User behavior-based right service management method and device, and medium

Abstract

The invention discloses a user behavior-based right service management method and device and a medium, and relates to the field of data processing methods.The method comprises the steps of obtaining first behavior information of a first user, calling a time sequence strategy to analyze the first behavior information, obtaining a first user behavior time sequence, and extracting a first right behavior, and obtaining the corresponding first interaction time. And analyzing the first interaction time in combination with a predetermined interaction threshold constraint to obtain a first behavior time period. And matching the first interaction behavior set corresponding to the time period with the first behavior information, and performing clustering to obtain a first clustering result. And traversing and matching in the user behavior database to obtain a target clustering result, obtaining a corresponding target user, establishing a first right service recommendation table according to a corresponding target right behavior, and displaying the first right service recommendation table to a user side of the first user. The technical problems of insufficient recommendation accuracy and low historical user matching efficiency during right and interest service management based on user behaviors in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing methods, and in particular to a rights and interests service management method, device and medium based on user behavior. Background Art

[0002] With the rapid development of Internet services, user behavior analysis and personalized recommendation technologies have become the core means to improve business conversion rates. Traditional recommendation systems mostly make recommendations based on static behavior tags or interaction data at a single time point, regarding user behavior as discrete events and failing to effectively capture the temporal characteristics of the sequential operations before and after rights and interests behaviors, resulting in the failure to accurately identify the golden conversion period after coupon redemption. This leads to inaccurate grasp of the temporal characteristics of user behavior and affects the accuracy of recommendations. At the same time, it is difficult to efficiently match target users with similar current user behavior patterns in a large amount of historical user data during the clustering analysis of user behavior, thereby affecting the efficiency of obtaining recommendation results.

[0003] Therefore, when managing rights and interests services based on user behavior in the prior art, there are technical problems of insufficient recommendation accuracy and low historical user matching efficiency. Summary of the Invention

[0004] This application provides a rights and interests service management method, device and medium based on user behavior, and solves the technical problems of insufficient recommendation accuracy and low historical user matching efficiency when managing rights and interests services based on user behavior in the prior art. Through precise temporalization strategies, effective vectorization analysis and similarity calculation, and a dynamic resource scheduling mechanism, the accuracy, matching efficiency and user experience of rights and interests service recommendations are improved.

[0005] This application provides a rights and interests service management method based on user behavior. The method includes: obtaining the first behavior information of a first user, and invoking a temporalization strategy to analyze the first behavior information to obtain the first user behavior time series; extracting the first rights and interests behavior in the first user behavior time series, and obtaining the first interaction time corresponding to the first rights and interests behavior; analyzing the first interaction time in combination with a predetermined interaction threshold constraint to obtain a first behavior period; matching the first interaction behavior set corresponding to the first behavior period in the first behavior information, and performing clustering analysis on the first interaction behavior set to obtain a first clustering result; traversing and matching the first clustering result in the user behavior database to obtain a target clustering result, and obtaining the corresponding target user; forming a first rights and interests service recommendation table according to the target rights and interests behavior of the target user, and displaying the first rights and interests service recommendation table to the user terminal of the first user.

[0006] In the implementation manner, obtaining the standard multi-dimensional traffic operation data stream includes: acquiring the first behavior information of the first user, and invoking the timing strategy to analyze the first behavior information to obtain the first user behavior timing, including: extracting any rights and interests behavior in the first behavior information according to the timing strategy; obtaining the time when the first user executes the any rights and interests behavior, denoted as any interaction time; constructing the first user behavior timing according to the corresponding relationship between the any rights and interests behavior and the any interaction time.

[0007] In the implementation manner, according to the predetermined pre-interaction step threshold and the predetermined post-interaction step threshold in the predetermined interaction threshold constraint, analyze the first interaction time to obtain the first behavior period.

