Account identification method, device, electronic device and storage medium

Abstract

The present disclosure is about an account identification method, device, electronic device and storage medium, and relates to the field of computer application technology, so as to at least solve the problem that the social platform in the related technology cannot identify the user of the target type of work. The method includes: obtaining the first interactive operation information of the account to be detected in the first historical time period and the social relationship information of the account to be detected, the first interactive operation information includes the first interactive operation, and the number of times of the first interactive operation, the first interactive operation is the operation performed by the device that logs into the account to be detected on the preset type of resource; according to the obtained first interactive operation information and social relationship information, determine the attention of the account to be detected to the preset type of resource; if the attention of the account to be detected to the preset type of resource is greater than the average attention, determine that the account to be detected is a recommended candidate account for the preset type of resource.

Description

Technical Field

[0001] The present disclosure relates to the field of computer application technology, and in particular to an account identification method, device, electronic device and storage medium. Background Art

[0002] People you may know (PYMK) works are an important part of social platforms. Through PYMK works, users can learn about their friends' dynamics. Therefore, by pushing PYMK works to users, the user experience can be improved.

[0003] In the related art, social platforms usually push PYMK works by sorting all PYMK works and pushing them to users in a certain proportion. However, since different users have different needs on social platforms, for example, some users have a demand for PYMK works, while others may have a demand for multi-channel network (MCN) works, how to identify users who have a demand for target type of works is an important challenge facing social platforms. Summary of the invention

[0004] The present disclosure provides an account identification method, device, electronic device and storage medium to at least solve the problem in the related art that the social platform cannot identify the users of the target type of works.

[0005] The technical solution of the present disclosure is as follows:

[0006] According to a first aspect of an embodiment of the present disclosure, there is provided an account identification method, comprising: obtaining first interactive operation information of an account to be detected within a first historical time period and social relationship information of the account to be detected, the first interactive operation information comprising a first interactive operation and the number of times of the first interactive operation, the first interactive operation being an operation performed on a preset type of resource by a device that logs in to the account to be detected; determining the degree of attention of the account to be detected to the preset type of resource based on the obtained first interactive operation information and social relationship information; if the degree of attention of the account to be detected to the preset type of resource is greater than the average degree of attention, determining that the account to be detected is a recommended candidate account for the preset type of resource.

[0007] Optionally, the above method also includes: obtaining second interactive operation information of the account on preset type resources within a second historical time period; the second interactive operation information includes a second interactive operation, the second interactive operation is an operation performed by a device of the logged-in account on the preset type resources, and the number of second interactive operations; determining the account's attention to the preset type resources based on the second interactive operation information; determining the average attention based on the account's attention to the preset type resources.

[0008] Optionally, the attention of the above account to the preset type of resources satisfies the following formula:

[0009] Wherein, Pr is the account's attention to the preset type of resources, a is the ratio of the number of the second interactive operation in the second interactive operation information to the number of the target interactive operation, and b i is the ratio of the number of the ith interactive operation in the second interactive operation information to the number of the second interactive operation; k1 is the weight of a, k i For b i , m is the number of interactive operations in the second interactive operation information, and i is a positive number.

[0010] Optionally, the target interactive operation is that a preset type of resource is pushed to an account, and the second interactive operation includes the account obtaining a preset type of resource, the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource; the i-th interactive operation is any one of the following: the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource.

[0011] Optionally, the above formula satisfies the following condition: E1(X1):E2(X2)=1:1.

[0012] Among them, X1=k1*a, And each b i The corresponding weight k i Equal; E1 is the mean of the first parameter X1 corresponding to the account, and E2 is the mean of the second parameter X2 corresponding to the account.

[0013] Optionally, the above method further includes: pushing preset type resources to the recommended candidate accounts.

[0014] Optionally, the first interactive operation information includes at least one of the number of times the account to be detected obtains resources of a preset type, the number of times the account to be detected is pushed resources of a preset type, the number of times the account to be detected likes resources of a preset type, and the number of times the account to be detected plays resources of a preset type; the social relationship information includes at least one of the number of first accounts followed by the account to be detected, the number of first accounts not followed by the account to be detected, the degree of association between the account to be detected and the second account, and the degree of association between the account to be detected and the third account; the first account is the account corresponding to the resource of the preset type, the second account is the first account followed by the account to be detected, and the third account is the first account not followed by the account to be detected.

[0015] According to a second aspect of an embodiment of the present disclosure, an account identification device is provided, comprising: an acquisition module, used to acquire first interactive operation information of an account to be detected on a preset type of resource and social relationship information of the account to be detected within a first historical time period, the first interactive operation information comprising a first interactive operation and the number of times the first interactive operation is performed on the preset type of resource by a device that logs in to the account to be detected; a model calculation module, used to determine the attention of the account to be detected on the preset type of resource based on the first interactive operation information and social relationship information acquired by the acquisition module; and an account determination module, used to determine that the account to be detected is a recommended candidate account for the preset type of resource when the attention of the account to be detected determined by the model calculation module on the preset type of resource is greater than the average attention determined by the calculation module.

[0016] Optionally, the above device also includes a computing module.

[0017] The acquisition module is also used to obtain the second interactive operation information of the account on the preset type of resources within the second historical time period; the second interactive operation information includes the second interactive operation, the second interactive operation is the operation performed by the device of the logged-in account on the preset type of resources, and the number of second interactive operations; the calculation module is used to determine the attention of each account to the preset type of resources based on the second interactive operation information obtained by the acquisition module; the calculation module is also used to determine the average attention based on the account's attention to the preset type of resources.

[0018] Optionally, the attention of the above account to the preset type of resources satisfies the following formula:

[0019] Wherein, Pr is the account's attention to the preset type of resources, a is the ratio of the number of the second interactive operation in the second interactive operation information to the number of the target interactive operation, and b i is the ratio of the number of the ith interactive operation in the second interactive operation information to the number of the second interactive operation; k1 is the weight of a, k i For b i , m is the number of interactive operations in the second interactive operation information, and i is a positive number.

[0020] Optionally, the target interactive operation is that a preset type of resource is pushed to an account, and the second interactive operation includes the account obtaining a preset type of resource, the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource; the i-th interactive operation is any one of the following: the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource.

[0021] Optionally, the above formula satisfies the following condition: E1(X1):E2(X2)=1:1.

[0022] Among them, X1=k1*a, And each b i The corresponding weight k i Equal; E1 is the mean of the first parameter X1 corresponding to the account, and E2 is the mean of the second parameter X2 corresponding to the account.

[0023] Optionally, the above device also includes a resource pushing module.

[0024] The resource push module is used to push preset type resources to the recommendation candidate accounts.

[0025] Optionally, the first interactive operation information includes at least one of the number of times the account to be detected obtains resources of a preset type, the number of times the account to be detected is pushed resources of a preset type, the number of times the account to be detected likes resources of a preset type, and the number of times the account to be detected plays resources of a preset type; the social relationship information includes at least one of the number of first accounts followed by the account to be detected, the number of first accounts not followed by the account to be detected, the degree of association between the account to be detected and the second account, and the degree of association between the account to be detected and the third account; the first account is the account corresponding to the resource of the preset type, the second account is the first account followed by the account to be detected, and the third account is the first account not followed by the account to be detected.

[0026] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the account identification method provided in the first aspect.

[0027] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, the computer-readable storage medium comprising instructions; when the instructions are executed by a processor of an electronic device, the electronic device executes the account identification method provided in the first aspect.

[0028] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided. The computer program product includes instructions. When the instructions are executed on a processor of an electronic device, the electronic device executes the account identification method provided in the first aspect.

[0029] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: in the present disclosure, the interactive operation information of the account on the preset type of resources can be the historical consumption information of the account on the preset type of resources, such as the preset type of resources can be PYMK videos, and all accounts can be divided into accounts that have a demand for PYMK videos and accounts that have a demand for MCN videos; further, in the present disclosure, the average attention of all accounts to the preset type of resources is used as an evaluation indicator of whether there is a demand for the preset type of resources; the electronic device can determine the attention of the account to be detected to the preset type of resources through the interactive operation information of the account to be detected on the preset type of resources, and its social relationship information; when the attention of the account to be detected to the preset type of resources is greater than the average attention, the account to be detected is determined as a recommended candidate account with a demand for the preset type of resources. According to the relevant interactive operation information and social relationship information of the account to be detected, combined with the average attention, the present disclosure can automatically identify accounts with a demand for preset type resources, realize accurate push of various types of resources, and improve user experience.

[0030] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0032] Figure 1 It is a schematic diagram of the architecture of an implementation environment according to an exemplary embodiment.

[0033] Figure 2 This is one of the flowchart diagrams of an account identification method according to an exemplary embodiment.

[0034] Figure 3 This is a second flowchart of an account identification method according to an exemplary embodiment.

[0035] Figure 4 This is a third flowchart of an account identification method according to an exemplary embodiment.

[0036] Figure 5 This is a fourth flowchart of an account identification method according to an exemplary embodiment.

[0037] Figure 6 The figure is a schematic diagram showing the structure of an account identification device according to an exemplary embodiment.

[0038] Figure 7The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0039] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0041] As described in the background technology, the video works in the social platform include not only PYMK videos, but also MCN videos. Although MCN videos are more beautifully produced than PYMK videos, not all users like MCN videos, and some users prefer PYMK videos. At present, the social platform pushes PYMK videos, usually according to a certain ratio from all PYMK videos to accounts. Since not all users like PYMK videos, when pushing PYMK videos to all accounts in the above manner, it may cause the video push to be not accurate enough, and the video pushed to the account is not the video it likes, resulting in a poor user experience. Here, PYMK videos refer to videos posted by people who may know the corresponding account. The people who may know can be determined through the user's address book, or they can refer to people who know people in the address book.

[0042] It should be noted that in the technical solution of the present invention, the acquisition, storage and application of interactive operation information and social relationship information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0043] Based on the above problems, an embodiment of the present disclosure provides an account identification method, and the electronic device can determine the attention of the account to be detected to the preset type of resources (such as PYMK video) based on the first interactive operation information of the account to be detected to the preset type of resources (such as PYMK video) and the social relationship information of the account to be detected; and in the present disclosure, the average value of the attention of all accounts to the preset type of resources is used as an evaluation indicator of whether the account to be detected has a demand for the preset type of resources, and then based on the comparison result of the attention of the account to be detected and the average attention, it is determined whether the account to be detected has a demand for the preset type of resources, so that the electronic device can accurately push the required preset type of resources to the account to be detected, thereby improving the user experience.

[0044] Figure 1 is an architecture diagram of an implementation environment according to an exemplary embodiment. Figure 1 As shown, the following account identification method can be applied in the implementation environment. The implementation environment includes a terminal 01 and an electronic device 02. The terminal 01 establishes a communication connection with the electronic device 02 through an application installed on the terminal 01.

