Target category focus assessment method and system for account behavior

Abstract

The account behavior target category focus degree evaluation method and system provided in the specification, after obtaining a content set corresponding to the historical behavior of a target account in a preset time period, the content quantity of the first category content of at least one first category and the general content quantity of the general category content of at least one general category in the content set are counted, then, based on the content quantity, the focus degree of the target account on the target category in the historical behavior is determined, the target category belongs to at least one first category, then, based on the general content quantity, the focus degree correction value of the historical behavior on the target category is determined, and based on the focus degree and the focus degree correction value, the target focus degree of the target account on the target category in the historical behavior is determined; the scheme can improve the accuracy of the target category focus degree evaluation of the account behavior.

Description

Technical Field

[0001] This manual relates to the field of attention assessment, and in particular to a method and system for assessing the attention of a target category of account behavior. Background Technology

[0002] In recent years, with the rapid development of internet technology, various accounts interact with each other on content exchange platforms. To conduct refined operations on these accounts, it is often necessary to evaluate their focus on specific content categories. Focus evaluation can be understood as assessing whether an account's interactive content is focused on a particular content category. Existing focus evaluation methods often determine the target account's content vertical by the proportion of content in a primary category, and then use that content vertical as the measure of focus.

[0003] In the process of researching and practicing existing technologies, the inventors of this invention discovered that using content categories as a way of focusing often only produces the existence of focused content categories, but cannot directly evaluate the intensity of focus. Moreover, the output only shows the relationship of the target account to a single content category, and cannot measure the distribution of other content categories. In addition, when evaluating focus, it is only evaluated from the dimension of content quantity, making the evaluation dimension relatively singular. Therefore, the accuracy of the target category focus evaluation of account behavior is low.

[0004] Therefore, there is a need for a more accurate method and system for assessing the focus of account behavior on target categories. Summary of the Invention

[0005] This manual provides a more accurate method and system for assessing target category focus in account behavior.

[0006] Firstly, this specification provides a method for evaluating the target category focus of account behavior, comprising: obtaining a content set corresponding to the historical behavior of a target account within a preset time period; counting the number of content in at least one primary category and the number of content in at least one general category in the content set; determining the focus of the target account on the target category in the historical behavior based on the number of content, wherein the target category belongs to the at least one primary category; determining a focus correction value for the historical behavior on the target category based on the number of general content; and determining the target focus of the target account on the target category in the historical behavior based on the focus and the focus correction value.

[0007] In some embodiments, the target account is a content output account, and the content set corresponding to the historical behavior includes the content output by the target account; or the target account is a content interaction account, and the content set corresponding to the historical behavior includes the content interacting with the target account, wherein the content interaction includes at least one of browsing, forwarding, commenting, liking, or collecting.

[0008] In some embodiments, the method further includes: determining a time decay method corresponding to each time period based on the time distance between each time period and the current time; and obtaining a time weight corresponding to each time period based on the time decay method.

[0009] In some embodiments, the time decay method includes a first time decay method and a second time decay method, and

[0010] The step of determining the time decay method corresponding to each time period based on the time distance between each time period and the current time includes: comparing the time distance between each time period and the current time with a preset time distance threshold; based on the comparison result, selecting a first time period and a second time period in each time period, wherein the first time period includes time periods in which the time distance exceeds the preset time distance threshold, and the second time period includes time periods in which the time distance does not exceed the preset time distance threshold; and determining the time decay method of the first time period as the first time decay method, and determining the time decay method of the second time period as the second time decay method.

[0011] In some embodiments, obtaining the time weight corresponding to each time period based on the time decay method includes: determining a first time weight corresponding to the first time period based on the first time decay method; determining a second time weight corresponding to the second time period based on the second time decay method; and using the first time weight and the second time weight as the time weight corresponding to each time period.

[0012] In some embodiments, determining the first time weight corresponding to the first time period based on the first time decay method includes: obtaining a preset time decay parameter and a first preset time constant; obtaining the time ratio between the time distance corresponding to the first time period and the first preset time constant, and determining a first initial time weight based on the time ratio; and fusing the first initial time weight with the preset time decay parameter to obtain the first time weight corresponding to the first time period.

[0013] In some embodiments, determining the second time weight corresponding to the second time period based on the second time decay method includes: obtaining a preset time decay parameter and a second preset time constant; fusing the second preset time constant with the time distance corresponding to the second time period to obtain a second initial time weight; and fusing the second initial time weight with the preset time decay parameter to obtain the second time weight corresponding to the second time period.

[0014] In some embodiments, fusing the second preset time constant with the time distance corresponding to the second time period to obtain the second initial time weight includes: adjusting the time distance corresponding to the second time period to obtain the adjusted time distance; adding the adjusted time distance to the second preset time constant to obtain the target time distance; and determining the second initial time weight based on the target time distance.

[0015] In some embodiments, determining the target account's focus on the target category in the historical behavior based on the content quantity includes: calculating the current content quantity corresponding to each time period in the content quantity; weighting the current content quantity based on the time weight corresponding to each time period; and determining the target account's focus on the target category in the historical behavior based on the weighted content quantity.

[0016] In some embodiments, determining the target account's focus on the target category in the historical behavior based on the weighted content quantity includes: summing the weighted content quantity to obtain the current total content quantity; selecting the quantity corresponding to the target category from the weighted total content quantity to obtain the target category content quantity; and obtaining a first ratio between the target category content quantity and the current total content quantity, and using the first ratio as the target account's focus on the target category in the historical behavior, wherein the focus represents the proportion of the target category content quantity in the total content quantity after time decay.

[0017] In some embodiments, determining the focus correction value of the historical behavior on the target category based on the quantity of generic content includes: weighting the quantity of generic content based on the time weight corresponding to each time period; selecting the current quantity of generic content in the target category from the weighted quantity of generic content, wherein the target category includes the target category and a first-level category similar to the target category; and determining the focus correction value of the historical behavior on the target category based on the weighted quantity of generic content and the current quantity of generic content.

[0018] In some embodiments, determining the focus correction value of the historical behavior on the target category based on the weighted general content quantity and the current general content quantity includes: calculating the quantity of similar content in similar categories corresponding to the target category based on the current general content quantity to obtain a first initial general content focus value, wherein the similar category is a first-level category belonging to the same target general category as the target category; comparing the weighted general content quantity and the current general content quantity to obtain a second initial general content focus value; and fusing the first initial general content focus value and the second initial general content focus value to obtain the general content focus value corresponding to the target category, and using the general content focus value as the focus correction value of the historical behavior on the target category.

[0019] In some embodiments, calculating the number of similar content in similar categories corresponding to the target category based on the current general content quantity to obtain a first initial general content focus includes: counting the quantity corresponding to the target category in the current general content quantity to obtain the target category content quantity; calculating the difference between the current general content quantity and the target category quantity to obtain the number of similar content in similar categories corresponding to the target category; and obtaining a second ratio between the target category content quantity and the number of similar content, and using the second ratio as the first initial general content focus, wherein the first initial general content focus represents the proportion of the target category content quantity after time decay in the number of similar content in the target category.

[0020] In some embodiments, comparing the weighted general content quantity with the current general content quantity to obtain a second initial general content focus includes: summing the weighted general content quantity to obtain the current total general content quantity; and obtaining a third ratio between the current general content quantity and the current total general content quantity, and using the third ratio as the second initial general content focus, wherein the second initial general content focus represents the proportion of the target general category content quantity in the total content quantity after time decay.

[0021] In some embodiments, determining the target focus of the target account on the target category in the historical behavior based on the focus and the focus correction value includes: obtaining a weighting coefficient corresponding to the target category; weighting the focus and the focus correction value based on the weighting coefficient; and fusing the weighted focus and the weighted focus correction value to obtain the target focus of the target account on the target category in the historical behavior.

[0022] In some embodiments, fusing the weighted focus and the weighted focus correction value to obtain the target focus of the target account on the target category in the historical behavior includes: adding the weighted focus and the weighted focus correction value to obtain the corrected focus of the target account on the target category in the historical behavior; and determining the confidence level of the corrected focus based on the content quantity, and calculating the product of the confidence level and the corrected focus to obtain the target focus.

[0023] In some embodiments, determining the confidence level of the corrected focus based on the number of contents includes: counting the number of contents for candidate historical time periods in the content set to obtain the total amount of historical content; determining the confidence level information of the target account based on the total amount of historical content; and modulating the confidence level information to obtain the confidence level of the corrected focus.

[0024] In some embodiments, determining the confidence information of the target account based on the total amount of historical content includes: adjusting the total amount of historical content to obtain a target total amount of historical content; obtaining the quantity difference between the target total amount of historical content and a preset confidence constant; and determining the confidence information of the target account based on the quantity difference.

[0025] In some embodiments, the step of counting the number of primary category content of at least one primary category and the number of generic content of at least one generic category in the content set includes: classifying the content in the content set to obtain primary category content of at least one primary category; determining the generic content of the at least one generic category based on the primary category content; and counting the number of primary category content and the number of generic content of the generic category in the content set respectively.

[0026] Secondly, this specification also provides a target category focus assessment system for account behavior, comprising: at least one storage medium storing at least one instruction set for performing target category focus assessment of account behavior; and at least one processor communicatively connected to the at least one storage medium, wherein, when the target category focus assessment system for account behavior is running, the at least one processor reads the at least one instruction set and executes the target category focus assessment method for account behavior described in the first aspect of this specification according to the instructions of the at least one instruction set.

[0027] As can be seen from the above technical solutions, the target category focus assessment method and system for account behavior provided in this specification obtains the content set corresponding to the historical behavior of the target account within a preset time period. Then, it counts the number of first-level category content and the number of generic category content for at least one generic category within the content set. Based on the content quantity, it determines the target account's focus on the target category in historical behavior, where the target category belongs to at least one first-level category. Then, based on the number of generic content, it determines the focus correction value for the historical behavior on the target category. Finally, based on the focus and the focus correction value, it determines the target account's target focus on the target category in historical behavior. Because this solution can determine the target account's focus on the target category based on the counted number of first-level category content, it can assess the focus intensity of any first-level category for the target account, not just a single category. Furthermore, it can correct the focus using the focus correction value for the target category determined by the number of generic content, thus fully considering the impact of content quantity and similar categories on focus during the focus assessment process. Therefore, it can improve the accuracy of target category focus assessment for account behavior.

[0028] Other functionalities of the target category focus assessment method and system for account behavior provided in this specification will be partially listed in the following description. The figures and examples presented below will be readily apparent to those skilled in the art. The inventive aspects of the target category focus assessment method and system for account behavior provided in this specification can be fully understood through practice or use of the methods, apparatus, and combinations described in the detailed examples below. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A schematic diagram illustrating an application scenario of a target category focus assessment system for account behavior provided according to an embodiment of this specification is shown.

[0031] Figure 2 A hardware structure diagram of a computing device provided according to an embodiment of this specification is shown; and

[0032] Figure 3 A flowchart is shown of a method for assessing target category focus of account behavior according to an embodiment of this specification. Detailed Implementation

[0033] The following description provides specific application scenarios and requirements for this specification, intended to enable those skilled in the art to make and use the contents of this specification. Various partial modifications to the disclosed embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments and applications without departing from the spirit and scope of this specification. Therefore, this specification is not limited to the embodiments shown, but rather to the widest scope consistent with the claims.

[0034] The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not restrictive. For example, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” used herein may also include the plural forms. When used in this specification, the terms “comprising,” “including,” and / or “containing” mean that the associated integers, steps, operations, elements, and / or components are present, but do not exclude the presence of one or more other features, integers, steps, operations, elements, components, and / or groups, or that other features, integers, steps, operations, elements, components, and / or groups may be added to the system / method.

[0035] Considering the following description, these and other features of this specification, as well as the operation and function of the related components of the structure, and the economy of assembly and manufacture of the parts, can be significantly improved. All of these form part of this specification with reference to the accompanying drawings. However, it should be clearly understood that the drawings are for illustrative and descriptive purposes only and are not intended to limit the scope of this specification. It should also be understood that the drawings are not drawn to scale.

[0036] The flowcharts used in this specification illustrate operations implemented according to some embodiments of this specification. It should be clearly understood that the operations in the flowcharts may not be implemented in a sequential order. Instead, the operations may be implemented in reverse order or simultaneously. Furthermore, one or more additional operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

[0037] Before describing the specific embodiments in this specification, the application scenarios of this specification will be introduced as follows:

[0038] For accounts that publish content, in the content focus evaluation scenario, the evaluation of whether the target account's published content is focused can be used as a tag for account understanding. This can provide operators with refined traffic control, account rating, C-end traffic sending characteristics, and targeted account support, so that accounts are more inclined to focus on content creation in their respective fields. For example, financial accounts can focus more on creating content in the financial category, and so on.

[0039] For ease of description, the terms that will appear in the following descriptions will be explained as follows:

[0040] Account behavior: The actions an account takes on a content platform. Account behavior can be categorized in various ways, including output and interaction. Output refers to publishing content, which can be original or sourced from other content sources. Interaction refers to engaging with content published by other accounts. Content interaction can take many forms, such as browsing, forwarding, commenting, liking, or saving.

[0041] Target category focus: This can be understood as the degree of focus on a target category. Focus can be understood as the degree to which one is absorbed in a particular (or a type of) thing or activity, or as the level of concentration. Focus can also represent the degree of preference.

[0042] It should be noted that the account evaluation scenario described above is only one of the multiple use cases provided in this specification. The target category focus assessment method and system for account behavior described in this specification can be applied not only to the content posting focus assessment scenario, but also to all scenarios of target category focus assessment for account behavior, such as fan interest assessment scenarios, or fan category focus assessment scenarios, etc. Those skilled in the art should understand that the application of the target category focus assessment method and system for account behavior described in this specification to other use cases is also within the scope of protection of this specification.

[0043] Figure 1 This diagram illustrates an application scenario of an account behavior target category focus assessment system 001 provided according to an embodiment of this specification. The account behavior target category focus assessment system 001 (hereinafter referred to as System 001) can be applied to target category focus assessment of account behavior in any scenario, such as focus assessment in content posting focus assessment, focus assessment in fan interest assessment, focus assessment in fan category focus assessment, etc. Figure 1 As shown, system 001 may include target user 100, client 200, server 300 and network 400.

[0044] Target user 100 can be the user who triggers the evaluation of the target category of account behavior. Target user 100 can perform the focus evaluation operation in client 200.

[0045] Client 200 can be a device that evaluates the target category focus of account behavior in response to a focus assessment operation by target user 100. In some embodiments, the target category focus assessment method for account behavior can be executed on client 200. In this case, client 200 may store data or instructions for executing the target category focus assessment method for account behavior described herein, and may execute or be used to execute said data or instructions. In some embodiments, client 200 may include a hardware device with data processing capabilities and the necessary programs required to drive the hardware device. Figure 1 As shown, client 200 can communicate with server 300. In some embodiments, server 300 can communicate with multiple clients 200. In some embodiments, client 200 can interact with server 300 via network 400 to receive or send messages, etc. In some embodiments, client 200 may include mobile devices, tablets, laptops, built-in devices in motor vehicles, or similar content, or any combination thereof. In some embodiments, the mobile device may include smart home devices, smart mobile devices, virtual reality devices, augmented reality devices, or similar devices, or any combination thereof. In some embodiments, the smart home device may include smart TVs, desktop computers, etc., or any combination thereof. In some embodiments, the smart mobile device may include smartphones, personal digital assistants, gaming devices, navigation devices, etc., or any combination thereof. In some embodiments, the virtual reality device or augmented reality device may include virtual reality headsets, virtual reality glasses, virtual reality patches, augmented reality headsets, augmented reality glasses, augmented reality patches, or similar content, or any combination thereof. For example, the virtual reality device or the augmented reality device may include Google Glass, head-mounted displays, VR, etc. In some embodiments, the built-in device in the motor vehicle may include an in-vehicle computer, an in-vehicle TV, etc. In some embodiments, client 200 may be a device with positioning technology for locating the position of client 200.

[0046] In some embodiments, the client 200 may have one or more applications (APPs) installed. The APPs provide the target user 100 with the ability and interface to interact with the outside world via the network 400. The APPs include, but are not limited to: web browser APPs, search APPs, chat APPs, shopping APPs, video APPs, financial management APPs, instant messaging tools, email clients, social media platform software, etc. In some embodiments, the client 200 may have a target APP installed. The target APP can collect a set of content corresponding to the historical behavior of the target account within a preset time period for the client 200. In some embodiments, the target user 100 can also trigger a focus assessment request through the target APP. The target APP can respond to the focus assessment request and execute the target category focus assessment method for account behavior described in this specification. The target category focus assessment method for account behavior will be described in detail later.

[0047] Server 300 may be a server providing various services, such as a backend server supporting the content set corresponding to the historical behavior of a target account within a preset time period obtained from client 200. In some embodiments, the target category focus assessment method for account behavior can be executed on server 300. In this case, server 300 may store data or instructions for executing the target category focus assessment method for account behavior described herein, and may execute or be used to execute the data or instructions. In some embodiments, server 300 may include a hardware device with data processing capabilities and the necessary programs required to drive the hardware device. Server 300 may communicate with multiple clients 200 and receive data sent by clients 200.

[0048] Network 400 serves as a medium to provide a communication connection between client 200 and server 300. Network 400 facilitates the exchange of information or data. For example... Figure 1As shown, client 200 and server 300 can connect to network 400 and transmit information or data to each other through network 400. In some embodiments, network 400 can be any type of wired or wireless network, or a combination thereof. For example, network 400 may include cable networks, wired networks, fiber optic networks, telecommunications networks, intranets, the Internet, local area networks (LANs), wide area networks (WANs), wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth networks, ZigBee networks, near field communication (NFC) networks, or similar networks. In some embodiments, network 400 may include one or more network access points. For example, network 400 may include wired or wireless network access points, such as base stations or Internet switching points, through which one or more components of client 200 and server 300 can connect to network 400 to exchange data or information.

[0049] It should be understood that Figure 1 The number of clients 200, servers 300, and networks 400 shown is merely illustrative. Depending on implementation needs, there can be any number of clients 200, servers 300, and networks 400.

[0050] It should be noted that the target category focus assessment method for account behavior can be executed entirely on the client 200, entirely on the server 300, or partially on the client 200 and partially on the server 300.

[0051] Figure 2 A hardware structure diagram of a computing device 600 provided according to an embodiment of this specification is shown. The computing device 600 can execute the target category focus assessment method for account behavior described in this specification. The target category focus assessment method for account behavior is described in other parts of this specification. When the target category focus assessment method for account behavior is executed on a client 200, the computing device 600 can be the client 200. When the target category focus assessment method for account behavior is executed on a server 300, the computing device 600 can be the server 300. When the target category focus assessment method for account behavior can be executed partly on the client 200 and partly on the server 300, the computing device 600 can be both the client 200 and the server 300.

[0052] like Figure 2 As shown, the computing device 600 may include at least one storage medium 630 and at least one processor 620. In some embodiments, the computing device 600 may also include a communication port 650 and an internal communication bus 610. Additionally, the computing device 600 may include I / O components 660.

[0053] The internal communication bus 610 can connect different system components, including storage medium 630, processor 620 and communication port 650.

[0054] I / O component 660 supports input / output between computing device 600 and other components.

[0055] Communication port 650 is used for data communication between computing device 600 and external sources. For example, communication port 650 can be used for data communication between computing device 600 and network 400. Communication port 650 can be a wired communication port or a wireless communication port.

[0056] Storage medium 630 may include a data storage device. The data storage device may be a non-transitory storage medium or a temporary storage medium. For example, the data storage device may include one or more of a disk 632, a read-only storage medium (ROM) 634, or a random access storage medium (RAM) 636. Storage medium 630 also includes at least one set of instructions stored in the data storage device. The instructions are computer program code, which may include programs, routines, objects, components, data structures, processes, modules, etc., that execute the target category focus assessment method for account behavior provided in this specification.

[0057] At least one processor 620 can be communicatively connected to at least one storage medium 630 and a communication port 650 via an internal communication bus 610. At least one processor 620 is used to execute the at least one instruction set described above. When the computing device 600 is running, at least one processor 620 reads the at least one instruction set and, according to the instructions of the at least one instruction set, executes the target category focus assessment method for account behavior provided in this specification. Processor 620 can execute all the steps included in the target category focus assessment method for account behavior. Processor 620 can be in the form of one or more processors. In some embodiments, processor 620 may include one or more hardware processors, such as a microcontroller, microprocessor, reduced instruction set computer (RISC), application-specific integrated circuit (ASIC), application-specific instruction set processor (ASIP), central processing unit (CPU), graphics processing unit (GPU), physical processing unit (PPU), microcontroller unit, digital signal processor (DSP), field-programmable gate array (FPGA), advanced RISC machine (ARM), programmable logic device (PLD), any circuit or processor capable of performing one or more functions, or any combination thereof. For illustrative purposes only, only one processor 620 is described in this specification for the computing device 600. However, it should be noted that the computing device 600 may also include multiple processors. Therefore, the operation and / or method steps disclosed in this specification may be executed by one processor as described herein, or they may be executed jointly by multiple processors. For example, if processor 620 of the computing device 600 in this specification executes steps A and B, it should be understood that steps A and B may also be executed jointly or separately by two different processors 620 (e.g., a first processor executes step A, a second processor executes step B, or the first and second processors jointly execute steps A and B).

[0058] Figure 3 A flowchart of a target category focus assessment method P100 for account behavior according to an embodiment of this specification is shown. As previously described, the computing device 600 can execute the target category focus assessment method P100 for account behavior according to this specification. Specifically, the processor 620 can read an instruction set stored in its local storage medium and then execute the target category focus assessment method P100 for account behavior according to the instructions in the instruction set. Figure 3 As shown, method P100 may include:

[0059] S110: Get the content set corresponding to the historical behavior of the target account within a preset time period.

[0060] The target account refers to the account whose target category focus needs to be evaluated. Target category focus can be understood as focus on a specific target category. Target accounts can be of various types, including content output accounts and content interaction accounts. Content output accounts are those that publish or output content. Content interaction accounts are those that interact with the output or published content on the content platform; the types of content interaction can be various, including at least one of browsing, forwarding, commenting, liking, or saving.

[0061] Historical behavior can be understood as the account behavior of the target account during a historical period. The content set corresponding to the target account's historical behavior can be of various types. For example, when the target account is a content output account, the content set corresponding to this historical behavior includes the content output by the target account; or, when the target account is a content interaction account, the content set corresponding to this historical behavior includes content interacting with the target account. There are various types of content interaction, as detailed above.

[0062] There are several ways to obtain the content set corresponding to the historical behavior of a target account within a preset time period, as follows:

[0063] For example, the processor 620 can receive a set of content corresponding to the historical behavior of the target account within a preset time period uploaded by the target user 100 through the terminal; or, it can obtain the original set of content corresponding to the account behavior of the target account from a content platform or network, select content within the preset time period from the original set of content, and thus obtain the set of content corresponding to the historical behavior; or, when the set of content corresponding to the historical behavior of the target account has a large number of contents or a large amount of memory, it can also receive a focus assessment request, which carries the storage address of the set of content corresponding to the historical behavior of the target account within the preset time period, and obtain the set of content based on the storage address.

[0064] S120: Count the number of first-level category content and the number of generic category content in the content set.

[0065] In this context, a primary category can be understood as a category obtained by classifying the content in a content collection into primary categories. Primary category content can be understood as the content corresponding to a primary category within the content collection.

[0066] In this context, a generic category can be understood as a category composed of multiple similar primary categories, or as a superordinate category of a primary category. For example, if the primary categories include stocks and wealth management, the generic category for these two primary categories could be finance, and so on. Generic category content refers to the content within a content set that belongs to the same generic category. The quantity of generic content refers to the number of pieces of content in the content set that belong to that generic category.

[0067] There are several ways to count the number of first-level category content and the number of generic category content in the content collection, as well as the number of generic category content. These methods are as follows:

[0068] For example, the processor 620 can classify the content in the content collection to obtain at least one first-level category content, determine at least one generic category content of a generic list based on the first-level category content, and count the number of first-level category content and the number of generic category content in the content collection respectively.

[0069] There are several ways to determine the content of at least one generic category based on the content of the first-level category. For example, the processor 620 can obtain the category attribute information of each first-level category, and determine the mapping relationship between each first-level category and the preset generic category based on the category attribute information. By determining the mapping relationship, the first-level category can be classified, thereby obtaining at least one generic category. Alternatively, the content of the first-level category of at least one first-level category can be clustered, and the at least one category obtained after clustering can be used as the generic category, and the content of the first-level category corresponding to the generic category can be used as the generic category content.

[0070] In some embodiments, during the evaluation of target category focus on account behavior, the impact of time on content categories can also be considered. Therefore, during the focus evaluation process, the time weight corresponding to each time period can be determined. Then, the content quantity and general content quantity are weighted based on the time weight to determine the target focus of the target category. There are multiple ways to determine the time weight corresponding to each time period. For example, the processor 620 can determine the time decay method corresponding to each time period based on the time distance between each time period and the current time, and obtain the time weight of each time period based on the time decay method. Specifically, it can be as follows:

[0071] (1) Based on the time distance between each time period and the current time, determine the time decay method corresponding to each time period.

[0072] The time period can be understood as a pre-set cycle for the amount of statistical content. This time period can be of various types, such as a week, a day, an hour, or other time periods. The time period can be set according to the actual application.

[0073] The time distance can be understood as the time difference between the current moment and the time period. For example, taking a time period of 1 day as an example, when the time period is day 1, the time distance between the time period and the current moment is 1 day. When the time period is day 2, the time distance between the time period and the current moment is 2 days, and so on. When the time period is day n, the time distance between the time period and the current moment is n days. Thus, the time distance between each time period within the preset time period and the current moment can be obtained.

[0074] The time decay method can be understood as a way to determine the time weight of each time period based on time decay. This time decay method can take various forms, such as a time decay function or a time decay algorithm. It can include a first time decay method and a second time decay method. The first time decay method differs from the second time decay method. Taking a time decay function as an example, this time decay function can be a piecewise function; different time intervals can correspond to different piecewise functions.

[0075] There are several ways to determine the time decay method for each time period based on the time distance between each time period and the current time. These methods can be as follows:

[0076] For example, the processor 620 can compare the time distance between each time period and the current time with a preset time distance threshold. Based on the comparison result, it selects the first time period and the second time period in each time period, determines the time decay method of the first time period as the first time decay method, and determines the time decay method of the second time period as the second time decay method.

[0077] The first time period includes time periods where the time distance exceeds a preset time distance threshold, and the second time period includes time periods where the time distance does not exceed the preset time distance threshold. For example, taking a preset time distance of 30 days from the current time as an example, the time period above the 30th day (t>30 days) can be used as the first time period, and the time period at or below the 30th day (t<=30 days) can be used as the second time period. The preset time distance can be set according to the actual application.

[0078] (2) Based on the time decay method, obtain the time weight corresponding to each time period.

[0079] The time weight can be understood as the degree of impact on focus within each time period. Taking posting as an example of account behavior, the longer the posting time, the smaller the impact on focus.

[0080] There are several ways to obtain the time weight corresponding to each time period based on the time decay method, as follows:

[0081] For example, the processor 620 can determine the first time weight corresponding to the first time period based on the first time decay method, determine the second time weight corresponding to the second time period based on the second time decay method, and use the first time weight and the second time weight as the time weight corresponding to each time period.

[0082] There are several ways to determine the first time weight corresponding to the first time based on the first time decay method. For example, the processor 620 can obtain the preset time decay parameter and the first preset constant, obtain the time ratio of the time distance corresponding to the first time period to the first preset time constant, and determine the first initial time weight based on the time ratio, and fuse the first initial time weight with the preset time decay parameter to obtain the first time weight corresponding to the first time period.

[0083] The preset time decay parameter can be understood as pre-set parameter information used to characterize time decay. The first preset time constant can be understood as a time constant pre-set in the first time decay method, which is used to determine the first initial time weight.

[0084] The time ratio can be understood as the ratio between the time distance corresponding to the first time period and the first preset time constant. Based on this time ratio, there are multiple ways to determine the first initial time weight. For example, the processor 620 can calculate the arctangent value of this time ratio and use the arctangent value as the first initial time weight.

[0085] After determining the first initial time weight, it can be fused with the preset time decay parameter. There are several ways to fuse them. For example, the processor 620 can directly calculate the product of the first initial time weight and the preset time decay parameter, and use this product as the first time weight corresponding to the first time period. For instance, taking a preset time distance threshold of 30 days, a preset time decay parameter of 0.64, and a first preset time constant of 80 as an example, the time decay function corresponding to the first time decay method can be as shown in formula (1):

[0086] δ(t)=0.64*arctan(t / 80),ift>30 (1)

[0087] Where δ(t) is the first time weight corresponding to the first time period, and t is the time distance.

[0088] There are several ways to determine the second time weight corresponding to the second time period based on the second time decay method. For example, the processor 620 can obtain a preset time decay parameter and a second preset time constant, fuse the second preset time constant with the time distance corresponding to the second time period to obtain the second initial time weight, and fuse the second initial time weight with the preset time decay parameter to obtain the second time weight corresponding to the second time period.

[0089] The second preset time constant can be understood as a time constant pre-set in the second time decay method, which is used to determine the second initial time weight. There are multiple ways to fuse the second preset time constant with the time distance corresponding to the second time period to obtain the second initial time weight. For example, the processor 620 can adjust the time distance corresponding to the second time period to obtain an adjusted time distance, add the adjusted time distance to the second preset time constant to obtain the target time distance, and determine the second initial time weight based on the target time distance.

[0090] There are several ways to adjust the time distance corresponding to the second time period. For example, the processor 620 can multiply the time distance corresponding to the second time period by a preset multiplication factor to obtain the adjusted target time distance, or it can multiply the time distance corresponding to the second time period by a preset adjustment factor to obtain the adjusted target time distance, and so on.

[0091] After adding the adjusted time distance to the second preset time constant, a second initial time weight can be determined based on the target time distance obtained from the addition. There are several ways to determine the second initial time weight. For example, the processor 620 can calculate the arctangent value of the target time distance and use this arctangent value as the second initial time weight.

[0092] After obtaining the second initial time weight, it can be fused with the preset time decay parameter to obtain the second time weight corresponding to the second time period. There are multiple ways to fuse them. For example, the processor 620 can directly obtain the product of the second initial time weight and the preset time decay parameter and use the product as the time weight corresponding to the second time period. For example, taking a preset time distance threshold of 30 days, a preset time decay parameter of 0.64, and a second preset time constant of 2 as an example, the time decay function corresponding to the second time decay parameter can be as shown in formula (2):

[0093] δ(t)=0.64*arctan(2t+2), ift<=30 (2)

[0094] Where δ(t) is the first time weight corresponding to the second time period, and t is the time distance.

[0095] After determining the first time weight corresponding to the first time period and the second time weight corresponding to the second time period, the first time weight and the second time weight can be used as the time weight corresponding to each time period.

[0096] After obtaining the time weight corresponding to each time period, the processor 620 continues to execute the following steps of method P100.

[0097] S130: Based on the amount of content, determine the target account's focus on the target category in its historical behavior.

[0098] The target category belongs to at least one first-level category, which can be understood as the target category being any one of the at least one first-level categories.

[0099] There are several ways to determine a target account's focus on a target category based on the amount of content, including the following:

[0100] For example, the processor 620 can count the current content quantity for each time period in the content quantity, weight the current content quantity based on the time weight corresponding to each time period, and determine the focus of the target account on the target category in the historical behavior based on the weighted content quantity.

[0101] There are several ways to calculate the current content quantity for each time period in the content quantity. For example, the processor 620 can obtain the corresponding time information for each piece of content in the content collection, and based on this time information, calculate the current content quantity for each time period in the content quantity. For instance, taking a time period of 1 day, and the content in the content collection being content published by the target account, the time information would be the publication time of that content, and based on that publication time, the current content quantity for each day would be calculated in the content quantity.

[0102] After calculating the current content quantity for each time period, the current content quantity can be weighted based on the time weight corresponding to each time period. There are several ways to weight the current content quantity based on the time weight. For example, the processor 620 can select a target time weight corresponding to each current quantity from the time weights corresponding to each time period, and then weight the current content quantity based on this target time weight to obtain the weighted content quantity.

[0103] After weighting the current content quantity, the focus of the target account on the target category in historical behavior can be determined based on the weighted content quantity. There are several ways to determine the focus of the target category. For example, the processor 620 accumulates the weighted content quantity to obtain the current total content quantity, selects the quantity corresponding to the target category from the weighted total content quantity to obtain the target category content quantity, and obtains the first ratio between the target category content quantity and the current total content quantity, and uses this first ratio as the focus of the target account on the target category in historical behavior, as shown in formula (3):

[0104]

[0105] Where y1 represents the focus of the target category, which indicates the proportion of content in the target category in the total content after time decay. δ(t) is the time decay function, used to characterize the time weight corresponding to each time period, Cnt. 一级类别i Let i be the number of contents in first-level category i on day t.

[0106] S140: Based on the amount of general content, determine the focus correction value of historical behavior on the target category.

[0107] The focus correction value can be understood as a value used to correct the focus on the target category based on the amount of general content.

[0108] There are several ways to determine the focus correction value of historical behavior on the target category based on the amount of general content, as follows:

[0109] For example, the processor 620 weights the quantity of generic content based on the time weight corresponding to each time period, selects the current quantity of generic content in the target generic category from the weighted quantity of generic content, and determines the focus correction value of historical behavior in the target category based on the weighted quantity of generic content and the current quantity of generic content.

[0110] The target broad category includes the target category and similar first-level categories. For example, if the target category is stocks, the target broad category could be finance. In this case, the target broad category could include stocks and similar first-level categories, such as funds, wealth management, etc.

[0111] The method of weighting the quantity of general content based on the time weight corresponding to each time period is similar to the method of weighting the quantity of content based on time weight. For details, please refer to the above text, and will not be repeated here.

[0112] After weighting the number of generic content items, the current number of generic content items for the target category can be selected from the weighted number of generic content items. There are several ways to select the current number of generic content items for the target category. For example, the processor 620 can select the generic category corresponding to the target category from at least one generic category to obtain the target generic category, and then filter the weighted number of generic content items corresponding to the target generic category from the weighted number of generic content items to obtain the current number of generic content items.

[0113] After selecting the current quantity of generic content, the focus correction value for historical behavior in the target category can be determined based on the weighted quantity of generic content and the current quantity of generic content. There are several ways to determine the focus correction value. For example, the processor 620 can calculate the quantity of similar content in similar categories corresponding to the target category based on the current quantity of generic content to obtain a first initial generic content focus value. It can then compare the weighted quantity of generic content with the current quantity of generic content to obtain a second initial generic content focus value. Finally, it can merge the first and second initial generic content focus values ​​to obtain the generic content focus value corresponding to the target category, and use this generic content focus value as the focus correction value for historical behavior in the target category. Specifically, this can be done as follows:

[0114] (1) Based on the current amount of general content, calculate the amount of similar content in similar categories corresponding to the target category to obtain the first initial general content focus.

[0115] Here, the first initial general content focus represents the proportion of content in the target category after time decay to the total amount of content in the same category. Similar categories can be understood as the first-level categories other than the target category within the target general category.

[0116] There are several ways to calculate the number of similar content items in the same category corresponding to the target category based on the current amount of general content, in order to obtain the first initial general content focus. These methods can be as follows:

[0117] For example, the processor 620 counts the number of the target category in the current general content quantity, obtains the target category content quantity, calculates the difference between the current general content quantity and the target category quantity, obtains the similar content quantity of the target category; and obtains the second ratio between the target category quantity and the similar content quantity, and uses the second ratio as the first initial general content focus.

[0118] (2) Compare the weighted general content quantity with the current general content quantity to obtain the second initial general content focus.

[0119] Among them, the second initial general content focus represents the proportion of the target category content in the total content after time decay.

[0120] There are several ways to compare the weighted general content quantity with the current general content quantity to obtain the second initial general content focus, as follows:

[0121] For example, the processor 620 can sum up the weighted general content quantity to obtain the current general content total quantity, and obtain the third ratio between the current general content quantity and the current general content total quantity, and use the third ratio as the second initial general content focus.

[0122] (3) The first initial general content focus and the second initial general content focus are merged to obtain the general content focus corresponding to the target category, and the general content focus is used as the focus correction value of historical behavior on the target category.

[0123] For example, the processor 620 can directly multiply the first initial general content focus and the second initial general content focus to obtain the general content focus corresponding to the target category, and use the general content focus as the focus correction value of historical behavior on the target category, as shown in formula (4):

[0124]

[0125] Where y2 is the focus correction value corresponding to the focus of the target category, δ(t) is the time decay function, used to characterize the time weight corresponding to each time period, and Cnt 一级类别i Cnt represents the number of contents in target category i on day t. 同类别泛内容类 The number of similar categories to the target category on day t, Cnt 泛类别i Let be the number of contents of target category i corresponding to target category i on day t.

[0126] S150: Based on focus level and focus correction value, determine the target account's focus level on the target category in historical behavior.

[0127] For example, the processor 620 can obtain the weighting coefficient corresponding to the target category, and based on the weighting coefficient, weight the focus and focus correction value respectively, and merge the weighted focus and the weighted focus correction value to obtain the target account's focus on the target category in historical behavior.

[0128] The weighting coefficient is a pre-defined weighting factor, which represents the weighting factor corresponding to the target category. Within at least one primary category, the weighting factors for each primary category can be all the same, partially the same, or different. This weighting coefficient may include a first weight corresponding to focus level and a second weight corresponding to the focus level correction value. The first weight can be greater than the second weight, and the sum of the first and second weights is 1.

[0129] After weighting the focus level and the focus level correction value using weighted coefficients, the weighted focus level and the weighted focus level correction value can be merged. There are several ways to merge them. For example, the processor 620 can add the weighted focus level and the weighted focus level correction value to obtain the corrected focus level of the target account for the target category in historical behavior, and determine the confidence level of the corrected focus level based on the amount of content. Then, it can calculate the product of the confidence level and the corrected focus level to obtain the target focus level.

[0130] Confidence score is a parameter used to characterize the comparability between different target accounts within a target category. Within a specific historical time period, when the content set contains a large amount of content, the closer the sum of the focus scores for each primary category corresponding to the target account is to 1, the higher the confidence score. Conversely, the smaller the content set contains, the closer the focus scores for each primary category corresponding to the target account are to 0, indicating a lower confidence score. Confidence score ensures that the focus scores of target accounts for the same target category are comparable. There are several ways to determine the confidence score of the corrected focus score based on the amount of content. For example, the processor 620 can count the amount of content in the candidate historical time period within the content set to obtain the total historical content. Based on this total historical content, it can determine the confidence score information of the target account and modulate this confidence score information to obtain the corrected focus score.

[0131] The confidence information can be understood as the input information of the confidence modulation function. By modulating the confidence information, the corrected confidence level of focus can be obtained. There are several ways to determine the confidence information of a target account based on the total amount of historical content. For example, the processor 620 can adjust the total amount of historical content to obtain the target total amount of historical content, obtain the difference between the target total amount of historical content and a preset confidence constant, and determine the confidence information of the target account based on this difference.

[0132] There are several ways to adjust the total amount of historical content. For example, the processor 620 can multiply the total amount of historical content by a preset multiple to obtain the target total amount of historical content, or it can multiply the total amount of historical content by a preset adjustment parameter to obtain the target total amount of historical content.

[0133] After obtaining the quantity difference between the total amount of target historical content and the preset confidence constant, the confidence information of the target account can be determined based on this quantity difference. There are several ways to determine the confidence information of the target account. For example, the processor 620 can calculate the arctangent value of the quantity difference and multiply the arctangent value by the preset confidence parameter to obtain the confidence information of the target account.

[0134] After determining the confidence information of the target account, the confidence information can be modulated to obtain the corrected confidence level of focus. There are various ways to modulate the confidence information. For example, the processor 620 can use a modulation function to modulate the confidence information to obtain the corrected confidence level of focus. Taking a preset confidence parameter of 0.636 and a preset confidence constant of 4 as an example, the specific method is shown in formula (5):

[0135] ρ(x)=G[0.636*arctan(2x-4)] (5)

[0136] Where ρ(x) is the confidence level of the corrected focus, x is the total amount of historical content, and G(x) is the modulation function, which can be specifically shown in formula (6):

[0137]

[0138] Where G(x) is the modulation function and x is the confidence information.

[0139] After determining the confidence level of the corrected focus, the product of the confidence level and the corrected focus can be calculated to obtain the target focus. Taking the candidate time period as the 30 days before the current moment, the content set as the content published by the target account, and the weight ratio of focus to focus correction value as 0.9:0.1 as an example, the target focus can be calculated as shown in formula (7):

[0140]

[0141] Among them, Y i For target focus level of target category i, ρ(Cnt) 近30天发文数 ) represents the confidence level, δ(t) represents the time weight corresponding to each time period, and Cnt represents the time weight. 一级类别i For the number of posts in each first-level category i on day t, Cnt 泛类别i Let i be the number of posts in the generic category i corresponding to the target category i on day t.

[0142] Through formula (7), it can be found that the formula satisfies the following principle:

[0143] (a) The focus level of all categories without any posting accounts is 0;

[0144] (b) The more posts a target account makes that belong to the same primary category, the higher its focus on that category.

[0145] (c) The longer the posting time, the smaller the impact on focus. The granularity of the impact decay of posts published before 30 days ago is greater than that of posts published within the last 30 days.

[0146] (d) Articles belonging to different primary categories but within the same broad content category will have a slight weighting for focus within that broad content category; and

[0147] (e) The sum of the focus scores of all categories of accounts that have published articles is less than or equal to 1. Accounts with the same number of articles published in the past 30 days have the same sum of focus scores for all categories. The sum of the focus scores of all categories of accounts is directly proportional to the number of articles published in the past 30 days.

[0148] After determining the target account's focus on the target category in its historical behavior, this focus can be output. There are several ways to output it. For example, the processor 620 can directly send the target account's focus on the target category to the content interaction platform so that the platform can make decisions about the target account. Alternatively, it can use the target account's focus on the target category as a focus tag, affix this tag to the target account, and send the tagged target account to the content platform or other content server for decision-making. Or, it can compare the target account's focus on the target category with the focus of other accounts on the target category and make decisions based on the comparison results. Alternatively, it can directly make decisions about the target account based on its focus on the target category.

[0149] There are several ways to make decisions about a target account. For example, the processor 620 can compare the target's focus with a focus threshold. If the focus threshold is exceeded, it can be determined that the target account is focused on the target category. The target account or the content published by the target account can then be recommended to consumers or users in the target category. Alternatively, the target's focus can be compared with a focus threshold. If the focus threshold is not exceeded, the frequency of the target account's content output or content interaction in the target category can be restricted, and so on.

[0150] This solution can be applied to assessment scenarios that evaluate the posting behavior preferences of target accounts. The following detailed explanation uses this scenario as an example, assuming the target account is a lifestyle account or any public account that can publish content. The overall calculation logic for target focus can be as follows:

[0151] C1. Calculate the proportion of posts under different content categories in the account's posts within 180 days. When calculating the number of posts by content category, a time decay factor is introduced. The older the post is, the smaller its weight, down to 0. The more recent the post is, the more its weight tends to be 1. The time decay factor function is a piecewise function. Specifically, as shown in formulas (1) and (2), it can be divided into posts from 180-30 days ago and posts from the last 30 days ago. According to business logic, the former has a greater decay intensity than the latter, so as to enhance the impact of posts from the last 30 days.

[0152] C2. Calculate the account's percentage within the same broad category based on the relationship between the primary content category and the broader content category (broad category). Then, weight the percentage of posts within the primary category and its corresponding broad category. Here, the broad content category can be understood as a higher-level concept than the primary content category. For example, if the primary category is "finance" and "finance" belongs to the same broad content category, an account that posts multiple articles on finance and a few on finance will have significantly higher focus on finance compared to an account that posts multiple articles on finance and a few on fitness.

