CN114139037A

CN114139037A - Method, device and equipment for determining resources and computer readable storage medium

Info

Publication number: CN114139037A
Application number: CN202111420417.XA
Authority: CN
Inventors: 毛顺辉; 周家宏; 宋伟; 林乐彬; ***; 谢乾龙; 冯俊国; 王兴星
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2021-11-26
Filing date: 2021-11-26
Publication date: 2022-03-04

Abstract

The application discloses a method, a device and equipment for determining resources and a computer readable storage medium, and belongs to the technical field of internet. The method comprises the following steps: acquiring a first position of a target object; determining a plurality of candidate resources located within a first range according to the first position; determining an index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource, wherein the index value is used for indicating the probability that the candidate resource is selected by the target object; and determining a target resource in the candidate resources based on the index values of the candidate resources, wherein the target resource is a resource to be recommended to the target object. The target resource and the target object determined by the method have higher matching degree, higher accuracy and higher reliability.

Description

Method, device and equipment for determining resources and computer readable storage medium

Technical Field

The embodiment of the application relates to the technical field of internet, in particular to a method, a device, equipment and a computer readable storage medium for determining resources.

Background

With the rapid development of the internet technology, the variety and functions of the application program based on the internet technology are more and more abundant, and the application program can recommend some resources to the user. For example, consumer applications recommend items of interest to a user. Therefore, how to determine the resources recommended to the user becomes more and more important.

When determining the target resource, the related art determines a plurality of candidate resources based on the position of the user, and determines the index value of each candidate resource based on the click rate and the conversion rate of each candidate resource in the historical time period. And taking the candidate resource with the index value meeting the requirement as the target resource.

However, the matching degree of the target resource determined by the method and the actual requirement of the user is low, so that the accuracy and the reliability of the determined target resource are not high.

Disclosure of Invention

Embodiments of the present application provide a method, an apparatus, a device, and a computer-readable storage medium for determining a resource, which may be used to solve problems in the related art. The technical scheme is as follows:

in one aspect, an embodiment of the present application provides a method for determining resources, where the method includes:

acquiring a first position of a target object;

determining a plurality of candidate resources located within a first range according to the first position;

determining an index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource, wherein the index value is used for indicating the probability that the candidate resource is selected by the target object;

and determining a target resource in the candidate resources based on the index values of the candidate resources, wherein the target resource is a resource to be recommended to the target object.

In a possible implementation manner, the determining an index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource includes:

inputting the object information of the target object and the resource information of the candidate resources into a click rate prediction model, and obtaining the click rate of the target object on the candidate resources through the click rate prediction model;

inputting the object information of the target object and the resource information of the candidate resource into a conversion rate prediction model, and obtaining the conversion rate of the target object in the candidate resource through the conversion rate prediction model;

and determining the index value of the candidate resource based on the click rate of the target object on the candidate resource and the conversion rate of the target object on the candidate resource.

In a possible implementation manner, before determining the index value of the candidate resource based on the click rate of the target object on the candidate resource and the conversion rate of the target object in the candidate resource, the method further includes:

inputting the object information of the target object and the resource information of the candidate resources into a resource numerical prediction model, and obtaining a predicted resource transfer numerical value of the target object in the candidate resources through the resource numerical prediction model;

the determining the index value of the candidate resource based on the click rate of the target object on the candidate resource and the conversion rate of the target object on the candidate resource comprises:

and determining the index value of the candidate resource based on the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer value of the target object on the candidate resource.

In a possible implementation manner, before the inputting the object information of the target object and the resource information of the candidate resource into the click-through rate prediction model and obtaining the click-through rate of the target object on the candidate resource through the click-through rate prediction model, the method further includes:

obtaining model information of a click rate prediction model, wherein the model information comprises at least one of query rate, utilization rate and load;

determining the state of the click rate prediction model based on the model information of the click rate prediction model;

and responding to the state of the click rate prediction model being an available state, and executing the operation of inputting the object information of the target object and the resource information of the candidate resource into the click rate prediction model.

In a possible implementation manner, the inputting the object information of the target object and the resource information of the candidate resource into a click-through rate prediction model, and obtaining the click-through rate of the target object on the candidate resource through the click-through rate prediction model includes:

inputting the object information of the target object and the resource information of the candidate resources into the click rate prediction model to obtain a first object characteristic of the target object and a first resource characteristic of the candidate resources;

and determining the click rate of the target object to the candidate resource based on the first object characteristic and the first resource characteristic.

In a possible implementation manner, after determining the index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource, the method further includes:

and correspondingly storing the object identifier of the first object, the resource identifier of the candidate resource and the index value of the candidate resource.

In another aspect, an embodiment of the present application provides an apparatus for determining a resource, where the apparatus includes:

the acquisition module is used for acquiring a first position of a target object;

a determining module, configured to determine, according to the first location, a plurality of candidate resources located within a first range;

the determining module is further configured to determine an index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource, where the index value is used to indicate a probability that the candidate resource is selected by the target object;

the determining module is further configured to determine a target resource among the plurality of candidate resources based on the index value of the candidate resource, where the target resource is a resource to be recommended to the target object.

In a possible implementation manner, the determining module is configured to input the object information of the target object and the resource information of the candidate resource into a click rate prediction model, and obtain a click rate of the target object on the candidate resource through the click rate prediction model; inputting the object information of the target object and the resource information of the candidate resource into a conversion rate prediction model, and obtaining the conversion rate of the target object in the candidate resource through the conversion rate prediction model; and determining the index value of the candidate resource based on the click rate of the target object on the candidate resource and the conversion rate of the target object on the candidate resource.

In a possible implementation manner, the determining module is further configured to input the object information of the target object and the resource information of the candidate resource into a resource numerical prediction model, and obtain a predicted resource transfer numerical value of the target object in the candidate resource through the resource numerical prediction model;

the determining module is used for determining the index value of the candidate resource based on the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer value of the target object on the candidate resource.