[0045] In an practicable manner, the electronic device 02 may be a server, a server cluster consisting of multiple servers, or a cloud computing service center. The electronic device 02 may include a processor, a memory, a network interface, and the like.

[0046] In an operative manner, the terminal 01 is used to provide voice and / or data connectivity services to the user. The terminal 01 may have different names, such as UE, end, terminal unit, terminal station, mobile station, mobile station, remote station, remote terminal, mobile device, wireless communication device, vehicle user equipment, terminal agent or terminal device, etc.

[0047] Optionally, the terminal 01 may be any handheld device, vehicle-mounted device, wearable device, or computer with communication functions, which is not limited in the embodiments of the present disclosure. For example, the handheld device may be a smart phone. The vehicle-mounted device may be a vehicle-mounted navigation system. The wearable device may be a smart bracelet. The computer may be a personal digital assistant (PDA), a tablet computer, or a laptop computer.

[0048] Those skilled in the art should understand that the above terminals are only examples, and other existing or future terminals, if applicable to the present disclosure, should also be included in the protection scope of the present disclosure and are included here by reference.

[0049] Based on the above implementation environment, the specific implementation process of the account identification method provided by the embodiment of the present disclosure is as follows:

[0050] The following is an illustrative description of the account identification method provided by the embodiment of the present disclosure in conjunction with the accompanying drawings.

[0051] Figure 2 is a flowchart of an account identification method according to an exemplary embodiment. Figure 2 As shown, the account identification method is applied to an electronic device, and the method includes the following S11 to S13.

[0052] S11. The electronic device obtains first interactive operation information of the account to be detected and social relationship information of the account to be detected within a first historical time period.

[0053] The first interactive operation information includes the first interactive operation and the number of the first interactive operation. The first interactive operation is an operation performed on a preset type of resource by a device that logs in to the account to be detected.

[0054] As a possible implementation method, the resources in the embodiments of the present disclosure may be videos, audios, articles, etc., and the embodiments of the present disclosure do not specifically limit this. For ease of description, the following mainly uses the resource as a video as an example for explanation. For example, the preset type resource may be a PYMK video, an MCN video, or other types of videos, and the embodiments of the present disclosure do not specifically limit this. For ease of understanding, the preset type resources in the present disclosure are explained using PYMK videos as an example.

[0055] The first interactive operation information includes at least one of the number of times the account to be detected obtains resources of a preset type, the number of times the account to be detected is pushed resources of a preset type, the number of times the account to be detected likes resources of a preset type, and the number of times the account to be detected plays resources of a preset type. The first interactive operation includes at least one of obtaining resources of a preset type, being pushed resources of a preset type, liking resources of a preset type, and playing resources of a preset type.

[0056] Exemplarily, obtaining a preset type resource here refers to clicking on a video corresponding to a preset type resource, having a preset type resource pushed refers to the server pushing a preset type resource to the account to be detected, and playing a preset type resource refers to the time for the account to be detected to play the preset type resource is greater than a first threshold, and the first threshold can be determined by a technician in this field.

[0057] The above social relationship information includes at least one of the number of first accounts followed by the account to be detected, the number of first accounts not followed by the account to be detected, the association degree between the account to be detected and the second account, and the association degree between the account to be detected and the third account; the first account is an account corresponding to a preset type of resource, the second account is the first account followed by the account to be detected, and the third account is the first account not followed by the account to be detected. For example, if the preset type of resource is a PYMK video, the first account can be the PYMK account of the account to be detected.

[0058] In some embodiments, the association between two accounts is determined based on the intersection of friends between the two accounts, for example, based on the number of common friends between the two accounts.

[0059] In one embodiment, the degree of association between the account to be detected and the second account can be determined by the number of common friends between the account to be detected and the second account. For example, the second account includes a second account 1 and a second account 2, the account to be detected has 2 common friends with the second account 1, and 5 common friends with the second account 2, then the degree of association between the account to be detected and the second account can be 7.

[0060] For example, if the number of first accounts corresponding to the account to be detected is 100 and the number of second accounts is 20, the number of third accounts may be 80. If the number of common friends between the account to be detected and the first account is 7, and the number of common friends between the account to be detected and the third account is 5, the association degree between the account to be detected and the second account may be 7, and the association degree between the account to be detected and the third account may be 5.

[0061] Furthermore, the above-mentioned first interactive operation information may also include the number of times the account to be detected pays attention to preset type resources, the number of times the account to be detected comments on preset type resources, the number of times the account to be detected reports preset type resources, the duration of the preset type resources played by the account to be detected, the number of times the account to be detected plays preset type resources, the ratio of the number of times the account to be detected obtains preset type resources to the number of times the account to be detected pushes preset type resources, the ratio of the number of times the account to be detected likes preset type resources to the number of times the account to be detected obtains preset type resources, the ratio of the number of times the account to be detected plays preset type resources to the number of times the account to be detected obtains preset type resources, the ratio of the number of times the account to be detected pays attention to preset type resources to the number of times the account to be detected obtains preset type resources, the ratio of the number of times the account to be detected shares preset type resources to the number of times the account to be detected obtains preset type resources, the ratio of the number of times the account to be detected comments on preset type resources to the number of times the account to be detected obtains preset type resources, etc.

[0062] The above social relationship information may also include the proportion of the third account in the first account, and the proportion of the second account in the first account.

[0063] It should be noted that the above description of the first interactive operation information and the social relationship information is only exemplary, and those skilled in the art can set them as needed.