[0008] In the implementation manner, traversing and matching the first clustering result in the user behavior database to obtain the target clustering result, and obtaining the corresponding target user, including: performing vectorization analysis on the behavior clusters with multiple behavior times in the first clustering result according to the vectorization strategy to generate a first behavior vector; extracting the first behavior data group in the user behavior database, where the first behavior data group refers to the first historical behavior clustering result and the first historical rights and interests behavior of the first historical user; obtaining the first historical behavior vector of the first historical behavior clustering result according to the vectorization strategy; calculating the first similarity between the first behavior vector and the first historical behavior vector; if the first similarity reaches the predetermined similarity threshold, taking the first historical behavior clustering result as the target clustering result, and taking the first historical user as the target user.

[0009] In the implementation manner, performing vectorization analysis on the behavior clusters with multiple behavior times in the first clustering result according to the vectorization strategy to generate a first behavior vector, including: extracting the first behavior cluster in the behavior clusters with multiple behavior times, and obtaining the first behavior frequency of the first behavior cluster; obtaining the first vector ordinal number of the first behavior cluster according to the vectorization strategy; marking the first behavior frequency to the first vector ordinal number to obtain the first behavior vector.

[0010] In the implementation manner, calculating the first similarity between the first behavior vector and the first historical behavior vector includes: obtaining any vector ordinal number; sequentially matching the second behavior frequency and the third behavior frequency corresponding to the any vector ordinal number in the first behavior vector and the first historical behavior vector; obtaining the similarity between the second behavior frequency and the third behavior frequency; obtaining the first similarity based on the similarity.

[0011] In an implementation manner, after obtaining the similarity between the second behavior frequency and the third behavior frequency, the method further includes: obtaining an arbitrary behavior cluster corresponding to the arbitrary vector ordinal number; performing collaborative analysis on the arbitrary behavior cluster and the target interest behavior to obtain an arbitrary cluster information value of the arbitrary behavior cluster; and adjusting the similarity with the arbitrary cluster information value as a weight.

[0012] In an implementation manner, after constructing a first interest service recommendation table according to the target interest behavior of the target user and displaying the first interest service recommendation table on the user side of the first user, the method further includes: matching a target service channel of the target interest behavior; monitoring the load of the target service channel to obtain a target load rate; and performing dynamic resource scheduling on the target service channel based on the target load rate.

[0013] The present application further provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing the interest service management method based on user behavior provided by the present application when executing the executable instructions stored in the memory.

[0014] The present application provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the interest service management method based on user behavior provided by the present application.

[0015] It is intended to solve the technical problems of insufficient recommendation accuracy and low historical user matching efficiency in the prior art when performing interest service management based on user behavior through the interest service management method, device, and medium proposed in the present application. By obtaining the first behavior information of the first user, analyzing the first behavior information by invoking a time-series strategy to obtain the first user behavior time series, extracting the first interest behavior in the first user behavior time series, and obtaining the first interaction time corresponding to the first interest behavior, analyzing the first interaction time in combination with a predetermined interaction threshold constraint to obtain a first behavior period, matching the first interaction behavior set corresponding to the first behavior period in the first behavior information, and performing clustering analysis on the first interaction behavior set to obtain a first clustering result, traversing and matching the first clustering result in a user behavior database to obtain a target clustering result, and obtaining a corresponding target user, constructing a first interest service recommendation table according to the target interest behavior of the target user, and displaying the first interest service recommendation table on the user side of the first user. Through precise time-series strategies, effective vectorization analysis and similarity calculation, and a dynamic resource scheduling mechanism, the accuracy, matching efficiency, and user experience of interest service recommendations are improved.

[0016] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific implementation manners of this application are specifically given below. Brief Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of this application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0018] Figure 1 Flowchart of the method for managing rights and interests services based on user behavior provided by an embodiment of this application; Figure 2 Flowchart of the method for managing rights and interests services based on user behavior provided by an embodiment of this application to obtain the corresponding target user; Figure 3 Structural diagram of the electronic device corresponding to the method for managing rights and interests services based on user behavior provided by an embodiment of this application.

[0019] Description of reference numerals: Processor 31, Memory 32, Input device 33, Output device 34. Detailed Description of the Embodiments

[0020] Embodiment 1

[0021] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific implementation manners of this application are specifically given below.

[0022] In order to make the purpose, technical solution and advantages of this application clearer, the present application will be further described in detail below in conjunction with the drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0023] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0024] As Figure 1 shown, the embodiments of this application provide a method for managing rights and interests services based on user behavior. The method includes: Obtaining the first behavior information of the first user, and invoking a temporalization strategy to analyze the first behavior information to obtain the first user behavior time series; extracting the first rights and interests behavior in the first user behavior time series, and obtaining the first interaction time corresponding to the first rights and interests behavior; analyzing the first interaction time in combination with a predetermined interaction threshold constraint to obtain the first behavior period.

[0025] Through the data logging technology or the log collection system, collect all the interaction behaviors and entitlement behaviors of the first user on the platform, and obtain the first behavior information of the first user. The interaction behaviors include page views, button clicks, order payments, etc., and the entitlement behaviors include red envelope receipts, cash entitlement withdrawals, etc. The timing strategy is to obtain the entitlement objects and execution times in the first behavior information, and obtain the first user behavior timing according to the corresponding relationship between the two. For example, if user A receives a coupon at 09:05, then receiving the coupon is an entitlement behavior, and the execution time is 09:05. Subsequently, extract the first entitlement behavior in the first user behavior timing. The first entitlement behavior is a random entitlement behavior in the first user behavior timing. At the same time, obtain the first interaction time corresponding to the first entitlement behavior. Further, analyze the first interaction time in combination with the predetermined interaction threshold constraint. The predetermined interaction threshold constraint is a time range rule set by the system for intercepting the associated operations before and after the entitlement behavior, including the predetermined pre-interaction step threshold and the predetermined post-interaction step threshold. Intercept the time periods before and after the first interaction time through the predetermined pre-interaction step threshold and the predetermined post-interaction step threshold respectively to obtain the first behavior period. Taking the first interaction time of 09:05 as an example, the predetermined interaction threshold constraint is "30 minutes before and after the entitlement behavior", and the behavior period of user A is from 08:35 to 09:35.

[0026] The method provided by the embodiment of the present application further includes: extracting any entitlement behavior in the first behavior information according to the timing strategy; obtaining the time when the first user executes the any entitlement behavior, denoted as the any interaction time; and constructing the first user behavior timing according to the corresponding relationship between the any entitlement behavior and the any interaction time.

[0027] Obtain the first behavior information of the first user, and retrieve the timing strategy to analyze the first behavior information to obtain the first user behavior timing, including: extracting any entitlement behavior in the first behavior information according to the timing strategy. The entitlement behavior has different meanings according to different business scenarios. In the e-commerce scenario, operations such as "coupon receipt", "point redemption", and "member service activation" all belong to entitlement behaviors. Specific entitlement behaviors can be set according to the actual application scenario. Subsequently, obtain the time when the first user executes the entitlement, that is, uses or obtains any entitlement behavior, and denote the time of using or obtaining any entitlement behavior as the any interaction time. Further, construct the first user behavior timing by using the corresponding relationship between the any entitlement behavior and the any interaction time, that is, construct the behavior timing of the first user based on the corresponding relationship between the any entitlement behavior and the corresponding usage time, and obtain the first user behavior timing. Record each entitlement and the corresponding execution time in the first user behavior timing.

[0028] Match the first interaction behavior set corresponding to the first behavior time period in the first behavior information, and perform clustering analysis on the first interaction behavior set to obtain a first clustering result; traverse and match the first clustering result in the user behavior database to obtain a target clustering result, and obtain the corresponding target user; form a first rights and interests service recommendation table according to the target rights and interests behavior of the target user, and display the first rights and interests service recommendation table on the user side of the first user.