In a possible implementation manner, the obtaining module is further configured to obtain model information of a click rate prediction model, where the model information includes at least one of a query rate, a utilization rate, and a load;

the determining module is further configured to determine a state of the click rate prediction model based on model information of the click rate prediction model; and responding to the state of the click rate prediction model being an available state, and executing the operation of inputting the object information of the target object and the resource information of the candidate resource into the click rate prediction model.

In a possible implementation manner, the determining module is configured to input the object information of the target object and the resource information of the candidate resource into the click-through rate prediction model to obtain a first object feature of the target object and a first resource feature of the candidate resource; and determining the click rate of the target object to the candidate resource based on the first object characteristic and the first resource characteristic.

In one possible implementation, the apparatus further includes:

and the storage module is used for correspondingly storing the object identifier of the first object, the resource identifier of the candidate resource and the index value of the candidate resource.

In another aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, where the memory stores at least one program code, and the at least one program code is loaded and executed by the processor, so as to enable the electronic device to implement any one of the above methods for determining resources.

In another 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 and executed by a processor to make a computer implement any of the above methods for determining resources.

In another aspect, a computer program or a computer program product is provided, in which at least one computer instruction is stored, the at least one computer instruction being loaded and executed by a processor, so as to enable a computer to implement any of the above methods for determining resources.

The technical scheme provided by the embodiment of the application at least has the following beneficial effects:

the technical scheme provided by the embodiment of the application determines the index value of each candidate resource based on the object information of the target object and the resource information of the candidate resource, so that the determined index value not only considers the candidate resource, but also considers the target object, and the determined index value of each candidate resource is more accurate. And when the target resource is determined based on the index value of each candidate resource, the determined target resource is higher in matching degree with the target object, higher in accuracy and higher in reliability.

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 diagram of an implementation environment of a method for determining resources according to an embodiment of the present application;

FIG. 2 is a flow chart of a method for determining resources according to an embodiment of the present disclosure;

FIG. 3 is an architecture diagram of a method for determining resources according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an apparatus for determining resources according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application;

fig. 6 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.

Fig. 1 is a schematic diagram of an implementation environment of a method for determining resources according to an embodiment of the present application, and as shown in fig. 1, the implementation environment includes: a terminal device 101 and a server 102.

The terminal device 101 may be at least one of a smart phone, a game console, a desktop computer, a tablet computer, an e-book reader, an MP3(Moving Picture Experts Group Audio Layer III, motion Picture Experts compression standard Audio Layer 3) player, an MP4(Moving Picture Experts Group Audio Layer IV, motion Picture Experts compression standard Audio Layer 4) player, and a laptop computer. The terminal device 101 is configured to send a first location where the first object is located to the server 102, so that the server 102 determines the target resource based on the first location.

The terminal device 101 may be generally referred to as one of a plurality of terminal devices, and the present embodiment is only illustrated by the terminal device 101. Those skilled in the art will appreciate that the number of terminal devices 101 may be greater or fewer. For example, the number of the terminal device 101 may be only one, or the number of the terminal device 101 may be several tens or several hundreds, or more, and the number of the terminal devices and the device types are not limited in the embodiment of the present application.

The server 102 may be a server, or a server cluster composed of multiple servers, or any one of a cloud computing platform and a virtualization center, which is not limited in this embodiment of the present application. The server 102 and the terminal apparatus 101 are communicatively connected via a wired network or a wireless network. The server 102 is configured to execute the method for determining resources provided by the embodiment of the present application. Of course, the server 102 may also have other functions, which are not limited in this embodiment.

Based on the foregoing implementation environment, the embodiment of the present application provides a method for determining a resource, which may be executed by the server 102 in fig. 1, taking a flowchart of the method for determining a resource provided in the embodiment of the present application as shown in fig. 2 as an example. As shown in fig. 2, the method comprises the steps of:

in step 201, a first position of the target object is obtained.

In the exemplary embodiment of the present application, the server and the terminal device are communicatively connected through a wired network or a wireless network, and an application program (hereinafter, simply referred to as an application program) for acquiring a resource is installed and operated in the terminal device. And responding to the selected instruction of the target object to the application program, and sending a resource recommendation request to the server by the terminal equipment, wherein the resource recommendation request carries the first position of the target object. The server receives the resource recommendation request, analyzes the resource recommendation request and obtains a first position of the target object.

Optionally, the home page of the application is displayed in response to a selected instruction of the application by the target object. A search box and a search control are displayed in the home page, and key information is obtained in response to the input operation of the target object in the search box. And responding to a selection instruction of the target object on the search control, and sending a resource recommendation request to the server by the terminal equipment, wherein the resource recommendation request carries the first position of the target object.

Optionally, the resource recommendation request may also carry other information, such as an object identifier of the target object and object information of the target object, which is not limited in this embodiment of the application.

In a possible implementation manner, an application having a positioning function is further installed and operated in the terminal device, and the terminal device obtains the first location where the first object is located by calling the application having the positioning function. The application program with the Positioning function is, for example, a Global Positioning System (GPS), and of course, the application program with the Positioning function may also be other types of application programs, which is not limited in this embodiment of the present application.

Optionally, a position determination control is further displayed in the home page of the application, and the first object may enter a position in the position determination control. The terminal device determines a position of the first object input as a first position.

The position of the first object input in the position determination control may be the current position of the first object, or may not be the current position of the first object, which is not limited in the embodiment of the present application.

In step 202, a plurality of candidate resources within a first range is determined based on the first location.

In a possible implementation manner, the embodiment of the present application does not limit the manner of determining the plurality of candidate resources located within the first range according to the first location. Optionally, the first range is determined from the first position. And taking the resource with the position in the first range as a candidate resource.

