Resource information determination method, device, electronic device and storage medium

Abstract

The embodiments of the present invention are applicable to the field of computer technology, and provide a method, device, electronic device and storage medium for determining resource information, wherein the method for determining resource information includes: determining a first feature corresponding to a first user; the first feature represents user information of the corresponding user; the first feature and at least two second features are input into a set model to obtain a first similarity between the first feature and each of the at least two second features; the second feature represents a user set of second users who interact with the corresponding resource; and based on the determined first similarity, determining resource information of the first resource pushed to the first user.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a resource information determination method, device, electronic device and storage medium. Background Art

[0002] In the e-commerce scenario, pushing resources to appropriate users can achieve higher resource click-through rates and order conversions. In related technologies, operators select users who are interested in each resource as the user set of the resource based on their understanding of each resource. For new users, the distance between the new user and the user set of each resource is calculated, and the resources corresponding to the user set with the closest distance are recommended to the new user. Related technologies directly calculate the similarity between users and each user set based on distance, which cannot accurately measure the relationship between users and resources, and the resources recommended to users are not accurate enough. Summary of the invention

[0003] In order to solve the above problems, the embodiments of the present invention provide a method, device, electronic device and storage medium for determining resource information, so as to at least solve the problem that the related technology directly calculates the similarity between the user and each user set through distance, and the resources recommended to the user are not accurate enough.

[0004] The technical solution of the present invention is achieved in this way:

[0005] In a first aspect, an embodiment of the present invention provides a method for determining resource information, the method comprising:

[0006] Determine a first feature corresponding to a first user; the first feature represents user information of the corresponding user;

[0007] Inputting the first feature and at least two second features into a setting model to obtain a first similarity between the first feature and each of the at least two second features; the second feature represents a user set of second users who interact with the corresponding resource;

[0008] Resource information of a first resource pushed to the first user is determined based on the determined first similarity.

[0009] In the above solution, the determining the first feature corresponding to the first user includes:

[0010] The first information and / or the second information of the first user are vectorized to obtain the first feature; the first information represents the attribute information of the first user; and the second information represents the resource interaction information of the first user.

[0011] In the above scheme, the method further comprises:

[0012] determining a first characteristic of each second user in a set of users of second users that interacted with the corresponding resource;

[0013] Based on the determined first characteristic of the second user, a second characteristic of a user set of the second users participating in the corresponding resource is determined.

[0014] In the above scheme, the method further comprises:

[0015] In the case of adding the second resource to the set resource list, determining a second similarity between the resource information of the second resource and the resource information of each resource in the set resource list; each resource in the set resource list corresponds to one of the at least two second features;

[0016] The second feature corresponding to the resource in the set resource list with the second similarity to the resource information of the second resource being the greatest is determined as the second feature corresponding to the second resource.

[0017] In the above solution, determining the resource information of the first resource pushed to the first user based on the determined first similarity includes:

[0018] The resource information of the resource corresponding to the second feature of the at least two second features whose first similarity with the first feature is greater than a set value is determined as the resource information of the first resource pushed to the first user.

[0019] In the above scheme, the method further comprises:

[0020] A user set of the second user corresponding to each resource is determined according to the access time of the resource page of the corresponding resource accessed by the second user.

[0021] In a second aspect, an embodiment of the present invention provides a model training method, the method comprising:

[0022] The first feature corresponding to the third user, the second feature of the user set corresponding to the third resource, and the label of the third user are concatenated to obtain first training data; the label indicates whether the third user visits the resource page of the third resource;

[0023] Inputting the first training data into the set model to obtain a probability value output by the set model; the probability value represents the similarity between the first feature of the third user and the second feature of the user set of the third resource;

[0024] A model parameter of the set model is adjusted based on the probability value.

[0025] In a third aspect, an embodiment of the present invention provides a resource information determination device, the device comprising:

[0026] A first determining module is used to determine a first feature corresponding to a first user; the first feature represents user information of the corresponding user;

[0027] A first input module, configured to input the first feature and at least two second features into a setting model to obtain a first similarity between the first feature and each of the at least two second features; the second feature represents a user set of second users interacting with the corresponding resource;

[0028] The second determining module is used to determine resource information of a first resource pushed to the first user based on the determined first similarity.