[0029] Match the first interaction behavior set corresponding to the first behavior time period in the first behavior information. The interaction behavior set includes all interaction operation behaviors of non-rights and interests behaviors, such as page browsing, button clicking, purchasing, collecting, etc. And perform clustering analysis on the interaction behaviors in the first interaction behavior set. For example, cluster all operations such as clicking, browsing, purchasing, and collecting into corresponding behavior clusters, so as to obtain a first clustering result. Further, traverse and match the first clustering result in the user behavior database to obtain a target clustering result. The target clustering result is a result whose similarity with the first clustering result is greater than or equal to a predetermined similarity threshold, so as to obtain the target user corresponding to the target clustering result. Finally, form a first rights and interests service recommendation table according to the target rights and interests behavior of the target user's historical record, and display the first rights and interests service recommendation table on the user side of the first user. This solves the technical problems of insufficient recommendation accuracy and low historical user matching efficiency in the prior art when managing rights and interests services based on user behavior. Through precise timing strategies, effective vectorization analysis and similarity calculation, and a dynamic resource scheduling mechanism, the accuracy, matching efficiency, and user experience of rights and interests service recommendations are improved.

[0030] As Figure 2 As shown, the method provided by the embodiment of the present application further includes: according to the vectorization strategy, perform vectorization analysis on the behavior clusters with behavior times in the first clustering result to generate a first behavior vector; extract the first behavior data group in the user behavior database. The first behavior data group refers to the first historical behavior clustering result and the first historical rights and interests behavior of the first historical user; obtain the first historical behavior vector of the first historical behavior clustering result according to the vectorization strategy; calculate the first similarity between the first behavior vector and the first historical behavior vector; if the first similarity reaches a predetermined similarity threshold, use the first historical behavior clustering result as the target clustering result, and record the first historical user as the target user.

[0031] According to the vectorization strategy, vectorization analysis is performed on the behavior clusters of multiple identifiers with behavior counts in the first clustering result to generate a first behavior vector. The vectorization strategy is a strategy for vectorizing each behavior cluster in the first clustering result. By performing vectorization transformation on each clustering cluster in the first clustering result, subsequent analysis can directly perform data processing based on vector features, thereby improving the efficiency of data analysis. Subsequently, a first behavior data group is extracted from the user behavior database. The user behavior database records data recorded by various users in the historical system or software, including data groups composed of users and their historical behavior clustering results and historical rights and interests behaviors during the corresponding behavior periods. Among them, the first behavior data group refers to the first historical behavior clustering result and the first historical rights and interests behavior of the first historical user. Further, according to the vectorization strategy, the same vectorization method is used to obtain the first historical behavior vector corresponding to the first historical behavior clustering result of the first historical user. The first historical behavior vector contains multiple vectors after behavior vectorization. Further, a first similarity between the first behavior vector and the first historical behavior vector is calculated. Finally, through a preset similarity threshold, it is determined whether the first similarity is greater than or equal to the preset similarity threshold. If the first similarity reaches, that is, is greater than or equal to the preset similarity threshold, the first historical behavior clustering result is used as the target clustering result, and the first historical user is recorded as the target user.

[0032] The method provided by the embodiment of the present application further includes: extracting a first behavior cluster from multiple behavior clusters of identifiers with behavior counts, and obtaining a first behavior frequency of the first behavior cluster; obtaining a first vector ordinal number of the first behavior cluster according to the vectorization strategy; and marking the first behavior frequency to the first vector ordinal number to obtain the first behavior vector.