The resource may be a merchant resource, a commodity resource, or an advertisement resource, and the type of the resource is not limited in the embodiment of the present application.

In response to the resource being a merchant resource, the location of the resource is the location of the merchant. And responding to the situation that the resource is the commodity resource, wherein the position of the resource is the position of a merchant where the commodity is located.

Optionally, the process of determining the first range according to the first position comprises: and determining an area by taking the first position as a reference point and the first length as a reference distance, and taking the range covered by the area as a first range.

Exemplarily, a first circle is determined by taking the first position as a center of a circle and the first length as a radius, and a range covered by the first circle is taken as a first range.

Optionally, the server stores the location of each resource, and after determining the first range, the server determines candidate resources among the resources based on the first range and the location of each resource. Exemplary candidate resources include: resource one, resource two, resource three, resource four and resource five.

In step 203, an index value of the candidate resource is determined based on the object information of the target object and the resource information of the candidate resource, where the index value is used to indicate a probability that the candidate resource is selected by the target object.

The object information of the target object comprises at least one of an object name, an object gender, an object age, a historical click record of the object, a historical conversion record of the object and a historical resource transfer value of the object. The resource information of the candidate resource comprises at least one of a resource name, a resource category, a resource value of the candidate resource, a click rate of the candidate resource in the target time period and a conversion rate of the candidate resource in the target time period. Of course, the object information of the target object may also include other information, and the resource information of the candidate resource may also include other information, which is not limited in this embodiment of the application.

In a possible implementation manner, the process of determining the index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource includes: and inputting the object information of the target object and the resource information of the candidate resource into an index value determination model, and obtaining the index value of the candidate resource based on the output result of the index value determination model.

Optionally, the index value is used to indicate the probability of the candidate resource being selected by the target object. The index value of the candidate resource is positively correlated with the probability of the candidate resource being selected by the target object. That is, the larger the index value of the candidate resource is, the higher the probability that the candidate resource is selected by the target object is. The smaller the index value of the candidate resource is, the lower the probability that the candidate resource is selected by the target object is.

The index value determination model is any type of model, and the embodiment of the present application does not limit this model. Illustratively, the index value determination model is a DNN model (Deep Neural Networks model).

Optionally, the structure of the index value determination model includes an input layer, a full connection layer, an attention mechanism, and an output layer. The input layer is used for inputting object information of the target object and resource information of the candidate resources, and the full-connection layer and the attention mechanism are used for processing the object information of the target object and the resource information of the candidate resources to obtain index values of the candidate resources. The output layer is used for outputting the index value of the candidate resource.

The index value determination model may determine the index values corresponding to a plurality of candidate resources at a time, or the index value determination model may determine the index values corresponding to only one candidate resource at a time.

Alternatively, since the metric value determination model may be one model or a model composed of a plurality of submodels, the process of invoking the metric value determination model to determine the metric value of the candidate resource is described in the following two cases.

In the first case, when the index value determination model is a single model, the target information of the target object and the resource information of the candidate resource are output to the index value determination model. And taking the output result of the index value determination model as the index value of the candidate resource.

And in the second case, the model for determining the index value comprises a click rate prediction model and a conversion rate prediction model. And inputting the object information of the target object and the resource information of the candidate resources into a click rate prediction model, and obtaining the click rate of the target object to the candidate resources through the click rate prediction model. And inputting the object information of the target object and the resource information of the candidate resources into a conversion rate prediction model, and obtaining the conversion rate of the target object in the candidate resources through the conversion rate prediction model. And determining the index value of the candidate resource based on the click rate of the target object to the candidate resource and the conversion rate of the target object to the candidate resource.

The click rate prediction model is used for predicting the click rate of the target object on the candidate resources, and the conversion rate prediction model is used for predicting the conversion rate of the target object on the candidate resources. The click rate prediction model and the conversion rate prediction model may be any type of model, which is not limited in the embodiment of the present application. Illustratively, the click-through rate prediction model and the conversion rate prediction model are both DNN models.

Optionally, the index value determination model may further include a resource value prediction model, and the resource value prediction model is configured to predict a predicted resource transfer value of the target object in the candidate resource. The resource value prediction model may be any type of model, which is not limited in the embodiments of the present application. Illustratively, the resource numerical prediction model is a DNN model.

In a possible implementation manner, the object information of the target object and the resource information of the candidate resource may also be input into the resource numerical prediction model, and the predicted resource transfer numerical value of the target object in the candidate resource is obtained through the resource numerical prediction model. And further, determining the index value of the candidate resource based on the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer value of the target object on the candidate resource.

The method and the device for determining the index value of the candidate resource are not limited in the embodiment of the application, and the process for determining the index value of the candidate resource based on the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer value of the target object on the candidate resource is not limited. Alternatively, the index value of the candidate resource may be determined in the following two ways.

The method comprises the following steps of obtaining click rate weight, conversion rate weight and predicted resource transfer value weight; and determining the index value of the candidate resource based on the click rate of the target object on the candidate resource, the click rate weight, the conversion rate of the target object on the candidate resource, the conversion rate weight, the predicted resource transfer value of the target object on the candidate resource and the predicted resource transfer value weight.

Alternatively, the index value S of the candidate resource i is determined according to the following formula (1)_i：

S_i＝A_i*α+B_i*β+C_i*γ (1)

In the above formula (1), A_iThe click rate of the target object to the candidate resource i is set, and alpha is the click rate weight; b is_iThe conversion rate of the target object in the candidate resource i is shown, and beta is the weight of the conversion rate; c_iThe predicted resource transfer value of the target object in the candidate resource i is shown, and gamma is the weight of the predicted resource transfer value.

And in the second implementation mode, the sum of the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer value of the target object on the candidate resource is used as the index value of the candidate resource.