[0029] In a fourth aspect, an embodiment of the present invention provides a model training device, the device comprising:

[0030] a splicing module, configured to splice a first feature corresponding to a third user, a second feature of a user set corresponding to a third resource, and a label of the third user to obtain first training data; the label indicates whether the third user has accessed a resource page of the third resource;

[0031] A second input module is used to input the first training data into the set model to obtain a probability value output by the set model; the probability value represents the similarity between the first feature of the third user and the second feature of the user set of the third resource;

[0032] An adjustment module is used to adjust the model parameters of the set model based on the probability value.

[0033] In a fifth aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the steps of the resource information determination method provided in the first aspect of the embodiment of the present invention or the steps of the model training method provided in the second aspect.

[0034] In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, including: the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the resource information determination method provided in the first aspect of the embodiment of the present invention or the steps of the model training method provided in the second aspect are implemented.

[0035] The embodiment of the present invention determines the first feature corresponding to the first user, inputs the first feature and at least two second features into a setting model, obtains the first similarity between the first feature and each of the at least two second features, and determines the resource information of the first resource pushed to the first user based on the first similarity. The first feature represents the user information of the corresponding user, and the second feature represents the user set of the second user who interacts with the corresponding resource. The embodiment of the present invention obtains the cross-relationship between the first user and the resource by setting a model, and can more accurately obtain the similarity between the first user and the user set of the resource, so that the resource information pushed to the user is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of an implementation flow of a method for determining resource information provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic diagram of an implementation flow of another resource information determination method provided by an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of an implementation flow of another resource information determination method provided by an embodiment of the present invention;

[0039] Figure 4 It is a schematic diagram of an implementation flow of another resource information determination method provided by an embodiment of the present invention;

[0040] Figure 5 It is a schematic diagram of a resource information push process provided by an application embodiment of the present invention;

[0041] Figure 6 is a schematic diagram of a resource information determination device provided by an embodiment of the present invention;

[0042] Figure 7 is a schematic diagram of a model training device provided by an embodiment of the present invention;

[0043] Figure 8 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Related technologies rely on operators to manually select resource information for push users, which requires operators to have strong business experience. However, resources change frequently, manual selection is inefficient, and the participating users of resources change in real time, so the real-time nature of the user set is not strong. Directly calculating the similarity between users and each seed population through distance cannot accurately measure the relationship between users and resources, and the resources recommended to users are not accurate enough.

[0046] In view of the shortcomings of the above-mentioned related technologies, an embodiment of the present invention provides a method for determining resource information, which can at least improve the accuracy of resources recommended to users. In order to illustrate the technical solution of the present invention, a specific embodiment is used for description below.

[0047] Figure 1 1 is a schematic diagram of an implementation flow of a method for determining resource information provided by an embodiment of the present invention. The execution subject of the method for determining resource information may be an electronic device, and the electronic device may be a desktop computer, a notebook computer, a server, etc. Figure 1 , the resource information determination method includes:

[0048] S101, determining a first feature corresponding to a first user; the first feature represents user information of the corresponding user.

[0049] Here, the first user refers to the user who pushes the resource information. Here, the resource refers to the activity. In the e-commerce scenario, the resource can be the platform's full discount activity, coupon distribution activity, payment cash back activity, etc.

[0050] The user information of the first user is vectorized to obtain a first feature corresponding to the first user. The user information of the first user includes the user's gender, age, interaction information with resources, etc.

[0051] In one embodiment, determining the first feature corresponding to the first user includes:

[0052] The first information and / or the second information of the first user are vectorized to obtain the first feature; the first information represents the attribute information of the first user; and the second information represents the resource interaction information of the first user.

[0053] Here, the first information refers to the attribute information of the first user, including the user's age, gender, height, etc. For example, gender is converted to one-hot, male is (1, 0), and female is (0, 1). The second information refers to the resource interaction information of the first user, such as the number of times the user clicks on the resource page in a month, the number of products purchased by the user in a month, etc. Here, the first feature of the user is represented by userV.

[0054] S102, inputting the first feature and at least two second features into a setting model to obtain a first similarity between the first feature and each of the at least two second features; the second feature represents a user set of second users interacting with the corresponding resource.

[0055] In the embodiment of the present invention, there is a resource list, each resource in the resource list corresponds to one of at least two second features, and each resource has a user set, which is composed of second users interacting with the corresponding resource.

[0056] In one embodiment, the user set of the second user corresponding to each resource is determined according to the access time of the second user accessing the resource page of the corresponding resource.

