Behavioral asset state determination method and apparatus, electronic device, and readable storage medium

Abstract

The present disclosure provides a behavior asset state determination method and device, electronic equipment and readable storage medium, relates to the technical field of data processing, in particular to the technical field of cloud computing, intelligent recommendation or intelligent marketing. The specific implementation scheme is: obtaining operation behavior and conversion behavior of a target user on a target service in a predetermined historical period; determining an operation behavior feature, the operation behavior feature being used to represent the operation behavior; determining feature discrimination of the operation behavior feature based on the conversion behavior; and determining a behavior asset state of the target user based on the feature discrimination. In the present scheme, the behavior asset state of the user can be effectively and accurately determined based on the feature discrimination of the operation behavior feature, and the processing effect of related processing based on the behavior asset state can be ensured.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more particularly to the fields of cloud computing, intelligent recommendation or intelligent marketing technology. Specifically, this disclosure relates to a method, apparatus, electronic device and readable storage medium for determining the state of behavioral assets. Background Technology

[0002] In online marketing of internet services, it is necessary to accumulate user behavior data and conduct marketing analysis on this data. From a data product perspective, this accumulated behavioral data is also called behavioral assets.

[0003] Behavioral asset status, derived from user behavioral asset analysis, measures the depth of a user's understanding of or the intensity of their interaction with internet services. As a crucial indicator in marketing analytics, accurately and effectively determining behavioral asset status has become a significant technical challenge. Summary of the Invention

[0004] To address at least one of the aforementioned deficiencies, this disclosure provides a method, apparatus, electronic device, and readable storage medium for determining the status of behavioral assets.

[0005] According to a first aspect of this disclosure, a method for determining the status of behavioral assets is provided, the method comprising:

[0006] Acquire the operational and conversion behaviors of target users towards the target service within a predetermined historical time period;

[0007] Determine the operational behavior characteristics, which are used to characterize operational behavior;

[0008] Feature distinguishability based on transformation behavior to determine operational behavior characteristics;

[0009] Determine the behavioral asset status of target users based on feature discrimination.

[0010] According to a second aspect of this disclosure, a behavioral asset status determination apparatus is provided, the apparatus comprising:

[0011] The behavior acquisition module is used to acquire the target user's operational and conversion behaviors towards the target service within a predetermined historical time period;

[0012] The operation behavior feature determination module is used to determine operation behavior features, which are used to characterize operation behavior.

[0013] The feature discrimination determination module is used to determine the feature discrimination of operational behavior features based on conversion behavior.

[0014] The Behavioral Asset Status Determination Module is used to determine the behavioral asset status of a target user based on feature discrimination.

[0015] According to a third aspect of this disclosure, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to at least one of the aforementioned processors; wherein,

[0018] The memory stores instructions that can be executed by at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the aforementioned method for determining the state of the behavioral assets.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the aforementioned asset status determination method.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method for determining the state of behavioral assets.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0023] Figure 1 This is a flowchart illustrating a method for determining the status of behavioral assets provided in an embodiment of this disclosure;

[0024] Figure 2 This is a flowchart illustrating a specific implementation of the behavioral asset status determination method provided in this disclosure.

[0025] Figure 3 This is a schematic diagram of the structure of a behavioral asset status determination device provided in an embodiment of this disclosure;

[0026] Figure 4 This is a block diagram of an electronic device used to implement the behavioral asset status determination method provided in the embodiments of this disclosure. Detailed Implementation

[0027] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0028] Behavioral asset status measures the depth of a user's understanding of or the intensity of their interaction with an internet service, and is an important indicator in marketing analytics. For example, different marketing strategies can be adopted for users with different behavioral asset statuses.

[0029] In related technologies, behavioral asset status is generally determined based on simple rules defined according to business needs. For example, if a user's exposure to a service's promotional page reaches a certain value, the user's behavioral asset status can be determined as A. Similarly, if a user's clicks on a service's promotional page reach a certain value, the user's behavioral asset status can be determined as B. This approach relies heavily on the defined rules and has a degree of subjectivity, which may not guarantee the accuracy of the determined behavioral asset status.

[0030] The behavioral asset status determination method, apparatus, electronic device, and readable storage medium provided in this disclosure are intended to solve at least one of the above-mentioned technical problems of the prior art.

