A method and apparatus for processing user data

Abstract

The application discloses a user data processing method and device, the method comprises: acquiring the behavior data of multiple types of users, the multiple types of users are divided based on a business label, the behavior data of a user comprises multiple behavior events and time sequence identifiers of the multiple behavior events; determining time sequence association rules corresponding to the multiple types of users based on the behavior events and the time sequence identifiers of the behavior events included in the behavior data of the multiple types of users; determining a time sequence behavior rule of a target type of user in the multiple types of users based on a first time sequence association rule corresponding to the target type of user and a second time sequence association rule corresponding to a non-target type of user; and determining whether a user to be identified belongs to the target type of user based on the time sequence behavior rule of the target type of user.

Description

[0001] This document is a divisional application of the patent application with application number "201910400073.2", application date "May 14, 2019", and application title "A method and apparatus for processing user data". Technical Field

[0002] This application relates to the field of data processing, and more particularly to a method and apparatus for processing user data. Background Technology

[0003] In existing technologies, user behavior data needs to be analyzed in many application scenarios for decision-making. For example, in risk identification scenarios, the behavior data of high-risk users and users to be identified can be analyzed to determine whether the user to be identified is a high-risk user based on the analysis results.

[0004] Typically, when analyzing user behavior data, we can analyze whether a user has performed certain behaviors or the frequency of those behaviors. However, in practice, this data analysis method is usually quite simple and cannot fully mine user behavior data, leading to difficulties in making effective decisions. Summary of the Invention

[0005] This application provides a user data processing method and apparatus to solve the problem in the prior art that the inability to fully mine user behavior data leads to the inability to effectively make decisions.

[0006] To solve the above-mentioned technical problems, the embodiments of this application are implemented as follows:

[0007] Firstly, a method for processing user data is proposed, including:

[0008] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0009] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0010] Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the temporal behavior rule of the target class user is determined.

[0011] Based on the temporal behavior rules of the target user group, determine whether the user to be identified belongs to the target user group.

[0012] Secondly, a user data processing apparatus is proposed, comprising:

[0013] The acquisition unit acquires behavioral data of multiple types of users, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0014] The processing unit determines the time-series association rules corresponding to the multiple types of users based on the behavioral events and their time-series identifiers included in the behavioral data of the multiple types of users.

[0015] The determining unit determines the temporal behavior rules of the target user based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user among the multiple user types.

[0016] The identification unit determines whether the user to be identified belongs to the target class of users based on the temporal behavior rules of the target class of users.

[0017] Thirdly, an electronic device is proposed, comprising:

[0018] Processor; and

[0019] Memory configured to store computer-executable instructions that, when executed, cause the processor to perform the following operations:

[0020] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0021] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0022] Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the temporal behavior rule of the target class user is determined.

[0023] Based on the temporal behavior rules of the target user group, determine whether the user to be identified belongs to the target user group.

[0024] Fourthly, a computer-readable storage medium is provided that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the following methods:

[0025] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0026] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0027] Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the temporal behavior rule of the target class user is determined.

[0028] Based on the temporal behavior rules of the target user group, determine whether the user to be identified belongs to the target user group.

[0029] Fifthly, a user data processing method is proposed, including:

[0030] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0031] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0032] Based on the time-series association rules corresponding to the multiple types of users, the time-series behavior rules of the multiple types of users are determined;

[0033] Based on the temporal behavior rules of the aforementioned multiple user types, multiple temporal behavior rule features are generated;

[0034] Based on the aforementioned multiple temporal behavior rule features, the temporal behavior features of the user to be processed are determined, so as to generate sample data including the temporal behavior features for model training.

[0035] Sixthly, a user data processing apparatus is proposed, comprising:

[0036] The acquisition unit acquires behavioral data of multiple types of users, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0037] The processing unit determines the time-series association rules corresponding to the multiple types of users based on the behavioral events and their time-series identifiers included in the behavioral data of the multiple types of users.

[0038] The first determining unit determines the temporal behavior rules of the multiple types of users based on the temporal association rules corresponding to the multiple types of users;

[0039] The generation unit generates multiple time-series behavior rule features based on the time-series behavior rules of the multiple types of users;

[0040] The second determining unit determines the temporal behavior features of the user to be processed based on the multiple temporal behavior rule features, so as to generate sample data including the temporal behavior features for model training.

[0041] Seventhly, an electronic device is proposed, comprising:

[0042] Processor; and

[0043] Memory configured to store computer-executable instructions that, when executed, cause the processor to perform the following operations:

[0044] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0045] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0046] Based on the time-series association rules corresponding to the multiple types of users, the time-series behavior rules of the multiple types of users are determined;

[0047] Based on the temporal behavior rules of the aforementioned multiple user types, multiple temporal behavior rule features are generated;

[0048] Based on the aforementioned multiple temporal behavior rule features, the temporal behavior features of the user to be processed are determined, so as to generate sample data including the temporal behavior features for model training.

[0049] Eighthly, a computer-readable storage medium is provided that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the following methods:

[0050] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0051] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0052] Based on the time-series association rules corresponding to the multiple types of users, the time-series behavior rules of the multiple types of users are determined;

[0053] Based on the temporal behavior rules of the aforementioned multiple user types, multiple temporal behavior rule features are generated;

[0054] Based on the aforementioned multiple temporal behavior rule features, the temporal behavior features of the user to be processed are determined, so as to generate sample data including the temporal behavior features for model training.