[0057] For each user set of a resource, the embodiment of the present invention sets an upper limit on the number of users, for example, the maximum number of users in the user set is 100. If it is found that the number of second users interacting with the corresponding resource is greater than 100, the second users are sorted in the order of the time when the second users access the resource page of the corresponding resource, and the second users who have recently accessed the resource page of the corresponding resource are placed at the front and sorted in sequence. The top 100 second users are selected to form the user set of the corresponding resource. In this way, the real-time performance of the user set can be ensured.

[0058] refer to Figure 2 In one embodiment, the method further comprises:

[0059] S201: Determine a first feature of each second user in a user set of second users who interact with a corresponding resource.

[0060] The user information of each second user in the user set is vectorized to obtain a first feature of each second user in the user set.

[0061] S202: Determine a second feature of a user set of second users who participate in the corresponding resource based on the determined first feature of the second user.

[0062] Here, the mean of the first feature of each second user in the user set may be calculated to obtain the second feature of the user set.

[0063] For example, the first feature of the second user in the user set is represented by userV, and the second feature is represented by seedV.

[0064] seedV=average_pooling(seed n (actid))=average_pooling(userV N)=average_pooling(userV1, userV2,..., userV N )=(average(userV 11 +userV 21 +…+userV N1 ), average(userV 12 +userV 22 +…+userV N2 ), …, average(userV 1K +userV 2K +…+userV NK )). Among them, userV NK It is represented as the K-th eigenvalue corresponding to the vector of the N-th user.

[0065] The first feature and at least two second features of the first user are input into the setting model to obtain a first similarity between the first feature output by the setting model and each of the at least two second features. Here, the setting model is used to determine the similarity between the features, and the first similarity output by the setting model is a probability value, which indicates the degree of similarity between the first feature and the second feature.

[0066] For example, a resource is a preferential resource about razors, a first user often searches for razor-related products, and the first user is a male, then the first similarity between the first feature of the first user and the second feature of the resource is relatively large.

[0067] Prior to this, the model needs to be trained with training data in advance.

[0068] Figure 3 1 is a schematic diagram of an implementation flow of a model training method provided by an embodiment of the present invention. The model training method is used to train the set model in the above embodiment. The execution subject of the model training method can be an electronic device, and the electronic device can be a desktop computer, a laptop computer, a server, etc. Figure 3 , model training methods include:

[0069] S301, concatenate a first feature corresponding to a third user, a second feature of a user set corresponding to a third resource, and a label of the third user to obtain first training data; the label indicates whether the third user accesses a resource page of the third resource.

[0070] Here, the third resource may be a resource in the resource list or not. Whether the third user visits the resource page of the third resource is known. The first feature of the third user and the second feature corresponding to the user set of the third resource are concatenated. For example, the first feature of the third user is userV, and the second feature corresponding to the third resource is seedV. The behavior of whether the third user visits the resource page of the third resource is represented by Y. If Y is visited, it is marked as 1, and if Y is not visited, it is marked as 0. The first training data is represented by X, then X = [userV, seedV, Y].

[0071] The embodiment of the present invention splices only one piece of training data of the set model. This is just an example of splicing training data, and does not mean that the set model only needs one piece of training data. The set model needs multiple training data for iterative training during training to ensure the accuracy of the output result of the set model.

[0072] S302: Input the first training data into the set model to obtain a probability value output by the set model; the probability value represents the similarity between the first feature of the third user and the second feature of the user set of the third resource.

[0073] The spliced ​​first training data is used as training data of the setting model and input into the setting model for model training. During the training process, the setting model will output a probability value, which indicates the similarity between the first feature of the third user and the second feature of the user set of the third resource.

[0074] S303: Adjust model parameters of the set model based on the probability value.

[0075] Adjust the model parameters of the model according to the probability value, such as adjusting the remaining number of iterations; adjusting the batch size, which refers to the number of samples fed into the model each time the neural network is trained; and adjusting the learning rate, which refers to the magnitude of the update of the network weights in the optimization algorithm.

[0076] The set model after adjusting the model parameters is retrained using the training data until the loss function of the set model converges. The trained set model can be used to obtain the similarity between the first feature of the user and the second feature corresponding to the resource.

[0077] S103: Determine resource information of a first resource pushed to the first user based on the determined first similarity.

[0078] In one embodiment, determining the resource information of the first resource to be pushed to the first user based on the determined first similarity includes:

[0079] The resource information of the resource corresponding to the second feature of the at least two second features whose first similarity with the first feature is greater than a set value is determined as the resource information of the first resource pushed to the first user.