[0031] Figure 1 A flowchart illustrating a method for determining the status of behavioral assets provided in an embodiment of this disclosure is shown, as follows: Figure 1 As shown, the method can mainly include:

[0032] Step S110: Obtain the target user's operation and conversion behavior on the target service within a predetermined historical time period;

[0033] Step S120: Determine the operational behavior characteristics, which are used to characterize the operational behavior;

[0034] Step S130: Determine the feature distinguishability of operational behavior characteristics based on conversion behavior;

[0035] Step S140: Determine the behavioral asset status of the target user based on feature discrimination.

[0036] The preset historical period is an observation cycle used for behavioral asset status analysis. The length of the preset historical period can be set according to actual needs, such as 30 days.

[0037] The relevant behaviors of target users towards the target service within a predetermined historical period can include operational behaviors and conversion behaviors. Operational behaviors can be interactive behaviors between users and relevant information of the target service. For example, operational behaviors can include search behaviors for the target service, access behaviors of mini-programs for the target service, and access behaviors of articles on relevant public accounts of the target service.

[0038] For example, information related to the target service can also include promotional information for the target service, such as promotional pages. User actions can include browsing or clicking on promotional pages.

[0039] Conversion behavior refers to the process by which a target user transforms from a casual viewer of information related to a target service into an actual user or a purchasing user. For example, conversion behavior could include adding the target service to a shopping cart or successfully purchasing and paying for the target service.

[0040] Operational behavior features are characteristic representations of a target user's operational behaviors towards a target service within a predetermined historical period. Operational behavior data can be acquired in advance, and multi-dimensional information can be extracted from this data to construct operational behavior features.

[0041] In this embodiment of the disclosure, the feature distinguishability of an operational behavior characteristic can be determined based on the conversion behavior. This feature distinguishability can represent the degree of influence of different operational behaviors on the conversion behavior. The higher the feature distinguishability of a certain operational feature, the higher the degree of influence of that feature on the user's final conversion behavior.

[0042] In this embodiment of the disclosure, the behavioral asset status is used to measure the depth of a target user's understanding of the target service or the closeness of their interaction with it.

[0043] As an example, behavioral asset states can be categorized into different types based on the depth of cognition or the closeness of interaction they represent. For instance, arranged in order from shallow to deep according to the depth of cognition or the closeness of interaction they represent, they can be passive cognition, shallow interaction, deep interaction, and transformation.

[0044] The extent to which the actions performed by the target user influence the conversion behavior can also reflect the depth of the target user's understanding of the target service or the closeness of their interaction. Therefore, the behavioral asset status of the target user can be determined based on feature discrimination.

[0045] The method provided in this disclosure involves acquiring the target user's operational and conversion behaviors towards a target service within a predetermined historical time period; determining operational behavior features to represent the operational behaviors; determining the feature distinguishability of the operational behavior features based on the conversion behaviors; and determining the target user's behavioral asset status based on the feature distinguishability. This solution can effectively and accurately determine the user's behavioral asset status based on the feature distinguishability of the operational behavior features, ensuring the effectiveness of related processing based on the behavioral asset status.

[0046] Compared to related technologies that determine the status of behavioral assets by defining simple rules, this solution takes a data-driven approach and determines the status of behavioral assets based on the distinguishability of operational behavior features. The determined status of behavioral assets is more effective and accurate, and avoids the impact of subjectivity in setting rules on the accuracy of the determined status of behavioral assets.

[0047] In one optional embodiment of this disclosure, determining the operational behavior characteristics includes:

[0048] Based on the behavioral data of operational behavior, the initial operational behavior characteristics are determined, which are used to characterize a single operational behavior.

[0049] Based on the frequency of operation behavior within a predetermined historical period, and based on the characteristics of the initial operation behavior, the characteristics of the operation behavior are determined.

[0050] Determine the behavioral asset status of the target user based on operational behavior characteristics.

[0051] In this embodiment of the disclosure, multi-dimensional information can be obtained from the behavioral data of the operational behavior to construct the operational behavior characteristics of a single operational behavior.

[0052] As an example, initial behavioral characteristics can be obtained by combining information such as the channel type identifier, data source type identifier, user behavior type identifier, and device type identifier of the operation. The channel type identifier indicates the application channel to which the operation belongs; the data source identifier indicates the data source providing the operation; the user behavior type identifier indicates the behavior type of the operation, such as display or click; and the device type identifier indicates the type of device the user uses to perform the operation, such as computer or mobile phone.

[0053] In this embodiment of the disclosure, the frequency of occurrence refers to the number of times an operation occurs repeatedly within a predetermined historical period, which reflects the degree to which the operation occurs. The frequency of occurrence of an operation has a significant impact on the user's behavioral asset status. For example, in user X's operation, the frequency of occurrence of operation m is n1, while in user Y's operation, the frequency of occurrence of operation m is n2. Since n1 is greater than n2, it can reflect that user X has a deeper understanding of the target service or a closer level of interaction with it than user Y.

[0054] Operational behavior features constructed based on the frequency of operation occurrences and initial operational behavior characteristics can include information on the frequency of operation behavior. This allows the frequency of operation behavior to be taken into account when determining the feature distinguishability of operational behavior features, making the final determined behavioral asset status more accurate and effective.

[0055] The operational behavior features provided in this embodiment can characterize operational behaviors with different frequencies separately, that is, can determine the degree of influence of operational behaviors with different frequencies on conversion behavior.

[0056] In one optional approach of this disclosure, the operational behavior characteristics are determined based on the frequency of occurrence of the operational behavior within a predetermined historical period and based on the characteristics of the initial operational behavior, including:

[0057] Based on the frequency of occurrence of operational behaviors within a predetermined historical period, frequency sub-features are determined.

[0058] The frequency sub-features are combined with the initial operational behavior features to obtain the operational behavior features.

[0059] In this embodiment of the disclosure, corresponding frequency sub-features can be defined for different generation frequencies, and the frequency sub-features can be combined with the initial operation behavior features to obtain operation behavior features.

[0060] As an example, the initial operation behavior feature is represented as: channel type identifier + data source type identifier + user behavior type identifier + device type identifier. After combining the frequency sub-feature with the initial operation behavior feature, the operation behavior feature is represented as: channel type identifier + data source type identifier + user behavior type identifier + device type identifier + frequency sub-feature.

[0061] In this example, the initial operational behavior feature representation can be understood as classifying operational behaviors into types based on information such as channel type, data source type, user behavior type, and device type. These resulting operational behavior types are equivalent to basic operational behavior types defined based on business requirements. The initial operational behavior features are used to characterize the operational behaviors for each basic operational behavior type. The representation of operational behavior features after introducing frequency sub-features is equivalent to further classifying operational behavior types based on their frequency of occurrence, resulting in operational behavior types that can distinguish between different frequencies of occurrence. These operational behavior features are used to characterize the operational behaviors that can be distinguished between these different frequency types.

[0062] As an example, the frequency of an operation within a predetermined historical period can be divided into single occurrences and multiple occurrences. A single-frequency sub-feature can be set for the single occurrences and a multi-frequency sub-feature can be set for the multiple occurrences.

[0063] In one optional embodiment of this disclosure, the feature discriminant is a Weight of Evidence (WOE) value, and the step of determining the feature discriminant of the operational behavior feature based on the conversion behavior includes:

[0064] For any type of target operation behavior feature among the operation behaviors, positive sample features and negative sample features are determined based on the transformation behavior;

[0065] The feature discrimination of the operational behavior feature is determined based on the number of positive sample features and the number of negative sample features.

[0066] In this embodiment of the disclosure, the feature discrimination index can be the WOE value. It is understood that the feature discrimination index can also be other similar indicators, such as the Information Value (IV) index.

[0067] In this embodiment of the disclosure, the operational behavior features are representations of operational behaviors under different operational behavior types. Based on the transformation behavior, the operational behavior features of operational behaviors under each operational behavior type can be distinguished into positive sample features and negative sample features. Thus, the feature discrimination degree of operational behaviors under operational behavior types is determined based on the number of positive sample features and the number of negative sample features.

[0068] When calculating the WOE value for each type of operational behavior feature, if any type of operational behavior feature is denoted as the target operational behavior feature, the positive and negative sample features in the target operational behavior feature can be determined based on the transformation behavior. The number of positive and negative sample features can be counted, and the feature discrimination of the operational behavior feature can be determined based on the number of positive and negative sample features.

[0069] As an example, the formula for calculating the WOE value is as follows: Formula 1:

[0070]

[0071] Wherein, WOE represents the WOE value of the target operation behavior feature, p(g) represents the number of positive sample features in the target operation behavior feature, and P(b) represents the number of negative sample features in the target operation behavior feature.

[0072] In one optional embodiment of this disclosure, determining the positive and negative sample features in the target operational behavior features based on the transformation behavior includes:

[0073] Based on conversion behavior, identify positive sample users and negative sample users among the target users;

[0074] The target operation behavior features corresponding to positive sample users are identified as positive sample features, and the target operation behavior features corresponding to negative sample users are identified as negative sample features.

[0075] In this embodiment of the disclosure, users who have conversion behavior, i.e. target users who have completed the conversion, can be regarded as positive sample users, and users who have not conversion behavior, i.e. target users who have not completed the conversion, can be regarded as negative sample users.

[0076] Since positive sample users have already completed the conversion, the actions they took before completing the conversion should have a positive impact on the conversion behavior. Therefore, the behavioral characteristics of the actions taken by positive sample users can be denoted as positive sample features. Correspondingly, the behavioral characteristics of the actions taken by negative sample users can be denoted as negative sample features.

[0077] In one optional approach of this disclosure, determining positive sample users and negative sample users among the target users based on conversion behavior includes:

[0078] Identify the target conversion behavior types corresponding to each target business;

[0079] Users who complete the conversion behavior of the target conversion behavior type within the preset historical period are identified as positive sample users, and users other than positive sample users are identified as negative sample users.

[0080] In this embodiment of the disclosure, conversion behavior can be classified into different conversion behavior types according to the strength of its conversion degree.

[0081] As an example, conversion behaviors can be categorized into shallow conversions and deep conversions. Shallow conversions represent weaker conversions, while deep conversions represent stronger conversions. For instance, adding a target service to a shopping cart is a shallow conversion, while successfully purchasing and paying for the target service is a deep conversion.

[0082] Different business types have different conversion rate requirements. For example, some exposure-based businesses require a lower conversion rate. Therefore, a correlation can be established between business types and conversion behavior types to determine the target conversion behavior type for the target business. Whether or not the conversion behavior of the target conversion behavior type has been completed can be used as the basis for determining whether the conversion is successful.

[0083] For example, if the target conversion behavior type corresponding to the target business is shallow conversion, then users who have completed shallow conversion can be considered as positive sample users, and users who have not completed shallow conversion can be considered as negative sample users.

[0084] In one optional approach of this disclosure, determining the behavioral asset status of a target user based on feature discriminativeness includes:

[0085] Determine the behavioral asset status value of the target user based on feature discrimination;

[0086] The behavioral asset status of a target user is determined based on the behavioral asset status value.

[0087] In this embodiment of the disclosure, the behavioral asset status value of the target user can be calculated based on the feature discrimination. The behavioral asset status value is a numerical indicator of the behavioral asset status of the target user, and different behavioral asset statuses can be distinguished based on the behavioral asset status value.

[0088] As an example, the numerical value of feature discrimination can be directly used as the behavioral asset state value.

[0089] In one optional approach of this disclosure, the target user corresponds to at least two operational behavior characteristics, and the behavioral asset state value of the target user is determined based on feature discrimination, including:

[0090] Identify the target feature with the highest discriminant value among the feature discriminants of the operational behavior characteristics corresponding to the target user;

[0091] The behavioral asset status value of the target user is determined based on the target feature discrimination.

[0092] In this embodiment of the disclosure, the actions that a target user may perform may correspond to multiple action types, each with different feature discrimination levels. Since a higher feature discrimination level indicates a higher degree of influence on conversion behavior, the highest feature discrimination level among the feature discrimination levels of the action characteristics corresponding to the target user can be determined as the target feature discrimination level, and then the asset status can be determined based on the target feature discrimination level.

[0093] In one optional approach of this disclosure, determining the behavioral asset state of a target user based on behavioral asset state values ​​includes:

[0094] Based on the pre-defined correspondence between asset status values ​​and behavioral asset status, and based on the behavioral asset status values ​​of the target user, the behavioral asset status of the target user is determined.

[0095] In this embodiment of the disclosure, the correspondence between asset status values ​​and behavioral asset status can be preset. As an example, different ranges of asset status values ​​corresponding to different behavioral asset statuses can be preset. When the behavioral asset status value of a target user belongs to the range of asset status values ​​corresponding to a certain behavioral asset status, the behavioral asset status can be taken as the behavioral asset status of the target user.

[0096] In one alternative embodiment of this disclosure, after determining the behavioral asset status of the target user based on feature discriminativeness, the method further includes at least one of the following:

[0097] Determine service promotion strategies for target users based on the status of behavioral assets;

[0098] The effectiveness of promoting the target service within a predetermined historical period is determined based on the status of behavioral assets.

[0099] In this embodiment of the disclosure, subsequent marketing processing can be based on behavioral asset states. Specifically, service promotion strategies for target users can be determined based on behavioral asset states. For example, a behavioral asset state of "deep interaction" indicates that users have a deep understanding of the target service, and promotion to these users will achieve better results. Therefore, when promoting services, the target service can be prioritized for promotion to users with a behavioral asset state of "deep interaction."

[0100] In this embodiment of the disclosure, the promotion effect of the target service within a predetermined historical period can be determined based on the status of behavioral assets. Specifically, if the target service is promoted within the predetermined historical period, the behavioral asset status of the target user before the predetermined historical period and the behavioral asset status of the target user after the predetermined historical period can be obtained. The changes in the behavioral asset status of the target user before and after the predetermined historical period can be judged to measure the promotion effect of the target service.

[0101] In one optional embodiment of this disclosure, before obtaining the target user's operational and conversion behaviors towards the target service within a predetermined historical time period, the method further includes:

[0102] Acquire target users' channel sub-operation behavior and channel sub-conversion behavior across various application channels;

[0103] Operational behaviors are determined based on the sub-operational behaviors of each channel, and conversion behaviors are determined based on the sub-conversion behaviors of each channel.

[0104] In this embodiment of the disclosure, behavioral data from different application channels can be integrated to ensure comprehensive analysis of user behavior data. For example, a universal user identifier can be set, and operational and conversion behaviors from different application channels can be associated with the universal user identifier, thereby achieving integration of behavioral data from different application channels.

[0105] As an example, after determining the target user's behavioral asset status, this status can be verified. This solution provides two verification methods: static verification and dynamic verification.

[0106] Static verification involves setting a fixed period and observing the actual conversion rate of target users corresponding to each behavioral asset state within that period. If the actual conversion rate matches the pattern shown by the asset state, the verification is considered successful. For example, users with deep interaction have a higher conversion rate than users with shallow interaction.

[0107] Dynamic verification involves accumulating daily behavioral assets based on the behavioral assets of the first day, and observing the actual conversion of target users corresponding to each behavioral asset status after each accumulation, until a preset number of days has been accumulated.

[0108] As an example, Figure 2 The diagram shows a flowchart of a specific implementation of the behavioral asset status determination method provided in this disclosure.

[0109] like Figure 2 As shown, data access refers to accessing behavioral data from different application channels. Behavioral data refers to operational behavior data. Conversion data refers to conversion behavior data. ID integration refers to the integration of behavioral data from different application channels.

[0110] Sample partitioning refers to dividing positive sample features into negative sample features.

[0111] Feature design refers to determining operational behavior features based on initial operational behavior features and their frequency of occurrence.

[0112] Feature selection, that is, based on conversion behavior, calculates the feature discrimination of each operational behavior feature.

[0113] State hierarchy, which is to determine the state of behavioral assets based on feature distinguishability.

[0114] The intermediate role is to select the corresponding target conversion behavior type for different target businesses, to distinguish them by calculating features, and to determine the status of behavior assets.

[0115] Data verification refers to verifying the accuracy of the behavioral asset status after it has been determined.

[0116] Based on and Figure 1 The method shown follows the same principle. Figure 3 A schematic diagram of the structure of a behavioral asset status determination device provided in an embodiment of this disclosure is shown, such as... Figure 3 As shown, the asset status determination device 30 may include:

[0117] The behavior acquisition module 310 is used to acquire the target user's operation behavior and conversion behavior towards the target service within a predetermined historical time period;

[0118] The operation behavior feature determination module 320 is used to determine the operation behavior features, which are used to characterize the operation behavior.

[0119] Feature discrimination determination module 330 is used to determine the feature discrimination of operational behavior features based on conversion behavior;

[0120] The behavioral asset status determination module 340 is used to determine the behavioral asset status of the target user based on feature discrimination.

[0121] The apparatus provided in this embodiment acquires the operational and conversion behaviors of a target user towards a target service within a predetermined historical time period; determines operational behavior features to represent the operational behaviors; determines the feature distinguishability of the operational behavior features based on the conversion behaviors; and determines the behavioral asset status of the target user based on the feature distinguishability. This solution can effectively and accurately determine the user's behavioral asset status based on the feature distinguishability of the operational behavior features, ensuring the processing effectiveness of related processing based on the behavioral asset status.