[0064] Since the first interactive operation information and the social relationship information are both historical interactive information of the account to be detected with the first account, the present disclosure determines the attention of the account to be detected to the preset type of resources based on the first interactive operation information and the social relationship information of the account to be detected, which can make the attention prediction more accurate.

[0065] S12: The electronic device determines the attention of the account to be detected to a preset type of resource according to the acquired first interactive operation information and social relationship information.

[0066] As a possible implementation, the attention of the account to be detected to the preset type of resource can be determined through a machine learning model, for example, the attention is determined through a trained attention recognition model, the input of which can be the first interactive operation information and the social relationship information, and the output is the attention. In a possible implementation, the attention recognition model here can be a trained extreme gradient boosting (eXtreme gradient boosting, XGBoost) model.

[0067] The above-mentioned first interactive operation information and social relationship information can be used as input features of the attention recognition model. Since the machine learning model can establish a connection between input features and output features, and the attention recognition model in the present disclosure establishes a connection between input features (first interactive operation information and social relationship information) and output features (attention), therefore, the attention recognition model in this step can determine the attention of the account to be detected to the preset type of resources based on the first interactive operation information and social relationship information of the account to be detected.

[0068] In another possible implementation, the attention output by the attention recognition model may be a predicted value of [0, 1]. The larger the predicted value is, the higher the demand of the corresponding account to be detected for the preset type of resources is.

[0069] S13: If the attention degree of the account to be detected to the preset type of resource is greater than the average attention degree, the electronic device determines that the account to be detected is a recommended candidate account for the preset type of resource.

[0070] As a possible implementation, since the average attention of all accounts to preset type resources is used as an evaluation indicator of whether an account needs preset type resources in the present disclosure, when the attention of the account to be detected to the preset type resources determined in the above step S12 is greater than the average attention, it can be determined that the account to be detected is a recommended candidate account for the preset type resources. The recommended candidate account refers to an account that needs preset type resources. For example, when the preset type resource is PYMK video, the above recommended candidate account refers to the account that needs PYMK video.

[0071] In one possible implementation, the present disclosure may use the above-mentioned average attention as a parameter of an attention recognition model. When the attention is greater than the average attention, the attention recognition model may output label 1, indicating that the account to be detected requires a preset type of resource; when the attention is less than or equal to the average attention, the attention recognition model may output label 0, indicating that the account to be detected has no demand for the preset type of resource.

[0072] The technical solution provided by the above embodiments has at least the following beneficial effects: the present disclosure determines the attention of the account to be detected to the preset type of resources based on the historical consumption information of the account to be detected for the preset type of resources, and the social relationship information with the first account, and then compares the attention of the account to be detected to the preset type of resources with the average attention of all accounts to the preset type of resources, so as to determine whether the account to be detected is a recommended candidate account that requires the preset type of resources, automatically identify accounts that have a demand for the preset type of resources, realize accurate push of each type of resources, and improve user experience.

[0073] In one practicable manner, combining Figure 2 ,like Figure 3 As shown, S10 is also included.

[0074] S10. The electronic device determines an average degree of attention of the account to a preset type of resource in a second historical time period.

[0075] As a possible implementation method, the social platform includes multiple users, and these users can log in to the social platform through their respective accounts. The virtual resources in the social platform may include PYMK videos and MCN videos. Since different users may have different preferences for virtual resources, some users prefer PYMK videos, while other users prefer MCN videos. Therefore, the accounts corresponding to these users have different requirements for obtaining PYMK videos or MCN videos. Since there are enough accounts in the social platform, and these accounts have different requirements for PYMK videos and MCN videos, the attention paid to PYMK videos and MCN videos is also different. Therefore, when determining the demand of these accounts for PYMK videos or MCN videos, the average attention paid by these accounts to preset type resources (PYMK ​​videos or MCN videos) can be used as an evaluation indicator to determine whether the account needs preset type resources. If the account's attention to preset type resources is greater than the average attention, it can be determined that the account has a demand for preset type resources.

[0076] For example, if the social platform includes n accounts, the average attention of these accounts to the preset type of resources may be:

[0077]

[0078] in, is the average attention of the account to the preset type of resources, Z1 is the attention of account 1 to the preset type of resources, Z2 is the attention of account 2 to the preset type of resources, Z3 is the attention of account 3 to the preset type of resources, ..., Z n The degree of attention that account n pays to resources of the preset type.

[0079] It should be noted that the first historical time period may be 30 days before the current moment, and the second historical time period may be 7 days before the current moment, and those skilled in the art may set it as needed. In a possible implementation, the first historical time period here may be the same as or different from the second historical time period described above.

[0080] In one practicable manner, combining Figure 3 ,like Figure 4 As shown, the above S10 can be specifically implemented through the following S101-S103.

[0081] S101. The electronic device obtains second interactive operation information of an account on a preset type of resource within a second historical time period.

[0082] The second interactive operation information includes the second interactive operation, which is an operation performed by the device of the logged-in account on the preset type of resource, and the number of the second interactive operation.

[0083] As a possible implementation, the second interactive operation information here may specifically include the number of times each account obtains preset type resources, the number of times each account is pushed preset type resources, the number of times each account likes preset type resources, the number of times each account plays preset type resources, and the number of times each account follows preset type resources. Following preset type resources here means that when an account is watching a preset type resource, it follows the account corresponding to the preset type resource.