[0080] Here, resource information of multiple first resources can be pushed to the first user at one time, or only the resource information of the resource with the greatest first similarity can be pushed to the first user. By setting a model to capture the correlation between the user and the user set of resources, the resource with the greatest correlation is pushed to the user, ensuring the accuracy of the pushed resources.

[0081] refer to Figure 4 In one embodiment, the method further comprises:

[0082] S401, when adding a second resource to a set resource list, determining a second similarity between resource information of the second resource and resource information of each resource in the set resource list; each resource in the set resource list corresponds to one second feature of the at least two second features.

[0083] If a new resource is developed, it is necessary to add the new resource to the set resource list, and the new resource has no users interacting with it. Here, the second resource is the new resource that is accurately added to the set resource list.

[0084] Determine the second similarity between the resource information of the second resource and the resource information of each resource in the set resource list, where the second similarity is the similarity between the resource information. The resource information includes the gender of the user to which the resource is directed, the commodity attributes of the resource, etc. For example, if one resource is a preferential resource about a sanitary napkin brand, and the sanitary napkin is targeted at female users, and if the other resource is a preferential resource about a razor, and the razor is targeted at male users, then the second similarity of the resource information of the two resources will be very low.

[0085] S402: Determine the second feature corresponding to the resource in the set resource list with the second greatest similarity to the resource information of the second resource as the second feature corresponding to the second resource.

[0086] Determine the second similarity between the resource information of the second resource and the resource information of each resource in the set resource list, and use the second feature corresponding to the resource in the set resource list with the greatest second similarity to the resource information of the second resource as the second feature corresponding to the second resource. That is, use the user set corresponding to the resource with the greatest second similarity as the user set of the second resource.

[0087] The embodiment of the present invention determines the first feature corresponding to the first user, inputs the first feature and at least two second features into a setting model, obtains the first similarity between the first feature and each of the at least two second features, and determines the resource information of the first resource pushed to the first user based on the first similarity. The first feature represents the user information of the corresponding user, and the second feature represents the user set of the second user who interacts with the corresponding resource. The embodiment of the present invention obtains the cross-relationship between the first user and the resource by setting a model, and can more accurately obtain the similarity between the first user and the user set of the resource, so that the resource information pushed to the user is more accurate.

[0088] refer to Figure 5 , Figure 5 It is a schematic diagram of a resource information push process provided by an application embodiment of the present invention. The resources in the effective resource list are generated according to the real-time resource data of the delivery side, and the user set of the resources in the effective resource list is generated according to the real-time click data of the user on the resources in the effective resource list. Here, the user set of the resources in the effective resource list can be updated every 10 minutes according to the real-time click data. The first feature of the user is determined according to the user information, and the second feature of the user set of each resource in the effective resource list is determined according to the first feature of each user in the user set.

[0089] When preparing to push resources to users, the similarity between the first feature of the user and the second feature of the resource is calculated by setting the model, and the resources corresponding to the second feature whose similarity is greater than the set value are pushed to the user. In the figure, the top resources are pushed to the user, and the top resources are resources whose similarity is greater than the set value.

[0090] The application embodiment of the present invention determines the user set of the resource by the real-time resource clicking user, which not only ensures the real-time characteristics of the resource, but also improves the efficiency of determining the user set. By setting a model to obtain the cross-relationship between the user and the resource, the similarity between the user and the user set of the resource can be obtained more accurately, making the resource information pushed to the user more accurate.

[0091] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0092] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0093] It should be noted that the technical solutions described in the embodiments of the present invention can be arbitrarily combined without conflict.

[0094] In addition, in the embodiments of the present invention, "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0095] refer to Figure 6 , Figure 6 is a schematic diagram of a resource information determination device provided by an embodiment of the present invention, such as Figure 6 As shown, the device includes: a first determination module, a first input module and a second determination module.

[0096] A first determining module is used to determine a first feature corresponding to a first user; the first feature represents user information of the corresponding user;

[0097] A first input module, configured to input the first feature and at least two second features into a setting model to obtain a first similarity between the first feature and each of the at least two second features; the second feature represents a user set of second users interacting with the corresponding resource;

[0098] The second determining module is used to determine resource information of a first resource pushed to the first user based on the determined first similarity.

