User behavior prediction methods, devices, electronic equipment, and storage media

Abstract

This invention discloses a user behavior prediction method, apparatus, electronic device, and storage medium. The method includes: acquiring historical behavior information input by the user for a target page-clicking behavior with a set execution timeout; extracting historical timeout behavior information and historical standard behavior information from the historical behavior information; predicting the execution timeout probability of the user's target page-clicking behavior based on the historical timeout behavior information; predicting the execution capability probability of the user's target page-clicking behavior based on the historical standard behavior information; and fusing the execution timeout probability and execution capability probability to determine the fusion result as the target probability of the user executing the target page-clicking behavior on schedule. The technical solution of this invention improves the accuracy of user behavior prediction.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a user behavior prediction method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of internet technology, the application of user behavior prediction is becoming increasingly widespread.

[0003] Currently, user behavior prediction considers only a few factors, resulting in poor accuracy. Summary of the Invention

[0004] This invention provides a user behavior prediction method, apparatus, electronic device, and storage medium, which improves the accuracy of user behavior prediction.

[0005] According to one aspect of the present invention, a user behavior prediction method is provided, the method comprising:

[0006] For users who click to browse pages for a target with a set execution deadline, obtain the user's historical input behavior information.

[0007] Extract historical timeout behavior information and historical standard behavior information from historical behavior information.

[0008] Based on historical timeout behavior information, predict the probability of timeout for user actions that involve clicking on a target page.

[0009] Based on historical standard behavior information, predict the probability of a user's ability to perform a target-oriented click-to-browse page action.

[0010] The execution timeout probability and execution capability probability are fused together, and the fusion result is determined as the target probability of the user's scheduled action of clicking to browse the page.

[0011] According to another aspect of the present invention, a user behavior prediction device is provided, the device comprising:

[0012] The historical behavior information acquisition module is used to acquire historical behavior information input by the user based on the user's click and browse page behavior for a target with an execution period set.

[0013] The historical behavior information extraction module is used to extract historical timeout behavior information and historical standard behavior information from historical behavior information;

[0014] The execution timeout probability prediction module is used to predict the execution timeout probability of a user's click-to-browse page behavior based on historical timeout behavior information;

[0015] The execution capability probability prediction module is used to predict the probability of a user's execution capability for a target page browsing behavior based on historical standard behavior information.

[0016] The target probability determination module is used to fuse the execution timeout probability and the execution capability probability, and determine the fusion result as the target probability of the user's scheduled execution of the target page browsing behavior.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the user behavior prediction method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the user behavior prediction method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the user behavior prediction method according to any embodiment of the present invention.

[0023] The technical solution of this invention obtains historical behavior information of the user for the target click-to-browse page behavior with an execution deadline set by the user. It extracts historical timeout behavior information and historical standard behavior information from the historical behavior information. Based on the historical timeout behavior information, it predicts the execution timeout probability of the user for the target click-to-browse page behavior. Based on the historical standard behavior information, it predicts the execution capability probability of the user for the target click-to-browse page behavior. It then fuses the execution timeout probability and the execution capability probability and determines the fusion result as the target probability of the user executing the target click-to-browse page behavior on schedule. This solves the problem of inaccurate user behavior prediction and improves the accuracy of user behavior prediction.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a user behavior prediction method provided in Embodiment 1 of the present invention;

[0027] Figure 2 This is a flowchart of a user behavior prediction method provided in Embodiment 2 of the present invention;

[0028] Figure 3 This is a scenario diagram of a user behavior prediction method provided in Embodiment 2 of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of a user behavior prediction device according to Embodiment 3 of the present invention;

[0030] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the user behavior prediction method of this invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1This is a flowchart illustrating a user behavior prediction method provided in Embodiment 1 of the present invention. This embodiment of the invention is applicable to situations involving the prediction of user behavior. The method can be executed by a user behavior prediction device, which can be implemented in hardware and / or software and can be configured in an electronic device that carries user behavior prediction functionality.

[0035] See Figure 1 The user behavior prediction methods shown include:

[0036] S110. For user clicks on page browsing behavior related to a target with an execution deadline set, obtain historical behavior information entered by the user.

[0037] An execution deadline can be a limitation on the execution time of a target page-viewing action. For target page-viewing actions with a set execution deadline, if the execution time exceeds the deadline, appropriate actions will be taken. Optionally, these actions may include: reminding the user to perform the target page-viewing action, deeming the expired action invalid, or penalizing the user who performed the action. Therefore, when predicting user behavior for target page-viewing actions with a set execution deadline, it is necessary to consider not only whether the action can be performed but also whether the execution time meets the deadline.