[0084] In another possible implementation manner, the first interactive operation information mentioned above may be the same as the second interactive operation information here, and the second interactive operation information here may also be different from the first interactive operation information mentioned above.

[0085] It should be noted that when the second interactive operation information is different from the first interactive operation information, the following formula for determining the degree of attention also needs to be changed, and those skilled in the art can make corresponding adjustments.

[0086] S102: The electronic device determines the account's attention to a preset type of resource according to the second interactive operation information.

[0087] As a possible implementation method, the account's attention to the preset type of resources satisfies the following formula:

[0088]

[0089] Wherein, Pr is the account's attention to the preset type of resources, a is the ratio of the number of the second interactive operation in the second interactive operation information to the number of the target interactive operation, and b i is the ratio of the number of the ith interactive operation in the second interactive operation information to the number of the second interactive operation; k1 is the weight of a, k i For b i , m is the number of interactive operations in the second interactive operation information, and i is a positive number.

[0090] In one possible implementation method, the target interactive operation is that a preset type of resource is pushed to an account, and the second interactive operation may include the account obtaining a preset type of resource, the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource; the i-th interactive operation may be any one of the following: the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource.

[0091] For example, the interactive operations of each account on the preset type of resources may include operations such as obtaining, liking, commenting, and following the preset type of resources. According to different interactive operations in the second interactive operation information, the above formula for determining the degree of attention may be improved. For example, when the second interactive operation information includes the first interactive operation, the second interactive operation, the third interactive operation, the fourth interactive operation, and the target interactive operation, the above formula for determining the degree of attention may be:

[0092] Pr=k1*ctr+k2*ltr+k3*lvtr+k4*wtr.

[0093] When the first interactive operation is that the account obtains a preset type of resource, the second interactive operation is that the account likes the preset type of resource, the third interactive operation is the number of times the account plays the preset type of resource, the fourth interactive operation is that the account pays attention to the preset type of resource, and the target interactive operation is that the account is pushed the preset type of resource, ctr is the ratio of the number of times the account obtains the preset type of resource to the number of times the account pushes the preset type of resource, ltr is the ratio of the number of times the account likes the preset type of resource to the number of times the account obtains the preset type of resource, lvtr is the ratio of the number of times the account plays the preset type of resource to the number of times the account obtains the preset type of resource, and wtr is the ratio of the number of times the account pays attention to the preset type of resource to the number of times the account obtains the preset type of resource; k1, k2, k3 and k4 are the weights of the corresponding parameters ctr, ltr, lvtr and wtr, respectively, which can be determined by technicians in this field based on prior knowledge.

[0094] For example, if the target account is pushed preset type resources 50 times, obtains preset type resources 30 times, likes preset type resources 10 times, plays preset type resources 15 times, and follows preset type resources 4 times, then ctr=30 / 50=0.6, ltr=10 / 30=1 / 3, lvtr=15 / 30=0.5, and wtr=4 / 30=2 / 15.

[0095] If k1=0.4, k2=0.2, k3=0.2, k4=0.2, then the target account's attention to the preset type of resources is:

[0096]

[0097] The attention determination formula disclosed in the present invention provides a method for determining the attention of an account to a preset type of resource, and provides a basis for determining an evaluation index for determining whether an account requires a preset type of resource.

[0098] Since the second interactive operation information is the interactive operation information of each account for the preset type of resources, in the present disclosure, the historical consumption of the account for the preset type of resources can be determined based on the second interactive operation information of each account for the preset type of resources, and the accuracy of the prediction of the account's attention to the preset type of resources can be improved based on these historical consumption situations.

[0099] S103: The electronic device determines an average degree of attention according to the degree of attention paid by the account to resources of a preset type.

[0100] As a possible implementation, after determining the attention of all accounts on the social platform to the preset type of resources according to the above formula, the average attention of these accounts can be determined. For example, the average attention of accounts to the preset type of resources can be calculated by the formula OK, Z n is the attention of the nth account to the preset type of resource, and Pr can be the attention of each account to the preset type of resource determined according to the formula for determining the attention, so Z n That is the Pr of the corresponding account.

[0101] The technical solution provided by the above embodiment has at least the following beneficial effects: the present disclosure provides an evaluation index for whether an account requires a preset type of resource, which can achieve the need differentiation of the accounts to be detected.

[0102] In one practicable manner, the above formula for determining the degree of attention satisfies the following condition: E1(X1):E2(X2)=1:1.

[0103] Among them, X1=k1*a, And each b i The corresponding weight ki Equal; E1 is the mean of the first parameter X1 corresponding to the account, and E2 is the mean of the second parameter X2 corresponding to the account.

[0104] In a possible implementation, corresponding to ctr, ltr, lvtr and wtr in the first formula above, X1 = k1*ctr, X2 = k2*ltr+k3*lvtr+k4*wtr, k2 = k3 = k4.

[0105] In practice, the above parameter ctr is more important than the parameters ltr, lvtr and wtr, so a method for determining the weights k1, k2, k3 and k4 corresponding to the parameters ctr, ltr, lvtr and wtr may be provided here.

[0106] Since E1 is the mean of the first parameter X1 for all accounts, and E2 is the mean of the second parameter X2 for all accounts, therefore:

[0107]

[0108] E(X2)=k2*(ltr1+ltr2+…+ltr n )+k3*(lvtr1+lvtr2+…+lvtr n )+k4*(wtr1+wtr2+…+wtr n ).