[0122] Optionally, the operation behavior feature determination module is specifically used for:

[0123] Based on the behavioral data of operational behavior, the initial operational behavior characteristics are determined, which are used to characterize a single operational behavior.

[0124] Based on the frequency of operation behavior within a predetermined historical period, and based on the characteristics of the initial operation behavior, the characteristics of the operation behavior are determined.

[0125] Determine the behavioral asset status of the target user based on operational behavior characteristics.

[0126] Optionally, when the operation behavior feature determination module determines operation behavior features based on the frequency of operation behavior within a predetermined historical period and based on initial operation behavior features, it is specifically used for:

[0127] Based on the frequency of occurrence of operational behaviors within a predetermined historical period, frequency sub-features are determined.

[0128] The frequency sub-features are combined with the initial operational behavior features to obtain the operational behavior features.

[0129] Optionally, the feature discriminant is the WOE value, and the feature discriminant determination module is specifically used for:

[0130] For any type of target operational behavior feature in the operational behavior, determine the positive sample features and negative sample features in the target operational behavior feature based on the transformation behavior;

[0131] The feature discrimination of the target operation behavior features is determined based on the number of positive sample features and the number of negative sample features.

[0132] Optionally, the feature discrimination determination module is specifically used to determine the positive and negative sample features in the target operation behavior features based on the transformation behavior:

[0133] Based on conversion behavior, identify positive sample users and negative sample users among the target users;

[0134] The target operation behavior features corresponding to positive sample users are identified as positive sample features, and the target operation behavior features corresponding to negative sample users are identified as negative sample features.

[0135] Optionally, the feature discrimination determination module is specifically used to determine positive sample users and negative sample users among the target users based on conversion behavior:

[0136] Identify the target conversion behavior types corresponding to each target business;

[0137] Users who complete the conversion behavior of the target conversion behavior type within the preset historical period are identified as positive sample users, and users other than positive sample users are identified as negative sample users.

[0138] Optionally, the behavioral asset status determination module is specifically used for:

[0139] Determine the behavioral asset status value of the target user based on feature discrimination;

[0140] The behavioral asset status of a target user is determined based on the behavioral asset status value.

[0141] Optionally, the target user corresponds to at least two operational behavior characteristics. When determining the target user's behavioral asset state value based on feature discrimination, the behavioral asset state determination module is specifically used for:

[0142] Identify the target feature with the highest discriminant value among the feature discriminants of the operational behavior characteristics corresponding to the target user;

[0143] The behavioral asset status value of the target user is determined based on the target feature discrimination.

[0144] Optionally, when determining the behavioral asset status of a target user based on the behavioral asset status value, the behavioral asset status determination module is specifically used for:

[0145] Based on the pre-defined correspondence between asset status values ​​and behavioral asset status, and based on the behavioral asset status values ​​of the target user, the behavioral asset status of the target user is determined.

[0146] Optionally, the above apparatus further includes a behavior asset status application module, which is used to perform at least one of the following after determining the behavior asset status of the target user based on feature discrimination:

[0147] Determine service promotion strategies for target users based on the status of behavioral assets;

[0148] The effectiveness of promoting the target service within a predetermined historical period is determined based on the status of behavioral assets.

[0149] Optionally, the device further includes a channel behavior data processing module, used for:

[0150] Before acquiring the target user's operational and conversion behaviors towards the target service within a predetermined historical time period, acquire the target user's channel sub-operational and channel sub-conversion behaviors across various application channels.

[0151] Operational behaviors are determined based on the sub-operational behaviors of each channel, and conversion behaviors are determined based on the sub-conversion behaviors of each channel.

[0152] It is understood that the above-described modules of the behavioral asset status determination device in this embodiment of the present disclosure have the ability to implement... Figure 1 The embodiments shown illustrate the functions of corresponding steps in the behavioral asset state determination method. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the aforementioned functions. These modules can be software and / or hardware, and each module can be implemented individually or integrated from multiple modules. For a detailed description of the functions of each module in the aforementioned behavioral asset state determination device, please refer to [link to relevant documentation]. Figure 1 The corresponding description of the behavior asset status determination method in the embodiments shown will not be repeated here.

[0153] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0154] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0155] The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the behavioral asset state determination method as provided in the embodiments of this disclosure.

