plurality of combinations to be selected;
and the recommendation module is configured to determine a target combination according to preset service indexes and stored combinations to be selected after receiving an information recommendation request sent by the user, and regenerate a recommendation component according to the target combination so as to display the recommendation component to the user.
9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111294011.1A CN114119139A (en) | 2021-11-03 | 2021-11-03 | Information recommendation method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111294011.1A CN114119139A (en) | 2021-11-03 | 2021-11-03 | Information recommendation method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114119139A true CN114119139A (en) | 2022-03-01 |
Family
ID=80380973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111294011.1A Pending CN114119139A (en) | 2021-11-03 | 2021-11-03 | Information recommendation method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114119139A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131838A (en) * | 2023-10-24 | 2023-11-28 | 天津异乡好居网络科技股份有限公司 | Form page generation method and device based on form image, electronic equipment and medium |
-
2021
- 2021-11-03 CN CN202111294011.1A patent/CN114119139A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131838A (en) * | 2023-10-24 | 2023-11-28 | 天津异乡好居网络科技股份有限公司 | Form page generation method and device based on form image, electronic equipment and medium |
| CN117131838B (en) * | 2023-10-24 | 2024-02-09 | 天津异乡好居网络科技股份有限公司 | Form page generation method and device based on form image, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537568B (en) | Information recommendation method and device | |
| CN113688313A (en) | Training method of prediction model, information pushing method and device | |
| CN111144974B (en) | Information display method and device | |
| CN112966186A (en) | Model training and information recommendation method and device | |
| CN107590205A (en) | A kind of service showing method, device and equipment | |
| CN110599307A (en) | Commodity recommendation method and device | |
| CN110766513A (en) | Information sorting method and device, electronic equipment and readable storage medium | |
| CN115048577A (en) | Model training method, device, equipment and storage medium | |
| CN111191132A (en) | Information recommendation method and device and electronic equipment | |
| CN113641894A (en) | Information recommendation method and device | |
| CN114119139A (en) | Information recommendation method and device, storage medium and electronic equipment | |
| CN113010809A (en) | Information recommendation method and device | |
| CN112561162A (en) | Information recommendation method and device | |
| CN112966577A (en) | Method and device for model training and information providing | |
| CN110033383B (en) | Data processing method, device, medium and apparatus | |
| CN113343085B (en) | Information recommendation method and device, storage medium and electronic equipment | |
| CN114676351A (en) | Method, device and equipment for determining recommended position and storage medium | |
| CN114860967A (en) | Model training method, information recommendation method and device | |
| CN114331602A (en) | Model training method based on transfer learning, information recommendation method and device | |
| CN114861043A (en) | Model training and recommended position determining method and device | |
| CN112966187A (en) | Information recommendation method and device | |
| CN113343130B (en) | Model training method, information display method and device | |
| CN110647680A (en) | User browsing behavior analysis method and device | |
| CN114331511A (en) | Information recommendation method and device | |
| US9946713B1 (en) | Digital media relationship analyzer and recommender |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |