CN113704621A

CN113704621A - Object information recommendation method, device, equipment and storage medium

Info

Publication number: CN113704621A
Application number: CN202111013837.6A
Authority: CN
Inventors: 王姝阳; 唐笛; 张楠; 赵强; 金龙; 袁欣; 王云翔; 肖韦东
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2021-08-31
Filing date: 2021-08-31
Publication date: 2021-11-26

Abstract

The application discloses an object information recommendation method, device, equipment and storage medium, and belongs to the technical field of internet. The method comprises the following steps: acquiring operation data based on a data display interface, wherein the data display interface comprises a plurality of pieces of object information, and the operation data is used for representing the operation behavior of the plurality of pieces of object information based on the current login account; performing prediction processing based on historical behavior data and operation data corresponding to the current login account to obtain a new taste parameter corresponding to the current login account, wherein the new taste parameter is used for representing whether the current user has new taste intention, and the historical behavior data at least represents whether any piece of object information is repeatedly displayed to the current user; and under the condition that the taste new parameter represents that the current user has the taste new intention, recommending at least one piece of object information to the current user according to the taste new parameter. The scheme can find new taste requirements of the user in time, recommend corresponding object information for the user, and improve recommendation effect.

Description

Object information recommendation method, device, equipment and storage medium

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method, an apparatus, a device, and a storage medium for object information recommendation.

Background

With the continuous development of internet technology, more and more people are used to buy needed articles on the internet. Because the quantity of the articles provided on the network is large, the articles are difficult to be checked by the user one by one, and therefore the articles or stores which are interested in the user can be recommended to the user according to the purchase record of the user.

Taking a take-out scene as an example, in the related art, a store in which a user is interested is determined according to historical behaviors of the user (for example, a purchasing behavior, a collecting behavior, an adding behavior, a browsing behavior of the store, and the like); during the user point-of-sale process, store information of the stores is presented to the user.

However, the situation that the user often bought a screen of a shop is caused by adopting the scheme, but the user has a certain demand for tasting new besides the demand for ordering in the familiar shop, so that the recommendation effect of the recommendation method is poor.

Disclosure of Invention

The embodiment of the application provides an object information recommendation method, device, equipment and storage medium, which can meet the new taste requirements of users in time and improve the recommendation effect. The technical scheme is as follows:

in one aspect, an object information recommendation method is provided, where the method includes:

acquiring operation data based on a data display interface, wherein the data display interface comprises a plurality of pieces of object information, and the operation data is used for representing the operation behavior of the plurality of pieces of object information based on a current login account;

performing prediction processing based on historical behavior data and the operation data corresponding to the current login account to obtain a new taste parameter corresponding to the current login account, wherein the new taste parameter is used for representing whether a current user has new taste intentions, and the historical behavior data at least represents whether any piece of object information is shown to the current user for multiple times;

and under the condition that the taste new parameter represents that the current user has a taste new intention, recommending at least one piece of object information to the current user according to the taste new parameter.

In one possible implementation, the historical behavior data includes at least one of:

displaying different object information based on the current login account;

based on the number of clicks of the current login account on different object information;

performing order generation operation on the articles corresponding to different object information based on the current login account;

a first list of object information clicked based on the current login account;

generating a second list of object information corresponding to an article for which an operation is performed based on an order executed by the current login account;

and the new taste preference information represents new taste preference of the current user in a target time period.

In one possible implementation, the operational data includes at least one of:

the sliding speed of the object information in the data display interface is measured;

the sliding direction of the object information in the data display interface is adjusted;

clicking the object information in the data display interface;

the purchase operation of the object information in the data display interface is carried out;

collecting the object information in the data display interface;

and the display duration of the object information in the data display interface is prolonged.

In one possible implementation, the feedback information includes at least one of:

in the plurality of pieces of object information displayed in the data display interface, the sliding speed of the current user on the object information corresponding to the article which has performed the order generation operation;

in the plurality of pieces of object information displayed in the data display interface, the sliding direction of the object information corresponding to the article on which the order generation operation is performed by the current user is the current direction;

whether the current user performs purchase adding operation on the article corresponding to the object information clicked by the history or not is judged;

whether the current user executes collection operation on the articles corresponding to the object information clicked by the history or not;

and the watching duration of the current user to the detail display information of any piece of object information.

In one aspect, an object information recommendation apparatus is provided, the apparatus including:

the operation data acquisition module is used for acquiring operation data based on a data display interface, the data display interface comprises a plurality of pieces of object information, and the operation data is used for representing operation behaviors of the plurality of pieces of object information based on a current login account;

the prediction module is used for performing prediction processing on the basis of historical behavior data and the operation data corresponding to the current login account to obtain a new taste parameter corresponding to the current login account, wherein the new taste parameter is used for representing whether a current user has new taste intentions, and the historical behavior data at least represents whether any piece of object information is shown to the current user for multiple times;

and the recommending module is used for recommending at least one piece of object information to the current user according to the taste new parameter under the condition that the taste new parameter represents that the current user has the taste new intention.

In one possible implementation, the prediction module includes:

the characteristic extraction unit is used for extracting the characteristics of the historical behavior data and the operation data to obtain feedback information of the object information, and the feedback information is used for representing at least one of feedback of the current user on the object information displayed for multiple times or feedback of the object information not displayed for multiple times;

and the prediction unit is used for performing prediction processing based on the feedback information to obtain a new taste parameter corresponding to the current login account.

In a possible implementation manner, the prediction unit is configured to perform prediction processing on the feedback information through a new-taste-intention prediction model to obtain a new-taste parameter corresponding to the current login account.

In a possible implementation manner, the prediction unit is configured to obtain a model file of the taste intention prediction model from a local place; and calling the model file to operate the new taste intention prediction model, and performing prediction processing on the feedback information to obtain new taste parameters corresponding to the current login account.

In one possible implementation, the apparatus further includes:

and the behavior data acquisition module is used for extracting the characteristics of the historical data corresponding to the current login account according to the configured behavior characteristic type to obtain the historical behavior data.

In one possible implementation, the behavior data obtaining module includes:

a sending unit, configured to send a data acquisition request to a server, where the data acquisition request carries the current login account, and the server is configured to, in response to the data acquisition request, perform feature extraction on historical data corresponding to the current login account according to the behavior feature type to obtain the historical behavior data, and return the historical behavior data to a terminal;

and the receiving unit is used for receiving the historical behavior data returned by the server.

In a possible implementation manner, the server is further configured to register a data source for any account in response to a data source registration operation, where the data source is configured to store historical data corresponding to the account;

the server also responds to the characteristic configuration operation, obtains an input behavior characteristic type, and associates the behavior characteristic type with a data source registered for each account;

the server also responds to the data acquisition request, determines a data source corresponding to the current login account, performs feature extraction on historical data stored in the data source based on the behavior feature type associated with the data source to obtain the historical behavior data, and returns the historical behavior data to the terminal.

displaying different object information based on the current login account;

the number of times of order generation operation executed on the articles corresponding to different object information based on the current login account;

a first list of object information clicked based on the current login account;

In one possible implementation, the operational data includes at least one of:

clicking the object information in the data display interface;

the purchase operation of the article corresponding to the object information in the data display interface is carried out;

collecting the object information corresponding to the object in the data display interface;

In one possible implementation, the recommendation module includes:

the sending unit is used for sending a data recommendation request to a server under the condition that the new taste parameter represents that the current user has new taste intention, wherein the data recommendation request carries the new taste parameter; the server is used for responding to the data recommendation request, acquiring a plurality of candidate object information, adjusting the arrangement sequence of the plurality of candidate object information according to the taste new parameters, determining the candidate object information with the front target number as the object information to be recommended, and returning the object information to be recommended;

a display unit for receiving and displaying the object information returned by the server

In a possible implementation manner, the recommending module is configured to, in response to a triggering operation on any one of the plurality of pieces of object information, recommend the at least one piece of object information to the current user according to the taste parameters, when the taste parameters indicate that the current user has a taste intention.

In one possible implementation, the recommendation module includes:

the first determining unit is used for determining first object information which is displayed for multiple times and is not triggered by the current user according to the feedback information;

and the recommending unit is used for recommending the at least one piece of object information to the current user according to the taste new parameter and the first object information under the condition that the taste new parameter represents that the current user has a taste new intention.

In a possible implementation manner, the taste new parameter is a taste new score, and the recommending module is configured to recommend the at least one piece of object information to the current user according to the taste new parameter in response to the taste new score being greater than a first threshold.

In one possible implementation, the recommendation module includes:

the second determining unit is used for determining at least one piece of object information recommended to the current user according to the taste new parameters;

the display unit is used for inserting a new list tag into the data display interface, and the new list tag is used for displaying the at least one piece of object information;

and the display unit is used for responding to the triggering operation of the taste list label and displaying the taste list, and the taste list comprises the at least one piece of object information.

In one aspect, a computer device is provided and includes one or more processors and one or more memories, where at least one program code is stored in the one or more memories and loaded by the one or more processors and executed to implement the object information recommendation method according to any of the possible implementations.

In one aspect, a computer-readable storage medium is provided, in which at least one program code is stored, and the at least one program code is loaded by a processor and executed to implement the operations performed by the object information recommendation method according to any one of the above possible implementation manners.

In one aspect, there is provided a computer program or computer program product comprising: computer program code which, when executed by a computer, causes the computer to perform the operations performed by the object information recommendation method of any one of the possible implementations described above.

The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:

according to the object information recommendation method, the device, the equipment and the storage medium provided by the embodiment of the application, through historical behavior data of a user and current operation data of the user, whether the user is interested in frequently displayed object information or not can be determined, so that whether the user currently has a new taste intention or not is determined, under the condition that the user has the new taste intention, corresponding object information is recommended for the user, the new taste requirement of the user is met in time, and the recommendation effect is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;

fig. 2 is a flowchart of an object information recommendation method provided in an embodiment of the present application;

fig. 3 is a flowchart of an object information recommendation method according to an embodiment of the present application;

FIG. 4 is a flowchart of obtaining historical behavior data according to an embodiment of the present disclosure;

fig. 5 is a flowchart for acquiring feedback information according to an embodiment of the present disclosure;

fig. 6 is a flowchart of recommendation object information provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram of an object information recommendation device according to an embodiment of the present application;

FIG. 8 is a schematic structural diagram of another object information recommendation device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a terminal provided in an embodiment of the present application;

fig. 10 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

It will be understood that the terms "first," "second," and the like as used herein may be used herein to describe various concepts, which are not limited by these terms unless otherwise specified. These terms are only used to distinguish one concept from another. For example, a first object may be termed a second object, and, similarly, a second object may be termed a first object, without departing from the scope of the present application.

As used herein, the terms "at least one," "a plurality," "each," and "any," at least one of which includes one, two, or more than two, a plurality of which includes two or more than two, and each of which refers to each of the corresponding plurality, and any of which refers to any of the plurality, for example, a plurality of objects includes 3 objects, and each of which refers to each of the 3 objects, and any of which refers to any of the 3 objects, which may be the first, second, or third.

The object recommendation method provided by the embodiment of the application is applied to computer equipment. In one possible implementation, the computer device is a terminal, which may be any type of terminal such as a desktop computer, a tablet computer, or a mobile phone. In one possible implementation, the computer device is a server. The server can be a server, a server cluster composed of a plurality of servers, or a cloud computing service center. In one possible implementation, the computer device includes a terminal and a server.

Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application, and as shown in fig. 1, the implementation environment includes a terminal 101 and a server 102. The terminal 101 and the server 102 are connected by a wireless or wired network.

Optionally, the terminal 101 is any type of terminal such as a desktop computer, a tablet computer, or a mobile phone, and the server 102 is a server, or a server cluster composed of several servers, or a cloud computing service center.

The terminal 101 has installed thereon a target application served by the server 102, through which the terminal 101 can implement functions such as data transmission, message interaction, and the like. Optionally, the target application is an application in an operating system of the terminal 101 or an application provided by a third party. For example, the target application is an e-commerce application having a function of shopping, but of course, the e-commerce application can also have other functions, such as a comment function, a mailing function, and the like.

The terminal 101 may obtain historical behavior data corresponding to the current login account from the server 102, obtain operation data based on the data display interface in the process of browsing the data display interface by the user, predict whether the user has an intention to taste new according to the historical behavior data and the operation data, and request corresponding recommendation data from the server 102 when the user has the intention to taste new.

The object information recommendation method provided by the embodiment of the application can be applied to any recommendation scene.

For example, to take-away scenarios.

The take-out application is provided with a shop recommendation interface, and a user can enter a shop interested in the user to place an order by browsing the shop recommendation interface. By adopting the method provided by the embodiment of the application, whether the user wants to try a new shop or not can be found in time, and then the shop which meets the requirements of the user is recommended to the user, so that the shop recommendation effect is improved.

As another example, it is applied to online shopping scenarios.

The electronic commerce application is provided with an article recommendation interface, and a user can place orders for articles in which the user is interested by browsing the article recommendation interface. By adopting the method provided by the embodiment of the application, whether the user wants to try a new article can be found in time, and then the article which meets the requirements of the user better is recommended to the user, so that the article recommendation effect is improved.

It should be noted that, in the embodiment of the present application, only the takeaway scenario and the online shopping scenario are taken as examples, and the recommendation scenario is exemplarily described and is not limited.

Fig. 2 is a flowchart of an object information recommendation method according to an embodiment of the present application. In the embodiment of the present application, an execution subject is taken as an example of a computer device for exemplary explanation, and the embodiment includes:

201. the computer equipment acquires operation data based on a data display interface, wherein the data display interface comprises a plurality of pieces of object information, and the operation data is used for representing operation behaviors of the plurality of pieces of object information based on a current login account.

The data display interface is used for displaying object information recommended to the current user. The object recommended to the current user may be a store, a commodity, or the like, that is, the object information may be store information of the store, commodity information of the commodity, or the like.

It should be noted that the data display interface may also display other information, for example, the data display interface further includes an interface switching option, an interface entry of another interface, and the like.

The operation data based on the data presentation interface is operation data of an operation triggered in the data presentation interface. The operation triggered by the user in the data display interface may be a sliding operation, a clicking operation, and the like, and the operation data of the operation may include a trigger object, a trigger position, an operation type, an operation track, and the like of the operation.

For example, when browsing the data presentation interface, the user may click any piece of object information in the data presentation interface, so that the data presentation interface presents the detail presentation information corresponding to the object information. For another example, when browsing the data display interface, the user may slide up and down to display the previous object information or to display the next object information.

By acquiring the operation data based on the data display interface, the user can be known which operations are executed in the data display interface, so that the operation behaviors of the user on the object information in the data display interface can be obtained, the operation behaviors can be click behaviors, sliding behaviors, purchase adding behaviors, collection behaviors, black-out behaviors and the like, and the operation behaviors are not limited in the embodiment of the application.

202. The computer equipment carries out prediction processing on the basis of historical behavior data and operation data corresponding to the current login account to obtain a new taste parameter corresponding to the current login account, the new taste parameter is used for representing whether the current user has new taste intentions, and the historical behavior data at least represents whether any piece of object information is shown to the current user for multiple times.

In the data display interface, any operation of sliding operation, clicking operation, purchase adding operation, collection operation, order placing operation and the like on the displayed object information is recorded by the terminal, and the recorded data can be regarded as historical behavior data. According to the historical behavior data, the object information browsed by the user at a certain time can be known, the object information clicked, purchased, collected and the like by the user at a certain time can be known, and whether the object information is displayed for the current user for many times or not can be known by analyzing the historical behavior data.

For example, the historical behavior data records that the current user has performed 3 ordering operations, 5 purchasing operations, and 1 collecting operation on the "object information a" within one month. As can be seen, the "object information a" is object information that is frequently presented to the current user. As another example, there is no record about "object information B" in the historical behavior data, so it can be known that "object information B" is not shown to the current user.

The operation data obtained in step 202 is operation data of the currently displayed pieces of object information, and the operation data can represent whether the currently displayed pieces of object information are interested by the current user. For example, the current user slides the data presentation interface downward at a fast speed, which indicates that the current user is not interested in the currently presented pieces of object information. For another example, if the current user clicks a piece of currently displayed object information, it indicates that the current user is interested in the object information.

According to the historical behavior data, it can be known whether each piece of object information which is currently shown is object information which is frequently shown to the current user or object information which is not shown to the current user. According to the operation data, the user can know which object information displayed currently is interested and which object information displayed currently is not interested. Therefore, by combining the historical behavior data and the operation data, the current user is interested in the frequently-displayed object information or the unexposed object information. If the user is interested in the object information which is not shown, the current user has the intention of tasting new at the moment.

It should be noted that, in one possible implementation, the plurality of pieces of object information currently presented are pieces of object information that are often presented to the current user. If the current user is not interested in the object information, the user can be considered to have a new intention.

203. And under the condition that the taste new parameter represents that the current user has the taste new intention, the computer equipment recommends at least one piece of object information to the current user according to the taste new parameter.

Wherein the taste parameter is capable of characterizing whether the user has a taste intention. Alternatively, the taste parameter may be a taste score, the higher the taste score, the stronger the taste intention of the user; the lower the taste score, the weaker the taste intent of the user.

According to the object information recommendation method provided by the embodiment of the application, through historical behavior data of the user and current operation data of the user, whether the user is interested in frequently displayed object information or not can be determined, so that whether the user has a new taste intention or not is determined, under the condition that the user has the new taste intention, corresponding object information is recommended for the user, new taste requirements of the user are met in time, and the recommendation effect is improved.

Fig. 3 is a flowchart of an object information recommendation method according to an embodiment of the present application. The embodiment of the present application takes an execution subject as an example for exemplary explanation, and the embodiment includes:

301. the terminal obtains operation data based on a data display interface, the data display interface comprises a plurality of pieces of object information, and the operation data is used for representing operation behaviors of the plurality of pieces of object information based on a current login account.

In one possible implementation, the operational data includes at least one of: the sliding speed of object information in the data display interface is calculated; the sliding direction of object information in the data display interface is determined; clicking the object information in the data display interface; adding purchase operation of object information in a data display interface; collecting the object information in the data display interface; and displaying the object information in the data display interface for a long time.

The operation data can represent the operation behavior of the current user on the plurality of pieces of object information and can represent whether the current user is interested in the currently displayed object information. For example, the operation data indicates that the current user slides down the data display interface at a faster sliding speed, which indicates that the current user is not interested in the currently displayed pieces of object information. For another example, the operation data represents that the current user performs purchase adding operation on certain currently displayed object information, which indicates that the current user is interested in the object information.

In a possible implementation manner, in order to find out the intention change of the current user in time, the terminal may obtain the operation data in real time, and after obtaining the operation data each time, execute a process of obtaining the new parameter. Optionally, the acquiring, by the terminal, the operation data based on the data display interface includes: and the terminal acquires the operation data based on the data display interface in real time.

In a possible implementation manner, the terminal may record log data according to the operation of the current user, and may obtain the operation data based on the data display interface by obtaining the log data. Optionally, the acquiring, by the terminal, the operation data based on the data display interface includes: acquiring operation data based on a data display interface from recorded log data; or generating log data according to the operation on the data display interface, and taking the log data as operation data.

302. The terminal acquires historical behavior data corresponding to the current login account, wherein the historical behavior data at least represents whether any piece of object information is displayed for a plurality of times to the current user.

In one possible implementation, the historical behavior data includes at least one of: displaying times of different object information based on the current login account; clicking times of different object information based on the current login account; performing order generation operation on the articles corresponding to different object information based on the current login account; a first list of object information clicked based on the current login account; generating a second list of object information corresponding to the article for which the operation is performed based on the order executed by the current login account; and the new taste preference information corresponds to the current login account and represents new taste preference of the current user in a target time period.

It should be noted that, in a possible implementation manner, the historical behavior data may be historical data recorded by the terminal, and may be directly obtained; in another possible implementation manner, the historical behavior data is obtained by processing historical data recorded by the terminal.

In the embodiment of the application, historical behavior data is obtained by processing historical data recorded by a terminal, and the historical behavior data is obtained by way of example. In a possible implementation manner, the behavior feature type may be configured in advance, so that the terminal automatically performs feature extraction on the historical data according to the configured behavior feature type to obtain the historical behavior data. Wherein the behavior feature types are used to characterize different historical behaviors. For example, the behavior feature type is the number of times that the user clicks different object information, and the terminal performs feature extraction on the historical data according to the behavior feature type, so that the number of times that the user clicks the object information a is 5, the number of times that the user clicks the object information B is 10, the number of times that the user clicks the object information C is 3, and the like can be obtained.

Optionally, the obtaining, by the terminal, historical behavior data corresponding to the current login account includes: and the terminal performs feature extraction on the historical data corresponding to the current login account according to the configured behavior feature type to obtain historical behavior data.

The history data may be stored locally in the terminal or in the server. For example, the historical data is stored in the server, the terminal can acquire the historical data from the server, and perform feature extraction on the historical data according to the configured behavior feature type to obtain historical behavior data; or the server performs feature extraction on the historical data according to the configured behavior feature type to obtain historical behavior data, and the terminal directly acquires the historical behavior data from the server.

In a possible implementation manner, the server performs feature extraction on the historical data to obtain historical behavior data, and the terminal directly acquires the historical behavior data from the server. The method for extracting the characteristics of the historical data corresponding to the current login account by the terminal according to the configured behavior characteristic type comprises the following steps: a terminal sends a data acquisition request to a server, wherein the data acquisition request carries a current login account; the server is used for responding to the data acquisition request, performing feature extraction on historical data corresponding to the current login account according to the behavior feature type to obtain historical behavior data, and returning the historical behavior data to the terminal; and the terminal receives the historical behavior data returned by the server.

The server is used for extracting the characteristics of the historical data, the calculation amount of the terminal is reduced, the speed of obtaining new tasting parameters is increased, the change of the current user intention can be found in time, and the object information is recommended to the current user when the current user has the new tasting intention in time.

