Behavior prediction method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a behavior prediction method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a current behavior in a current event of a user and a plurality of historical events of the user, constructing a user behavior network model according to relevance between each historical behavior in the plurality of historical events and the current behavior, and predicting a next behavior according to the current behavior and the user behavior network model, obtaining a next behavior associated with the current behavior; the historical event comprises a plurality of historical behaviors, and the user behavior network model is a probabilistic Boolean network model. According to the method, the user behavior network model is constructed through the plurality of historical behaviors in the plurality of historical events of the user and the current behavior of the user, and the next behavior of the user is predicted based on the user behavior network model and the current behavior of the user, so that a prediction model does not need to be trained, and the prediction efficiency of the user behavior is improved to a certain extent.

Description

Technical Field

[0001] The present application relates to the technical field of big data analysis, and in particular to a behavior prediction method, apparatus, computer equipment, readable storage medium, and program product. Background Art

[0002] With the rapid development of the Internet and mobile technology, more and more users choose to complete their behaviors online (for example, sharing knowledge through online query, browsing, downloading, sharing, etc.), and a large amount of online data will be generated during the online behavior process, such as the order of occurrence of each online action, the event, the address, etc. Providing personalized behavior recommendations to users based on their online data can improve the efficiency of their online behavior and increase user experience. In related technologies, prediction models are usually trained based on the huge and complex data on the Internet, and user behavior is predicted based on the prediction model, and behavior recommendations can be made based on the prediction results.

[0003] However, the above-mentioned user behavior prediction methods have the problem of low prediction efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a behavior prediction method, device, computer equipment, readable storage medium and program product that can improve the efficiency of user behavior prediction in response to the above technical problems.

[0005] In a first aspect, the present application provides a behavior prediction method, comprising:

[0006] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0007] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0008] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0009] In one embodiment, the user behavior network model is constructed based on the correlation between each historical behavior and the current behavior in multiple historical events, including:

[0010] According to the correlation between each historical behavior and the current behavior in multiple historical events, construct an initial behavior logic function corresponding to each current behavior contained in the current event;

[0011] Get the associated parameters of each historical behavior and the current behavior;

[0012] According to the associated parameters and each initial behavior logic function, a user behavior network model is constructed.

[0013] In one embodiment, the historical events are discrete behavior events, and the step of obtaining the correlation parameters between each historical behavior and the current behavior includes:

[0014] According to the occurrence of each historical behavior in multiple historical events, the probability of occurrence of the historical behavior in multiple preset scenarios is determined;

[0015] Determine the structure matrix of each initial behavior logic function;

[0016] According to the occurrence probability of historical behaviors and the structural matrix of the logic function of each initial behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0017] In one embodiment, the historical event is an event of continuous behavior, and the acquisition of the associated parameters of each historical behavior and the current behavior includes:

[0018] Analyze the correlation between each historical behavior and current behavior in multiple historical events, and determine the steady-state distribution function corresponding to the correlation;

[0019] Determine the transition probability between each historical behavior and the current behavior according to the steady-state distribution function;

[0020] According to the transition probability between each historical behavior and the current behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0021] In one embodiment, the user behavior network model is constructed based on the association parameters and each initial behavior logic function, including:

[0022] Perform multiplication operation on all initial behavior logic functions to obtain the behavior logic function after operation;

[0023] According to the behavioral logic function and associated parameters after operation, a user behavior network model is constructed.

[0024] In one embodiment, the method further comprises:

[0025] Get control parameters; control parameters are used to control the probability of the current behavior;

[0026] According to the correlation between historical behaviors and current behaviors in multiple historical events, a user behavior network model is constructed, including:

[0027] According to the correlation between historical behaviors and current behaviors in multiple historical events, as well as control parameters, a user behavior network model is constructed.

[0028] In a second aspect, the present application also provides a behavior prediction device, comprising:

[0029] The acquisition module is used to acquire the current behavior of the user in the current event and multiple historical events of the user; the historical events include multiple historical behaviors;

[0030] A construction module is used to construct a user behavior network model based on the correlation between each historical behavior and the current behavior in multiple historical events; the user behavior network model is a probabilistic Boolean network model;

[0031] The prediction module is used to predict the next behavior based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0034] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0035] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0037] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0038] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0039] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0040] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0041] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0042] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0043] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0044] The above behavior prediction method, device, computer equipment, readable storage medium and program product obtain the current behavior of the user in the current event, as well as multiple historical events of the user, and construct a user behavior network model based on the correlation between each historical behavior in multiple historical events and the current behavior, and predict the next behavior based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior; the historical event includes multiple historical behaviors, and the user behavior network model is a probabilistic Boolean network model. The above method constructs a user behavior network model by analyzing the correlation between multiple historical behaviors in multiple historical events of the user and the user's current behavior, and predicts the user's next behavior based on the user behavior network model and the user's current behavior. Compared with the existing method of training a prediction model based on the user's historical behavior and predicting user behavior based on the prediction model, the present application does not need to train a prediction model, which improves the prediction efficiency of user behavior to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A diagram of an application environment of a behavior prediction method in an embodiment;

[0047] Figure 2 A flow chart of a behavior prediction method in one embodiment;

[0048] Figure 3 A flow chart of a behavior prediction method in another embodiment;

[0049] Figure 4 A flow chart of a behavior prediction method in another embodiment;

[0050] Figure 5 A flow chart of a behavior prediction method in another embodiment;

[0051] Figure 6 A flow chart of a behavior prediction method in another embodiment;

[0052] Figure 7 A flow chart of a behavior prediction method in another embodiment;

[0053] Figure 8 is a structural block diagram of a behavior prediction device in one embodiment;

[0054] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] With the rapid development of the Internet and mobile technology, more and more users choose to complete their behaviors online (for example, sharing knowledge by searching, browsing, downloading, sharing, etc. online). A large amount of online data will be generated in the process of online behaviors, such as the order of occurrence of various online actions, the events that occurred, the addresses where they occurred, etc. Providing users with personalized behavior recommendations based on their online data can improve the efficiency of their online behaviors and increase user experience.

[0057] In general, the user behavior network is a complex concept. It involves various behaviors of users on many Internet products and the correlation between these behaviors. If we can analyze the user's behavior and simulate the operations that the user may perform, we can better understand the user's real needs and behavior patterns, and thus formulate more accurate marketing strategies and product optimization plans. In related technologies, prediction models are usually trained based on huge and complex data on the Internet, and user behavior is predicted based on the prediction model, and behavior recommendations can be made based on the prediction results. The above-mentioned user behavior prediction methods have the following main shortcomings:

[0058] 1) Limited model accuracy: If the model design is inaccurate or there is a large difference with the actual user behavior, the simulation results may be inaccurate, resulting in limited model accuracy; 2) Data uncertainty: When training the model, a large amount of parameters and data need to be input. The precision and accuracy of these data and parameters have an important impact on the model training results. If the data and parameters are inaccurate, the model prediction results may also be inaccurate; 3) Failure to reflect the prediction probability: Traditional model predictions are all deterministic predictions, which can only give the user's next possible behavior, but cannot reflect the probability of the behavior; 4) Low prediction efficiency: When it is necessary to predict the user's next behavior, it is necessary to first train the prediction model corresponding to the user, and then predict the user's next behavior based on the prediction model. This application aims to solve the above problems.

[0059] After introducing the background technology of the behavior prediction method provided by the embodiment of the present application, the following briefly describes the implementation environment involved in the behavior prediction method provided by the embodiment of the present application. The behavior prediction method provided by the embodiment of the present application can be applied to Figure 1 In the application environment shown, the implementation environment includes a server 104, which can be implemented by an independent server 104 or a server cluster composed of multiple servers 104, and a data storage system 102 can store data that the server 104 needs to process. The data storage system 102 can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the server 104 can obtain multiple historical events of the user and the current behavior of the user in the current event, and then, based on the correlation between the multiple historical events of the user and the current behavior of the user in the current event, a user behavior network model is constructed, and based on the user behavior network model and the current behavior of the user, the next behavior of the user is predicted.

[0060] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific terminal may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0061] After introducing the application scenarios of the behavior prediction method provided in the embodiments of the present application, the following focuses on introducing the behavior prediction method described in the present application.

[0062] In one embodiment, Figure 2 As shown, a behavior prediction method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0063] S201. Obtain the current behavior of the user in the current event and multiple historical events of the user.

[0064] The current event refers to the event that the user is currently performing, and the current event includes multiple behaviors, such as the previous behavior, the current behavior, and the next behavior; the current behavior refers to the behavior that the user is performing in the current event.

[0065] Among them, historical events include multiple historical actions.

[0066] It should be noted that the behaviors in historical events and the behaviors in current events can both refer to behaviors such as querying, browsing, downloading, and sharing.

[0067] In an embodiment of the present application, when it is necessary to predict the next behavior of the user, the current behavior of the user in the current event and the multiple historical behaviors respectively included in the user's multiple historical events can be obtained first; optionally, the current behavior of the user in the current event can be obtained from the server in real time, and the multiple historical behaviors respectively included in the user's multiple historical events can be obtained from the storage database in the server.

[0068] Optionally, after obtaining the current behavior of the user in the current event and the user's multiple historical events as described above, data preprocessing can be performed on the user's current behavior in the current event and the user's multiple historical events to obtain preprocessed data, and then feature extraction can be performed on the preprocessed data to obtain feature-extracted data.

[0069] For example, the collected raw data can be cleaned, converted and standardized to improve data quality and ensure that it can be applied to the probabilistic Boolean network; in addition, meaningful feature data can be extracted from the preprocessed data to facilitate the construction of the probabilistic Boolean network model.

[0070] Optionally, if each user's behavior is regarded as each node in the Boolean network , whether the user behavior occurs corresponds to the 1 and 0 states of the node respectively, and the value range of the node is called the logical domain. To represent logic using matrices, we equate 1 with , equating 0 to , that is, the matrix representation is shown in the following formula (1):

[0071]

[0072] In addition, the interaction relationship between user behaviors is defined as the mutual inhibition relationship between nodes in the Boolean network, using the Boolean function Assume that the user will perform two actions, search and download, which correspond to nodes 1 and 2 in the Boolean network respectively. The possible states of the system are as follows:

[0073] (1) After the search, the download operation will be performed. If the system is initially in state 00, the system will reach state 11 after the search is performed;

[0074] (2) No download operation will be performed after the search. If the system is initially in state 00, the system will reach state 01 or 10 after the search is performed.

[0075] S202: construct a user behavior network model based on the correlation between each historical behavior and the current behavior in multiple historical events.

[0076] Among them, the user behavior network model is a probabilistic Boolean network model.

[0077] In an embodiment of the present application, after obtaining multiple historical behaviors in multiple historical events and the current behavior in the current event, the correlation between each historical behavior in the multiple historical events and the current behavior can be analyzed, and based on the correlation between each historical behavior in the multiple historical events and the current behavior, a user behavior network model can be constructed.

[0078] Optionally, an initial Boolean network model can be constructed based on each historical behavior in multiple historical events, and then based on the relationship between the initial Boolean network model and the current behavior, the correlation between each historical behavior in multiple historical events and the current behavior is determined. Then, based on the correlation between each historical behavior in multiple historical events and the current behavior, a user behavior network model is constructed.

[0079] S203: predict the next behavior based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0080] In an embodiment of the present application, after the current behavior of the current event is obtained as described above and the user behavior network model is determined, the next behavior associated with the current behavior can be predicted based on the user behavior network model to obtain the next behavior associated with the current behavior.

[0081] The behavior prediction method provided in the embodiment of the present application obtains the current behavior of the user in the current event, as well as multiple historical events of the user, and constructs a user behavior network model based on the correlation between each historical behavior in multiple historical events and the current behavior, and predicts the next behavior based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior; the historical event includes multiple historical behaviors, and the user behavior network model is a probabilistic Boolean network model. The above method constructs a user behavior network model by analyzing the correlation between multiple historical behaviors in multiple historical events of the user and the user's current behavior, and predicts the user's next behavior based on the user behavior network model and the user's current behavior. Compared with the existing method of training a prediction model based on the user's historical behavior and predicting user behavior based on the prediction model, the present application does not need to train a prediction model, which improves the prediction efficiency of user behavior to a certain extent.

[0082] In one embodiment, Figure 2 Based on the embodiment shown, a method for constructing a user behavior network model can be described, see Figure 3 The above S202 "building a user behavior network model based on the correlation between each historical behavior and the current behavior in multiple historical events" includes:

[0083] S301. Constructing an initial behavior logic function corresponding to each current behavior included in the current event according to the correlation between each historical behavior and the current behavior in multiple historical events.

[0084] In the embodiment of the present application, after the correlation between each historical behavior and the current behavior in the multiple historical events is obtained, the initial behavior logic function corresponding to each current behavior contained in the current event can be constructed according to the correlation between each historical behavior and the current behavior in the multiple historical events. Optionally, the user's n historical behaviors can be constructed as a Boolean network with n nodes, and the initial behavior logic function corresponding to each current behavior contained in the current event can be seen in the following formula (2):

[0085]

[0086] in, , ,..., Respectively represent multiple historical behaviors in historical events, , ,..., Respectively represent n different logical relationships, , ,..., Respectively represent multiple behaviors in the current event.

[0087] in, represents the mutual influence between user behaviors, so that the user behavior network is simulated as a probabilistic Boolean network. Each logical function have Possibility, for The probability of , denoted as That is ,and , assuming that the above probabilistic Boolean networks are independent of each other, that is, the logic function Independent of each other.

[0088] S302: Obtain the correlation parameters between each historical behavior and the current behavior.

[0089] The associated parameters include associated parameters when the historical event is a discrete behavior event and associated parameters when the historical event is a continuous behavior event.

[0090] In the embodiment of the present application, after the initial behavior logic function corresponding to each current behavior included in the current event is obtained, the association parameters between each historical behavior and the current behavior can also be obtained.

[0091] Optionally, two methods for obtaining associated parameters are provided below:

[0092] First, when historical events are discrete acts, see Figure 4 , S302 "obtaining the associated parameters of each historical behavior and the current behavior" includes:

[0093] S401. Determine the occurrence probability of the historical behavior in multiple preset scenarios according to the occurrence of each historical behavior in multiple historical events.

[0094] In the embodiment of the present application, it is assumed that each historical behavior in each historical event is independent of each other, so the occurrence of each historical behavior in multiple historical events can be listed one by one to obtain a matrix such as the following formula (3):

[0095]

[0096] in, , , each row of the K matrix represents a possible historical event. For example, the first row of the K matrix represents that the user's historical behaviors are all query historical events, and the second row of the K matrix represents that except for the last historical behavior which is a review behavior, all other historical behaviors of the user are query historical events.

[0097] It should be noted that each row of the matrix K represents a possible scenario, and the probability of occurrence of historical behaviors under multiple scenarios of the matrix K can be expressed by the following formula (4):

[0098]

[0099] in, Represents the element in the i-th row and j-th column of matrix K.

[0100] S402: Determine the structure matrix of each initial behavior logic function.

[0101] In the embodiment of the present application, after the above formula (2) determines the initial behavior logic function corresponding to each current behavior contained in the current event, formula (2) can be converted to obtain the conversion form shown in the following formula (5):

[0102]

[0103] in, , ,..., That is the structural matrix of each initial behavior logic function.

[0104] S403: Determine the correlation parameters between each of the historical behaviors and the current behavior according to the occurrence probability of the historical behaviors and the structural matrix of each initial behavior logic function.

[0105] In an embodiment of the present application, after the probability of occurrence of historical behaviors and the structural matrix of each initial behavior logic function are obtained as described above, the association parameters of each historical behavior and the current behavior can be determined based on the probability of occurrence of historical behaviors and the structural matrix of each initial behavior logic function.

[0106] Optionally, the association parameter L between each historical behavior and the current behavior can be expressed by the following formula (6):

[0107]

[0108] The mathematical expectation of the correlation parameter L between each historical behavior and the current behavior can be expressed by the following formula (7):

[0109]

[0110] in, , represents the transition probability from event i to event i.

[0111] In summary, when the historical event is a discrete behavior event, the association parameters between each historical behavior and the current behavior are obtained.

[0112] Second, in the case of historical events being events of continuous conduct, cf. Figure 5 , S302 "obtaining the associated parameters of each historical behavior and the current behavior" includes:

[0113] S501, analyzing the correlation between each historical behavior and the current behavior in multiple historical events, and determining a steady-state distribution function corresponding to the correlation.

[0114] In the embodiment of the present application, if the historical event is an event of continuous behavior, then there is a steady-state distribution, see formula (8):

[0115]

[0116] Make .

[0117] S502: Determine the transition probability between each historical behavior and the current behavior according to the steady-state distribution function.

[0118] In the embodiment of the present application, after the steady-state distribution function corresponding to the correlation is obtained as described above, the transition probability matrix between the nodes of each behavior in the user behavior network based on the probabilistic Boolean network model can be obtained according to the steady-state distribution function corresponding to the correlation as follows:

[0119]

[0120] S503: Determine association parameters between each historical behavior and the current behavior according to the transition probability between each historical behavior and the current behavior.

[0121] In the embodiment of the present application, after the transition probabilities between each historical behavior and the current behavior are obtained, the association parameters between each historical behavior and the current behavior can be determined according to the transition probabilities between each historical behavior and the current behavior. Optionally, the association parameters between each historical behavior and the current behavior refer to the following formula (10):

[0122]

[0123] In summary, when the historical event is a continuous behavior event, the association parameters between each historical behavior and the current behavior are obtained.

[0124] S303: Construct a user behavior network model according to the associated parameters and each initial behavior logic function.

[0125] In an embodiment of the present application, after obtaining the association parameters between each historical behavior and the current behavior, as well as the initial behavior logic functions corresponding to each current behavior contained in the current event, a user behavior network model can be constructed based on the association parameters and the initial behavior logic functions.

[0126] Optionally, a specific implementation method for constructing a user behavior network model is provided below. Figure 6 The above S303 “constructing a user behavior network model according to the associated parameters and each initial behavior logic function” includes:

[0127] S601: Perform multiplication operation on all initial behavior logic functions to obtain the behavior logic function after operation.

[0128] In the embodiment of the present application, after the initial behavior logic function is obtained as described above, a multiplication operation may be performed on all the initial behavior logic functions to obtain the behavior logic after the operation.

[0129] Optionally, after obtaining the initial behavior logic function shown in formula (2), all the initial behavior logic functions can be multiplied to obtain the behavior logic after operation shown in Figure (11):

[0130]

[0131] in, .

[0132] in, .

[0133] S602: construct a user behavior network model based on the calculated behavior logic function and associated parameters.

[0134] In an embodiment of the present application, after obtaining the post-calculation behavior logic function and associated parameters as described above, a mathematical expectation operation can be performed on the post-calculation behavior logic function to obtain the post-calculation behavior logic function, and based on the post-calculation behavior logic function and associated parameters, a user behavior network model can be constructed.

[0135] Optional, remember The mathematical expectation of , we can get:

[0136]

[0137] The method for constructing a user behavior network model provided in the embodiment of the present application provides a data basis for subsequently determining the next behavior of the user based on the user behavior network model.

[0138] In one embodiment, Figure 2-Figure 6 Based on the embodiment shown, see Figure 7 , the above method further comprises:

[0139] S204: Obtain control parameters.

[0140] Among them, the control parameter is used to control the probability of the current behavior occurring.

[0141] In the embodiment of the present application, control parameters can also be obtained when constructing the user behavior network model.

[0142] The above S202 “building a user behavior network model based on the correlation between each historical behavior and the current behavior in multiple historical events” includes:

[0143] S202: construct a user behavior network model according to the correlation between each historical behavior and the current behavior in multiple historical events, as well as control parameters.

[0144] In an embodiment of the present application, after obtaining multiple historical behaviors in multiple historical events and the current behavior in the current event, the correlation between each historical behavior in the multiple historical events and the current behavior can be analyzed, and after obtaining the control parameters, a user behavior network model can be constructed based on the correlation between each historical behavior in the multiple historical events and the current behavior, and the control parameters.

[0145] The method for constructing the user behavior network model provided in the embodiment of the present application refers to the control parameters, so that the constructed user behavior network model is more accurate.

[0146] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0147] Based on the same inventive concept, the embodiment of the present application also provides a behavior prediction device for implementing the behavior prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more behavior prediction device embodiments provided below can refer to the limitations on the behavior prediction method above, and will not be repeated here.

[0148] In an exemplary embodiment, Figure 8 As shown, a behavior prediction device is provided, comprising: an acquisition module 10, a construction module 11 and a prediction module 12, wherein:

[0149] The acquisition module 10 is used to acquire the current behavior of the user in the current event and multiple historical events of the user; the historical events include multiple historical behaviors.

[0150] The construction module 11 is used to construct a user behavior network model according to the correlation between each historical behavior and the current behavior in multiple historical events; the user behavior network model is a probabilistic Boolean network model.

[0151] The prediction module 12 is used to predict the next behavior based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0152] In an exemplary embodiment, the construction module 11 includes: a first construction unit, an acquisition unit, and a second construction unit, wherein:

[0153] The first construction unit is specifically used to construct an initial behavior logic function corresponding to each current behavior included in the current event according to the correlation between each historical behavior and the current behavior in multiple historical events;

[0154] An acquisition unit, specifically used to acquire the associated parameters of each historical behavior and the current behavior;

[0155] The second construction unit is specifically used to construct a user behavior network model according to the associated parameters and each initial behavior logic function.

[0156] In an exemplary embodiment, the above-mentioned historical events are events of discrete behaviors, and the above-mentioned acquisition unit is specifically used to determine the probability of occurrence of historical behaviors in multiple preset scenarios based on the occurrence of each historical behavior in multiple historical events; determine the structural matrix of each initial behavior logic function; and determine the association parameters between each historical behavior and the current behavior based on the probability of occurrence of historical behaviors and the structural matrix of each initial behavior logic function.

[0157] In an exemplary embodiment, the historical event is an event of continuous behavior, and the acquisition unit is specifically used to analyze the correlation between each historical behavior and the current behavior in multiple historical events, and determine the steady-state distribution function corresponding to the correlation; determine the transition probability between each historical behavior and the current behavior according to the steady-state distribution function; determine the association parameters between each historical behavior and the current behavior according to the transition probability between each historical behavior and the current behavior.

[0158] In an exemplary embodiment, the second construction unit is specifically used to perform multiplication operations on all initial behavior logic functions to obtain the behavior logic functions after the operations; and to construct a user behavior network model based on the behavior logic functions after the operations and associated parameters.

[0159] In an exemplary embodiment, the above device further includes: an acquisition module, used to acquire a control parameter; the control parameter is used to control the probability of the current behavior occurring;

[0160] The above-mentioned construction module is also used to construct a user behavior network model according to the correlation between each historical behavior and the current behavior in multiple historical events, as well as control parameters.