[0033] According to the vectorization strategy, perform vectorization analysis on the behavior clusters of multiple identifiers with behavior counts in the first clustering result to generate a first behavior vector, including: by extracting the first behavior cluster from the behavior clusters of multiple identifiers with behavior counts in the first clustering result, the first behavior cluster being a randomly selected behavior cluster with a behavior count identifier, where the behavior count identifier is the number of times the behavior appears in the behavior cluster, and at the same time obtaining the first behavior frequency of this first behavior cluster, the first behavior frequency being the specific behavior count of the first behavior cluster. Further, according to the vectorization strategy, obtain the first vector ordinal number of the first behavior cluster, the first vector ordinal number being the sequential identifier of the first behavior cluster in the first clustering result, used to reflect the specific behavior represented by the first behavior cluster, and this sequential identifier being a fixed identifier that will not change due to the number of behavior clusters. Finally, mark the first behavior frequency to the first vector ordinal number to obtain the first behavior vector. Among them, the first behavior vector can contain multiple vectors after behavior vectorization. The first behavior vector obtained in this way can clearly reflect the specific behavior of the user and the corresponding frequency characteristics.

[0034] The method provided by the embodiment of the present application further includes: obtaining an arbitrary vector ordinal number; sequentially matching the second behavior frequency and the third behavior frequency corresponding to the arbitrary vector ordinal number in the first behavior vector and the first historical behavior vector; obtaining the similarity between the second behavior frequency and the third behavior frequency; and obtaining the first similarity based on the similarity.

[0035] Calculating the first similarity between the first behavior vector and the first historical behavior vector includes: obtaining an arbitrary vector ordinal number, the arbitrary vector ordinal number being any one of the vector ordinal numbers included in the first behavior vector. Subsequently, respectively match the second behavior frequency and the third behavior frequency corresponding to the arbitrary vector ordinal number in the first behavior vector and the first historical behavior vector. The second behavior frequency is the behavior frequency corresponding to the arbitrary vector ordinal number in the first behavior vector, and the third behavior frequency is the behavior frequency corresponding to the arbitrary vector ordinal number in the first historical behavior vector. Further, obtain the similarity between the second behavior frequency and the third behavior frequency, and obtain the first similarity by taking the average of the similarities of all behavior clusters. The first similarity reflects the similarity between the target user and the first user in the user behavior database.

[0036] The method provided by the embodiment of the present application further includes: obtaining the arbitrary behavior cluster corresponding to the arbitrary vector ordinal number; performing collaborative analysis on the arbitrary behavior cluster and the target interest behavior to obtain the arbitrary cluster information value of the arbitrary behavior cluster; and adjusting the similarity with the arbitrary cluster information value as the weight.

[0037] After obtaining the similarity between the second behavior frequency and the third behavior frequency, it further includes: obtaining the arbitrary behavior cluster corresponding to the arbitrary vector ordinal number, that is, obtaining the behavior corresponding to the arbitrary vector ordinal number. Further, a collaborative analysis is performed on the arbitrary behavior cluster and the target interest behavior, so as to obtain the arbitrary cluster information value of the arbitrary behavior cluster. This information value is the relevance between the behavior cluster and the target interest behavior. The higher the relevance, the higher the connection between the corresponding behavior and the target interest behavior. When performing the collaborative analysis, the number of records of the target interest behavior in all behavior data groups in the user behavior database is obtained, and all historical behavior clustering results in the behavior data groups including the target interest behavior in advance are included. The occurrence times of the behavior clusters in all historical behavior clustering results are respectively obtained. The information value of the behavior cluster is obtained according to the ratio of the occurrence times to the number of records, and the corresponding arbitrary cluster information value is obtained. Finally, the similarity is adjusted with the arbitrary cluster information value as the weight. That is, the calculation result is obtained by multiplying the original similarity by the weight parameter, and the adjusted similarity is obtained.

[0038] The method provided by the embodiment of the present application further includes: matching the target service channel of the target interest behavior; performing load monitoring on the target service channel to obtain the target load rate; and performing dynamic resource scheduling on the target service channel based on the target load rate.