In a possible implementation manner, relevant personnel can configure behavior feature types in a server, wherein the server is further configured to register a data source for any account in response to a data source registration operation, and the data source is used for storing historical data corresponding to the account; the server is also used for responding to the characteristic configuration operation, acquiring the input behavior characteristic type, and associating the behavior characteristic type with the data source registered for each account; the server is also used for responding to the data acquisition request, determining a data source corresponding to the current login account, performing feature extraction on historical data stored in the data source based on the behavior feature type associated with the data source to obtain historical behavior data, and returning the historical behavior data to the terminal.

It should be noted that, the data source registered in the embodiment of the present application may store history data generated based on a certain application, or may store only history data generated by a certain service of a certain application. For example, the target application provides a plurality of services such as a take-out service, a taxi taking service, a store holding service, and the like, and if the method provided by the embodiment of the application is applied to the take-out service but not applied to other services, only historical data generated by the take-out service can be stored in the data source.

For example, as shown in fig. 4, a data source is registered for each account on the Metis (cloud storage module), a relevant person registers a behavior feature type and a data format supported by a terminal on the Edge (filtering network) service, and an association relationship between the behavior feature type, the data source, and the data format supported by the terminal is established. Subsequently, the terminal can request an Edge service to obtain historical behavior data, the Edge service determines a corresponding data source according to an account sent by the terminal, obtains corresponding historical behavior data from the historical data of the data source according to the configured behavior feature type, converts the historical behavior data into data which can be recognized by the terminal according to a data format supported by the terminal, and returns the data to the terminal.

303. And the terminal extracts the characteristics of the historical behavior data and the operation data to obtain feedback information of the plurality of pieces of object information, wherein the feedback information is used for representing at least one of the feedback of the current user to the object information displayed for a plurality of times or the feedback to the object information which is not displayed for a plurality of times.

The embodiment of the application can determine whether the current user has the intention of tasting new or not in time, and whether a piece of object information is 'new' to the user or not depends on the familiar program of the user to the object information. The familiarity of a user with certain object information is related to the time and the frequency of seeing the object information last time and whether the object information is interacted with before. Therefore, it is necessary to associate whether or not the user is familiar with certain object information with various behaviors of the user. Therefore, the historical behavior data can be regarded as the interaction characteristics of the user and the object information, that is, the historical behavior data is used for representing the interaction behavior of the user and the object information, and the historical behavior data can also represent whether the user is familiar with certain object information.

When the user operates the terminal in real time, the generated operation data is used for representing the operation behavior of the current user on the information of the plurality of objects, so that the historical behavior data and the operation data are crossed, and the feedback information of the user on the displayed new/long-term object information can be calculated in time, namely the feedback behavior sequence of the user on the displayed new/long-term object information. In one possible implementation, the feedback information includes at least one of: in a plurality of pieces of object information displayed in the data display interface, the sliding speed of the current user on the object information corresponding to the article which is subjected to the order generation operation is increased; in a plurality of pieces of object information displayed in the data display interface, the sliding direction of the current user on the object information corresponding to the article which is subjected to the order generation operation; whether the current user performs purchase adding operation on the articles corresponding to the object information clicked by the history or not; whether the current user executes collection operation on the articles corresponding to the object information clicked by the history or not; and the watching duration of the current user on the detail display information of any piece of object information.

Optionally, as shown in fig. 5, the terminal obtains operation data through a buried point, sends the obtained operation data to a feature service, and performs feature extraction on historical behavior data and operation data in the feature service to obtain feedback information on a plurality of pieces of object information. And when the feedback information needs to be processed, acquiring the feedback information from the feature service. Optionally, the feature service may be used to provide services for multiple services, which is not limited in this embodiment of the present application.

304. And the terminal carries out prediction processing based on the feedback information to obtain a new taste parameter corresponding to the current login account.

The feedback information is used for representing at least one of feedback of the current user to the object information displayed for multiple times or feedback of the object information not displayed for multiple times, that is, the feedback information is used for representing feedback of the current user to the 'new/old' object information. For example, if the feedback information indicates that the current user swipes the "old" object information displayed on the data display interface quickly, the current user may be considered to be not interested in the "old" object information, and at this time, the current user may be considered to have new intention and want to browse the "new" object information. For another example, if the feedback information indicates that the current user swipes the "new" object information displayed on the data display interface quickly, the current user may be considered to be not interested in the "new" object information, and at this time, the current user may be considered to be not interested in the "new" object information, and wants to browse the "old" object information.

Therefore, the feedback information can reflect whether the current user has the intention of tasting new, and therefore prediction processing is performed based on the feedback information, and the tasting new parameters corresponding to the current login account can be obtained. In one possible implementation, the taste parameter includes whether the current user has a taste intention or the current user does not have a taste intention. The terminal can classify the feedback information according to the set classification rule, and the new parameter is the obtained classification result. The terminal carries out prediction processing based on the feedback information to obtain new taste parameters corresponding to the current login account, and the method comprises the following steps: and classifying the feedback information according to the configured distribution rule to obtain new taste parameters corresponding to the current login account.

For example, when the classification rule represents that the current user quickly slides the 'old' object information displayed on the data display interface, the current user is considered to have new taste intention; and if the sliding speed of the current user on the object information corresponding to the item which is subjected to the order generation operation in the feedback information is high, the current user is considered to have a new intention.

In another possible implementation, the feedback information may also be processed by the model to obtain the taste new parameters. Optionally, performing prediction processing based on the feedback information to obtain a taste new parameter corresponding to the current login account, including: and predicting the feedback information through a new-taste prediction model to obtain new-taste parameters corresponding to the current login account. The new-taste-intention prediction model is a model used for predicting new-taste parameters, and can be obtained through sample data training, wherein the sample data comprises sample feedback information corresponding to a sample account and sample trust parameters corresponding to the sample account; predicting the sample feedback information through a tasting new intention prediction model to obtain a prediction tasting new parameter corresponding to the sample account; and training a tasting intention prediction model according to the difference between the predicted tasting parameter and the sample trust parameter so as to converge the difference between the predicted tasting parameter and the sample trust parameter.

In the embodiment of the present application, the more detailed the content included in the operation data is, the more accurate the determined trust parameter is, but the longer the time required for the content included in the operation data to transmit the operation data to the server is. The method and the device are used for discovering the new tasting intention of the user in time in the process that the user browses the data display interface so as to recommend corresponding information to the user, and therefore the method and the device have higher requirements on timeliness.

Therefore, in one possible implementation, the new intention prediction model can be deployed on the terminal, and the time consumption of data transmission can be reduced. In general, if the model is deployed in a server, the terminal can only send part of data to the server because data transmission needs much time. If the new-tasting intention prediction model is deployed on the terminal, the terminal can acquire more detailed operation data because the time consumption of data transmission is avoided, so that the prediction result of the new-tasting intention prediction model is more accurate. For example, the terminal may further obtain a gesture of the user, and may further obtain data measured by a sensor disposed at the terminal. Optionally, the terminal performs prediction processing on the feedback information through a new-taste-intention prediction model to obtain new-taste parameters corresponding to the current login account, including: obtaining a model file of a new intention prediction model from the local; and (4) operating the new taste intention prediction model by calling the model file, and performing prediction processing on the feedback information to obtain new taste parameters corresponding to the current login account.

