Event speculation system, method, electronic device, and storage medium

Abstract

The application relates to an event speculation system, method, electronic device and storage medium. The event speculation system comprises a front-end event collection terminal and a server. The front-end event collection terminal is used for collecting front-end events and uploading the front-end events to the server. The server comprises a front-end event receiving interface, a back-end event collection module and an intelligent inference module. The front-end event receiving interface is used for sending the front-end events to the intelligent inference module. The back-end event collection module is used for collecting back-end events and sending the back-end events to the intelligent inference module. The intelligent inference module is used for loading preset inference rules based on a rule library, and inferring missing events according to the front-end events, the back-end events and the preset inference rules. Through the combination of the front-end events and the back-end events, the intelligent inference module can infer the missing user behavior events in the case that part of the front-end events are missing, thereby providing a data basis for accurate analysis of user behavior and greatly improving the accuracy of user behavior analysis.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to event prediction systems, methods, electronic devices, and storage media. Background Technology

[0002] The collection of user behavior events is the foundation for user behavior analysis and prediction, as well as personalized and precise marketing. User behavior events are typically collected at the system's front end. However, in practice, situations may arise where front-end events cannot be collected, or the collected events may be lost, resulting in missing front-end event records stored on the back-end server. This hinders accurate recording and analysis of user behavior.

[0003] In existing technologies, some human-computer interaction interfaces cannot embed data collection code, such as integrated third-party interface components, which cannot embed event collection code at the source code level. Therefore, it is urgent to solve how to obtain user behavior events when front-end events cannot be collected or the collected events are lost. Summary of the Invention

[0004] In view of the above problems, embodiments of this application are proposed to provide an event prediction system, method, electronic device, and storage medium that overcomes or at least partially solves the above problems.

[0005] According to a first aspect of this application, an event prediction system is provided, the system comprising: a front-end event acquisition terminal, and a server;

[0006] The front-end event acquisition terminal is used to acquire front-end events from a preset interactive interface and upload the front-end events to the front-end event receiving interface in the server.

[0007] The server includes the front-end event receiving interface, the back-end event acquisition module, and the intelligent inference module;

[0008] The front-end event receiving interface is used to send the front-end event to the intelligent inference module;

[0009] The backend event acquisition module is used to collect backend events and send the backend events to the intelligent inference module;

[0010] The intelligent inference module is used to infer missing events based on the front-end events, the back-end events, and preset inference rules.

[0011] Optionally, the intelligent inference module includes: an event pool, a time window processing module, and a rule engine;

[0012] The event pool is used to store the front-end events and the back-end events;

[0013] The time window processing module is used to process the front-end events and the back-end events within a preset time interval, and input the processed front-end events and back-end events into the rule engine;

[0014] The rule engine is used to infer missing events based on the front-end events, the back-end events, and the preset inference rules, and generate inferred events.

[0015] Optionally, the intelligent inference module further includes: a deduplication processing module;

[0016] The deduplication processing module is used to receive the speculative events sent by the rule engine, perform deduplication processing on the speculative events, and output the target speculative event.

[0017] Optionally, the rule engine includes any of the following:

[0018] Rule engines based on logic, rule engines based on neural networks, and rule engines based on probability calculation.

[0019] Optionally, the server may further include a user event processing module;

[0020] The user event processing module is used to process the front-end events, the back-end events, and the target missing events in a unified manner.

[0021] Optionally, the server may further include a user event storage module;

[0022] The user event storage module is used to uniformly store the front-end events, the back-end events, and the target missing events.

[0023] Optionally, the server further includes: a rule base, the rule base including the preset inference rules;

[0024] The rule base is used to send preset inference rules to the intelligent inference module and generate the corresponding rule engine.

[0025] Optionally, the attribute information corresponding to the preset inference rule in the rule base includes any one or a combination of the following:

[0026] Event combination, event sequence order, logical relationship between events, event occurrence time constraint, event interval time constraint, and event occurrence frequency constraint.