[0156] Compared with existing technologies, this electronic device acquires the target user's operational and conversion behaviors towards the target service within a predetermined historical period; determines operational behavior characteristics to represent these behaviors; determines the feature discrimination of these operational behavior characteristics based on conversion behaviors; and determines the target user's behavioral asset status based on the feature discrimination. This solution can effectively and accurately determine the user's behavioral asset status based on the feature discrimination of operational behavior characteristics, ensuring the effectiveness of related processing based on the behavioral asset status.

[0157] The readable storage medium is a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform a behavioral asset state determination method as provided in the embodiments of this disclosure.

[0158] Compared with existing technologies, this readable storage medium obtains the target user's operational and conversion behaviors towards the target service within a predetermined historical period; determines the operational behavior characteristics used to represent the operational behaviors; determines the feature discrimination of the operational behavior characteristics based on the conversion behaviors; and determines the target user's behavioral asset status based on the feature discrimination. In this solution, the user's behavioral asset status can be effectively and accurately determined based on the feature discrimination of the operational behavior characteristics, ensuring the processing effectiveness of related processing based on the behavioral asset status.

[0159] The computer program product includes a computer program that, when executed by a processor, implements the behavioral asset state determination method as provided in the embodiments of this disclosure.

[0160] Compared with existing technologies, this computer program product obtains the target user's operational and conversion behaviors towards the target service within a predetermined historical period; determines the operational behavior characteristics used to represent the operational behaviors; determines the feature discrimination of the operational behavior characteristics based on the conversion behaviors; and determines the target user's behavioral asset status based on the feature discrimination. In this solution, the user's behavioral asset status can be effectively and accurately determined based on the feature discrimination of the operational behavior characteristics, ensuring the processing effectiveness of related processing based on the behavioral asset status.

[0161] Figure 4 A schematic block diagram of an example electronic device 40 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0162] like Figure 4 As shown, the electronic device 40 includes a computing unit 410, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 420 or a computer program loaded from a storage unit 480 into a random access memory (RAM) 430. The RAM 430 may also store various programs and data required for the operation of the device 40. The computing unit 410, ROM 420, and RAM 430 are interconnected via a bus 440. An input / output (I / O) interface 450 is also connected to the bus 440.

[0163] Multiple components in device 40 are connected to I / O interface 450, including: input unit 460, such as keyboard, mouse, etc.; output unit 470, such as various types of monitors, speakers, etc.; storage unit 480, such as disk, optical disk, etc.; and communication unit 490, such as network card, modem, wireless transceiver, etc. Communication unit 490 allows device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0164] The computing unit 410 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 410 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 410 executes the behavioral asset state determination method provided in the embodiments of this disclosure. For example, in some embodiments, executing the behavioral asset state determination method provided in the embodiments of this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 480. In some embodiments, part or all of the computer program can be loaded and / or installed on device 40 via ROM 420 and / or communication unit 490. When the computer program is loaded into RAM 430 and executed by the computing unit 410, one or more steps of the behavioral asset state determination method provided in the embodiments of this disclosure can be performed. Alternatively, in other embodiments, the computing unit 410 can be configured to execute the behavioral asset state determination method provided in the embodiments of this disclosure by any other suitable means (e.g., by means of firmware).

[0165] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0167] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, or any suitable combination of the foregoing.

[0168] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0169] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0170] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0171] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0172] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining the status of behavioral assets, comprising: Acquire target users' channel-specific operational behaviors and channel-specific conversion behaviors towards the target service across various application channels; Based on the sub-operation behaviors of each channel, determine the target user's operation behavior on the target service within a predetermined historical period, and based on the conversion behavior of each channel, determine the target user's conversion behavior on the target service within a predetermined historical period; Based on the behavioral data of the operation behavior, an initial operation behavior feature is determined, which is used to characterize a single operation behavior. Based on the frequency of the operation behavior within the predetermined historical time period, a frequency sub-feature is determined; The frequency sub-feature is combined with the initial operation behavior feature to obtain the operation behavior feature; the operation behavior feature is used to characterize the operation behavior. Determine the feature distinguishability of the operational behavior features based on the transformation behavior and the operational behavior features; The behavioral asset status of the target user is determined based on the feature discrimination. The behavioral asset status is used to measure the depth of a target user's understanding of the target service or the level of interaction.