[0055] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0056] The technical solution provided in this application, when analyzing user behavior data, fully considers the temporal identifiers of behavioral events included in the behavior data, thus enabling comprehensive mining of user behavior data. When analyzing the behavior data of multiple types of users, it can fully mine the behavior data of multiple types of users to obtain temporal association rules that reflect the temporal sequence of behaviors of multiple types of users, thereby obtaining temporal behavior rules for the target type of users. Therefore, when making decisions based on the temporal behavior rules of the target type of users, effective decision-making can be carried out. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating a user data processing method according to an embodiment of this application;

[0059] Figure 2 This is a flowchart illustrating a user data processing method according to an embodiment of this application;

[0060] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application;

[0061] Figure 4 This is a schematic diagram of the structure of a user data processing apparatus according to an embodiment of this application;

[0062] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application;

[0063] Figure 6 This is a schematic diagram of the structure of a user data processing device according to an embodiment of this application. Detailed Implementation

[0064] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0065] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0066] Figure 1 This is a schematic flowchart illustrating a user data processing method according to an embodiment of this application. The user data processing method is described below.

[0067] S102: Obtain behavioral data from multiple user groups.

[0068] In S102, multiple user categories can be obtained based on business tags. Business tags can be determined based on specific application scenarios. For example, in a risk identification scenario, business tags can include high risk and low risk, or high risk, medium risk and low risk; in a marketing scenario, business tags can include target users and non-target users.

[0069] Behavioral data for multiple user groups can be behavioral data for multiple user groups within a set time period. This set time period can be determined according to actual needs and is not specifically limited here.

[0070] This embodiment may include the following steps when acquiring behavioral data from multiple types of users:

[0071] First, obtain behavioral data from multiple users with different business tags.

[0072] Taking a user as an example, when acquiring a user's behavior data, the user's behavior data may include multiple behavior events and the time sequence identifiers of these multiple behavior events. The time sequence identifiers of the behavior events can represent the order in which the behavior events occur.

[0073] For example, user A's behavioral events within a certain time period include event 1, event 2, event 3, event 4, and event 5. The time sequence identifiers of events 1 to 5 are 2, 4, 1, 3, and 5, respectively. Therefore, the order in which events 1 to 5 occur is: event 3, event 1, event 4, event 2, and event 5.

[0074] It should be noted that among the behavioral data of multiple users, the behavioral events included in the behavioral data of different users may be the same or different. The time sequence identifier of the same behavioral event in the behavioral data of different users may be the same or different. The number of times the same behavioral event appears in the behavioral data of a user may be once or multiple times. There are no specific limitations here.

[0075] Secondly, the behavioral data of multiple users are grouped according to business tags to obtain behavioral data of multiple user categories.

[0076] When grouping, the behavioral data of users with the same business tags can be grouped together to obtain the behavioral data of one type of user. In this way, based on multiple different business tags, behavioral data of multiple types of users can be obtained.

[0077] For example, in a risk identification scenario, the behavioral data of high-risk users can be grouped into one group and the behavioral data of low-risk users into another group based on the business labels of high risk and low risk, thus obtaining behavioral data of two types of users.

[0078] After obtaining behavioral data from multiple user groups, S104 can be executed.

[0079] S104: Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple types of users, determine the temporal association rules corresponding to the multiple types of users.

[0080] In S104, when determining the time-series association rules corresponding to multiple user types, taking one user type as an example, the following steps may be included:

[0081] First, based on the behavioral events included in the behavioral data of a class of users, frequent itemsets are identified.

[0082] In this embodiment, the number of frequent itemsets can be multiple. When determining frequent itemsets, the following principles can be followed:

[0083] A behavioral event that occurs once or multiple times in a user's behavioral data is counted as one occurrence. A frequent itemset includes at least one behavioral event that occurs in at least one user's behavioral data.

[0084] Secondly, based on frequent itemsets and the temporal identifiers of the behavioral events included in the frequent itemsets, temporal association rules corresponding to a class of users are determined.

[0085] Specifically, taking one frequent itemset as an example, when determining the temporal association rule, the user corresponding to the frequent itemset can be identified. The user corresponding to the frequent itemset can be understood as a user whose behavioral data includes behavioral events from the frequent itemset. After obtaining the user corresponding to the frequent itemset, the temporal association rule corresponding to the frequent itemset can be obtained based on the temporal identifier of the behavioral events in the frequent itemset in the behavioral data of the user corresponding to the frequent itemset.

[0086] After obtaining the temporal association rule corresponding to a frequent itemset, the same method can be used to obtain the temporal association rules corresponding to multiple frequent itemsets. The temporal association rules corresponding to multiple frequent itemsets constitute the temporal association rules corresponding to a class of users.

[0087] To make it easier to understand, the following example uses three users in one user category.

[0088] Suppose a user group includes three users, A, B, and C. The behavioral events and their time sequence identifiers in the behavioral data of users A, B, and C are shown in Table 1.

[0089] Table 1

[0090] A 1 1 A 2 2 A 3 3 A 4 4 B 1 1 B 2 2 B 3 3 B 4 4 C 1 1 C 3 2 C 5 3

[0091] When determining the time-series association rules for users A, B, and C, firstly, based on the behavioral events of users A, B, and C in Table 1, the following frequent itemsets can be obtained:

[0092] (1), (2), (3), (4), (5), (1,2), (1,3), (1,4), (1,5), (2,3), (2,4), (3,4), (3,5), (1,2,3), (1,2,4), (1,3,4), (1,3,5), (2,3,4), (1,2,3,4).

[0093] Secondly, taking one of the frequent itemsets (1, 2) as an example, we can determine that the users corresponding to the frequent itemset are user A and user B. Based on the temporal identifiers of events 1 and 2 in the behavioral data of user A and user B, we can obtain the temporal association rule 1→2 (→ can also be represented in other ways) corresponding to the frequent itemset (1, 2).

[0094] For other frequent itemsets, the same method can be used to obtain the corresponding temporal association rules, and then the temporal association rules for users A, B, and C can be obtained:

[0095] 1, 2, 3, 4, 5, 1→2, 1→3, 1→4, 1→5, 2→3, 2→4, 3→4, 3→5, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4.

[0096] Optionally, in the process of determining the temporal association rules described above, after obtaining multiple frequent itemsets, the multiple frequent itemsets can be filtered to remove frequent itemsets with a length less than or equal to a preset threshold. The length of a frequent itemset can be understood as the number of behavioral events included in the frequent itemset, and the preset threshold can be determined according to actual needs.

[0097] After filtering multiple frequent itemsets, time-series association rules can be obtained based on the filtered frequent itemsets and the time sequence identifiers of the behavioral events included in the filtered frequent itemsets.

[0098] Taking the three users A, B, and C mentioned above as examples, after obtaining multiple frequent itemsets, we can filter out frequent itemsets with a length of 1 from these frequent itemsets, obtaining frequent itemsets with a length equal to or greater than 2. Based on these frequent itemsets and the temporal identifiers of the behavioral events included in these frequent itemsets, we can obtain the following temporal association rules:

[0099] 1→2, 1→3, 1→4, 1→5, 2→3, 2→4, 3→4, 3→5, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4.

[0100] After obtaining the temporal association rules for one type of user based on the method described above, the temporal association rules for other types of users can be obtained using the same method.

[0101] After obtaining the time-series association rules corresponding to multiple types of users, S106 can be executed.

[0102] S106: Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, determine the temporal behavior rule of the target class user.

[0103] In S106, target users can be understood as a type of user among multiple user types whose temporal behavior rules need to be determined, while non-target users can be understood as other user types besides target users. To facilitate the distinction between the temporal association rules corresponding to different user types, the temporal association rule corresponding to the target user type can be represented as the first temporal association rule, and the temporal association rule corresponding to the non-target user type can be represented as the second temporal association rule.

[0104] In this embodiment, the temporal behavior rules corresponding to the target user class can be understood as the temporal rules that the target user class's behavioral events satisfy. Determining the temporal behavior rules for the target user class may include the following steps:

[0105] Based on the first temporal association rule and the second temporal association rule, the target temporal association rule in the first temporal association rule is determined.

[0106] Based on the target time-series association rules, determine the time-series behavior rules of target class users.

[0107] When determining the target time-series association rule, at least the following three methods can be used:

[0108] The first method:

[0109] The temporal association rules in the first temporal association rule that do not belong to the second temporal association rule are taken as the target temporal association rules.

[0110] For example, suppose the first temporal association rule is: 1→2, 1→3, 1→4, 1→5, 2→3, 2→4, 3→4, 3→5, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4, and the second temporal association rule is: 1→3, 1→4, 1→5, 3→4, 3→5, 4→5, 3→4→5, 1→3→4→5. Then, the following rules from the first temporal association rule that do not belong to the second temporal association rule can be used as the target temporal association rule: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4.

[0111] The second method:

[0112] Identify identical temporal association rules among the first and second temporal association rules; determine the first confidence level of the identical temporal association rule among target users and the second confidence level among non-target users; identify the temporal association rule among the identical temporal association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target temporal association rule.

[0113] In this embodiment, the first confidence level and the second confidence level can be determined using the same method. The first confidence level can be the probability that a behavioral event corresponding to a time-series association rule occurs in the behavioral data of the target class of users. The probability of a behavioral event occurring in the behavioral data of the target class of users can be defined as the ratio of the number of times the behavioral event occurs in the behavioral data of the target class of users to the total number of users in the target class.

[0114] For example, for a temporal association rule 1→2→3 for users A, B, and C recorded above, the corresponding behavioral events are event 1, event 2, and event 3. According to Table 1, events 1, 2, and 3 appear twice in the behavioral data of users A, B, and C, and the total number of users is 3. Therefore, the probability of events 1, 2, and 3 appearing is 0.67. 0.67 can be regarded as the first confidence level of the temporal association rule 1→2→3.

[0115] Furthermore, the first confidence level can also be the conditional probability of the behavioral events corresponding to the temporal association rule appearing in the behavioral data of the target class of users. Taking the temporal association rule a→b→c as an example, the conditional probability of the behavioral events a, b, and c corresponding to the temporal association rule a→b→c appearing in the behavioral data of the target class of users can be defined as the ratio of the probability of behavioral events a, b, and c appearing in the behavioral data of the target class of users to the probability of behavioral events a and b appearing in the behavioral data of the target class of users.

[0116] For example, for the temporal association rule 1→2→3 for users A, B, and C recorded above, the corresponding behavioral events are event 1, event 2, and event 3. According to Table 1, the probability of occurrence of event 1, event 2, and event 3 is 0.67, and the probability of occurrence of event 1 and event 2 is 0.67. Therefore, the conditional probability of occurrence of event 1, event 2, and event 3 is 1. 1 can be regarded as the first confidence level of temporal association rule 1→2→3.

[0117] After obtaining the first and second confidence levels of the temporal association rule using the methods described above, the target temporal association rule can be determined using the second method. For ease of understanding, examples can be provided when determining the target temporal association rule.

[0118] Assume the first temporal association rule and the first confidence level are: 1→2 (0.67), 1→3 (1), 1→4 (0.67), 1→5 (0.33), 2→3 (0.67), 2→4 (0.67), 3→4 (0.67), 3→5 (0.33), 1→2→3 (0.67), 1→2→4 (0.67), 1→3→4 (0.67) , 1→3→5(0.33), 2→3→4(0.67), 1→2→3→4(0.67), the second temporal association rule and the second confidence level are: 1→3(0.5), 1→4(0.5), 1→5(0.5), 3→4(0.5), 3→5(0.5), 4→5(1), 3→4→5(0.5), 1→3→4→5(0.5).

[0119] Therefore, the identical temporal association rules for both target and non-target users are 1→3, 1→4, 1→5, 3→4, and 3→5. The ratios of the first and second confidence levels of these temporal association rules are 2, 1.33, 0.67, 1.33, and 0.67, respectively. Assuming a threshold of 1 is set, then 1→3, 1→4, and 3→4 can be used as target temporal association rules.

[0120] The third method:

[0121] The combination of the target temporal association rules obtained by the first and second methods described above is taken as the target temporal association rule. The specific implementation method will not be described in detail here.

[0122] It should be noted that, in practical applications, any of the three methods described above can be selected to determine the target temporal association rule. Preferably, if there is a temporal association rule in the first temporal association rule that does not belong to the second temporal association rule, then the first or third method can be selected to determine the target temporal association rule; otherwise, the second method can be selected to determine the target temporal association rule.

[0123] After obtaining the target temporal association rules based on the methods described above, the temporal behavior rules of the target class of users can be determined based on the target temporal association rules.

[0124] When determining the temporal behavior rules for target users, one approach is to directly use the target temporal association rules as the corresponding temporal behavior rules for the target users. For example, if the target temporal associations are: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4, then the temporal behavior rules for the target users are: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4.

[0125] Another approach is to use the target time-series association rules with a credibility of not less than a set credibility threshold as the time-series behavior rules for the target user class.

[0126] For example, if the target temporal association is: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4, with confidence levels of 0.67, 0.67, 0.67, 0.67, 0.67, 0.67, 0.33, 0.67, 0.67, and assuming a confidence threshold of 0.5, then the temporal behavior rules for the target user class could be: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 2→3→4, 1→2→3→4.

[0127] In this embodiment, any of the above implementation methods can be selected to determine the temporal behavior rules of the target user class; no specific limitation is made here.

[0128] After obtaining the time-series behavior rules for the target user group, S108 can be executed.

[0129] S108: Based on the temporal behavior rules of the target class users, determine whether the user to be identified belongs to the target class users.

[0130] The user to be identified can be understood as a user without a business tag. When determining whether the user to be identified belongs to the target class of users based on the time-series behavior rules of the target class of users, the following steps may be included:

[0131] First, acquire the behavioral data of the user to be identified.

[0132] The behavioral data of the user to be identified may include multiple behavioral events of the user within a set time period, as well as the time sequence identifiers of these multiple behavioral events.

[0133] Secondly, based on the behavioral events and their temporal identifiers included in the behavioral data of the user to be identified, the temporal association rules for the user to be identified are determined.

[0134] When determining the temporal association rules for the user to be identified, the specific implementation method can be found in the above-described content on determining the temporal association rules corresponding to a type of user, which will not be repeated here.

[0135] Finally, determine whether the temporal association rule of the user to be identified matches the temporal behavior rule of the target user. If yes, the user to be identified belongs to the target user; otherwise, the user to be identified belongs to a non-target user.

[0136] For example, given the sequential behavior rules of the target class users as: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 2→3→4, 1→2→3→4, then:

[0137] Suppose the temporal association rules for the user to be identified are: 3→4, 1→2→3, 1→2→4, 1→3→4. By comparison, it can be seen that the temporal association rules 1→2→3, 1→2→4 and 1→3→4 for the user to be identified match the temporal behavior rules 1→2→3, 1→2→4 and 1→3→4 for the target user. Therefore, it can be determined that the user to be identified belongs to the target user.

[0138] Suppose the temporal association rules for the user to be identified are: 4→5, 2→3→5, 2→4→5, 3→4→5. By comparison, it can be seen that none of the temporal association rules for the user to be identified match any of the temporal behavior rules for the target user. Therefore, it can be determined that the user to be identified does not belong to the target user.

[0139] In this embodiment, after determining that the user to be identified belongs to the target class of users, further processing can be carried out on the user to be identified based on the application scenario.

[0140] For example, in a risk identification scenario, if it is determined that user A is a high-risk user, user A can be directly blocked from accessing secure pages or conducting online transactions; if it is determined that user A is a low-risk user, user A can be directly granted access, allowing user A to access secure pages or conduct online transactions.

[0141] In this way, in risk identification scenarios, after identifying the user to be identified based on the time-series behavior rules, the user can be blocked or admitted based on the identification results without the need for other judgments. Therefore, the system pressure can be reduced. In addition, after determining that the user to be identified is a low-risk user based on the time-series behavior rules, the user can be admitted without the need for other judgments. The whole process takes less time, thus improving the user experience.

[0142] For example, in a marketing scenario, if it's determined that user A is a target user, product information for the target product can be pushed to user A; if it's determined that user A is not a target user, the recommendation of product information for the target product can be canceled. This allows for precise targeting, avoiding the recommendation of unwanted product information to users, thereby improving the user experience.

[0143] The technical solution provided in this application, when analyzing user behavior data, fully considers the temporal identifiers of behavioral events included in the behavior data, thus enabling comprehensive mining of user behavior data. When analyzing the behavior data of multiple types of users, it can fully mine the behavior data of multiple types of users to obtain temporal association rules that reflect the temporal sequence of behaviors of multiple types of users, and then obtain the temporal behavior rules of the target type of users. Therefore, when determining whether the user to be identified belongs to the target type of user based on the temporal behavior rules of the target type of users, effective identification can be performed.

[0144] Figure 2 This is a flowchart illustrating a user data processing method according to an embodiment of this application. The user data processing method includes the following steps.

[0145] S202: Obtain behavioral data from multiple user groups.

[0146] Among them, multiple user categories are divided based on business tags, and a user's behavioral data can include multiple behavioral events and time sequence identifiers of multiple behavioral events.

[0147] S204: Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, determine the temporal association rules corresponding to the multiple user types;

[0148] For the specific implementation of S202 to S204 above, please refer to Figure 1 The specific implementation of the corresponding steps in the illustrated embodiments will not be described again here.

[0149] S206: Based on the time-series association rules corresponding to the multiple types of users, determine the time-series behavior rules for the multiple types of users.

[0150] In S206, for one type of target user, it can be based on Figure 1 The method described in the illustrated embodiment determines the temporal behavior rules of the target class users. After obtaining the temporal behavior rules of the target class users, the temporal behavior rules of non-target class users other than the target class users can be determined based on the same method.

[0151] S208: Based on the temporal behavior rules of the multiple types of users, generate multiple temporal behavior rule features.

[0152] In this embodiment, one temporal behavior rule can generate one temporal behavior rule feature, and the number of multiple temporal behavior rule features can be equal to the total number of temporal behavior rules for multiple types of users.

[0153] For example, the temporal behavior rules for multiple user types include: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4, 4→5, 3→4→5, 1→3→4→5. Then, based on the temporal behavior rule 1→2, a temporal behavior rule feature fea1 can be generated; based on the temporal behavior rule 2→3, a temporal behavior rule feature fea2 can be generated; and so on, resulting in 12 temporal behavior rule features fea1 to fea12.

[0154] S210: Based on the multiple temporal behavior rule features, determine the temporal behavior features of the user to be processed, so as to generate sample data including the temporal behavior features for model training.

[0155] In S210, when determining the temporal behavior characteristics of the user to be processed based on multiple temporal behavior rule characteristics, the following steps may be included:

[0156] First, obtain the behavioral data of the users to be processed.

[0157] The behavioral data of the user to be processed may include multiple behavioral events of the user within a set time period, as well as the time sequence identifiers of the multiple behavioral events.

[0158] Secondly, based on the behavioral events and their temporal identifiers included in the behavioral data of the users to be processed, the temporal association rules for the users are determined.

[0159] For details on the implementation method, please refer to the above. Figure 1 The specific details of the time-series association rules for determining a type of user, as described in the illustrated embodiment, will not be repeated here.

[0160] Finally, for one of the temporal behavior rule features, it can be determined whether the temporal association rule of the user to be processed matches the temporal behavior rule corresponding to the temporal behavior rule feature. Here, the temporal behavior rule corresponding to the temporal behavior rule feature can be understood as the temporal behavior rule that generates the temporal behavior rule feature. For example, if fea1 is generated by temporal behavior rule 1→2 as described above, then the temporal behavior rule corresponding to fea1 is 1→2.

[0161] If the judgment result is yes, it can be determined that the user to be processed has the characteristics of the time-series behavior rule; otherwise, it can be determined that the user to be processed does not have the characteristics of the time-series behavior rule.

[0162] After determining whether a user to be processed has a temporal behavior rule feature based on the method described above, it is possible to determine whether the user to be processed has other temporal behavior rule features based on the same method, which will not be described in detail here.

[0163] In this embodiment, whether a user to be processed has multiple temporal behavioral rule features can be represented by numerical values, which can be regarded as the temporal behavioral features of the user to be processed.

[0164] For example, if a user to be processed has a certain temporal behavior rule feature, it can be represented by the value 1; if a user to be processed does not have a certain temporal behavior rule feature, it can be represented by the value 0. The values ​​0 and 1 can be regarded as the temporal behavior features of the user to be processed.

[0165] For ease of understanding, we will still use the 12 temporal behavior rule features fea1 to fea12 recorded above as an example. The temporal behavior rules corresponding to the 12 temporal behavior rule features fea1 to fea12 are: 1→2, 2→3, 2→4, 1→2→3, 1→2→4, 1→3→4, 1→3→5, 2→3→4, 1→2→3→4, 4→5, 3→4→5, 1→3→4→5.

[0166] Assuming the temporal association rules for the user to be processed include: 1→2, 2→4, 3→4, 1→2→3, 1→3→4, 1→3→5, 1→2→3→4, then it can be determined that the user to be processed has temporal behavior rule features fea1, fea3, fea4, fea6, fea7, fea9, and does not have temporal behavior rule features fea2, fea5, fea8, fea10, fea11, fea12. Since 1 indicates that the user to be processed has a certain temporal behavior rule feature, and 0 indicates that the user to be processed does not have a certain temporal behavior rule feature, the temporal behavior features of the user to be processed are: 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0.

[0167] In this embodiment, after determining the temporal behavior characteristics of the user to be processed, and given the known business tags of the user to be processed, sample data can also be obtained based on the temporal behavior characteristics of the user to be processed. This sample data includes the temporal behavior characteristics of the user to be processed and can be used for model training.

[0168] For example, after obtaining the temporal behavioral characteristics of target users and non-target users, these temporal behavioral characteristics can be used as sample data for model training to obtain a model for identifying whether a user is a target user or a non-target user. After obtaining the model, when identifying the user to be identified based on the model, the temporal behavioral characteristics of the user to be identified can also be determined based on the method described in this embodiment. The temporal behavioral characteristics of the user to be identified can be used as model input, and based on the model output, it can be determined whether the user to be identified belongs to the target user or a non-target user.

[0169] The technical solution provided in this application, when analyzing user behavior data, fully considers the temporal identifiers of behavioral events included in the behavior data, thus enabling comprehensive mining of user behavior data. When analyzing the behavior data of multiple types of users, it can fully mine the behavior data of multiple types of users to obtain temporal association rules that reflect the temporal sequence of behaviors of multiple types of users, thereby obtaining temporal behavior rules for multiple types of users. Based on the temporal behavior rules for multiple types of users, multiple temporal behavior rule features are generated. Therefore, based on multiple temporal behavior rule features, richer user temporal behavior features can be obtained, so that after modeling based on sample data including temporal behavior features, effective decision processing can be performed based on the trained model.

[0170] The foregoing has described specific embodiments of this application. 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 results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0171] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0172] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0173] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0174] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a user data processing device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0175] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0176] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0177] Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the temporal behavior rule of the target class user is determined.

[0178] Based on the temporal behavior rules of the target user group, determine whether the user to be identified belongs to the target user group.

[0179] The above is as stated in this application. Figure 3 The user data processing apparatus disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0180] The electronic device can also perform Figure 1 The method, and implement the user data processing device in Figure 1 The functions described in the illustrated embodiments will not be repeated here.

[0181] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0182] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 1 The method of the illustrated embodiment is specifically used to perform the following operations:

[0183] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0184] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0185] Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the temporal behavior rule of the target class user is determined.

[0186] Based on the temporal behavior rules of the target user group, determine whether the user to be identified belongs to the target user group.

[0187] Figure 4 This is a schematic diagram of the structure of a user data processing apparatus 40 according to an embodiment of this application. Please refer to... Figure 4 In one software implementation, the user data processing device 40 may include: an acquisition unit 41, a processing unit 42, a determination unit 43, and an identification unit 44, wherein:

[0188] Acquisition unit 41 acquires behavioral data of multiple types of users, wherein the multiple types of users are divided based on business tags, and the behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events;

[0189] Processing unit 42 determines the time-series association rules corresponding to the multiple types of users based on the behavioral events and time-series identifiers included in the behavioral data of the multiple types of users.

[0190] The determining unit 43 determines the temporal behavior rules of the target user based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user among the multiple user types.

[0191] The identification unit 44 determines whether the user to be identified belongs to the target class of users based on the temporal behavior rules of the target class of users.

[0192] Optionally, the determining unit 43 determines the temporal behavior rules of the target user group, including:

[0193] Based on the first temporal association rule and the second temporal association rule, the target temporal association rule in the first temporal association rule is determined;

[0194] Based on the target time-series association rules, the time-series behavior rules of the target class of users are determined.

[0195] Optionally, the determining unit 43 determines the target temporal association rule in the first temporal association rule, including at least one of the following:

[0196] The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule;

[0197] Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

[0198] Optionally, the first confidence level is the probability or conditional probability of the behavioral event corresponding to the time-series association rule appearing in the behavioral data of the target class user.

[0199] Optionally, the identification unit 44 determines whether the user to be identified belongs to the target class of users based on the temporal behavior rules of the target class of users, including:

[0200] Obtain the behavioral data of the user to be identified, wherein the behavioral data includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events;

[0201] Based on the behavioral events and their temporal identifiers included in the behavioral data of the user to be identified, the temporal association rules of the user to be identified are determined;

[0202] Determine whether the temporal association rule of the user to be identified matches the temporal behavior rule of the target user;

[0203] If so, then the user is determined to belong to the target user category;

[0204] If not, then it is determined that the user does not belong to the target user category.

[0205] Optionally, the processing unit 42 determines the time-series association rules corresponding to the multiple types of users, including:

[0206] For one type of user, perform the following operations:

[0207] Based on the behavioral events included in the behavioral data of the aforementioned user group, determine the frequent itemsets;

[0208] Based on the frequent itemsets and the temporal identifiers of the behavioral events included in the frequent itemsets, the temporal association rules corresponding to the type of user are determined.

[0209] The user data processing device 40 provided in this application embodiment can also perform... Figure 1 The method, and implement the user data processing device in Figure 1 The functions of the embodiments shown are not described in detail here.

[0210] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 5 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0211] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0212] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0213] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a user data processing device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0214] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0215] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0216] Based on the temporal association rules corresponding to the multiple types of users, the temporal behavior rules of the multiple types of users are determined;

[0217] Based on the temporal behavior rules of the aforementioned multiple user types, multiple temporal behavior rule features are generated;

[0218] Based on the aforementioned multiple temporal behavior rule features, the temporal behavior features of the user to be processed are determined, so as to generate sample data including the temporal behavior features for model training.

[0219] The above is as stated in this application. Figure 5The user data processing apparatus disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0220] The electronic device can also perform Figure 2 The method, and implement the user data processing device in Figure 2 The functions described in the illustrated embodiments will not be repeated here.

[0221] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0222] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 2 The method of the illustrated embodiment is specifically used to perform the following operations:

[0223] Acquire behavioral data of multiple user categories, which are divided based on business tags. The behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events.

[0224] Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

[0225] Based on the temporal association rules corresponding to the multiple types of users, the temporal behavior rules of the multiple types of users are determined;

[0226] Based on the temporal behavior rules of the aforementioned multiple user types, multiple temporal behavior rule features are generated;

[0227] Based on the aforementioned multiple temporal behavior rule features, the temporal behavior features of the user to be processed are determined, so as to generate sample data including the temporal behavior features for model training.