[0099] In one embodiment, when determining the first feature corresponding to the first user, the first determination module is used to:

[0100] The first information and / or the second information of the first user are vectorized to obtain the first feature; the first information represents the attribute information of the first user; and the second information represents the resource interaction information of the first user.

[0101] The device also includes:

[0102] A third determining module, configured to determine a first feature of each second user in a user set of second users interacting with the corresponding resource;

[0103] Based on the determined first characteristic of the second user, a second characteristic of a user set of the second users participating in the corresponding resource is determined.

[0104] The device also includes:

[0105] a fourth determination module, configured to determine, when adding a second resource to a set resource list, a second similarity between resource information of the second resource and resource information of each resource in the set resource list; each resource in the set resource list corresponds to one of the at least two second features;

[0106] The second feature corresponding to the resource in the set resource list with the second similarity to the resource information of the second resource being the greatest is determined as the second feature corresponding to the second resource.

[0107] In one embodiment, when determining the resource information of the first resource to be pushed to the first user based on the determined first similarity, the second determination module is configured to:

[0108] The resource information of the resource corresponding to the second feature of the at least two second features whose first similarity with the first feature is greater than a set value is determined as the resource information of the first resource pushed to the first user.

[0109] The device also includes:

[0110] The fifth determining module is used to determine the user set of the second user corresponding to each resource according to the access time of the resource page of the corresponding resource accessed by the second user.

[0111] refer to Figure 7 , Figure 7 is a schematic diagram of a model training device provided by an embodiment of the present invention, such as Figure 7 As shown, the device includes: splicing, a second input module and an adjustment module.

[0112] a splicing module, configured to splice a first feature corresponding to a third user, a second feature of a user set corresponding to a third resource, and a label of the third user to obtain first training data; the label indicates whether the third user has accessed a resource page of the third resource;

[0113] A second input module is used to input the first training data into the set model to obtain a probability value output by the set model; the probability value represents the similarity between the first feature of the third user and the second feature of the user set of the third resource;

[0114] An adjustment module is used to adjust the model parameters of the set model based on the probability value.

[0115] In actual application, the first determination module, the first input module and the second determination module can be implemented by a processor in an electronic device, such as a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU) or a programmable gate array (FPGA).

[0116] It should be noted that: the resource information determination device provided in the above embodiment only uses the division of the above modules as an example when determining resource information. In actual applications, the above processing can be assigned to different modules as needed, that is, the internal structure of the device is divided into different modules to complete all or part of the processing described above. In addition, the resource information determination device provided in the above embodiment and the resource information determination method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0117] Based on the hardware implementation of the above program modules and in order to implement the method of the embodiment of the present application, the embodiment of the present application also provides an electronic device. Figure 8 Schematic diagram of the hardware structure of the electronic device of the present application embodiment. Figure 8 As shown, the electronic equipment includes:

[0118] Communication interface, which can exchange information with other devices such as network equipment;

[0119] The processor is connected to the communication interface to realize information exchange with other devices, and is used to execute the method provided by one or more technical solutions of the electronic device side when running the computer program. The computer program is stored in the memory.

[0120] Of course, in actual applications, the various components in the electronic device are coupled together through the bus system. It is understandable that the bus system is used to achieve connection and communication between these components. In addition to the data bus, the bus system also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 8 In the specification, various buses are labeled as bus systems.

[0121] The memory in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer program used to operate on the electronic device.

[0122] It can be understood that the memory can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), direct memory bus random access memory (DRRAM). The memory described in the embodiments of the present application is intended to include but is not limited to these and any other suitable types of memory.

[0123] The method disclosed in the above embodiment of the present application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the program in the memory and completes the steps of the above method in combination with its hardware.

[0124] Optionally, when the processor executes the program, the corresponding processes implemented by the electronic device in each method of the embodiments of the present application are implemented, which will not be described in detail here for the sake of brevity.

[0125] In an exemplary embodiment, the present application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, including a first memory storing a computer program, and the computer program can be executed by a processor of an electronic device to complete the steps of the aforementioned method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0126] In the several embodiments provided in the present application, it should be understood that the disclosed devices, electronic devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0127] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0128] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0129] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0130] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0131] It should be noted that the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0132] In addition, in the examples of the present application, "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0133] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining resource information, characterized in that: The method comprises: Determine a first feature corresponding to a first user; the first feature represents user information of the corresponding user; the user information includes attribute information of the first user and / or resource interaction information of the first user; Inputting the first feature and at least two second features into a setting model, obtaining a first similarity between the first feature and each of the at least two second features; wherein the second feature represents a user set of second users interacting with the corresponding resource; the second feature is determined based on user information of each second user in the user set corresponding to the resource, and / or, when the second resource is added to a setting resource list, the second feature is determined based on a second similarity between resource information of the resource in the setting resource list and resource information of the second resource; Resource information of a first resource pushed to the first user is determined based on the determined first similarity.