Alternatively, the index value S of the candidate resource i is determined according to the following formula (2)_i：

S_i＝A_i+B_i+C_i (2)

In the above formula (2), A_iPoints of candidate resource i for target objectHit rate, B_iConversion rate of target object in candidate resource i, C_iThe predicted resource transfer value at candidate resource i for the target object.

It should be noted that any one of the above implementation manners may be selected to determine the index value of the candidate resource, and other manners may also be adopted to determine the index value of the candidate resource, which is not limited in this embodiment of the application.

In a possible implementation manner, before the object information of the target object and the resource information of the candidate resource are input into the index value determination model, the state of the index value determination model needs to be determined, and when the state of the index value determination model is a callable state, the object information of the target object and the resource information of the candidate resource can be input into the index value determination model, so as to determine the index value of the candidate resource.

When the index value determination model includes the click rate prediction model, the conversion rate prediction model and the resource value prediction model, the state of the click rate prediction model, the state of the conversion rate prediction model and the state of the resource value prediction model need to be determined respectively. And respectively inputting the object information of the target object and the resource information of the candidate resource into the model with the state being the calling state, and further obtaining the index value of the candidate resource.

When the state of the click rate prediction model, the state of the conversion rate prediction model and the state of the resource numerical value prediction model are all in an available state, the object information of the target object and the resource information of the candidate resource are respectively input into the click rate prediction model, the conversion rate prediction model and the resource numerical value prediction model, the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer numerical value of the target object on the candidate resource are respectively obtained, and the obtained index value of the candidate resource is more accurate based on the click rate of the target object on the candidate resource, the conversion rate of the target object on the candidate resource and the predicted resource transfer numerical value of the target object on the candidate resource.

Optionally, the process of determining the state of the click-through rate prediction model comprises: model information of the click-through rate prediction model is obtained, wherein the model information comprises at least one of query rate, utilization rate and load. And determining the state of the click rate prediction model based on the model information of the click rate prediction model. The Query rate may be a Query rate Per Second (QPS) or a Query rate Per Minute (QPM), which is not limited in the embodiment of the present application.

The process of determining the state of the click-through rate prediction model based on the model information of the click-through rate prediction model comprises the following steps: and determining the non-invokable degree of the click rate prediction model based on the model information of the click rate prediction model. And determining that the state of the click rate prediction model is an invocable state in response to the fact that the invocable degree of the click rate prediction model is larger than a first threshold value, and determining that the state of the click rate prediction model is an invocable state in response to the fact that the invocable degree of the click rate prediction model is not smaller than the first threshold value.

Optionally, the first threshold may be set based on experience, or may be adjusted based on a scene, and a value of the first threshold is not limited in this embodiment of the application.

Alternatively, the invokable degree X of the click rate prediction model is determined according to the following formula (3) based on the model information of the click rate prediction model.

X＝D₁*δ+D₂*ε+D₃*θ (3)

In the above formula (3), D₁For the query rate of the click-through rate prediction model, δ is the query rate weight, D₂For the utilization of the click-through prediction model, ε is the utilization weight, D₃The load of the click rate prediction model is θ, and the load weight is θ.

It should be noted that other ways may also be selected to determine the non-invokable degree of the click rate prediction model, which is not limited in the embodiment of the present application.

In a possible implementation manner, in response to that the state of the click rate prediction model is an invocable state, inputting the object information of the target object and the resource information of the candidate resource into the click rate prediction model, and obtaining the click rate of the target object on the candidate resource through the click rate prediction model includes: and inputting the object information of the target object and the resource information of the candidate resources into a click rate prediction model to obtain a first object characteristic of the target object and a first resource characteristic of the candidate resources. And determining the click rate of the target object to the candidate resource based on the first object characteristic and the first resource characteristic.

The process of determining the click rate of the target object to the candidate resource based on the first object characteristic and the first resource characteristic comprises the following steps: and calling a target function, processing the first object characteristic and the first resource characteristic to obtain a first numerical value, and taking the first numerical value as the click rate of the target object on the candidate resource.

Optionally, the objective function is an arbitrary function, which is not limited in this application. Illustratively, the objective function is a vector point-by-point function.

In one possible implementation, the process of determining the state of the conversion rate prediction model and the process of determining the state of the resource numerical value prediction model are similar to the process of determining the state of the click rate prediction model. Optionally, the process of determining the state of the conversion prediction model comprises: model information of the conversion rate prediction model is obtained, and the model information comprises at least one of query rate, utilization rate and load. Determining a state of the conversion rate prediction model based on the model information of the conversion rate prediction model.

Wherein the process of determining the state of the conversion prediction model based on the model information of the conversion prediction model comprises: determining the non-invokable degree of the conversion rate prediction model based on the model information of the conversion rate prediction model. And determining the state of the conversion rate prediction model to be an invokable state in response to the invokable degree of the conversion rate prediction model being greater than a second threshold, and determining the state of the conversion rate prediction model to be an invokable state in response to the invokable degree of the conversion rate prediction model not being less than the second threshold.

Optionally, the second threshold may be set based on experience, or may be adjusted based on a scene, and a value of the second threshold is not limited in this embodiment of the application.

Alternatively, the degree of non-involability Y of the conversion rate prediction model is determined according to the following formula (4) based on the model information of the conversion rate prediction model.

Y＝E₁*δ+E₂*ε+E₃*θ (4)

In the above formula (4), E₁Query rate for the conversion prediction model, δ is the query rate weight, E₂For the conversion prediction model utilization, ε is the utilization weight, E₃To predict the load of the model for conversion, θ is the load weight.

It should be noted that other ways may also be selected to determine the non-invokable degree of the conversion rate prediction model, which is not limited in the embodiment of the present application.

In one possible implementation manner, in response to that the state of the conversion rate prediction model is an invocable state, inputting the object information of the target object and the resource information of the candidate resource into the conversion rate prediction model, and obtaining the conversion rate of the target object in the candidate resource through the conversion rate prediction model includes: and inputting the object information of the target object and the resource information of the candidate resources into the conversion rate prediction model to obtain a second object characteristic of the target object and a second resource characteristic of the candidate resources. And determining the conversion rate of the target object in the candidate resource based on the second object characteristic and the second resource characteristic.

Wherein, the process of determining the conversion rate of the target object in the candidate resource based on the second object characteristic and the second resource characteristic comprises: and calling a target function, processing the second object characteristic and the second resource characteristic to obtain a second numerical value, and taking the second numerical value as the conversion rate of the target object in the candidate resource.

Optionally, the process of determining the state of the resource numerical prediction model includes: model information of the resource numerical prediction model is obtained, and the model information comprises at least one of query rate, utilization rate and load. And determining the state of the resource numerical prediction model based on the model information of the resource numerical prediction model.

The process of determining the state of the resource numerical prediction model based on the model information of the resource numerical prediction model includes: and determining the non-invokable degree of the resource numerical prediction model based on the model information of the resource numerical prediction model. And determining that the state of the resource numerical value prediction model is an invokable state in response to the invokable degree of the resource numerical value prediction model being greater than a third threshold, and determining that the state of the resource numerical value prediction model is an invokable state in response to the invokable degree of the resource numerical value prediction model being not less than the third threshold.

Optionally, the third threshold may be set based on experience, or may be adjusted based on a scene, and a value of the third threshold is not limited in this embodiment of the application.

Alternatively, the invokable degree Z of the resource numerical prediction model is determined according to the following equation (5) based on the model information of the resource numerical prediction model.

Z＝F₁*δ+F₂*ε+F₃*θ (5)

In the above formula (5), F₁Query rate for a resource numerical prediction model, δ being a query rate weight, F₂For the resource value, the utilization of the model is predicted, ε is the utilization weight, F₃The load of the resource numerical prediction model is shown, and theta is a load weight.

It should be noted that other ways may also be selected to determine the invokable degree of the resource numerical prediction model, which is not limited in the embodiment of the present application.

In a possible implementation manner, in response to that the state of the resource numerical prediction model is an invocable state, the object information of the target object and the resource information of the candidate resource are input into the resource numerical prediction model, and the process of obtaining the predicted resource transfer value of the target object in the candidate resource through the resource numerical prediction model includes: and inputting the object information of the target object and the resource information of the candidate resources into a resource numerical prediction model to obtain a third object characteristic of the target object and a third resource characteristic of the candidate resources. And determining the predicted resource transfer value of the target object in the candidate resource based on the third object characteristic and the third resource characteristic.

Wherein, the process of determining the predicted resource transfer value of the target object in the candidate resource based on the third object characteristic and the third resource characteristic comprises: and calling a target function, processing the third object characteristic and the third resource characteristic to obtain a third numerical value, and taking the third numerical value as an expected resource transfer numerical value of the target object in the candidate resource.

Optionally, after the index value corresponding to each candidate resource is determined, the object identifier of the first object, the resource identifier of the candidate resource, and the index value of the candidate resource may be correspondingly stored in the storage space of the server.

The object identifier of the first object is an identifier capable of uniquely representing the first object, such as the object identifier of the first object being an account number of the first object. The resource identifier of the candidate resource is an identifier capable of uniquely representing the candidate resource, for example, the resource identifier of the candidate resource is a resource name of the candidate resource.

The following table one is a table showing a corresponding relationship between an object identifier of a first object, a resource identifier of a candidate resource, and an index value of the candidate resource provided in the embodiment of the present application.

Watch 1

As shown in the above table one, the object is identified as the first object, the candidate resources include resources one to five, and the index value of each candidate resource is shown in the above table one, which is not repeated herein.

In step 204, a target resource is determined among the plurality of candidate resources based on the index values of the candidate resources, wherein the target resource is a resource to be recommended to the target object.

In a possible implementation manner, after determining the index value of each candidate resource based on step 203, the process of determining the target resource among the plurality of candidate resources based on the index values of the candidate resources includes: and taking the candidate resources with the index values meeting the target requirements in the candidate resources as target resources.

Wherein the indicator value satisfies a target requirement for indicating that the indicator value is greater than a target threshold. The target threshold value can be set based on experience, and can also be adjusted according to a scene, and the value of the target threshold value is not limited in the embodiment of the application.

Illustratively, the target requirement is an index value greater than 75, and based on the above table one and the target requirement, resource three, resource four, and resource five are determined as target resources.

Optionally, after the target resource is determined from the multiple candidate resources, the target resource is sent to the terminal of the target object, so that the terminal of the target object displays the target resource, that is, the purpose of recommending the target resource to the target object is achieved.

In a possible implementation manner, a first candidate resource may be determined in the candidate resources based on the index value of the candidate resource, the first candidate resource is refined, and a second candidate resource is determined from the refined first candidate resource. And after the second candidate resources are rearranged, determining the target resources from the rearranged second candidate resources.

Optionally, in step 203, after the object identifier of the first object, the resource identifier of the candidate resource, and the index value of the candidate resource are stored correspondingly, when the first object requests resource recommendation again, the server receives a secondary resource recommendation request sent by the terminal device, where the secondary resource recommendation request carries the second location where the first object is located and the object identifier of the first object. A plurality of reference resources within a second range is determined based on the second location. And acquiring a plurality of candidate resources and index values of the candidate resources based on the object identification of the first object. Based on the reference resource and the candidate resource, a target resource is determined.

The process of determining a plurality of reference resources located in the second range according to the second location is similar to the process of determining a plurality of candidate resources located in the first range according to the first location in step 202, and is not repeated herein.