Optionally, the server compresses, converts and the like the trained taste and novelty intention model to generate a model file, and sends the model file to each terminal, and the terminal can call the model file to run the taste and novelty intention prediction model when needing to use the taste and novelty intention prediction model.

It should be noted that, in the embodiment of the present application, only by taking the example that feature extraction is performed on historical behavior data and operation data to obtain feedback information of a plurality of pieces of object information, prediction processing is performed based on the feedback information to obtain a taste new parameter corresponding to a current login account, prediction processing is performed on the historical behavior data and the operation data corresponding to the current login account to obtain a taste new parameter corresponding to the current login account, and an exemplary description is given. In another embodiment, the historical behavior data and the operation data corresponding to the current login account may be directly subjected to prediction processing to obtain the taste new parameters corresponding to the current login account. In one possible implementation manner, the historical behavior data and the operation data may be subjected to prediction processing by a taste intention prediction model to obtain taste parameters. The terminal carries out prediction processing based on historical behavior data and operation data corresponding to the current login account number to obtain new taste parameters corresponding to the current login account number, and the method comprises the following steps: and predicting historical behavior data and operation data corresponding to the current login account through a new-tasting intention prediction model to obtain new-tasting parameters corresponding to the current login account.

The new-taste-intention prediction model is a model used for predicting new-taste parameters, and can be obtained through sample data training, wherein the sample data comprises sample historical behavior data, sample operation data and sample trust parameters corresponding to a sample account; predicting the historical behavior data and the operation data of the sample through a new tasting intention prediction model to obtain a new prediction parameter corresponding to the sample account; and training a tasting intention prediction model according to the difference between the predicted tasting parameter and the sample trust parameter so as to converge the difference between the predicted tasting parameter and the sample trust parameter.

It should be noted that, after the terminal acquires the feedback information, the terminal may further send the feedback information to the server, and the server may use the feedback information sent by the terminal as training data of the model, so as to update the model. The updated model may also be subsequently deployed to various terminals.

In an embodiment of the present application, the taste parameter is used to characterize whether the current user has a taste intention, and optionally, the taste parameter includes whether the current user has a taste intention or the current user does not have a taste intention. Optionally, the taste parameter is expressed in the form of a taste value, and the size of the taste value represents the strength or not of the current user's taste intention. In one possible implementation, when the taste value is greater than the first threshold, indicating that the current user has a taste intention, the more the taste value exceeds the first threshold, the stronger the taste intention of the user.

The first threshold may be any value, for example, 0, 50, etc., which is not limited in this embodiment of the application.

305. And the terminal sends a data recommendation request to the server under the condition that the new-tasting parameter represents that the current user has a new-tasting intention, wherein the data recommendation request carries the new-tasting parameter.

If the new-taste parameter indicates that the current user has new-taste intention, the current user wants to browse some unfamiliar object information, and a plurality of pieces of object information familiar to the current user are usually displayed in the data display interface. For example, taking a take-out scene as an example, the data presentation interface usually presents store information of stores frequently bought by users. Therefore, the plurality of pieces of object information currently displayed in the data display interface may no longer meet the requirements of the user, and the terminal needs to recommend the object information for the current user again according to the requirements of the current user.

In the embodiment of the present application, a terminal request server is taken as an example to recommend object information for a current user, and "recommend object information for the current user again" is exemplarily described. After the terminal determines that the current user has the intention of tasting new, the terminal sends a data recommendation request to the server so as to enable the server to recommend new object information. In order to enable the new object information recommended by the server to meet the requirements of the current user, a new-tasting parameter can be carried in the data recommendation request, so that the server recommends the object information for the current user according to the new-tasting parameter.

In the embodiment of the present application, the server may adopt any information recommendation method to recommend the object information to the terminal, and the method for recommending the object information by the server is not limited in the embodiment of the present application, and the embodiment of the present application is only exemplarily described in the following two examples.

Optionally, the server is configured to, in response to the data recommendation request, obtain multiple pieces of candidate object information, adjust an arrangement order of the multiple pieces of candidate object information according to the refresh parameter, determine the candidate object information of the previous target number as object information to be recommended, and return the object information to be recommended. Wherein, according to the refresh parameter, adjusting the arrangement order of the plurality of candidate object information may be: and adjusting the arrangement sequence of object information unfamiliar to the current user in the plurality of pieces of candidate object information forwards.

Wherein, the server can adopt any method to obtain the plurality of candidate information. For example, the server obtains a plurality of candidate object information including at least one of: according to object information triggered by a user in real time, acquiring other object information similar to the object information as candidate object information; determining object information with longer display time in a data display interface, and acquiring other object information similar to the object information as candidate object information; acquiring a plurality of pieces of object information as candidate object information according to preference information of a user, wherein the preference information represents the preference of the current user in a target time period; and acquiring a plurality of pieces of object information as candidate object information according to the keywords input by the user. The embodiment of the application does not limit the way in which the server acquires the plurality of pieces of candidate object information.

Optionally, the server is configured to respond to the data recommendation request, obtain multiple pieces of candidate object information according to the taste new parameter in the data recommendation request, determine the multiple pieces of candidate object information as object information to be recommended, and return the object information to be recommended.

It should be noted that, in the embodiment of the present application, under the condition that the new-taste parameter represents that the current user has a new-taste intention, the terminal may directly send a data recommendation request to the server to obtain new object information; or when the user performs trigger operation in the data display interface, sending a data recommendation request to the server to acquire new object information.

If the user carries out triggering operation on any piece of object information in the data display interface, the fact that the user is browsing the data display interface is indicated, the object information is recommended to the user at the moment, and a better recommendation effect can be achieved. In one possible implementation manner, in the case that the terminal indicates that the current user has a new-taste intention, sending a data recommendation request to the server by the terminal includes: and under the condition that the taste new parameter represents that the current user has the taste new intention, responding to the trigger operation of any one piece of object information in the plurality of pieces of object information, and sending a data recommendation request to the server.

In addition, if the user performs a triggering operation on the object information in the data presentation interface, it indicates that the user may be interested in the object information, and in order to improve the recommendation effect, the object information triggered by the user may also be sent to the server, so that the server retrieves similar other object information according to the object information and recommends the similar other object information to the user. In a possible implementation manner, in a case that the taste new parameter represents that the current user has a taste new intention, a data recommendation request carrying the taste new parameter and the triggered object information is sent to the server in response to a triggering operation on any one of the plurality of pieces of object information.

Optionally, the server is configured to respond to the data recommendation request, and obtain multiple pieces of candidate object information according to the triggered object information; and adjusting the arrangement sequence of the plurality of pieces of candidate object information according to the taste new parameters, determining the candidate object information with the front target number as the object information to be recommended, and returning the object information to be recommended.

In a possible implementation manner, in order to avoid that the user is not interested in the object information newly recommended by the server, the terminal may further perform aggregation and precipitation on object information which is repeatedly displayed but not clicked for many times in the data display interface accessed by the user, and upload the object information of the aggregation and precipitation when the server is requested to recommend the object information, so that the server optimizes the object information to be recommended. Optionally, the terminal sends a data recommendation request to the server when the refresh-attempting parameter indicates that the current user has a refresh-attempting intention, including: according to the feedback information, determining first object information which is displayed for multiple times and is not triggered by the current user; and under the condition that the new taste parameter represents that the current user has new taste intention, sending a data recommendation request carrying the new taste parameter and the first object information to the server.