[0039] After constructing the first interest service recommendation table according to the target interest behavior of the target user and displaying the first interest service recommendation table to the user terminal of the first user, it further includes: matching the target service channel of the target interest behavior. The target service channel is a background interface or service that provides interest services, such as a membership opening API or a coupon redemption interface, usually identified by a URL or a service name. Subsequently, load monitoring is performed on the target service channel, and the percentage of the current request volume of the service channel in its maximum carrying capacity is monitored to obtain the target load rate. Exemplarily, during the Double 11 period of an e-commerce platform, the QPS of the coupon redemption interface increased from 200 to 1500 (maximum capacity = 1200), and the load rate = 125%, triggering an overload alarm. Finally, dynamic resource scheduling is performed on the target service channel based on the target load rate.

[0040] The technical solution provided by the embodiments of the present invention obtains the first behavior information of the first user, retrieves the time-series strategy to analyze the first behavior information, obtains the first user behavior time series, extracts the first rights and interests behavior, and obtains the corresponding first interaction time. Analyze the first interaction time in combination with the predetermined interaction threshold constraint to obtain the first behavior period. Match the first behavior information with the first interaction behavior set corresponding to this period, and perform clustering to obtain the first clustering result. Traverse and match in the user behavior database to obtain the target clustering result, obtain the corresponding target user, form the first rights and interests service recommendation table according to the corresponding target rights and interests behavior, and display it on the user side of the first user. This solves the technical problems of insufficient recommendation accuracy and low historical user matching efficiency in the prior art when managing rights and interests services based on user behavior. Through precise time-series strategies, effective vector analysis and similarity calculation, and a dynamic resource scheduling mechanism, the accuracy, matching efficiency, and user experience of rights and interests service recommendations are improved.

[0041] Embodiment 2

[0042] Based on the same inventive concept as the method for managing rights and interests services based on user behavior in the foregoing embodiments, the present invention also provides a system for managing rights and interests services based on user behavior. The system can be implemented in a hardware and / or software manner and is generally integrated into an electronic device for executing the method provided by any embodiment of the present invention. The system includes: a behavior time series acquisition module, configured to acquire the first behavior information of the first user, and retrieve the time-series strategy to analyze the first behavior information to obtain the first user behavior time series; an interaction time acquisition module, configured to extract the first rights and interests behavior in the first user behavior time series, and obtain the first interaction time corresponding to the first rights and interests behavior; a behavior period acquisition module, configured to analyze the first interaction time in combination with the predetermined interaction threshold constraint to obtain the first behavior period; a clustering result acquisition module, configured to match the first behavior information with the first interaction behavior set corresponding to the first behavior period, and perform clustering analysis on the first interaction behavior set to obtain the first clustering result; a target user acquisition module, configured to traverse and match the first clustering result in the user behavior database to obtain the target clustering result, and obtain the corresponding target user; a recommendation display module, configured to form the first rights and interests service recommendation table according to the target rights and interests behavior of the target user, and display the first rights and interests service recommendation table on the user side of the first user.

[0043] Next, the specific configuration of the behavior timing acquisition module will be described in detail. The behavior timing acquisition module may further include: obtaining the standard traffic multi-dimensional operation data stream, including: obtaining the first behavior information of the first user, and invoking the timing strategy to analyze the first behavior information to obtain the first user behavior timing, including: according to the timing strategy, extracting any rights and interests behavior in the first behavior information; obtaining the time when the first user executes the any rights and interests behavior, denoted as any interaction time; constructing the first user behavior timing according to the corresponding relationship between the any rights and interests behavior and the any interaction time.

[0044] Next, the specific configuration of the behavior period acquisition module will be described in detail. The behavior period acquisition module may further include: analyzing the first interaction time according to the predetermined pre-interaction step threshold and the predetermined post-interaction step threshold in the predetermined interaction threshold constraint to obtain the first behavior period.