[0109] Among them, ctr1, ctr2, ..., ctr n are the parameters ctr corresponding to n accounts in the social platform. Similarly, ltr1, ltr2, …, ltr in the above formula n , lvtr1, lvtr2, ...lvtr n , wtr1, wtr2, ..., wtr n They are also the parameters ltr, lvtr and wtr corresponding to n accounts in the social platform.

[0110] Since the parameters ctr, ltr, lvtr and wtr corresponding to each account can be determined by counting the interactive operation information of the corresponding account by the electronic device, the ctr1+ctr2+…+ctr in the above formula is n , ltr1+ltr2+…+ltr n ,lvtr1+lvtr2+…+lvtr n and wtr1+wtr2+…+wtr n can be determined by the electronic device; and since E1(X1):E2(X2)=1:1, and k2=k3=k4, the values ​​of k1, k2, k3 and k4 can be determined.

[0111] The technical solution provided by the above embodiment has at least the following beneficial effects: the embodiment of the present disclosure provides a special case of weights, compared with determining k based on experience i The value of , where the weight is determined based on the average value of the first parameter X1 corresponding to all accounts and the average value of the second parameter X2 corresponding to all accounts, is more suitable for the attention determination formula, making the attention determined by the formula more accurate.

[0112] In one practicable manner, combining Figure 4 ,like Figure 5 As shown, after the above step S13, S14 is also included.

[0113] S14. The electronic device pushes preset type resources to the recommendation candidate account.

[0114] As a possible implementation manner, since the recommended candidate account is an account that requires a preset type of resource, the electronic device can push the preset type of resource to the recommended candidate account.

[0115] Exemplarily, if the preset type of resource is PYMK video, the above-mentioned recommendation candidate account is an account that requires PYMK video, and the electronic device can push PYMK video to the recommendation candidate account.

[0116] In another possible implementation, when the server divides all accounts into recommended candidate accounts and non-recommended candidate accounts, and the preset type resources in the social platform include PYMK videos and MCN videos, the electronic device can push PYMK videos to the recommended candidate accounts and push MCN videos to the non-recommended candidate accounts.

[0117] The technical solution provided by the above embodiments has at least the following beneficial effects: In the embodiments of the present disclosure, by determining the recommended candidate accounts for preset type resources of the electronic device and pushing the preset type resources to the recommended candidate accounts, accurate push of resources is achieved and the user experience is improved.

[0118] In an practicable manner, the above-mentioned attention recognition model can be a trained XGBoost model, and the training set of the XGBoost model can include the first interactive operation information and social relationship information corresponding to multiple fourth accounts; since the training set is used to train the parameters of the XGBoost model, the training set also includes the attention corresponding to the fourth account, that is, the training set includes both the input features of the XGBoost model and the output features corresponding to the input features. The first interactive operation information and social relationship information corresponding to the fourth account in the training set, as well as the attention corresponding to the fourth account can be determined by a technician in this field based on expert experience.

[0119] The fourth account mentioned above is an account that has been exposed to preset type resources a number of times greater than the second threshold in the first historical time period, that is, the fourth account refers to an account that has been pushed preset type resources a number of times greater than the second threshold by the electronic device.

[0120] The training of the XGBoost model can be based on the first interactive operation information and social relationship information corresponding to the fourth account, as well as the attention corresponding to the fourth account, combined with the XGBoost algorithm to continuously adjust the model parameters, and determine the training stop condition of the XGBoost model according to the loss function, thereby completing the training of the XGBoost model, that is, determining the attention recognition model.

[0121] In one feasible manner, the attention recognition model in the present disclosure can be retrained every set number of days, and its corresponding training set also needs to be updated, that is, the first interactive operation information and social relationship information corresponding to the fourth account in the first historical time period before the current moment, and the attention corresponding to the fourth account are determined as data in the training set.

[0122] When the attention recognition model is updated, the corresponding training set can use the attention determined by the previous attention recognition model, the first interactive operation information and the social relationship information as the training set data when updating the attention recognition model. By continuously training the attention recognition model, the updated attention recognition model can more accurately determine the attention of the account to be detected.

[0123] The above only briefly describes the training process of the XGBoost model. The specific training process can refer to the conventional technical means in this field and will not be repeated here.

[0124] Figure 6 is a schematic diagram of the structure of an account identification device according to an exemplary embodiment. Figure 6 As shown, the account identification device 20 includes an acquisition module 201 , a model calculation module 202 , an account determination module 203 , a calculation module 204 and a resource push module 205 .

[0125] The acquisition module 201 is used to acquire the first interactive operation information of the account to be detected and the social relationship information of the account to be detected in the first historical time period, wherein the first interactive operation information includes the first interactive operation and the number of the first interactive operation, and the first interactive operation is an operation performed by the device that logs in to the account to be detected on a preset type of resource. For example, the acquisition module 201 can execute the above step S11.

[0126] The model calculation module 202 is used to determine the attention of the account to be detected to the preset type of resource according to the first interactive operation information and the social relationship information obtained by the acquisition module 201. For example, the model calculation module 202 can execute the above step S12.

[0127] The account determination module 203 is used to determine that the account to be detected is a recommended candidate account for the preset type of resource if the attention of the account to be detected determined by the model calculation module 202 to the preset type of resource is greater than the average attention. For example, the account determination module 203 can execute the above step S13.

[0128] Optionally, the above device also includes a calculation module 204.

[0129] The acquisition module 201 is further used to acquire the second interactive operation information of the account on the preset type of resource in the second historical time period; the second interactive operation information includes the second interactive operation, which is the operation performed by the device of the logged-in account on the preset type of resource, and the number of the second interactive operation. For example, the acquisition module 201 can execute the above step S101.