Optionally, the server is configured to obtain a plurality of pieces of candidate object information in response to the data recommendation request, adjust an arrangement order of the plurality of pieces of candidate object information according to the taste new parameter and the first object information, determine the candidate object information of the previous target number as object information to be recommended, and return the object information to be recommended.

Wherein, adjusting the plurality of candidate object information according to the taste new parameter and the first object information may include: adjusting the arrangement sequence of object information unfamiliar to the current user in the plurality of pieces of candidate object information forward according to the new taste parameters; according to the first object information, the order of arrangement of candidate object information similar to the first object information among the plurality of pieces of candidate object information is adjusted backward.

Optionally, the terminal sends a data recommendation request to the server, where the data recommendation request may simultaneously carry the refresh parameter, the first object information, and the object information triggered by the user, so that the server performs more accurate recommendation, which is not limited in this embodiment of the present application.

In a possible implementation manner, the taste new parameter is a taste new score, and the terminal recommends at least one piece of object information to the current user according to the taste new parameter when the taste new parameter indicates that the current user has a taste new intention, including: and in response to the taste parameter being greater than the first threshold, recommending at least one piece of object information to the current user according to the taste score. Optionally, a taste score greater than a first threshold indicates that the current user has a taste intent; optionally, a taste score greater than the first threshold indicates that the current user has a taste intent, and the taste intent is stronger.

Taking a take-away scene as an example, as shown in fig. 6, a terminal displays a merchant list, a user clicks merchant information 601 of a first merchant in the merchant list, and the terminal displays detailed information of the first merchant. And the terminal also sends a data recommendation request to the server, wherein the data recommendation request carries the taste new parameter, the merchant identifier or the merchant information of the first merchant, and the merchant identifier or the merchant information which is displayed to the user for many times and is not triggered by the user. And the server returns merchant information of at least one merchant to the terminal according to the data recommendation request. After browsing the detailed information of the first merchant, the user may return to the merchant list, at this time, the terminal inserts a new-tasting list tag 602 in the merchant list according to the merchant information of at least one merchant returned by the server, and if the user clicks the new-tasting list tag, the new-tasting list is expanded.

It should be noted that, in the embodiment of the present application, a manner of determining the object information to be recommended is not limited, and any recommendation method may be adopted to determine the object information to be recommended. In one possible implementation manner, the server may recommend new object information for the terminal through the information recommendation model. Optionally, when the information recommendation model is trained, a sequence generalization feature may be added to make object information recommended by the information recommendation model more diversified. In addition, the recall rate of object information unfamiliar to the user can be increased by methods such as sample weighting and multi-object training.

306. And the terminal receives and displays the object information returned by the server based on the data recommendation request.

In the embodiment of the application, after the terminal receives the object information returned by the server, the object information can be displayed on the next page of the data display interface, and the current user displays the object information returned by the server by page turning operations such as sliding the data display interface. Or after receiving the object information returned by the server, the terminal directly replaces the object information currently displayed on the data display interface with the object information returned by the server. Or the terminal inserts a taste list tag in the data display interface, wherein the taste list tag is used for displaying at least one object, and the taste list is displayed in response to the triggering operation of the taste list tag, and comprises the at least one object.

It should be noted that, in the embodiment of the present application, only the terminal requests the server to recommend the object information is taken as an example, and at least one piece of object information is recommended to the current user according to the taste new parameter is exemplarily described. In yet another embodiment, the data may be acquired by the terminal itself. The method and the device do not limit the recommendation of at least one piece of object information to the current user by the terminal according to the taste new parameters.

In addition, in order to ensure that the user is browsing the data presentation interface when recommending new object information to the user, the new object information may be acquired after the user performs an operation in the data presentation interface. In one possible implementation manner, in the case that the taste parameter indicates that the current user has the intention of taste, in response to a trigger operation on any one of the plurality of pieces of object information, at least one piece of object information is recommended to the current user according to the taste parameter.

In a possible implementation manner, in order to avoid that the new object information recommended to the current user includes object information that is not interested by the user, the object information that is not interested by the user may be determined first, and then information recommendation is performed according to the object information that is not interested by the user. Optionally, in a case that the taste new parameter indicates that the current user has a taste new intention, recommending at least one piece of object information to the current user according to the taste new parameter, including: according to the feedback information, determining first object information which is displayed for multiple times and is not triggered by the current user; and under the condition that the taste new parameter represents that the current user has the taste new intention, recommending at least one piece of object information to the current user according to the taste new parameter and the first object information.

In one possible implementation manner, the taste new parameter is a taste new score, and in a case that the taste new parameter indicates that the current user has a taste new intention, at least one piece of object information is recommended to the current user according to the taste new parameter, including: and in response to the taste score being greater than the first threshold, recommending at least one piece of object information to the current user according to the taste score.

The taste score being greater than the first threshold may indicate that the current user has a taste intention, or the taste score being greater than the first threshold may indicate that the current user has a taste intention and the taste intention is relatively strong.

In one possible implementation manner, recommending at least one piece of object information to the current user according to the taste new parameter includes: determining at least one piece of object information recommended to the current user according to the taste new parameters; inserting a tasting list label in the data display interface, wherein the tasting list label is used for displaying at least one piece of object information; and in response to the triggering operation of the taste list tag, showing a taste list, wherein the taste list comprises at least one piece of object information.

The user may be made aware that new object information is recommended by presenting the user with a taste list tab, and browse recommended new object information by triggering the taste list tab. Thus, if the user does not want to browse new object information, the taste new list tag may not be triggered; the taste list tab may be triggered if the user wants to browse new object information.

In addition, in the embodiment of the application, through feature extraction of historical behavior data and operation data, feedback of a current user on familiar object information or feedback of unfamiliar object information can be obtained, whether the user is interested in the familiar object information or the unfamiliar object information can be accurately determined according to the feedback, and whether the current user has a taste intention or not can be accurately inferred.

In addition, in the embodiment of the application, the tasting new intention prediction model is deployed on the terminal, so that data transmission between the terminal and the server is reduced, and the efficiency of acquiring tasting new parameters is improved. In addition, the new taste intention prediction model is deployed on the terminal, information such as user gestures and the like acquired by the terminal can be processed, and the obtained new taste parameters are more accurate.

In addition, in the embodiment of the application, the new object information is recommended to the user not only when the user has a new intention, but also after the user performs a trigger operation on the object information in the data display interface, so that the situation that the user only opens the data display interface and does not browse, but recommends the new object information to the user is avoided, and the calculation amount required by recommendation is reduced on the basis of ensuring the recommendation effect.

In addition, in the embodiment of the application, the terminal can display the recommended object information to the user in a tag inserting mode, so that the user has strong perception on the recommended data, and the recommendation effect is improved.

Fig. 7 is a schematic structural diagram of an object information recommendation device according to an embodiment of the present application, and referring to fig. 7, the object information recommendation device includes:

an operation data obtaining module 701, configured to obtain operation data based on a data display interface, where the data display interface includes a plurality of pieces of object information, and the operation data is used to represent an operation behavior of the plurality of pieces of object information based on a current login account;

the prediction module 702 is configured to perform prediction processing based on historical behavior data and the operation data corresponding to the current login account to obtain a taste parameter corresponding to the current login account, where the taste parameter is used to represent whether a current user has a taste intention, and the historical behavior data at least represents whether any piece of object information has been shown to the current user for multiple times;

the recommending module 703 is configured to recommend at least one piece of object information to the current user according to the taste new parameter when the taste new parameter indicates that the current user has a taste new intention.