[0153] C3. Weight the results obtained in C1 and C2 in a 9:1 ratio. Introduce the influence of sending content of the same generic category as in C2. That is, when the target account sends the same generic content, the focus score of the first-level category under the same generic content category is increased, thereby correcting the focus score of the first-level category and obtaining the corrected focus score of each first-level category.

[0154] The corrected focus scores (focus scores) obtained in C4 and C3 sum to 1 for each primary category within the target account. At this point, the primary categories within the target account are comparable. To ensure comparability between accounts, the corrected focus scores of the target account can be weighted based on the number of posts published in the past 30 days. The more posts published in the past 30 days, the closer the sum of the corrected focus scores for each primary category within the target account is to 1. The fewer posts, the closer it is to 0, meaning a lower confidence level. In this example, when the number of posts is less than or equal to 2, the sum of the corrected focus scores for each primary category within the target account can be 0, meaning a confidence level of 0 and no focus evaluation, thus avoiding the influence of abnormal data due to insufficient data volume.

[0155] The overall calculation logic of the target focus in this scheme reveals that the calculated target focus is a score between 0 and 1, generated through mathematical logic. This 0-1 range represents the strength of an account's focus, allowing for the quantification of focus intensity. Focus is calculated for each content category, resulting in the focus distribution across all primary content categories. Furthermore, by introducing the relationship between primary content categories and general categories, different primary categories within the same general category can be individually weighted to avoid calculation biases caused by incomplete segmentation of primary content categories. The impact of posting time can also be considered; when counting posts, the older the post, the lower its weight, down to 0, while the weight of more recent posts approaches 1. The attenuation weights across different time periods are also individually segmented. Finally, the overall focus calculation within an account can be weighted based on the number of posts in the last 30 days to control the confidence level of the account's focus, thus achieving comparability of focus between accounts. The time decay factor and article weight calculation logic in this solution can be customized and optimized according to business needs.

[0156] It should be noted that this solution can be applied not only to evaluating the behavioral preferences of a target account's posts, but also to other similar scenarios, such as calculating fan interests and fan focus categories. Taking the calculation of fan interests as an example, the content set can consist of the fan's usual posts or interactions. The calculated target focus level for a target category can be understood as the behavioral preference for that category. When the target focus level exceeds a focus threshold, it can be determined that the fan's interest lies in that target category or objects within that category. These objects can include people, animals, or other objects, etc.

[0157] In summary, the target category focus assessment method P100 and system 001 for account behavior provided in this specification obtain the content set corresponding to the historical behavior of the target account within a preset time period. Then, it counts the number of first-level category content and the number of generic category content for at least one generic category within the content set. Based on the content quantity, it determines the target account's focus on the target category in historical behavior, where the target category belongs to at least one first-level category. Then, based on the number of generic content, it determines the focus correction value for the historical behavior on the target category. Finally, based on the focus and the focus correction value, it determines the target account's target focus on the target category in historical behavior. Because this scheme can determine the target account's focus on the target category based on the counted number of first-level category content, it can assess the focus intensity of any first-level category for the target account, not just a single category. Furthermore, it can correct the focus using the focus correction value for the target category determined by the number of generic content, thus fully considering the impact of content quantity and similar categories on focus during the focus assessment process. Therefore, it can improve the accuracy of target category focus assessment for account behavior.

[0158] This specification, in another aspect, provides a non-transitory storage medium storing at least one set of executable instructions for performing target category focus assessment of account behavior. When the executable instructions are executed by a processor, they instruct the processor to implement the steps of the target category focus assessment method P100 for account behavior described in this specification. In some possible embodiments, various aspects of this specification can also be implemented as a program product comprising program code. When the program product is run on a computing device 600, the program code causes the computing device 600 to perform the steps of the target category focus assessment method P100 for account behavior described in this specification. The program product for implementing the above method may employ a portable compact disk read-only memory (CD-ROM) containing program code and may run on the computing device 600. However, the program product of this specification is not limited thereto. In this specification, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system. The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium can also be any readable medium other than a readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. Program code for performing the operations described herein may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages.The program code can be executed entirely on computing device 600, partially on computing device 600, as a standalone software package, partially on computing device 600 and partially on a remote computing device, or entirely on a remote computing device.

[0159] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0160] In summary, after reading this detailed disclosure, those skilled in the art will understand that the foregoing detailed disclosure is presented by way of example only and is not restrictive. Although not explicitly stated herein, those skilled in the art will understand that this specification requires various reasonable changes, improvements, and modifications to the embodiments. These changes, improvements, and modifications are intended to be made by this specification and are within the spirit and scope of the exemplary embodiments described herein.

[0161] Furthermore, certain terms in this specification have been used to describe embodiments of this specification. For example, "an embodiment," "an embodiment," and / or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with that embodiment may be included in at least one embodiment of this specification. Therefore, it is to be emphasized and understood that two or more references to "an embodiment" or "an embodiment" or "alternative embodiment" in various parts of this specification do not necessarily refer to the same embodiment. Moreover, specific features, structures, or characteristics may be suitably combined in one or more embodiments of this specification.

[0162] It should be understood that in the foregoing description of the embodiments in this specification, various features are combined in a single embodiment, drawing, or description for the purpose of simplifying the description and to aid in understanding a feature. However, this does not mean that the combination of these features is necessary, and those skilled in the art, upon reading this specification, may readily identify some of the devices as separate embodiments. That is, the embodiments in this specification can also be understood as an integration of multiple secondary embodiments. It is also valid when each secondary embodiment contains fewer than all the features of a single foregoing disclosed embodiment.

[0163] Each patent, patent application, publication of the patent application, and other materials such as articles, books, specifications, publications, documents, articles, etc., cited herein may be incorporated by reference. All contents used for all purposes, except for any history of prosecution documents relating to it, that may be inconsistent with or conflict with this document, or any such history of prosecution documents that may have a limiting effect on the widest extent of the claims, are now or hereafter associated with this document. For example, in the event of any inconsistency or conflict between the description, definition, and / or use of terms associated with any of the included materials and the terms, description, definition, and / or used in connection with this document, the terms used herein shall prevail.

[0164] Finally, it should be understood that the embodiments disclosed herein are illustrative of the principles of the embodiments described in this specification. Other modified embodiments are also within the scope of this specification. Therefore, the embodiments disclosed in this specification are merely examples and not limitations. Those skilled in the art can implement the applications described in this specification using alternative configurations based on the embodiments in this specification. Therefore, the embodiments in this specification are not limited to the embodiments precisely described in the applications.

Claims

1. A method for evaluating the focus of account behavior on target categories, comprising: Obtain the content set corresponding to the historical behavior of the target account within a preset time period, wherein the preset time period includes at least one time cycle; The number of content items in at least one primary category and the number of generic content items in at least one generic category are counted in the content set, wherein the at least one primary category includes the target category; Based on the time distance between each time period and the current moment, the time decay method corresponding to each time period is determined, and the time weight corresponding to each time period is determined based on the time decay method. The time weight represents the degree of influence of each time period on the focus in the historical behavior. Based on the time weight and the content quantity, the focus of the target account on the target category in the historical behavior is determined; Based on the time weight and the amount of general content, determine the focus correction value of the historical behavior on the target category; Based on the focus level and the focus level correction value, determine the corrected focus level of the target account for the target category in the historical behavior; as well as Based on the amount of content, the confidence level of the corrected focus is determined, and based on the confidence level and the corrected focus, the target focus of the target account on the target category in the historical behavior is obtained.