[0130] The calculation module 204 is further configured to determine the account's attention to the preset type of resource according to the second interactive operation information obtained by the obtaining module 201. For example, the calculation module 204 may execute the above step S102.

[0131] The calculation module 204 is further configured to determine the average degree of attention according to the degree of attention of the account to the preset type of resource. For example, the calculation module 204 may also execute the above step S103.

[0132] Optionally, the attention of the above account to the preset type of resources satisfies the following formula:

[0133]

[0134] Wherein, Pr is the account's attention to the preset type of resources, a is the ratio of the number of the second interactive operation in the second interactive operation information to the number of the target interactive operation, and b i is the ratio of the number of the ith interactive operation in the second interactive operation information to the number of the second interactive operation; k1 is the weight of a, k i for b i , m is the number of interactive operations in the second interactive operation information, and i is a positive number.

[0135] Optionally, the target interactive operation is that a preset type of resource is pushed to an account, and the second interactive operation includes the account obtaining a preset type of resource, the account liking a preset type of resource, the account playing a preset type of resource, and the account following a preset type of resource.

[0136] The i-th interactive operation is any one of the following: an account likes a preset type resource, an account plays a preset type resource, and an account follows a preset type resource.

[0137] Optionally, the above attention determination formula satisfies the following condition: E1(X1):E2(X2)=1:1.

[0138] Among them, X1=k1*a, And each b i The corresponding weight k i Equal; E1 is the mean of the first parameter X1 corresponding to the account, and E2 is the mean of the second parameter X2 corresponding to the account.

[0139] Optionally, the account identification device 20 further includes a resource push module 205 .

[0140] The resource push module 205 is used to push preset type resources to the recommendation candidate accounts. For example, the resource push module 205 can execute the above step S14.

[0141] Optionally, the first interactive operation information includes at least one of the number of times the account to be detected obtains resources of a preset type, the number of times the account to be detected is pushed resources of a preset type, the number of times the account to be detected likes resources of a preset type, and the number of times the account to be detected plays resources of a preset type.

[0142] The social relationship information includes at least one of the number of first accounts followed by the account to be detected, the number of first accounts not followed by the account to be detected, the association degree between the account to be detected and the second account, and the association degree between the account to be detected and the third account; the first account is an account corresponding to a preset type of resource, the second account is the first account followed by the account to be detected, and the third account is the first account not followed by the account to be detected.

[0143] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0144] Figure 7 is a schematic diagram of the structure of an electronic device 30 provided by the present disclosure. Figure 7 The electronic device 30 may include at least one processor 301 and a memory 303 for storing instructions executable by the processor 301. The processor 301 is configured to execute the instructions in the memory 303 to implement the account identification method in the above embodiment. Figure 6 The functions implemented by the acquisition module 201, the model calculation module 202, the account determination module 203, the calculation module 204 and the resource push module 205 in the account identification device are similar to those Figure 7 The function of the processor 301 in is the same.

[0145] In some embodiments, the electronic device 30 may be Figure 1 The server shown.

[0146] In addition, the electronic device 30 may further include a communication bus 302 and at least one communication interface 304 .

[0147] The processor 301 may be a GPU, a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the disclosed solution.

[0148] Communication bus 302 may include a pathway for transmitting information between the above-mentioned components.

[0149] The communication interface 304 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0150] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit via a bus. The memory may also be integrated with the processing unit and be a volatile storage medium in the GPU.

[0151] The memory 303 is used to store instructions for executing the solution of the present disclosure, and the execution is controlled by the processor 301. The processor 301 is used to execute the instructions stored in the memory 303, so as to realize the functions in the method of the present disclosure.

[0152] In a specific implementation, as an embodiment, the processor 301 may include one or more GPUs, such as Figure 7 GPU0 and GPU1 in .

[0153] In a specific implementation, as an embodiment, the electronic device 30 may include multiple processors, such as Figure 6301 and processor 307 in FIG. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-GPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0154] In a specific implementation, as an embodiment, the electronic device 30 may further include an output device 305 and an input device 306. The output device 305 communicates with the processor 301 and may display information in a variety of ways. For example, the output device 305 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 306 communicates with the processor 301 and may receive user input in a variety of ways. For example, the input device 306 may be a mouse, a keyboard, a touch screen device, or a sensor device.

[0155] Those skilled in the art will understand that Figure 7 The structure shown in the figure does not constitute a limitation on the electronic device 30, and may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0156] In addition, the present disclosure also provides a computer-readable storage medium, which includes instructions. When the instructions are executed by a processor of an electronic device, the electronic device executes the account identification method provided in the above embodiment.

[0157] In addition, the present disclosure also provides a computer program product, which includes instructions. When the instructions are executed on a processor of an electronic device, the electronic device executes the account identification method provided in the above embodiment.