[0045] Next, the specific configuration of the clustering result acquisition module will be described in detail. The clustering result acquisition module further includes: traversing and matching the first clustering result in the user behavior database to obtain the target clustering result, and obtaining the corresponding target user, including: according to the vectorization strategy, performing vectorization analysis on the behavior clusters with multiple behavior times in the first clustering result to generate the first behavior vector; extracting the first behavior data group in the user behavior database, where the first behavior data group refers to the first historical behavior clustering result and the first historical rights and interests behavior of the first historical user; obtaining the first historical behavior vector of the first historical behavior clustering result according to the vectorization strategy; calculating the first similarity between the first behavior vector and the first historical behavior vector; if the first similarity reaches the predetermined similarity threshold, taking the first historical behavior clustering result as the target clustering result and taking the first historical user as the target user.

[0046] Next, the specific configuration of the clustering result acquisition module will be described in detail. The clustering result acquisition module further includes: according to the vectorization strategy, performing vectorization analysis on the behavior clusters with multiple behavior times in the first clustering result to generate the first behavior vector, including: extracting the first behavior cluster from the behavior clusters with multiple behavior times, and obtaining the first behavior frequency of the first behavior cluster; obtaining the first vector ordinal number of the first behavior cluster according to the vectorization strategy; marking the first behavior frequency to the first vector ordinal number to obtain the first behavior vector.

[0047] Next, the specific configuration of the clustering result acquisition module will be described in further detail. The clustering result acquisition module further includes: calculating a first similarity between the first behavior vector and the first historical behavior vector, including: obtaining an arbitrary vector ordinal number; sequentially matching the second behavior frequency and the third behavior frequency corresponding to the arbitrary vector ordinal number in the first behavior vector and the first historical behavior vector; obtaining the similarity between the second behavior frequency and the third behavior frequency; and obtaining the first similarity based on the similarity.

[0048] Next, the specific configuration of the clustering result acquisition module will be described in further detail. The clustering result acquisition module further includes: after obtaining the similarity between the second behavior frequency and the third behavior frequency, further including: obtaining an arbitrary behavior cluster corresponding to the arbitrary vector ordinal number; performing collaborative analysis on the arbitrary behavior cluster and the target interest behavior to obtain an arbitrary cluster information value of the arbitrary behavior cluster; and adjusting the similarity with the arbitrary cluster information value as a weight.

[0049] Next, the specific configuration of the recommendation display module will be described in detail. The recommendation display module further includes: after forming a first interest service recommendation table according to the target interest behavior of the target user and displaying the first interest service recommendation table to the user terminal of the first user, further including: matching a target service channel of the target interest behavior; performing load monitoring on the target service channel to obtain a target load rate; and performing dynamic resource scheduling on the target service channel based on the target load rate.

[0050] The various units and modules included are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0051] Embodiment III

[0052] Figure 3 It is a schematic structural diagram of an electronic device provided in Embodiment III of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The displayed electronic device is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present invention. As Figure 3 shown, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device can be one or more, Figure 3 taking one processor 31 as an example, the processor 31, the memory 32, the input device 33, and the output device 34 in the electronic device can be connected through a bus or other means, Figure 3 taking the connection through a bus as an example.

[0053] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for managing rights and interests services based on user behavior in the embodiments of the present invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 32, that is, implements the above-mentioned method for managing rights and interests services based on user behavior.

[0054] Note that the above is only a preferred embodiment of the present invention and the applied technical principle. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A rights service management method based on user behavior, characterized in that: include: Acquire first behavior information of a first user, and call a time sequence strategy to analyze the first behavior information to obtain a time sequence of the first user behavior; Extracting a first equity behavior in the first user behavior time series, and obtaining a first interaction time corresponding to the first equity behavior; Analyze the first interaction time in combination with a predetermined interaction threshold constraint to obtain a first behavior time period; matching a first interaction behavior set corresponding to the first behavior time period in the first behavior information, and performing cluster analysis on the first interaction behavior set to obtain a first clustering result; Traversing and matching the first clustering result in the user behavior database to obtain a target clustering result, and obtaining a corresponding target user; A first rights and interests service recommendation table is formed according to the target rights and interests behavior of the target user, and the first rights and interests service recommendation table is displayed to the user terminal of the first user.