As shown in fig. 8, in one possible implementation, the prediction module 702 includes:

a feature extraction unit 7021, configured to perform feature extraction on the historical behavior data and the operation data to obtain feedback information on the pieces of object information, where the feedback information is used to represent at least one of feedback of the current user on object information that is displayed multiple times or feedback of object information that is not displayed multiple times;

the predicting unit 7022 is configured to perform prediction processing based on the feedback information to obtain a taste new parameter corresponding to the current login account.

In a possible implementation manner, the predicting unit 7022 is configured to perform prediction processing on the feedback information through a taste intention prediction model to obtain taste parameters corresponding to the current login account.

In a possible implementation manner, the predicting unit 7022 is configured to obtain a model file of the taste intention prediction model from the local; and calling the model file to operate the new taste intention prediction model, and performing prediction processing on the feedback information to obtain new taste parameters corresponding to the current login account.

In one possible implementation, the apparatus further includes:

and a behavior data obtaining module 704, configured to perform feature extraction on historical data corresponding to the current login account according to the configured behavior feature type, so as to obtain the historical behavior data.

In one possible implementation, the behavior data obtaining module 704 includes:

a sending unit 7041, configured to send a data obtaining request to a server, where the data obtaining request carries the current login account, and the server is configured to, in response to the data obtaining request, perform feature extraction on historical data corresponding to the current login account according to the behavior feature type to obtain the historical behavior data, and return the historical behavior data to a terminal;

a receiving unit 7042, configured to receive the historical behavior data returned by the server.

displaying different object information based on the current login account;

a first list of object information clicked based on the current login account;

In one possible implementation, the operational data includes at least one of:

clicking the object information in the data display interface;

In one possible implementation, the recommending module 703 includes:

a sending unit 7031, configured to send a data recommendation request to a server when the taste new parameter indicates that the current user has a taste new intention, where the data recommendation request carries the taste new parameter; the server is used for responding to the data recommendation request, acquiring a plurality of candidate object information, adjusting the arrangement sequence of the plurality of candidate object information according to the taste new parameters, determining the candidate object information with the front target number as the object information to be recommended, and returning the object information to be recommended;

a display unit 7032, configured to receive and display the object information returned by the server

In a possible implementation manner, the recommending module 703 is configured to, in response to a triggering operation on any one of the pieces of object information, recommend the at least one piece of object information to the current user according to the taste parameters, when the taste parameters indicate that the current user has a taste intention.

In one possible implementation, the recommending module 703 includes:

a first determining unit 7033, configured to determine, according to the feedback information, first object information that is shown multiple times and is not triggered by the current user;

a recommending unit 7034, configured to recommend the at least one piece of object information to the current user according to the taste new parameter and the first object information when the taste new parameter indicates that the current user has a taste new intention.

In a possible implementation manner, the taste new parameter is a taste new score, and the recommending module 703 is configured to recommend the at least one piece of object information to the current user according to the taste new parameter in response to that the taste new score is greater than a first threshold.

In one possible implementation, the recommending module 703 includes:

a second determining unit 7035, configured to determine, according to the taste new parameter, at least one piece of object information recommended to the current user;

the display unit 7032 is configured to insert a tasting new list tag in the data display interface, where the tasting new list tag is used to display the at least one piece of object information;

a display unit 7032, configured to display a taste list in response to a trigger operation on the taste list tag, where the taste list includes the at least one piece of object information.

It should be noted that: in the object information recommending apparatus according to the above embodiment, when recommending object information, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the computer device may be divided into different functional modules to complete all or part of the functions described above. In addition, the object information recommendation apparatus provided in the above embodiment and the object information recommendation method embodiment belong to the same concept, and specific implementation processes thereof are detailed in the method embodiment and are not described herein again.

In an exemplary embodiment, a computer device is provided, which includes one or more processors and one or more memories, in which at least one program code is stored, and the at least one program code is loaded and executed by the one or more processors to implement the object information recommendation method in the above-described embodiment.

Optionally, the computer device is provided as a terminal. Fig. 9 shows a block diagram of a terminal 900 according to an exemplary embodiment of the present application. The terminal 900 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. Terminal 900 may also be referred to by other names such as user equipment, portable terminals, laptop terminals, desktop terminals, and the like.

The terminal 900 includes: a processor 901 and a memory 902.

Processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 901 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 901 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 902 is used for storing at least one program code for execution by the processor 901 to implement the object information recommendation method provided by the method embodiments in the present application.

In some embodiments, terminal 900 can also optionally include: a peripheral interface 903 and at least one peripheral. The processor 901, memory 902, and peripheral interface 903 may be connected by buses or signal lines. Various peripheral devices may be connected to the peripheral interface 903 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 904, display screen 905, camera 906, audio circuitry 907, positioning component 908, and power supply 909.

The peripheral interface 903 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, memory 902, and peripheral interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902 and the peripheral interface 903 may be implemented on a separate chip or circuit board, which is not limited by this embodiment.

The Radio Frequency circuit 904 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 904 communicates with communication networks and other communication devices via electromagnetic signals. The radio frequency circuit 904 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 904 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 904 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 904 may also include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 905 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 905 is a touch display screen, the display screen 905 also has the ability to capture touch signals on or over the surface of the display screen 905. The touch signal may be input to the processor 901 as a control signal for processing. At this point, the display 905 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 905 may be one, providing the front panel of the terminal 900; in other embodiments, the number of the display panels 905 may be at least two, and each of the display panels is disposed on a different surface of the terminal 900 or is in a foldable design; in still other embodiments, the display 905 may be a flexible display disposed on a curved surface or a folded surface of the terminal 900. Even more, the display screen 905 may be arranged in a non-rectangular irregular figure, i.e. a shaped screen. The Display panel 905 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 906 is used to capture images or video. Optionally, camera assembly 906 includes a front camera and a rear camera. The front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 906 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

Audio circuit 907 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 901 for processing, or inputting the electric signals to the radio frequency circuit 904 for realizing voice communication. For stereo sound acquisition or noise reduction purposes, the microphones may be multiple and disposed at different locations of the terminal 900. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 901 or the radio frequency circuit 904 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, audio circuit 907 may also include a headphone jack.

The positioning component 908 is used to locate the current geographic Location of the terminal 900 for navigation or LBS (Location Based Service). The Positioning component 908 may be a Positioning component based on the GPS (Global Positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.

Power supply 909 is used to provide power to the various components in terminal 900. The power source 909 may be alternating current, direct current, disposable or rechargeable. When power source 909 comprises a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 900 can also include one or more sensors 910. The one or more sensors 190 include, but are not limited to: acceleration sensor 911, gyro sensor 912, pressure sensor 913, fingerprint sensor 914, optical sensor 915, and proximity sensor 916.

The acceleration sensor 911 can detect the magnitude of acceleration in three coordinate axes of the coordinate system established with the terminal 900. For example, the acceleration sensor 911 may be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 901 can control the display screen 905 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 911. The acceleration sensor 911 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 912 may detect a body direction and a rotation angle of the terminal 900, and the gyro sensor 912 may cooperate with the acceleration sensor 911 to acquire a 3D motion of the user on the terminal 900. The processor 901 can implement the following functions according to the data collected by the gyro sensor 912: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

The pressure sensor 913 may be disposed on a side bezel of the terminal 900 and/or underneath the display 905. When the pressure sensor 913 is disposed on the side frame of the terminal 900, the user's holding signal of the terminal 900 may be detected, and the processor 901 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 913. When the pressure sensor 913 is disposed at a lower layer of the display screen 905, the processor 901 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 905. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 914 is used for collecting a fingerprint of the user, and the processor 901 identifies the user according to the fingerprint collected by the fingerprint sensor 914, or the fingerprint sensor 914 identifies the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, processor 901 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings, etc. The fingerprint sensor 914 may be disposed on the front, back, or side of the terminal 900. When a physical key or vendor Logo is provided on the terminal 900, the fingerprint sensor 914 may be integrated with the physical key or vendor Logo.