[0228] Figure 6 This is a schematic diagram of the structure of a user data processing apparatus 60 according to an embodiment of this application. Please refer to... Figure 6 In one software implementation, the user data processing device 40 may include: an acquisition unit 61, a processing unit 62, a first determination unit 63, a generation unit 64, and a second determination unit 65, wherein:

[0229] Acquisition unit 61 acquires behavioral data of multiple types of users, wherein the multiple types of users are divided based on business tags, and the behavioral data of a user includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events;

[0230] Processing unit 62 determines the time-series association rules corresponding to the multiple types of users based on the behavioral events and time-series identifiers included in the behavioral data of the multiple types of users.

[0231] The first determining unit 63 determines the time-series behavior rules of the multiple types of users based on the time-series association rules corresponding to the multiple types of users.

[0232] The generation unit 64 generates multiple time-series behavior rule features based on the time-series behavior rules of the multiple types of users;

[0233] The second determining unit 65 determines the temporal behavior features of the user to be processed based on the multiple temporal behavior rule features, so as to generate sample data including the temporal behavior features for model training.

[0234] Optionally, the second determining unit 65 determines the temporal behavior characteristics of the user to be processed based on the plurality of temporal behavior rule characteristics, including:

[0235] Obtain the behavior data of the user to be processed, the behavior data including multiple behavior events and the time sequence identifiers of the multiple behavior events;

[0236] Based on the behavioral events and their temporal identifiers included in the behavioral data of the user to be processed, the temporal association rules of the user to be processed are determined.

[0237] For one of the temporal behavior rule features, perform the following operations:

[0238] Determine whether the temporal association rule of the user to be processed matches the temporal behavior rule corresponding to the temporal behavior rule feature;

[0239] If so, then it is determined that the user to be processed has the temporal behavior rule characteristics;

[0240] If not, then it is determined that the user to be processed does not have the characteristics of the time-series behavior rule.

[0241] The user data processing device 60 provided in this application embodiment can also perform... Figure 2 The method, and implement the user data processing device in Figure 2 The functions of the embodiments shown are not described in detail here.

[0242] In summary, the above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

[0243] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0244] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0245] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0246] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

Claims

1. A method for processing user data, comprising: Acquire behavioral data from multiple user groups; Based on the behavioral data of the multiple user types, determine the time-series association rules corresponding to the multiple user types; Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the target temporal association rule in the first temporal association rule is determined; Based on the target temporal association rules, determine the temporal behavior rules of the target class of users; Based on the temporal behavior rules of the target class of users, determine whether the user to be identified belongs to the target class of users; The determination of the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

2. The method as described in claim 1, The first confidence level is the probability or conditional probability of the behavioral event corresponding to the time-series association rule appearing in the behavioral data of the target class user.

3. The method as described in claim 1, wherein determining the temporal behavior rules of the target user group based on the target temporal association rules includes: Among the target time-series association rules, those with a confidence level not less than a set confidence threshold are determined as the time-series behavior rules for the target user class. The confidence level of the target time-series association rule is the probability or conditional probability of the behavioral event corresponding to the target time-series association rule appearing in the behavioral data of the target user class; or, The target time-series association rule is determined as the time-series behavior rule of the target class of users.

4. The method as described in claim 1, wherein determining whether a user to be identified belongs to the target class of users based on the temporal behavior rules of the target class of users includes: Obtain the behavioral data of the user to be identified, wherein the behavioral data includes multiple behavioral events and the time sequence identifiers of the multiple behavioral events; Based on the behavioral events and their temporal identifiers included in the behavioral data of the user to be identified, the temporal association rules of the user to be identified are determined; Determine whether the temporal association rule of the user to be identified matches the temporal behavior rule of the target user; If so, then the user is determined to belong to the target user category; If not, then it is determined that the user does not belong to the target user category.

5. The method as described in claim 1, wherein the multiple user categories are divided based on business tags; obtaining behavioral data of the multiple user categories includes: Acquire behavioral data from multiple users with different business tags; The behavioral data of multiple users are grouped according to business tags to obtain behavioral data of multiple user categories.

6. The method as described in claim 1, wherein a user's behavior data includes multiple behavior events and time sequence identifiers of the multiple behavior events; based on the behavior data of the multiple types of users, determining the time sequence association rules corresponding to the multiple types of users includes: Based on the behavioral events and their temporal identifiers included in the behavioral data of the multiple user types, temporal association rules corresponding to the multiple user types are determined.

7. The method of claim 6, wherein determining the time-series association rules corresponding to the multiple types of users includes: For one type of user, perform the following operations: Based on the behavioral events included in the behavioral data of the aforementioned user group, determine the frequent itemsets; Based on the frequent itemsets and the temporal identifiers of the behavioral events included in the frequent itemsets, the temporal association rules corresponding to the type of user are determined.

8. The method of claim 1, further comprising at least one of the following: If the target user is a high-risk user and the user to be identified belongs to the target user, the user to be identified will be intercepted. If the target user is a low-risk user and the user to be identified belongs to the target user, the user to be identified will be granted access. If the target user is a target user and the user to be identified belongs to the target user, push product information of the target product to the user to be identified; If the target user is a target user and the user to be identified does not belong to the target user, then the push of product information of the target product to the user to be identified will be cancelled.