2. The rights service management method based on user behavior according to claim 1 is characterized in that: Acquiring first behavior information of a first user, and invoking a time sequence strategy to analyze the first behavior information to obtain a time sequence of the first user behavior, including: Extract any equity behavior in the first behavior information according to the timing strategy; Obtain the time when the first user performs the arbitrary rights and interests behavior, recorded as arbitrary interaction time; The first user behavior time series is constructed according to the corresponding relationship between the arbitrary equity behavior and the arbitrary interaction time.

3. The rights service management method based on user behavior according to claim 1 is characterized in that: include: The first interaction time is analyzed according to the predetermined pre-interaction step threshold and the predetermined post-interaction step threshold in the predetermined interaction threshold constraint to obtain the first behavior time period.

4. The rights service management method based on user behavior according to claim 1 is characterized in that: Traversing and matching the first clustering result in the user behavior database to obtain a target clustering result, and obtaining a corresponding target user, including: According to the vectorization strategy, a plurality of behavior clusters with identifications of behavior times in the first clustering result are vectorized and analyzed to generate a first behavior vector; Extracting a first behavior data group from the user behavior database, where the first behavior data group refers to a first historical behavior clustering result and a first historical equity behavior of a first historical user; Acquire a first historical behavior vector of the first historical behavior clustering result according to the vectorization strategy; Calculating and obtaining a first similarity between the first behavior vector and the first historical behavior vector; If the first similarity reaches a predetermined similarity threshold, the first historical behavior clustering result is used as the target clustering result, and the first historical user is recorded as the target user.

5. The rights service management method based on user behavior according to claim 4 is characterized in that: According to the vectorization strategy, a plurality of behavior clusters with identifications of behavior times in the first clustering result are vectorized and analyzed to generate a first behavior vector, including: Extracting a first behavior cluster from a plurality of behavior clusters having identifications of behavior times, and obtaining a first behavior frequency of the first behavior cluster; Acquire a first vector ordinal of the first behavior cluster according to the vectorization strategy; The frequency of the first behavior is marked onto the first vector ordinal number to obtain the first behavior vector.

6. The rights service management method based on user behavior according to claim 5 is characterized in that: Calculating a first similarity between the first behavior vector and the first historical behavior vector includes: Get the ordinal of any vector; sequentially matching the second behavior frequency and the third behavior frequency corresponding to the arbitrary vector sequence number in the first behavior vector and the first historical behavior vector; Obtaining the similarity between the second behavior frequency and the third behavior frequency; The first similarity is obtained based on the similarity.

7. The rights service management method based on user behavior according to claim 6 is characterized in that: After obtaining the similarity between the second behavior frequency and the third behavior frequency, the method further includes: Obtaining any behavior cluster corresponding to the arbitrary vector ordinal number; Perform collaborative analysis on the arbitrary behavior cluster and the target equity behavior to obtain the arbitrary cluster information value of the arbitrary behavior cluster; The similarity is adjusted by taking the information value of the arbitrary cluster as a weight.

8. The rights service management method based on user behavior according to claim 1 is characterized in that: After forming a first rights and interests service recommendation table according to the target rights and interests behavior of the target user and displaying the first rights and interests service recommendation table to the user terminal of the first user, the method further includes: A target service channel matching the target equity behavior; Performing load monitoring on the target service channel to obtain a target load rate; Dynamically schedule resources for the target service channel based on the target load rate.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; A processor is used to implement the user behavior-based rights service management method as described in any one of claims 1 to 8 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for managing rights and interests services based on user behavior as described in any one of claims 1 to 8 is implemented.

Images