[0158] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0159] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An account identification method, characterized in that: include: Acquire first interactive operation information of the account to be detected and social relationship information of the account to be detected within a first historical time period, where the first interactive operation information includes a first interactive operation and the number of times the first interactive operation is performed on a preset type of resource by a device that logs in to the account to be detected; According to the first interactive operation information and the social relationship information obtained, the attention degree of the to-be-detected account to the preset type of resource is determined; the attention degree of the account to the preset type of resource satisfies the following formula: E1(X1):E2(X2)=1:1; Wherein, Pr is the attention of the account to the preset type of resource, a is the ratio of the number of second interactive operations to the number of target interactive operations in the second interactive operation information, the second interactive operation information includes the second interactive operation, the second interactive operation is the operation performed by the device logged into the account on the preset type of resource, and the number of the second interactive operation, b i is the ratio of the number of the ith interaction operation in the second interaction operation information to the number of the second interaction operation; k1 is the weight of a, k i for b i , m is the number of interactive operations in the second interactive operation information, and i is a positive number; the target interactive operation is that the preset type resource is pushed to the account, and the second interactive operation includes that the account obtains the preset type resource, the account likes the preset type resource, the account plays the preset type resource, and the account follows the preset type resource; the i-th interactive operation is any one of the following: the account likes the preset type resource, the account plays the preset type resource, and the account follows the preset type resource; X1=k1*a, And each b i The corresponding weight k i are equal; E1 is the mean value of the first parameter X1 corresponding to the account, and E2 is the mean value of the second parameter X2 corresponding to the account; If the attention degree of the account to be detected to the preset type of resource is greater than the average attention degree, the account to be detected is determined to be a recommended candidate account for the preset type of resource.

2. The account identification method according to claim 1, characterized in that: Also includes: Acquire the second interactive operation information of the account on the preset type of resource within a second historical time period; Determining, according to the second interactive operation information, the degree of attention of the account to the preset type of resource; The average degree of attention is determined according to the degree of attention of the account to the preset type of resource.

3. The account identification method according to claim 1 or 2, characterized in that: The method further comprises: Push the preset type of resource to the recommendation candidate account.

4. The account identification method according to claim 1, characterized in that: The first interactive operation information includes at least one of the number of times the account to be detected obtains the preset type of resources, the number of times the account to be detected is pushed the preset type of resources, the number of times the account to be detected likes the preset type of resources, and the number of times the account to be detected plays the preset type of resources; The social relationship information includes at least one of the number of first accounts followed by the account to be detected, the number of first accounts not followed by the account to be detected, the association degree between the account to be detected and the second account, and the association degree between the account to be detected and the third account; the first account is an account corresponding to the preset type of resource, the second account is the first account followed by the account to be detected, and the third account is the first account not followed by the account to be detected.

5. An account identification device, characterized in that: include: an acquisition module, configured to acquire first interaction operation information of an account to be detected and social relationship information of the account to be detected within a first historical time period, wherein the first interaction operation information includes a first interaction operation and a number of times of the first interaction operation, wherein the first interaction operation is an operation performed on a resource of a preset type by a device that logs in to the account to be detected; A model calculation module is used to determine the attention of the to-be-detected account to the preset type of resource according to the first interactive operation information and the social relationship information acquired by the acquisition module; the attention of the account to the preset type of resource satisfies the following formula: E1(X1):E2(X2)=1:1; Wherein, Pr is the attention of the account to the preset type of resource, a is the ratio of the number of second interactive operations to the number of target interactive operations in the second interactive operation information, the second interactive operation information includes the second interactive operation, the second interactive operation is the operation performed by the device logged into the account on the preset type of resource, and the number of the second interactive operation, b i is the ratio of the number of the ith interaction operation in the second interaction operation information to the number of the second interaction operation; k1 is the weight of a, k i for b i , m is the number of interactive operations in the second interactive operation information, and i is a positive number; the target interactive operation is that the preset type resource is pushed to the account, and the second interactive operation includes that the account obtains the preset type resource, the account likes the preset type resource, the account plays the preset type resource, and the account follows the preset type resource; the i-th interactive operation is any one of the following: the account likes the preset type resource, the account plays the preset type resource, and the account follows the preset type resource; X1=k1*a, And each b i The corresponding weight k i are equal; E1 is the mean value of the first parameter X1 corresponding to the account, and E2 is the mean value of the second parameter X2 corresponding to the account; The account determination module is used to determine that the account to be detected is a recommended candidate account for the preset type of resource when the attention degree of the account to be detected to the preset type of resource determined by the model calculation module is greater than the average attention degree.

6. The account identification device according to claim 5, characterized in that: The device also includes a computing module; The acquisition module is further used to acquire the second interactive operation information of the account on the preset type of resource within a second historical time period; The calculation module is used to determine the attention degree of the account to the preset type of resource according to the second interactive operation information obtained by the obtaining module; The calculation module is further used to determine the average attention degree according to the attention degree of the account to the preset type of resources.

7. The account identification device according to claim 6, characterized in that: The device also includes a resource push module; The resource push module is used to push the preset type of resources to the recommendation candidate account.

8. The account identification device according to claim 5, characterized in that: The first interactive operation information includes at least one of the number of times the account to be detected obtains the preset type of resources, the number of times the account to be detected is pushed the preset type of resources, the number of times the account to be detected likes the preset type of resources, and the number of times the account to be detected plays the preset type of resources; The social relationship information includes at least one of the number of first accounts followed by the account to be detected, the number of first accounts not followed by the account to be detected, the association degree between the account to be detected and the second account, and the association degree between the account to be detected and the third account; the first account is an account corresponding to the preset type of resource, the second account is the first account followed by the account to be detected, and the third account is the first account not followed by the account to be detected.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the account identification method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes instructions; when the instructions are executed by a processor of an electronic device, the electronic device executes the account identification method as described in any one of claims 1 to 4.

11. A computer program product, characterized in that The computer program product includes instructions, and when the instructions are executed on a processor of an electronic device, the electronic device executes the account identification method according to any one of claims 1 to 4.

Images