[0161] Each module in the above-mentioned behavior prediction device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0162] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store event behavior data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a behavior prediction method is implemented.

[0163] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0164] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0165] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0166] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0167] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0168] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0169] According to the correlation between each historical behavior and the current behavior in multiple historical events, construct an initial behavior logic function corresponding to each current behavior contained in the current event;

[0170] Get the associated parameters of each historical behavior and the current behavior;

[0171] According to the associated parameters and each initial behavior logic function, a user behavior network model is constructed.

[0172] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0173] According to the occurrence of each historical behavior in multiple historical events, the probability of occurrence of the historical behavior in multiple preset scenarios is determined;

[0174] Determine the structure matrix of each initial behavior logic function;

[0175] According to the occurrence probability of historical behaviors and the structural matrix of the logic function of each initial behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0176] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0177] Analyze the correlation between each historical behavior and current behavior in multiple historical events, and determine the steady-state distribution function corresponding to the correlation;

[0178] Determine the transition probability between each historical behavior and the current behavior according to the steady-state distribution function;

[0179] According to the transition probability between each historical behavior and the current behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0180] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0181] Perform multiplication operation on all initial behavior logic functions to obtain the behavior logic function after operation;

[0182] According to the behavioral logic function and associated parameters after operation, a user behavior network model is constructed.

[0183] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0184] Get control parameters; control parameters are used to control the probability of the current behavior;

[0185] According to the correlation between historical behaviors and current behaviors in multiple historical events, a user behavior network model is constructed, including:

[0186] According to the correlation between historical behaviors and current behaviors in multiple historical events, as well as control parameters, a user behavior network model is constructed.

[0187] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0188] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0189] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0190] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0191] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0192] According to the correlation between each historical behavior and the current behavior in multiple historical events, construct an initial behavior logic function corresponding to each current behavior contained in the current event;

[0193] Get the associated parameters of each historical behavior and the current behavior;

[0194] According to the associated parameters and each initial behavior logic function, a user behavior network model is constructed.

[0195] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0196] According to the occurrence of each historical behavior in multiple historical events, the probability of occurrence of the historical behavior in multiple preset scenarios is determined;

[0197] Determine the structure matrix of each initial behavior logic function;

[0198] According to the occurrence probability of historical behaviors and the structural matrix of the logic function of each initial behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0199] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0200] Analyze the correlation between each historical behavior and current behavior in multiple historical events, and determine the steady-state distribution function corresponding to the correlation;

[0201] Determine the transition probability between each historical behavior and the current behavior according to the steady-state distribution function;

[0202] According to the transition probability between each historical behavior and the current behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0204] Perform multiplication operation on all initial behavior logic functions to obtain the behavior logic function after operation;

[0205] According to the behavioral logic function and associated parameters after operation, a user behavior network model is constructed.

[0206] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0207] Get control parameters; control parameters are used to control the probability of the current behavior;

[0208] According to the correlation between historical behaviors and current behaviors in multiple historical events, a user behavior network model is constructed, including:

[0209] According to the correlation between historical behaviors and current behaviors in multiple historical events, as well as control parameters, a user behavior network model is constructed.

[0210] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0211] Get the current behavior of the user in the current event, as well as multiple historical events of the user; historical events include multiple historical behaviors;

[0212] According to the correlation between each historical behavior and current behavior in multiple historical events, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model;

[0213] The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0215] According to the correlation between each historical behavior and the current behavior in multiple historical events, construct an initial behavior logic function corresponding to each current behavior contained in the current event;

[0216] Get the associated parameters of each historical behavior and the current behavior;

[0217] According to the associated parameters and each initial behavior logic function, a user behavior network model is constructed.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0219] According to the occurrence of each historical behavior in multiple historical events, the probability of occurrence of the historical behavior in multiple preset scenarios is determined;

[0220] Determine the structure matrix of each initial behavior logic function;

[0221] According to the probability of occurrence of historical behaviors and the structural matrix of the logic function of each initial behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] Analyze the correlation between each historical behavior and current behavior in multiple historical events, and determine the steady-state distribution function corresponding to the correlation;

[0224] Determine the transition probability between each historical behavior and the current behavior according to the steady-state distribution function;

[0225] According to the transition probability between each historical behavior and the current behavior, the correlation parameters between each historical behavior and the current behavior are determined.