9. A method for processing user data, comprising: Acquire behavioral data from multiple user groups; Based on the behavioral data of the multiple user types, determine the time-series association rules corresponding to the multiple user types; Based on the temporal association rules corresponding to the multiple types of users, the temporal behavior rules of the multiple types of users are determined; Based on the temporal behavior rules of the various user types, the temporal behavior characteristics of the user to be processed are determined, so as to generate sample data including the temporal behavior characteristics for model training. The determination of the temporal behavior rules for the multiple user types includes: For any target user among the multiple user categories, based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user, a target temporal association rule is determined in the first temporal association rule; according to the target temporal association rule, the temporal behavior rule of the target user is determined; wherein, determining the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

10. The method of claim 9, wherein determining the temporal behavior characteristics of the user to be processed based on the temporal behavior rules of the multiple types of users includes: Based on the temporal behavior rules of the aforementioned multiple user types, multiple temporal behavior rule features are generated; Based on the aforementioned multiple temporal behavior rule features, the temporal behavior features of the user to be processed are determined.

11. The method of claim 10, wherein determining the temporal behavior characteristics of the user to be processed based on the plurality of temporal behavior rule characteristics includes: Obtain the behavior data of the user to be processed, the behavior data including multiple behavior events and the time sequence identifiers of the multiple behavior events; Based on the behavioral events and their temporal identifiers included in the behavioral data of the user to be processed, the temporal association rules of the user to be processed are determined. For one of the temporal behavior rule features, perform the following operations: Determine whether the temporal association rule of the user to be processed matches the temporal behavior rule corresponding to the temporal behavior rule feature; If so, then it is determined that the user to be processed has the temporal behavior rule characteristics; If not, then it is determined that the user to be processed does not have the characteristics of the time-series behavior rule.

12. A user data processing apparatus, comprising: The acquisition unit acquires behavioral data from multiple user groups. The processing unit determines the time-series association rules corresponding to the multiple types of users based on the behavioral data of the multiple types of users; The determining unit determines the target temporal association rule in the first temporal association rule based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user among the multiple user types; and determines the temporal behavior rule of the target user according to the target temporal association rule. The identification unit determines whether the user to be identified belongs to the target class of users based on the temporal behavior rules of the target class of users; The determining unit determines the target temporal association rule in the first temporal association rule, including at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

13. A user data processing apparatus, comprising: The acquisition unit acquires behavioral data from multiple user groups. The processing unit determines the time-series association rules corresponding to the multiple types of users based on the behavioral data of the multiple types of users; The first determining unit determines the temporal behavior rules of the multiple types of users based on the temporal association rules corresponding to the multiple types of users; The second determining unit determines the temporal behavior characteristics of the user to be processed based on the temporal behavior rules of the multiple types of users, so as to generate sample data including the temporal behavior characteristics for model training. The first determining unit determines the temporal behavior rules of the multiple types of users, including: For any target user among the multiple user categories, based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user, a target temporal association rule is determined in the first temporal association rule; according to the target temporal association rule, the temporal behavior rule of the target user is determined; wherein, determining the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

14. An electronic device, comprising: processor; as well as Memory configured to store computer-executable instructions that, when executed, cause the processor to perform the following operations: Acquire behavioral data from multiple user groups; Based on the behavioral data of the multiple user types, determine the time-series association rules corresponding to the multiple user types; Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the target temporal association rule in the first temporal association rule is determined; Based on the target temporal association rules, determine the temporal behavior rules of the target class of users; Based on the temporal behavior rules of the target class of users, determine whether the user to be identified belongs to the target class of users; The determination of the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

15. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the following method: Acquire behavioral data from multiple user groups; Based on the behavioral data of the multiple user types, determine the time-series association rules corresponding to the multiple user types; Based on the first temporal association rule corresponding to the target class user and the second temporal association rule corresponding to the non-target class user among the multiple user types, the target temporal association rule in the first temporal association rule is determined; Based on the target temporal association rules, determine the temporal behavior rules of the target class of users; Based on the temporal behavior rules of the target class of users, determine whether the user to be identified belongs to the target class of users; in, Determining the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

16. An electronic device comprising: processor; as well as Memory configured to store computer-executable instructions that, when executed, cause the processor to perform the following operations: Acquire behavioral data from multiple user groups; Based on the behavioral data of the multiple user types, determine the time-series association rules corresponding to the multiple user types; Based on the temporal association rules corresponding to the multiple types of users, the temporal behavior rules of the multiple types of users are determined; Based on the temporal behavior rules of the various user types, the temporal behavior characteristics of the user to be processed are determined, so as to generate sample data including the temporal behavior characteristics for model training. The determination of the temporal behavior rules for the multiple user types includes: For any target user among the multiple user categories, based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user, a target temporal association rule is determined in the first temporal association rule; according to the target temporal association rule, the temporal behavior rule of the target user is determined; wherein, determining the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

17. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the following method: Acquire behavioral data from multiple user groups; Based on the behavioral data of the multiple user types, determine the time-series association rules corresponding to the multiple user types; Based on the temporal association rules corresponding to the multiple types of users, the temporal behavior rules of the multiple types of users are determined; Based on the temporal behavior rules of the various user types, the temporal behavior characteristics of the user to be processed are determined, so as to generate sample data including the temporal behavior characteristics for model training. in, Determining the temporal behavior rules for the multiple user groups includes: For any target user among the multiple user categories, based on the first temporal association rule corresponding to the target user and the second temporal association rule corresponding to the non-target user, a target temporal association rule is determined in the first temporal association rule; according to the target temporal association rule, the temporal behavior rule of the target user is determined; wherein, determining the target temporal association rule in the first temporal association rule includes at least one of the following: The temporal association rule that does not belong to the second temporal association rule in the first temporal association rule is determined as the target temporal association rule; Identify identical time-series association rules in the first and second time-series association rules; determine the first confidence level of the identical time-series association rules in the target class of users and the second confidence level in the non-target class of users; identify the time-series association rules whose ratio of the first confidence level to the second confidence level is not less than a set threshold as the target time-series association rules.

Images