[0038] Historical page browsing behavior can be the same as the target page browsing behavior and has been completed. Compared to the target page browsing behavior, historical page browsing behavior and the target page browsing behavior can be the same user behavior, but the historical page browsing behavior has been completed, while the target page browsing behavior is pending execution. Historical page browsing behavior also has a corresponding execution time and execution period. The description of the execution period of historical page browsing behavior is the same as that of the target page browsing behavior, and will not be repeated here.

[0039] Optionally, when predicting a user's target page-clicking behavior with a set execution deadline, the user can input historical behavior information corresponding to at least one previous page-clicking behavior. The target page-clicking behavior is predicted by obtaining this historical behavior information.

[0040] S120. Extract historical timeout behavior information and historical standard behavior information from historical behavior information.

[0041] Historical page browsing behavior can include historical timeout behavior and historical standard behavior. Historical timeout behavior refers to page browsing behavior where the execution time did not meet the execution period. Historical standard behavior refers to page browsing behavior where the execution time met the execution period. Accordingly, historical behavior information can include historical timeout behavior information and historical standard behavior information.

[0042] Specifically, the execution time of each historical page-viewing behavior can be compared with the corresponding execution period of that behavior. If the execution time of a historical page-viewing behavior is within the corresponding execution period, the historical behavior information corresponding to that behavior is identified as historical standard behavior information. If the execution time of a historical page-viewing behavior exceeds the corresponding execution period, the historical behavior information corresponding to that behavior is identified as historical timeout behavior information.

[0043] S130. Based on historical timeout behavior information, predict the execution timeout probability of the user's target click to browse the page.

[0044] The execution timeout probability is used to characterize the probability that the execution time of the target page-viewing behavior will exceed the execution period. Optionally, the higher the execution timeout probability, the greater the likelihood that the execution time of the target page-viewing behavior will exceed the execution period; conversely, the lower the execution timeout probability, the less likely that the execution time of the target page-viewing behavior will exceed the execution period.

[0045] Optionally, historical timeout behavior information can be input into the execution timeout probability prediction model to obtain the execution timeout probability of the user's target click browsing page behavior.

[0046] Optionally, quantitative analysis can be performed based on historical timeout behavior information to analyze and predict the probability of timeout for user actions targeting page views. For example, quantitative analysis methods can include time series analysis and decision analysis. Time series analysis methods include moving averages, smoothing coefficients, seasonal index forecasting, and modified regression analysis; decision analysis methods include cost-volume-profit analysis, input-output analysis, regression analysis, linear programming, and econometrics.

[0047] S140. Based on historical standard behavior information, predict the probability of a user's ability to perform a page browsing behavior targeting a specific user.

[0048] The execution capability probability is used to characterize the probability that the target's click-to-browse page behavior can be executed. Optionally, the higher the execution capability probability, the greater the likelihood that the target's click-to-browse page behavior will be executed; conversely, the lower the execution capability probability, the less likely that the target's click-to-browse page behavior will be executed.

[0049] Optionally, historical standard behavior information can be input into the execution capability probability prediction model to obtain the execution capability probability of a user's target click-and-browse page behavior.

[0050] Optionally, quantitative analysis can be performed based on historical standard behavior information to analyze and predict the probability of a user's ability to perform a click-and-browse page behavior targeting a specific user.

[0051] S150. The execution timeout probability and execution capability probability are fused together, and the fusion result is determined as the target probability of the user's scheduled execution of the target page browsing behavior.

[0052] Specifically, the execution timeout probability and the execution capability probability can be weighted and subtracted to obtain a fusion result, which can then be used as the probability of a user clicking to browse the page on schedule to achieve their target.

[0053] The technical solution of this invention obtains historical behavior information of the user for a target click-to-browse page behavior with a set execution deadline. It extracts historical timeout behavior information and historical standard behavior information from this historical behavior information. Based on the historical timeout behavior information, it predicts the execution timeout probability of the user's target click-to-browse page behavior. Based on the historical standard behavior information, it predicts the execution capability probability of the user's target click-to-browse page behavior. The execution timeout probability and execution capability probability are fused, and the fusion result is determined as the target probability of the user executing the target click-to-browse page behavior on schedule. By considering both the execution capability and the execution deadline of the target click-to-browse page behavior, the target probability of the user executing the target click-to-browse page behavior on schedule is determined, thus balancing the execution capability and the timeliness of the target click-to-browse page behavior, thereby improving the accuracy of the prediction of the target click-to-browse page behavior.

[0054] In an optional embodiment of the present invention, the execution timeout probability and the execution capability probability are fused, specifically by: calculating the difference between the execution capability probability and the execution timeout probability, and determining the difference as the fusion result.

[0055] Specifically, the difference between the execution capability probability and the execution timeout probability can be calculated, and the difference can be determined as the fusion result.

[0056] This solution calculates the difference between the probability of execution capability and the probability of execution timeout, and uses this difference as the fusion result to determine the target probability of a user's scheduled action of clicking and browsing the page. By directly calculating the difference between the probability of execution capability and the probability of execution timeout, the calculation efficiency of determining the target probability of a user's scheduled action of clicking and browsing the page is improved.

[0057] In an optional embodiment of the present invention, predicting the probability of a user's ability to perform a target click-to-browse page action based on historical standard behavior information is specifically defined as: predicting the probability of a user's ability to perform a target click-to-browse page action based on historical environmental information and historical standard behavior information.

[0058] Historical environment information can be environmental information that influences historical page browsing behavior. For example, historical page browsing behavior can be the act of clicking and browsing a page. Historical environment information can include, for instance, the response speed of the application corresponding to the browsed page.

[0059] This solution predicts the probability of a user's ability to perform a target page-clicking behavior based on historical environmental information and historical standard behavior information. In addition to historical standard behavior information, it also considers historical environmental information, using richer information to predict the probability of a user's ability to perform a target page-clicking behavior, thereby improving the accuracy of the predicted probability of performance and, consequently, the accuracy of the predicted probability of a user performing the target page-clicking behavior on schedule.

[0060] In an optional embodiment of the present invention, historical timeout behavior information is specified as historical timeout duration and historical timeout result; historical standard behavior information is specified as historical execution time and historical behavior result.

[0061] Historical timeout duration can be the length of time that a historical timeout action exceeds its corresponding execution period. Historical timeout result can be the change in the execution result before and after executing the historical timeout action. For example, a historical timeout action could be a resource transfer action, and the historical timeout result could be the amount of resources transferred. Another example is a historical timeout action could be a page view click action, and the historical timeout result could be the number of clicks for this page view click action.

[0062] Historical execution time can be the execution time of historical standard behaviors. Historical page-viewing behavior results can include the change in execution results before and after executing the historical standard behavior, and the cumulative amount of execution results after executing the historical standard behavior. For example, a historical standard behavior can be a resource transfer behavior, and the historical behavior results can include the amount of resources transferred and the resource balance. The resource transfer amount can be the change in execution results before and after executing the historical standard behavior, and the resource balance can be the cumulative amount of execution results after executing the historical standard behavior. As another example, historical page-viewing behavior is simply clicking to view a page; the historical behavior results can include the number of clicks for this page-viewing behavior and the cumulative number of page views.

[0063] This solution, by specifying historical timeout behavior information into historical timeout duration and historical timeout results, focuses more specifically on information related to timeouts, avoiding interference from other information in predicting execution timeout probabilities, and further improving the efficiency of predicting the execution timeout probability of user clicks on target page views. By specifying historical standard behavior information into historical execution time and historical behavior results, it utilizes more targeted information to predict execution capability probabilities, further improving the efficiency of predicting the execution capability probability of user clicks on target page views. This, in turn, further improves the efficiency of determining the target probability of a user executing the target click on a page view on schedule.

[0064] Example 2

[0065] Figure 2 This is a flowchart of a user behavior prediction method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment of the present invention specifies "predicting the execution timeout probability of a user's click-to-browse page behavior based on historical timeout behavior information" as "inputting historical timeout behavior information into the execution timeout probability prediction model to obtain the execution timeout probability of the user's click-to-browse page behavior," thus improving the efficiency and accuracy of predicting the execution timeout efficiency of a user's click-to-browse page behavior. It should be noted that parts not described in detail in this embodiment of the present invention can be found in the descriptions of other embodiments.

[0066] See Figure 2 The user behavior prediction methods shown include:

[0067] S210. For user clicks on page browsing behavior related to a target with an execution deadline set, obtain historical behavior information entered by the user.

[0068] S220. Extract historical timeout behavior information and historical standard behavior information from historical behavior information.

[0069] S230. Input the historical timeout behavior information into the execution timeout probability prediction model to obtain the execution timeout probability of the user's target click browsing page behavior.

[0070] The execution timeout probability prediction model predicts the execution timeout probability of a user's target page browsing action based on historical timeout behavior information corresponding to previously executed timeout behaviors. For example, the execution timeout probability prediction model may include linear regression models, logistic regression models, decision tree models, perceptron models, or convolutional neural network models, etc.

[0071] The execution timeout probability prediction model can be trained by obtaining historical timeout behavior information as training samples for execution timeout probability prediction, and then inputting the training samples into the untrained model.

[0072] S240. Based on historical standard behavior information, predict the probability of a user's ability to perform a target-oriented click-to-browse page action.

[0073] S250. The execution timeout probability and execution capability probability are fused together, and the fusion result is determined as the target probability of the user's scheduled execution of the target page browsing behavior.

[0074] The technical solution of this invention improves the efficiency and accuracy of predicting the execution timeout probability of user clicks on a target page by inputting historical timeout behavior information into the execution timeout probability prediction model.

[0075] In an optional embodiment of the present invention, the probability of a user's ability to perform a target click-to-browse page action is predicted based on historical standard behavior information. Specifically, this is achieved by inputting historical standard behavior information into the action ability probability prediction model to obtain the probability of a user's ability to perform a target click-to-browse page action.

[0076] An execution capability probability prediction model can predict the probability of a user's ability to perform a target action of clicking to browse a page, based on historical standard behavior information corresponding to previously executed standard behaviors. For example, execution capability probability prediction models may include linear regression models, logistic regression models, decision tree models, perceptron models, or convolutional neural network models.

[0077] The execution capability probability prediction model can be trained by obtaining historical standard behavior information as training samples for execution capability probability prediction, and then inputting the training samples into the untrained model.

[0078] This solution improves the efficiency and accuracy of predicting the probability of a user's execution capability for a target page-clicking behavior by inputting historical standard behavior information into the execution capability probability prediction model.

[0079] In an optional embodiment of the present invention, before inputting historical timeout behavior information into the execution timeout probability prediction model, the method further includes: obtaining the behavior scenario corresponding to the target click browsing page behavior; and selecting the execution timeout probability prediction model from multiple candidate models based on the behavior scenario.

[0080] A behavioral scenario can be the application context of the target page-clicking behavior. Different behavioral scenarios have varying degrees of urgency regarding execution time limits, and the probability of timeout for a user's target page-clicking behavior also differs. Each candidate model corresponds one-to-one with each behavioral scenario. Based on the behavioral scenario, a corresponding candidate model can be selected from multiple options to serve as the execution timeout probability prediction model.

[0081] This solution obtains the behavioral scenario corresponding to the target click-to-browse page behavior. Based on the behavioral scenario, it selects an execution timeout probability prediction model from multiple candidate models. The behavioral scenario is used as an influencing factor for the execution timeout probability prediction. By selecting the execution timeout probability prediction model based on the behavioral scenario, the solution predicts the execution timeout probability of the user's click-to-browse page behavior, thereby further improving the accuracy of the execution timeout probability prediction.

[0082] In an optional embodiment of the present invention, before inputting historical standard behavior information into the execution capability probability prediction model, the method further includes: obtaining the behavior scenario corresponding to the target click browsing page behavior; and selecting the execution capability probability prediction model from multiple candidate models based on the behavior scenario.

[0083] The probability of a user's ability to click and browse a target page varies depending on the behavioral scenario. Each candidate model corresponds one-to-one with each behavioral scenario. Based on the behavioral scenario, a suitable candidate model can be selected from multiple options to serve as the probability prediction model for execution capability.

[0084] This solution obtains the behavioral scenario corresponding to the target click-and-browse page behavior. Based on the behavioral scenario, it selects an execution capability probability prediction model from multiple candidate models. The behavioral scenario is used as an influencing factor for the execution capability probability prediction. By selecting the execution capability probability prediction model based on the behavioral scenario, the accuracy of the execution capability probability prediction is further improved.

[0085] Figure 3 This is a scenario diagram illustrating a user behavior prediction method provided in Embodiment 2 of the present invention. See also... Figure 3 The user behavior prediction method shown includes: acquiring historical standard behavior information input by the user; performing digital twin simulation on the historical standard behavior information to generate an execution capability probability prediction model; acquiring historical timeout behavior information input by the user; preprocessing the historical timeout behavior information; and training an execution timeout probability prediction model based on the preprocessed historical timeout behavior information; for the user's target page browsing behavior with a set execution deadline, calculating the difference between the output of the execution capability probability prediction model and the output of the execution timeout probability prediction model, thereby achieving algorithm matching and optimization of the execution capability probability prediction model and the execution timeout probability prediction model, and obtaining the target probability of the user executing the target page browsing behavior on schedule.

[0086] The execution timeout probability prediction model is generated through simulation using digital twin technology. Data preprocessing may include data cleaning of historical timeout behavior information and labeling the execution timeout probabilities corresponding to the historical timeout behavior information. By preprocessing the historical timeout behavior information, abnormal data can be removed, and the accuracy of the execution timeout probability prediction model can be determined based on the labeled execution timeout probabilities.

[0087] The probability of execution capability can be determined using the following formula:

[0088]

[0089] Where Y represents the probability of a user's ability to perform a page browsing behavior targeting a specific target; x1, x2, ... represent historical standard behavior information; This is historical environmental information.

[0090] When determining the probability of a user's ability to perform a click-and-browse-page action targeting a specific target, the influence of historical environmental information is considered in addition to historical standard behavior information.

[0091] Optionally, alternative models for predicting the probability of execution capability can be trained for different behavioral scenarios. When predicting the probability of a user's execution capability for the target click-to-browse-page behavior, the behavioral scenario corresponding to the target click-to-browse-page behavior is obtained. Based on the behavioral scenario, an execution capability probability model is selected from multiple alternative models for predicting the probability of execution capability. The execution capability probability model is then used to predict the probability of a user's execution capability for the target click-to-browse-page behavior.

[0092] The following formula can be used to determine the execution timeout probability:

[0093]

[0094] Where W is the probability of timeout for the user's click-to-browse page action; x i1 ,x i2 ...represents historical timeout behavior information; This is the adjustment value.

[0095] The adjustment value is used to adjust the output of the execution timeout probability prediction model. Optionally, the adjustment value can be set and adjusted by technical personnel based on experience. The adjustment value can also be set according to different behavioral scenarios.

[0096] Optionally, alternative models for predicting execution timeout probabilities can be trained for different behavioral scenarios. When predicting the execution timeout probability of a user's click-to-browse-page behavior, the behavioral scenario corresponding to the click-to-browse-page behavior is obtained. Based on the behavioral scenario, an execution timeout probability model is selected from multiple alternative models for predicting execution timeout probabilities. The execution timeout probability model is then used to predict the execution timeout probability of a user's click-to-browse-page behavior.

[0097] The following formula can be used to calculate the probability of a user's timely execution of a target action based on a click-through page view:

[0098]

[0099] Where R is the probability that the user's click-to-browse-page behavior will be executed on schedule; Y is the probability that the user's click-to-browse-page behavior will be executed; and W is the probability that the user's click-to-browse-page behavior will time out.

[0100] This solution acquires historical standard behavior information input by the user, performs digital twin simulation on this information, generates an execution capability probability prediction model, acquires historical timeout behavior information input by the user, preprocesses this information, and trains an execution timeout probability prediction model based on the preprocessed information. For a user's target page-clicking behavior with a set execution deadline, the output of the execution capability probability prediction model is compared with the output of the execution timeout probability prediction model. This achieves algorithm matching and optimization of the two models, yielding the probability that the user's target page-clicking behavior will be executed on schedule. By using the pre-generated execution capability probability prediction model and execution timeout probability prediction model, the efficiency and accuracy of execution capability probability and execution timeout probability prediction are improved.

[0101] Example 3

[0102] Figure 4 This is a schematic diagram of a user behavior prediction device provided in Embodiment 3 of the present invention. This embodiment of the present invention is applicable to situations involving the prediction of user behavior. The device can execute a user behavior prediction method and can be implemented in hardware and / or software. The device can be configured in an electronic device that carries user behavior prediction functionality.

[0103] See Figure 4 The user behavior prediction device shown includes: a historical behavior information acquisition module 410, a historical behavior information extraction module 420, an execution timeout probability prediction module 430, an execution capability probability prediction module 440, and a target probability determination module 450. Among these,

[0104] The historical behavior information acquisition module 410 is used to acquire historical behavior information input by the user for target page clicks with execution deadlines set by the user.

[0105] The historical behavior information extraction module 420 is used to extract historical timeout behavior information and historical standard behavior information from historical behavior information.

[0106] The execution timeout probability prediction module 430 is used to predict the execution timeout probability of a user's click-to-browse page behavior based on historical timeout behavior information.

[0107] The execution capability probability prediction module 440 is used to predict the probability of a user's execution capability for a target click-to-browse page behavior based on historical standard behavior information.

[0108] The target probability determination module 450 is used to fuse the execution timeout probability and the execution capability probability, and determine the fusion result as the target probability of the user's scheduled execution of the target page browsing behavior.

[0109] The technical solution of this invention obtains historical behavior information of the user for a target click-to-browse page behavior with a set execution deadline. It extracts historical timeout behavior information and historical standard behavior information from this historical behavior information. Based on the historical timeout behavior information, it predicts the execution timeout probability of the user's target click-to-browse page behavior. Based on the historical standard behavior information, it predicts the execution capability probability of the user's target click-to-browse page behavior. The execution timeout probability and execution capability probability are fused, and the fusion result is determined as the target probability of the user executing the target click-to-browse page behavior on schedule. By considering both the execution capability and the execution deadline of the target click-to-browse page behavior, the target probability of the user executing the target click-to-browse page behavior on schedule is determined, thus balancing the execution capability and the timeliness of the target click-to-browse page behavior, thereby improving the accuracy of the prediction of the target click-to-browse page behavior.

[0110] In an optional embodiment of the present invention, the target probability determination module 450 includes: a fusion result determination unit, used to calculate the difference between the execution capability probability and the execution timeout probability, and determine the difference as the fusion result.

[0111] In an optional embodiment of the present invention, the execution timeout probability prediction module 430 includes: a timeout probability model prediction unit, used to input historical timeout behavior information into the execution timeout probability prediction model to obtain the execution timeout probability of the user's target click browsing page behavior.

[0112] In an optional embodiment of the present invention, the execution capability probability prediction module 440 includes: a capability probability model prediction unit, used to input historical standard behavior information into the execution capability probability prediction model to obtain the execution capability probability of the user's target click browsing page behavior.

[0113] In an optional embodiment of the present invention, before the execution timeout probability prediction module 430 inputs historical timeout behavior information into the execution timeout probability prediction model, the execution timeout probability prediction module 430 further includes: a behavior scenario determination unit, used to obtain the behavior scenario corresponding to the target click browsing page behavior; and a candidate model filtering unit, used to filter the execution timeout probability prediction model from multiple candidate models according to the behavior scenario.

[0114] In an optional embodiment of the present invention, the execution capability probability prediction module 440 includes: an execution capability probability prediction unit, used to predict the execution capability probability of a user's target click browsing page behavior based on historical environmental information and historical standard behavior information.

[0115] In an optional embodiment of the present invention, the historical timeout behavior information includes the historical timeout duration and the historical timeout result; the historical standard behavior information includes the historical behavior result and the historical execution time.

[0116] The user behavior prediction device provided in the embodiments of the present invention can execute the user behavior prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0117] The acquisition, storage, and application of historical behavior information, historical timeout behavior information, historical standard behavior information, and historical environmental information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0118] Example 4

[0119] Figure 5A schematic diagram of an electronic device 500 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0120] like Figure 5 As shown, the electronic device 500 includes at least one processor 501 and a memory, such as a read-only memory (ROM) 502 and a random access memory (RAM) 503, communicatively connected to the at least one processor 501. The memory stores computer programs executable by the at least one processor. The processor 501 can perform various appropriate actions and processes based on the computer program stored in the ROM 502 or loaded into the RAM 503 from storage unit 508. The RAM 503 can also store various programs and data required for the operation of the electronic device 500. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0121] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0122] Processor 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 501 performs the various methods and processes described above, such as user behavior prediction methods.

[0123] In some embodiments, the user behavior prediction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by processor 501, one or more steps of the user behavior prediction method described above may be performed. Alternatively, in other embodiments, processor 501 may be configured to perform the user behavior prediction method by any other suitable means (e.g., by means of firmware).