In a possible implementation manner, in response to that all the reference resources are included in the candidate resources, the index value of the candidate resource consistent with the reference resource is used as the index value of the reference resource, and the reference resource of which the index value meets the target requirement in the reference resource is used as the target resource.

Exemplary candidate resources include: resource one, resource two, resource three, resource four and resource five, the reference resource includes: and if the resource I, the resource II, the resource III and the resource IV are the same, all the reference resources can be determined to be included in the candidate resources. And acquiring index values corresponding to the resource I, the resource II, the resource III and the resource IV respectively. And determining the target resource based on index values respectively corresponding to the resource I, the resource II, the resource III and the resource IV.

Optionally, when the candidate resource includes a partial reference resource, taking an index value of the candidate resource consistent with the first resource as an index value of the first resource, where the first resource is any one of the partial reference resources; and acquiring an index value of a second resource, wherein the second resource is any one of the reference resources except the first resource. And determining the target resource based on the index value of the first resource and the index value of the second resource.

In one possible implementation manner, there may be three implementation manners described below to obtain the index value of the second resource.

In the first implementation manner, at least one third resource is acquired based on the position of the second resource. And determining the index value of the second resource based on the click rate, the conversion rate and the resource transfer value of the at least one third resource in the target time period.

The process of obtaining at least one third resource based on the location of the second resource is similar to the process of determining a plurality of candidate resources located in the first range according to the first location, and is not described herein again.

The target time period is any historical time period, and the time length of the target time period is any, which is not limited in the embodiment of the present application.

Optionally, the process of determining the index value of the second resource based on the click rate, the conversion rate and the resource transfer value of the at least one third resource in the target time period includes: and determining the click rate, the conversion rate and the resource transfer value of each third resource in the target time period. And determining the average value of the first click rates based on the click rates of the third resources in the target time period. And determining the average value of the first conversion rate based on the conversion rate of each third resource in the target time period. And determining a first resource transfer average value based on the resource transfer values of the third resources in the target time period. And determining an index value of the second resource based on the first click rate average value, the first conversion rate average value and the first resource transfer average value.

Optionally, the click rate ctr of the third resource i in the target time period is shown in the following formula (6)_iThe determination formula of (2).

In the above formula (6), V_iIs the number of times that the third resource i is clicked in the target time period, U_iIs the number of exposures of the third resource i for the target time period.

The conversion cvr of the third resource i in the target time period is shown in the following formula (7)_iThe determination formula of (2).

In the above formula (7), W_iIs the conversion number, V, of the third resource i in the target time period_iIs the number of clicks of the third resource i in the target time period.

The value P of the resource transfer of the third resource i in the target time period is shown in the following formula (8)_iThe determination formula of (2).

In the above equation (8), W is the value of the resource transfer for each conversion of the first resource i in the target time period_iIs the conversion number of the third resource i in the target time period.

And determining at least one fourth resource matched with the resource type of the second resource, and determining the index value of the second resource based on the click rate, the conversion rate and the resource transfer value of the at least one fourth resource in the target time period.

The target time period is any historical time period, the time length of the target time period is any, and the time length is not limited in the embodiment of the application.

Optionally, the process of determining the index value of the second resource based on the click rate, the conversion rate and the resource transfer value of the at least one fourth resource in the target time period includes: and determining the click rate, the conversion rate and the resource transfer value of each fourth resource in the target time period. And determining a second average click rate value based on the click rate of each fourth resource in the target time period, determining a second average conversion rate value based on the conversion rate of each fourth resource in the target time period, and determining a second average resource transfer value based on the resource transfer value of each fourth resource in the target time period. And determining an index value corresponding to the second resource based on the second click rate average value, the second conversion rate average value and the second resource transfer average value.

The process of determining the click rate, the conversion rate and the resource transfer value of each fourth resource in the target time period is similar to the process of determining the click rate, the conversion rate and the resource transfer value of each third resource in the target time period in the above implementation manner, and details are not repeated here.

And in the third implementation mode, the pocket bottom value of the second resource is used as the index value corresponding to the second resource.

Optionally, each resource corresponds to one pocket bottom value, and the pocket bottom value corresponding to the second resource may also be directly used as an index value of the second resource.

It should be noted that any one of the above implementations may be selected to determine the index value of the second resource, which is not limited in the embodiment of the present application. The index value of the second resource can be determined by the first implementation manner, when the index value of the second resource cannot be determined by the second implementation manner, the index value of the second resource is determined by the second implementation manner, and when the index value of the second resource cannot be determined by the second implementation manner, the index value of the second resource is determined by the third implementation manner.

Exemplary candidate resources include: resource one, resource two, resource three, resource four and resource five, the reference resource includes: resource one, resource two, resource three, resource four, resource five and resource six. The candidate resource comprises a partial reference resource. And acquiring index values corresponding to the resource I, the resource II, the resource III, the resource IV and the resource V respectively. And acquiring the index value of the resource six according to any one of the three implementation modes. And determining the target resource based on index values corresponding to the resource I, the resource II, the resource III, the resource IV, the resource V and the resource VI respectively.

The method determines the index value of each candidate resource based on the object information of the target object and the resource information of the candidate resource, so that the determined index value not only considers the candidate resource, but also considers the target object, and the determined index value of each candidate resource is more accurate. And when the target resource is determined based on the index value of each candidate resource, the determined target resource is higher in matching degree with the target object, higher in accuracy and higher in reliability.

Fig. 3 is an architecture diagram of a method for determining resources according to an embodiment of the present application, as shown in fig. 3, including an online system, a proximity system, and a computing power regulation system.

The online system is used for recalling the candidate resources, and after the candidate resources are recalled, the candidate resources are sent to a near line calculation module in the near line system through mafks (message queue).