[0226] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0227] Perform multiplication operation on all initial behavior logic functions to obtain the behavior logic function after operation;

[0228] According to the behavioral logic function and associated parameters after operation, a user behavior network model is constructed.

[0229] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0230] Get control parameters; control parameters are used to control the probability of the current behavior;

[0231] According to the correlation between historical behaviors and current behaviors in multiple historical events, a user behavior network model is constructed, including:

[0232] According to the correlation between historical behaviors and current behaviors in multiple historical events, as well as control parameters, a user behavior network model is constructed.

[0233] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0234] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0235] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0236] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A behavior prediction method, characterized in that: The method comprises: Acquire the current behavior of the user in the current event and multiple historical events of the user; the historical events include multiple historical behaviors; According to the correlation between each historical behavior in the multiple historical events and the current behavior, a user behavior network model is constructed; the user behavior network model is a probabilistic Boolean network model; The next behavior is predicted based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

2. The method according to claim 1, characterized in that: The constructing of a user behavior network model according to the correlation between each historical behavior in the multiple historical events and the current behavior includes: According to the correlation between each historical behavior in the multiple historical events and the current behavior, construct an initial behavior logic function corresponding to each current behavior included in the current event; Obtaining correlation parameters between each of the historical behaviors and the current behavior; The user behavior network model is constructed according to the association parameters and each of the initial behavior logic functions.

3. The method according to claim 2, characterized in that The historical events are discrete behavior events, and obtaining the associated parameters of each of the historical behaviors and the current behavior includes: Determining the probability of occurrence of the historical behaviors in multiple preset scenarios according to the occurrence of each historical behavior in the multiple historical events; Determine the structure matrix of each of the initial behavior logic functions; According to the occurrence probability of the historical behaviors and the structural matrix of the logic functions of the initial behaviors, the correlation parameters between the historical behaviors and the current behaviors are determined.

4. The method according to claim 2, characterized in that: The historical events are events of continuous behaviors, and the obtaining of associated parameters of each of the historical behaviors and the current behavior includes: Analyzing the correlation between each historical behavior in the multiple historical events and the current behavior, and determining a steady-state distribution function corresponding to the correlation; Determine the transition probability between each of the historical behaviors and the current behavior according to the steady-state distribution function; According to the transition probability between each of the historical behaviors and the current behavior, the association parameters between each of the historical behaviors and the current behavior are determined.

5. The method according to claim 2, characterized in that: The step of constructing the user behavior network model according to the association parameters and each of the initial behavior logic functions includes: Perform multiplication operation on all initial behavior logic functions to obtain the behavior logic function after operation; The user behavior network model is constructed based on the calculated behavior logic function and the associated parameters.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire a control parameter; the control parameter is used to control the probability of the current behavior occurring; The constructing of a user behavior network model according to the correlation between each historical behavior in the multiple historical events and the current behavior includes: The user behavior network model is constructed according to the correlation between each historical behavior in the multiple historical events and the current behavior, and the control parameters.

7. A behavior prediction device, characterized in that: The device comprises: An acquisition module, used to acquire a current behavior of a user in a current event, and a plurality of historical events of the user; the historical events include a plurality of historical behaviors; A construction module, used to construct a user behavior network model according to the correlation between each historical behavior in the multiple historical events and the current behavior; the user behavior network model is a probabilistic Boolean network model; The prediction module is used to predict the next behavior based on the current behavior and the user behavior network model to obtain the next behavior associated with the current behavior.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images