2. The method for evaluating the focus of account behavior according to claim 1, wherein, The target account is a content output account, and the content set corresponding to the historical behavior includes the content output by the target account. or The target account is a content interaction account, and the content set corresponding to the historical behavior includes content that has been interacted with the target account. The content interaction includes at least one of browsing, forwarding, commenting, liking, or collecting.

3. The method for evaluating the focus of account behavior according to claim 1, wherein, The time decay method includes a first time decay method and a second time decay method, and The step of determining the time decay method corresponding to each time period based on the time distance between each time period and the current time includes: Compare the time distance between each time period and the current moment with a preset time distance threshold; Based on the comparison results, a first time period and a second time period are selected from each time period. The first time period includes time periods in which the time distance exceeds the preset time distance threshold, and the second time period includes time periods in which the time distance does not exceed the preset time distance threshold. The time decay method of the first time period is determined to be the first time decay method, and the time decay method of the second time period is determined to be the second time decay method.

4. The method for evaluating the focus of account behavior according to claim 3, wherein, The step of determining the time weight corresponding to each time period based on the time decay method includes: Based on the first time decay method, determine the first time weight corresponding to the first time period; Based on the second time decay method, determine the second time weight corresponding to the second time period; and The first time weight and the second time weight are used as the time weights corresponding to each time period.

5. The method for evaluating the focus of account behavior according to claim 4, wherein, The step of determining the first time weight corresponding to the first time period based on the first time decay method includes: Obtain the preset time decay parameter and the first preset time constant; Obtain the time ratio between the time distance corresponding to the first time period and the first preset time constant, and determine the first initial time weight based on the time ratio; and The first initial time weight is fused with the preset time decay parameter to obtain the first time weight corresponding to the first time period.

6. The method for evaluating the focus of account behavior according to claim 4, wherein, The step of determining the second time weight corresponding to the second time period based on the second time decay method includes: Obtain the preset time decay parameter and the second preset time constant; The second preset time constant is fused with the time distance corresponding to the second time period to obtain the second initial time weight; and The second initial time weight is fused with the preset time decay parameter to obtain the second time weight corresponding to the second time period.

7. The method for evaluating the focus of account behavior on target categories according to claim 6, wherein, The step of fusing the second preset time constant with the time distance corresponding to the second time period to obtain the second initial time weight includes: The time distance corresponding to the second time period is adjusted to obtain the adjusted time distance; Add the adjusted time distance to the second preset time constant to obtain the target time distance; and The second initial time weight is determined based on the target time distance.

8. The method for evaluating the focus of account behavior according to claim 1, wherein, Determining the target account's focus on the target category in the historical behavior based on the time weight and the content quantity includes: The current content quantity corresponding to each time period is calculated from the content quantity; The current content quantity is weighted based on the time weight corresponding to each time period; and Based on the weighted content quantity, the focus of the target account on the target category in the historical behavior is determined.

9. The method for evaluating the focus of account behavior according to claim 8, wherein, The determination of the target account's focus on the target category in the historical behavior based on the weighted content quantity includes: The weighted content quantities are summed to obtain the current total content quantity; Select the quantity corresponding to the target category from the weighted total content to obtain the content quantity of the target category; and Obtain a first ratio between the number of content items in the target category and the current total amount of content, and use the first ratio as the focus of the target account on the target category in the historical behavior. The focus represents the proportion of the number of content items in the target category in the total amount of content after time decay.

10. The method for evaluating the focus of account behavior according to claim 1, wherein, The determination of the focus correction value for the historical behavior in the target category based on the time weight and the amount of general content includes: The quantity of general content is weighted based on the time weight corresponding to each time period; Select the current content quantity of the target generic category from the weighted generic content quantity, wherein the target generic category includes the target category and first-level categories similar to the target category; and Based on the weighted general content quantity and the current general content quantity, the focus correction value of the historical behavior on the target category is determined.

11. The method for evaluating the focus of account behavior according to claim 10, wherein, The determination of the focus correction value for the historical behavior in the target category based on the weighted general content quantity and the current general content quantity includes: Based on the current amount of generic content, the amount of similar content in similar categories corresponding to the target category is calculated to obtain the first initial generic content focus. The similar category is a first-level category that belongs to the same target generic category as the target category. The weighted general content quantity is compared with the current general content quantity to obtain the second initial general content focus; and The first initial general content focus and the second initial general content focus are fused to obtain the general content focus corresponding to the target category, and the general content focus is used as the focus correction value of the historical behavior on the target category.

12. The method for evaluating the focus of account behavior according to claim 11, wherein, The step of calculating the number of similar content items in similar categories corresponding to the target category based on the current number of general content items, in order to obtain a first initial general content focus, includes: The number of the target category is obtained by counting the number of the current general content; Calculate the difference between the current number of generic content items and the number of items in the target category to obtain the number of similar content items in similar categories corresponding to the target category; and Obtain a second ratio between the number of content in the target category and the number of content in the same category, and use the second ratio as the first initial general content focus. The first initial general content focus represents the proportion of the number of content in the target category after time decay in the number of content in the same category.

13. The method for evaluating the focus of account behavior according to claim 11, wherein, The step of comparing the weighted general content quantity with the current general content quantity to obtain the second initial general content focus includes: The weighted quantities of generic content are summed to obtain the current total quantity of generic content; and Obtain a third ratio between the current quantity of generic content and the current total quantity of generic content, and use the third ratio as the second initial generic content focus. The second initial generic content focus represents the proportion of the quantity of target generic content in the total content after time decay.

14. The method for evaluating the focus of account behavior on target categories according to claim 1, wherein, The determination of the corrected focus level of the target account for the target category in the historical behavior, based on the focus level and the focus correction value, includes: Obtain the weighting coefficients corresponding to the target category; Based on the weighting coefficients, the focus level and the focus correction value are weighted separately; and The weighted focus value and the weighted focus correction value are added together to obtain the corrected focus value of the target account for the target category in the historical behavior.

15. The method for evaluating the target category focus of account behavior according to claim 14, wherein, The step of obtaining the target account's target focus on the target category in the historical behavior based on the confidence level and the corrected focus level includes: The target focus is obtained by multiplying the confidence level and the corrected focus level.

16. The method for evaluating the focus of account behavior according to claim 15, wherein, Determining the confidence level of the corrected focus based on the quantity of content includes: The total amount of historical content is obtained by counting the number of candidate historical time periods in the content set. Based on the total amount of historical content, the confidence level information of the target account is determined; and The confidence information is modulated to obtain the confidence level of the corrected focus.

17. The method for evaluating the focus of account behavior according to claim 16, wherein, The determination of the confidence information of the target account based on the total amount of historical content includes: The total amount of historical content is adjusted to obtain the target total amount of historical content; Obtain the quantity difference between the total amount of the target historical content and the preset confidence constant; and Based on the difference in quantity, the confidence level information of the target account is determined.

18. The method for evaluating the focus of account behavior according to claim 1, wherein, The step of counting the number of first-level category content and the number of generic category content in the content set includes: The content in the content set is classified to obtain at least one first-level category of content; Based on the content of the primary category, determine the generic category content of the at least one generic category; and The number of contents in the first-level category and the number of contents in the general category are counted in the content set.

19. A target category focus assessment system for account behavior, comprising: At least one storage medium storing at least one set of instructions for performing target category focus assessment of account behavior; as well as At least one processor is communicatively connected to the at least one storage medium. When the target category focus assessment system for account behavior is running, the at least one processor reads the at least one instruction set and executes the target category focus assessment method for account behavior according to any one of claims 1-18 according to the instructions of the at least one instruction set.

Images