A near line calculation module in the near line system receives the candidate resource, and invokes a refinement model pre-estimation service (corresponding to the index value determination model in the embodiment shown in fig. 2) to process the candidate resource, so as to obtain an index value of the candidate resource. When the refined model prediction service is called, a calculation force regulation and control module based on a calculation force regulation and control system is needed to determine the state of the refined model prediction service. And responding to the state of the fine scheduling model prediction service as an adjustable state, and then calling.

The smart model pre-estimation service feeds back model information of the smart model pre-estimation service to the calculation force regulation and control module in real time, and the calculation force regulation and control module determines the state of the smart model pre-estimation service based on the model information of the smart model pre-estimation service.

The near line calculation module stores an index value of the candidate resource in a redis (cache memory).

The online system obtains an index value of the candidate resource from the redis, and obtains a first candidate resource based on the index value of the candidate resource. And then entering a fine scheduling stage, and calling a fine scheduling model estimation service to process the first candidate resource in the fine scheduling stage to obtain a second candidate resource.

The second candidate resource may be used as the target resource, or the second candidate resource may be rearranged, and the target resource is determined in the rearranged candidate resources.

Fig. 4 is a schematic structural diagram of an apparatus for determining resources according to an embodiment of the present application, and as shown in fig. 4, the apparatus includes:

an obtaining module 401, configured to obtain a first position where a target object is located;

a determining module 402, configured to determine, according to the first location, a plurality of candidate resources located within a first range;

the determining module 402 is further configured to determine an index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource, where the index value is used to indicate a probability that the candidate resource is selected by the target object;

the determining module 402 is further configured to determine a target resource among the multiple candidate resources based on the index value of the candidate resource, where the target resource is a resource to be recommended to the target object.

In a possible implementation manner, the determining module 402 is configured to input object information of a target object and resource information of a candidate resource into a click rate prediction model, and obtain a click rate of the target object on the candidate resource through the click rate prediction model; inputting the object information of the target object and the resource information of the candidate resources into a conversion rate prediction model, and obtaining the conversion rate of the target object in the candidate resources through the conversion rate prediction model; and determining the index value of the candidate resource based on the click rate of the target object on the candidate resource and the conversion rate of the target object on the candidate resource.

In a possible implementation manner, the determining module 402 is further configured to input the object information of the target object and the resource information of the candidate resource into the resource numerical prediction model, and obtain a predicted resource transfer value of the target object in the candidate resource through the resource numerical prediction model;

a determining module 402, configured to determine an index value of the candidate resource based on the click rate of the target object on the candidate resource, the conversion rate of the target object in the candidate resource, and the predicted resource transfer value of the target object in the candidate resource.

In a possible implementation manner, the obtaining module 401 is further configured to obtain model information of the click rate prediction model, where the model information includes at least one of a query rate, a utilization rate, and a load;

the determining module 402 is further configured to determine a state of the click rate prediction model based on model information of the click rate prediction model; and responding to the state of the click rate prediction model as an available state, and executing the operation of inputting the object information of the target object and the resource information of the candidate resource into the click rate prediction model.

In a possible implementation manner, the determining module 402 is configured to input object information of a target object and resource information of a candidate resource into a click rate prediction model to obtain a first object feature of the target object and a first resource feature of the candidate resource; and determining the click rate of the target object to the candidate resource based on the first object characteristic and the first resource characteristic.

In one possible implementation, the apparatus further includes:

The device determines the index value of each candidate resource based on the object information of the target object and the resource information of the candidate resource, so that the determined index value not only considers the candidate resource, but also considers the target object, and the determined index value of each candidate resource is more accurate. And when the target resource is determined based on the index value of each candidate resource, the determined target resource is higher in matching degree with the target object, higher in accuracy and higher in reliability.

It should be understood that, when the above-mentioned apparatus is provided to implement its functions, it is only illustrated by the division of the above-mentioned functional modules, and in practical applications, the above-mentioned functions may be distributed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.

Fig. 5 shows a block diagram of a terminal device 500 according to an exemplary embodiment of the present application. The terminal device 500 may be a portable mobile terminal such as: 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. The terminal device 500 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

In general, the terminal device 500 includes: a processor 501 and a memory 502.

The processor 501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 501 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 501 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 501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, processor 501 may also include an AI (Artificial Intelligence) processor for processing computational operations related to machine learning.

Memory 502 may include one or more computer-readable storage media, which may be non-transitory. Memory 502 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 memory 502 is used to store at least one instruction for execution by processor 501 to implement the method of determining resources provided by the method embodiments herein.

In some embodiments, the terminal device 500 may further include: a peripheral interface 503 and at least one peripheral. The processor 501, memory 502 and peripheral interface 503 may be connected by a bus or signal lines. Each peripheral may be connected to the peripheral interface 503 by a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 504, display screen 505, camera assembly 506, audio circuitry 507, positioning assembly 508, and power supply 509.

The peripheral interface 503 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 501 and the memory 502. In some embodiments, the processor 501, memory 502, and peripheral interface 503 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 501, the memory 502, and the peripheral interface 503 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

The Radio Frequency circuit 504 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 504 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 504 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 504 includes: 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 circuitry 504 may communicate with other terminal devices via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, generations of mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 504 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 505 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 505 is a touch display screen, the display screen 505 also has the ability to capture touch signals on or over the surface of the display screen 505. The touch signal may be input to the processor 501 as a control signal for processing. At this point, the display screen 505 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 screen 505 may be one, and is disposed on the front panel of the terminal device 500; in other embodiments, the display screens 505 may be at least two, respectively disposed on different surfaces of the terminal device 500 or in a folding design; in other embodiments, the display 505 may be a flexible display, disposed on a curved surface or on a folded surface of the terminal device 500. Even more, the display screen 505 can be arranged in a non-rectangular irregular figure, i.e. a shaped screen. The Display screen 505 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 506 is used to capture images or video. Optionally, camera assembly 506 includes a front camera and a rear camera. In general, a front camera is provided on the front panel of the terminal apparatus 500, and a rear camera is provided on the rear surface of the terminal apparatus 500. 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 506 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 circuitry 507 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 501 for processing, or inputting the electric signals to the radio frequency circuit 504 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different positions of the terminal device 500. 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 501 or the radio frequency circuit 504 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 circuitry 507 may also include a headphone jack.