2. The method according to claim 1, wherein, The feature discriminant is the Weight of Evidence (WOE) value. Determining the feature discriminant of the operational behavior feature based on the conversion behavior and the operational behavior feature includes: For any type of target operation behavior feature among the operation behaviors, positive sample features and negative sample features are determined based on the transformation behavior; The feature discrimination of the target operation behavior feature is determined based on the number of positive sample features and the number of negative sample features.

3. The method according to claim 2, wherein, The step of determining the positive and negative sample features in the target operation behavior features based on the transformation behavior includes: Based on the conversion behavior, positive sample users and negative sample users among the target users are identified; The target operation behavior features corresponding to the positive sample users are determined as positive sample features, and the target operation behavior features corresponding to the negative sample users are determined as negative sample features.

4. The method according to claim 3, wherein, The step of determining positive sample users and negative sample users among the target users based on the conversion behavior includes: Identify the target conversion behavior types corresponding to each target business; The target users who completed the conversion behavior of the target conversion behavior type within a preset historical period are identified as positive sample users, and the users other than the positive sample users are identified as negative sample users.

5. The method according to claim 1, wherein, Determining the behavioral asset status of the target user based on the feature discrimination includes: The behavioral asset status value of the target user is determined based on the feature discrimination. The behavioral asset status of the target user is determined based on the behavioral asset status value.

6. The method according to claim 5, wherein, The target user corresponds to at least two of the aforementioned operational behavior features, and the determination of the target user's behavioral asset state value based on the feature discrimination includes: Determine the target feature discriminant with the highest value among the feature discriminants of the operational behavior features corresponding to the target user; The behavioral asset status value of the target user is determined based on the target feature discrimination.

7. The method according to claim 5, wherein, Determining the target user's behavioral asset status based on the behavioral asset status value includes: Based on the preset correspondence between asset status values ​​and behavioral asset status, and based on the behavioral asset status values ​​of the target user, the behavioral asset status of the target user is determined.

8. The method of claim 1, after determining the behavioral asset state of the target user based on the feature distinguishability, the method further comprises at least one of the following: Determine the service promotion strategy for the target user based on the status of the behavioral assets; The promotional effect on the target service within the predetermined historical period is determined based on the status of the behavioral assets.

9. A device for determining the status of a behavioral asset, comprising: The behavior acquisition module is used to acquire the target user's channel sub-operation behavior and channel sub-conversion behavior for the target service under various application channels; Based on the sub-operation behaviors of each channel, determine the target user's operation behavior on the target service within a predetermined historical period, and based on the conversion behavior of each channel, determine the target user's conversion behavior on the target service within a predetermined historical period; An operation behavior feature determination module is used to determine initial operation behavior features based on the behavior data of the operation behavior, wherein the initial operation behavior features are used to characterize a single operation behavior. Based on the frequency of the operation behavior within the predetermined historical time period, a frequency sub-feature is determined; The frequency sub-feature is combined with the initial operation behavior feature to obtain the operation behavior feature; the operation behavior feature is used to characterize the operation behavior. The feature discrimination determination module is used to determine the feature discrimination of the operation behavior features based on the conversion behavior and the operation behavior features. ； A behavior asset status determination module is used to determine the behavior asset status of the target user based on the feature discrimination. The behavioral asset status is used to measure the depth of a target user's understanding of the target service or the level of interaction.

10. The apparatus according to claim 9, wherein, The feature discriminant is the Weight of Evidence (WOE) value, and the feature discriminant determination module is specifically used for: For any type of target operation behavior feature among the operation behaviors, positive sample features and negative sample features are determined based on the transformation behavior; The feature discrimination of the target operation behavior feature is determined based on the number of positive sample features and the number of negative sample features.

11. The apparatus according to claim 10, wherein, The feature discrimination determination module is specifically used to determine the positive and negative sample features in the target operation behavior features based on the transformation behavior: Based on the conversion behavior, positive sample users and negative sample users among the target users are identified; The target operation behavior features corresponding to the positive sample users are determined as positive sample features, and the target operation behavior features corresponding to the negative sample users are determined as negative sample features.

12. The apparatus according to claim 11, wherein, The feature discrimination determination module, when determining positive sample users and negative sample users among the target users based on the conversion behavior, is specifically used for: Identify the target conversion behavior types corresponding to each target business; The target users who completed the conversion behavior of the target conversion behavior type within a preset historical period are identified as positive sample users, and the users other than the positive sample users are identified as negative sample users.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-8.

Images