2. The method according to claim 1, characterized in that The determining a first feature corresponding to the first user includes: The first information and / or the second information of the first user are vectorized to obtain the first feature; the first information represents the attribute information of the first user; and the second information represents the resource interaction information of the first user.

3. The method according to claim 1, characterized in that The method further comprises: determining a first characteristic of each second user in a set of users of second users that interacted with the corresponding resource; Based on the determined first characteristic of the second user, a second characteristic of a user set of the second users participating in the corresponding resource is determined.

4. The method according to claim 1, characterized in that: The method further comprises: In the case of adding the second resource to the set resource list, determining a second similarity between the resource information of the second resource and the resource information of each resource in the set resource list; each resource in the set resource list corresponds to one of the at least two second features; The second feature corresponding to the resource in the set resource list with the second similarity to the resource information of the second resource being the greatest is determined as the second feature corresponding to the second resource.

5. The method according to claim 1, characterized in that The determining, based on the determined first similarity, resource information of the first resource to be pushed to the first user includes: The resource information of the resource corresponding to the second feature of the at least two second features whose first similarity with the first feature is greater than a set value is determined as the resource information of the first resource pushed to the first user.

6. The method according to claim 1, characterized in that The method further comprises: A user set of the second user corresponding to each resource is determined according to the access time of the resource page of the corresponding resource accessed by the second user.

7. A model training method for training the setting model as claimed in claim 1, characterized in that: The method comprises: The first feature corresponding to the third user, the second feature of the user set corresponding to the third resource, and the label of the third user are concatenated to obtain the first training data; the label represents whether the third user visits the resource page of the third resource; wherein the first feature represents the user information of the corresponding user, and the user information includes the attribute information of the third user and / or the resource interaction information of the third user; the second feature represents the user set of users who interact with the third resource; the second feature is determined according to the user information of each user in the user set corresponding to the resource, and / or, when the second resource is added to the set resource list, the second feature is determined according to the second similarity between the resource information of the resource in the set resource list and the resource information of the second resource; Inputting the first training data into the set model to obtain a probability value output by the set model; the probability value represents the similarity between the first feature of the third user and the second feature of the user set of the third resource; A model parameter of the set model is adjusted based on the probability value.

8. A resource information determination device, characterized in that: include: A first determining module is used to determine a first feature corresponding to a first user; the first feature represents user information of the corresponding user; The user information includes attribute information of the first user and / or resource interaction information of the first user; A first input module, used for inputting the first feature and at least two second features into a setting model, and obtaining a first similarity between the first feature and each of the at least two second features; wherein the second feature represents a user set of second users interacting with the corresponding resource; the second feature is determined based on user information of each second user in the user set corresponding to the resource, and / or, in the case of adding the second resource to a setting resource list, the second feature is determined based on a second similarity between resource information of the resource in the setting resource list and resource information of the second resource; The second determining module is used to determine resource information of a first resource pushed to the first user based on the determined first similarity.

9. A model training device, characterized in that: include: A splicing module, used for splicing a first feature corresponding to a third user, a second feature of a user set corresponding to a third resource, and a label of the third user to obtain first training data; the label represents whether the third user visits a resource page of the third resource; wherein the first feature represents user information of the corresponding user, and the user information includes attribute information of the third user and / or resource interaction information of the third user; the second feature represents a user set of users who interact with the third resource; the second feature is determined based on user information of each user in the user set corresponding to the resource, and / or, in the case of adding the second resource to a set resource list, the second feature is determined based on a second similarity between resource information of the resource in the set resource list and resource information of the second resource; A second input module is used to input the first training data into a set model to obtain a probability value output by the set model; the probability value represents the similarity between the first feature of the third user and the second feature of the user set of the third resource; An adjustment module is used to adjust the model parameters of the set model based on the probability value.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the resource information determination method according to any one of claims 1 to 6 or the model training method according to claim 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes the resource information determination method according to any one of claims 1 to 6 or the model training method according to claim 7.

Images