The positioning component 508 is used to locate the current geographic position of the terminal device 500 for navigation or LBS (Location Based Service). The Positioning component 508 may be a Positioning component based on the Global Positioning System (GPS) in the united states, the beidou System in china, or the galileo System in russia.

The power supply 509 is used to supply power to the various components in the terminal device 500. The power source 509 may be alternating current, direct current, disposable or rechargeable. When power supply 509 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, the terminal device 500 further includes one or more sensors 510. The one or more sensors 510 include, but are not limited to: acceleration sensor 511, gyro sensor 512, pressure sensor 513, fingerprint sensor 514, optical sensor 515, and proximity sensor 516.

The acceleration sensor 511 may detect the magnitude of acceleration on three coordinate axes of the coordinate system established with the terminal apparatus 500. For example, the acceleration sensor 511 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 501 may control the display screen 505 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 511. The acceleration sensor 511 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 512 may detect a body direction and a rotation angle of the terminal device 500, and the gyro sensor 512 may cooperate with the acceleration sensor 511 to acquire a 3D motion of the user on the terminal device 500. The processor 501 may implement the following functions according to the data collected by the gyro sensor 512: 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 513 may be disposed on a side bezel of the terminal device 500 and/or on a lower layer of the display screen 505. When the pressure sensor 513 is disposed on the side frame of the terminal device 500, the holding signal of the user to the terminal device 500 can be detected, and the processor 501 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 513. When the pressure sensor 513 is disposed at the lower layer of the display screen 505, the processor 501 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 505. 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 514 is used for collecting a fingerprint of the user, and the processor 501 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 514, or the fingerprint sensor 514 identifies the identity of the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, the processor 501 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 514 may be disposed on the front, back, or side of the terminal device 500. When a physical button or a vendor Logo is provided on the terminal device 500, the fingerprint sensor 514 may be integrated with the physical button or the vendor Logo.

The optical sensor 515 is used to collect the ambient light intensity. In one embodiment, the processor 501 may control the display brightness of the display screen 505 based on the ambient light intensity collected by the optical sensor 515. Specifically, when the ambient light intensity is high, the display brightness of the display screen 505 is increased; when the ambient light intensity is low, the display brightness of the display screen 505 is reduced. In another embodiment, processor 501 may also dynamically adjust the shooting parameters of camera head assembly 506 based on the ambient light intensity collected by optical sensor 515.

The proximity sensor 516, also called a distance sensor, is generally provided on the front panel of the terminal apparatus 500. The proximity sensor 516 is used to collect the distance between the user and the front surface of the terminal device 500. In one embodiment, when the proximity sensor 516 detects that the distance between the user and the front surface of the terminal device 500 gradually decreases, the processor 501 controls the display screen 505 to switch from the bright screen state to the dark screen state; when the proximity sensor 516 detects that the distance between the user and the front surface of the terminal device 500 becomes gradually larger, the processor 501 controls the display screen 505 to switch from the screen-on state to the screen-on state.

Those skilled in the art will appreciate that the configuration shown in fig. 5 is not limiting of terminal device 500 and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components may be used.

Fig. 6 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 600 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where at least one program code is stored in the one or more memories 602, and is loaded and executed by the one or more processors 601 to implement the method for determining resources according to the foregoing method embodiments. Of course, the server 600 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 600 may also include other components for implementing the functions of the device, which is not described herein again.

In an exemplary embodiment, there is also provided a computer readable storage medium having at least one program code stored therein, the at least one program code being loaded and executed by a processor to cause a computer to implement any of the above-mentioned methods of determining resources.

Alternatively, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (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, in which at least one computer instruction is stored, which is loaded and executed by a processor, to cause a computer to implement any of the above-mentioned methods of determining resources.

It should be understood that reference to "a plurality" herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

The above description is only exemplary of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like that are made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of determining resources, the method comprising:

acquiring a first position of a target object;

2. The method of claim 1, wherein the determining the index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource comprises:

3. The method of claim 2, wherein before determining the indicator value of the candidate resource based on the click rate of the target object on the candidate resource and the conversion rate of the target object in the candidate resource, the method further comprises:

4. The method of claim 2, wherein before inputting the object information of the target object and the resource information of the candidate resource into a click-through rate prediction model and obtaining the click-through rate of the target object on the candidate resource through the click-through rate prediction model, the method further comprises:

5. The method according to any one of claims 2 to 4, wherein the inputting the object information of the target object and the resource information of the candidate resource into a click-through rate prediction model, and obtaining the click-through rate of the target object on the candidate resource through the click-through rate prediction model, comprises:

6. The method according to any one of claims 1 to 4, wherein after determining the index value of the candidate resource based on the object information of the target object and the resource information of the candidate resource, the method further comprises:

7. An apparatus for determining resources, the apparatus comprising:

8. An electronic device, comprising a processor and a memory, wherein at least one program code is stored in the memory, and wherein the at least one program code is loaded and executed by the processor to cause the electronic device to implement the method for determining resources according to any one of claims 1 to 6.

9. A computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded and executed by a processor to cause a computer to implement the method of determining resources of any of claims 1 to 6.

10. A computer program product having stored therein at least one computer instruction which is loaded and executed by a processor to cause a computer to implement a method of determining resources as claimed in any one of claims 1 to 6.