The optical sensor 915 is used to collect ambient light intensity. In one embodiment, the processor 901 may control the display brightness of the display screen 905 based on the ambient light intensity collected by the optical sensor 915. Specifically, when the ambient light intensity is high, the display brightness of the display screen 905 is increased; when the ambient light intensity is low, the display brightness of the display screen 905 is reduced. In another embodiment, the processor 901 can also dynamically adjust the shooting parameters of the camera assembly 906 according to the ambient light intensity collected by the optical sensor 915.

A proximity sensor 916, also referred to as a distance sensor, is provided on the front panel of the terminal 900. The proximity sensor 916 is used to collect the distance between the user and the front face of the terminal 900. In one embodiment, when the proximity sensor 916 detects that the distance between the user and the front face of the terminal 900 gradually decreases, the processor 901 controls the display 905 to switch from the bright screen state to the dark screen state; when the proximity sensor 916 detects that the distance between the user and the front surface of the terminal 900 gradually becomes larger, the display 905 is controlled by the processor 901 to switch from the breath screen state to the bright screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 9 does not constitute a limitation of terminal 900, and may include more or fewer components than those shown, or may combine certain components, or may employ a different arrangement of components.

Optionally, the computer device is provided as a server. Fig. 10 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 1000 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 1001 and one or more memories 1002, where the memory 1002 stores at least one program code, and the at least one program code is loaded and executed by the processors 1001 to implement the methods provided by the method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the server may also include other components for implementing the functions of the device, which are not described herein again.

The server 800 is configured to perform the steps performed by the server in the above method embodiments.

In an exemplary embodiment, a computer-readable storage medium, such as a memory including a program code, which is executable by a processor in a computer device to perform the object information recommendation method in the above embodiments, is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program or a computer program product is also provided, which includes computer program code, which, when executed by a computer, causes the computer to implement the object information recommendation method in the above-described embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An object information recommendation method, characterized in that the method comprises:

2. The method according to claim 1, wherein the performing prediction processing based on the historical behavior data and the operation data corresponding to the current login account to obtain the taste improvement parameter corresponding to the current login account includes:

extracting the characteristics of the historical behavior data and the operation data to obtain feedback information of the plurality of pieces of object information, wherein the feedback information is used for representing at least one of feedback of the current user on object information displayed for multiple times or feedback on object information not displayed for multiple times;

and performing prediction processing based on the feedback information to obtain a new taste parameter corresponding to the current login account.

3. The method according to claim 2, wherein the performing prediction processing based on the feedback information to obtain a taste new parameter corresponding to the current login account includes:

and predicting the feedback information through a new-taste prediction model to obtain new-taste parameters corresponding to the current login account.

4. The method according to claim 3, wherein the predicting the feedback information by using the taste intention prediction model to obtain taste parameters corresponding to the current login account comprises:

obtaining a model file of the tasting new intention prediction model from the local;

and calling the model file to operate the new taste intention prediction model, and performing prediction processing on the feedback information to obtain new taste parameters corresponding to the current login account.

5. The method according to claim 1, wherein before performing prediction processing based on the historical behavior data and the operation data corresponding to the current login account to obtain the taste-new parameter corresponding to the current login account, the method further comprises:

and according to the configured behavior feature type, performing feature extraction on the historical data corresponding to the current login account to obtain the historical behavior data.

6. The method according to claim 5, wherein the performing feature extraction on the historical data corresponding to the current login account according to the configured behavior feature type to obtain the historical behavior data comprises:

sending a data acquisition request to a server, wherein the data acquisition request carries the current login account, and the server is used for responding to the data acquisition request, extracting the characteristics of historical data corresponding to the current login account according to the behavior characteristic type to obtain the historical behavior data, and returning the historical behavior data to the terminal;

and receiving the historical behavior data returned by the server.

7. The method according to claim 6, wherein the server is further configured to register a data source for any account in response to a data source registration operation, wherein the data source is configured to store historical data corresponding to the account;

the server is also used for responding to the characteristic configuration operation, acquiring an input behavior characteristic type, and associating the behavior characteristic type with a data source registered for each account;

the server is further used for responding to the data acquisition request, determining a data source corresponding to the current login account, performing feature extraction on historical data stored in the data source based on a behavior feature type associated with the data source to obtain the historical behavior data, and returning the historical behavior data to the terminal.

8. The method according to claim 1, wherein the recommending at least one piece of object information to the current user according to the taste parameters in the case that the taste parameters characterize that the current user has a taste intention, comprises:

under the condition that the new taste parameters represent that the current user has new taste intentions, sending a data recommendation request to a server, wherein the data recommendation request carries the new taste parameters;

the server is used for responding to the data recommendation request, acquiring a plurality of pieces of candidate object information, adjusting the arrangement sequence of the plurality of pieces of candidate object information according to the taste new parameters, determining the candidate object information with the front target number as the object information to be recommended, and returning the object information to be recommended;

and receiving and displaying the object information returned by the server.

9. The method according to claim 1, wherein the recommending at least one piece of object information to the current user according to the taste parameters in the case that the taste parameters characterize that the current user has a taste intention, comprises:

and under the condition that the taste new parameter represents that the current user has a taste new intention, responding to the triggering operation of any one piece of object information in the plurality of pieces of object information, and recommending the at least one piece of object information to the current user according to the taste new parameter.

10. The method according to claim 2, wherein the recommending at least one piece of object information to the current user according to the taste parameters in the case that the taste parameters characterize that the current user has a taste intention, comprises:

according to the feedback information, determining first object information which is displayed for multiple times and is not triggered by the current user;

and under the condition that the taste parameter represents that the current user has the taste intention, recommending the at least one piece of object information to the current user according to the taste parameter and the first object information.

11. The method of claim 1, wherein the taste new parameter is a taste new score, and the recommending at least one piece of object information to the current user according to the taste new parameter if the taste new parameter indicates that the current user has a taste new intention comprises:

and in response to the taste new score being larger than a first threshold value, recommending the at least one piece of object information to the current user according to the taste new score.

12. The method of claim 1, wherein recommending at least one piece of subject information to the current user based on the taste parameters comprises:

determining at least one piece of object information recommended to the current user according to the taste new parameters;

inserting a tasting new list tag in the data display interface, wherein the tasting new list tag is used for displaying the at least one piece of object information;

and in response to the triggering operation of the taste list tag, presenting a taste list, wherein the taste list comprises the at least one piece of object information.

13. An object information recommendation apparatus, characterized in that the apparatus comprises:

14. A computer device comprising one or more processors and one or more memories having at least one program code stored therein, the at least one program code being loaded and executed by the one or more processors to perform operations performed by the object information recommendation method of any one of claims 1-12.

15. A computer-readable storage medium having stored therein at least one program code, the at least one program code being loaded into and executed by a processor to perform operations performed by the object information recommendation method according to any one of claims 1 to 12.