[0124] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0126] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0128] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0129] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0130] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0131] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A user behavior prediction method, characterized in that, The method includes: For user clicks on page views for targets with set execution deadlines, obtain the user's historical behavior information. Historical timeout behavior information and historical standard behavior information are extracted from the historical behavior information; wherein, historical timeout behavior is the historical page browsing behavior whose execution time has not met the execution period; historical standard behavior is the historical page browsing behavior whose execution time has met the execution period. Based on the historical timeout behavior information, predict the execution timeout probability of the user's click-to-browse-page behavior; wherein, the execution timeout probability is used to characterize the probability that the execution time of the target click-to-browse-page behavior exceeds the execution period; Based on the historical standard behavior information, predict the probability of the user's ability to perform the target click-to-browse page behavior; wherein, the probability of performance capability is used to characterize the probability of performing the target click-to-browse page behavior; The execution timeout probability and the execution capability probability are fused together, and the fusion result is determined as the target probability that the user will perform the target click and browse page behavior on schedule. The step of predicting the execution timeout probability of the user's target click-to-browse page behavior based on the historical timeout behavior information includes: Based on the adjustment value and the historical timeout behavior information, the execution timeout probability of the user's click-to-browse page behavior targeting the target is predicted; wherein, the adjustment value is set according to different behavioral scenarios; The step of predicting the probability of a user's ability to perform a page-browsing action targeting the target based on the historical standard behavior information includes: Based on historical environmental information and the historical standard behavior information, the probability of the user's ability to perform the action of clicking and browsing the target page is predicted; wherein, the historical environmental information is the response speed of the application corresponding to the browsing page.

2. The method according to claim 1, characterized in that, The step of fusing the execution timeout probability and the execution capability probability includes: Calculate the difference between the execution capability probability and the execution timeout probability, and determine the difference as the fusion result.

3. The method according to claim 1, characterized in that, The step of predicting the execution timeout probability of the user's target click-to-browse page behavior based on the historical timeout behavior information includes: The historical timeout behavior information is input into the execution timeout probability prediction model to obtain the execution timeout probability of the user's click-to-browse page behavior for the target.

4. The method according to claim 3, characterized in that, The step of predicting the probability of a user's ability to perform a page-browsing action targeting a specific object based on the historical standard behavior information includes: The historical standard behavior information is input into the execution capability probability prediction model to obtain the execution capability probability of the user's click-to-browse page behavior for the target.

5. The method according to claim 4, characterized in that, Before inputting the historical timeout behavior information into the execution timeout probability prediction model, the following steps are also included: Obtain the behavioral scenario corresponding to the target's click-and-browse-page behavior; Based on the behavioral scenario, the execution timeout probability prediction model is selected from multiple candidate models.

6. The method according to claim 1, characterized in that, The historical timeout behavior information includes the historical timeout duration and the historical timeout result; the historical standard behavior information includes the historical execution time and the historical behavior result.

7. A user behavior prediction device, characterized in that, The device includes: The historical behavior information acquisition module is used to acquire the historical behavior information input by the user for the user's click browsing page behavior with an execution period set for the target to be executed by the user; The historical behavior information extraction module is used to extract historical timeout behavior information and historical standard behavior information from the historical behavior information; wherein, historical timeout behavior is historical page browsing behavior whose execution time has not met the execution period; historical standard behavior is historical page browsing behavior whose execution time has met the execution period. An execution timeout probability prediction module is used to predict the execution timeout probability of the user's target click-to-browse page behavior based on the historical timeout behavior information; wherein, the execution timeout probability is used to characterize the probability that the execution time of the target click-to-browse page behavior exceeds the execution period; An execution capability probability prediction module is used to predict the execution capability probability of the user's target click-to-browse page behavior based on the historical standard behavior information; wherein, the execution capability probability is used to characterize the probability of performing the target click-to-browse page behavior; The target probability determination module is used to fuse the execution timeout probability and the execution capability probability, and determine the fusion result as the target probability that the user will perform the target click to browse the page on schedule; The execution timeout probability prediction module includes: An execution timeout probability prediction unit is used to predict the execution timeout probability of the user's click-to-browse-page behavior for the target based on an adjustment value and the historical timeout behavior information; wherein, the adjustment value is set according to different behavioral scenarios; The execution capability probability prediction module includes: An execution capability probability prediction unit is used to predict the probability of the user's execution capability for the target click browsing page behavior based on historical environmental information and the historical standard behavior information; wherein, the historical environmental information is the response speed of the application corresponding to the browsing page.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the user behavior prediction method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the user behavior prediction method according to any one of claims 1-6.

Images