[0027] According to a second aspect of this application, an event prediction method is provided, characterized in that the method includes:

[0028] Collect front-end events from a preset interactive interface;

[0029] If a frontend event is detected, retrieve the backend event;

[0030] The missing events are inferred based on the front-end events, the back-end events, and the preset inference rules.

[0031] According to a third aspect of this application, an electronic device is provided, characterized in that it includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus.

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute programs stored in memory.

[0034] According to a fourth aspect of this application, a computer-readable storage medium is provided on which a computer program is stored.

[0035] The event prediction system in this application includes: a front-end event acquisition terminal and a server; the front-end event acquisition terminal is used to acquire front-end events from a preset interactive interface and upload the front-end events to the front-end event receiving interface in the server; the server includes the front-end event receiving interface, a back-end event acquisition module, and an intelligent prediction module; wherein, the front-end event receiving interface is used to send front-end events to the intelligent prediction module; the back-end event acquisition module is used to acquire back-end events and send back-end events to the intelligent prediction module; the intelligent prediction module is used to load preset prediction rules based on a rule base and predict missing events based on front-end events, back-end events, and preset prediction rules. Through the above event prediction system, front-end events and back-end events can be combined, and the missing user behavior events can be predicted using the intelligent prediction module. This allows for the inference and completion of user behavior sequences even when some front-end events are missing, providing a data foundation for accurate user behavior analysis and greatly improving the accuracy of user behavior analysis.

[0036] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application.

[0038] Figure 1This is a schematic diagram illustrating an event prediction system according to an exemplary embodiment;

[0039] Figure 2 yes Figure 1 A schematic diagram of an intelligent inference module 1023 in an event inference system according to an exemplary embodiment;

[0040] Figure 3 yes Figure 2 Another schematic diagram of the intelligent inference module 1023 in an event inference system illustrated in an exemplary embodiment;

[0041] Figure 4 yes Figure 2 A schematic diagram of a neural network learning architecture for a rule model based on a neural network in a rule engine 10233 of an event prediction system according to an exemplary embodiment;

[0042] Figure 5 yes Figure 1 Another schematic diagram of server 102 in an event prediction system illustrated in an exemplary embodiment;

[0043] Figure 6 yes Figure 1 Another schematic diagram of server 102 in an event prediction system illustrated in an exemplary embodiment;

[0044] Figure 7 yes Figure 1 Another schematic diagram of server 102 in an event prediction system illustrated in an exemplary embodiment;

[0045] Figure 8 This is a schematic diagram illustrating another event prediction system according to an exemplary embodiment;

[0046] Figure 9 yes Figure 8 A schematic diagram of an intelligent inference program in an exemplary embodiment of another event inference system;

[0047] Figure 10 This is a flowchart illustrating an event prediction method according to an exemplary embodiment. Detailed Implementation

[0048] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0049] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0050] The event prediction system, method, electronic device, and storage medium provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0051] The first embodiment of this application relates to an event prediction system. Figure 1 This is a schematic diagram illustrating an event prediction system according to an exemplary embodiment, such as... Figure 1 As shown, it includes: a front-end event acquisition terminal 101 and a server 102.

[0052] The front-end event acquisition terminal 101 is used to acquire front-end events from a preset interactive interface and upload the front-end events to the front-end event receiving interface 1021 in the server.

[0053] Server 102 includes a front-end event receiving interface 1021, a back-end event acquisition module 1022, and an intelligent inference module 1023;

[0054] The front-end event receiving interface 1021 is used to send the front-end event to the intelligent inference module 1023; the back-end event collection module 1022 is used to collect back-end events and send the back-end events to the intelligent inference module 1023; the intelligent inference module 1023 is used to infer the missing event based on the front-end event, the back-end event and the preset inference rule.

[0055] Specifically, front-end events refer to user behavior events collected on the human-computer interaction interface and transmitted to the back-end server, while back-end events refer to events that occur on the system's back-end server for a specific user.

[0056] Backend events come in several types, including resource events, business events, and content events. Resource events refer to user actions on server resources, such as playing or stopping a video. Business events are user-generated business-related events, such as placing an order or making a payment. Content events are user-generated content within the system, such as publishing articles, uploading videos, posting comments, or liking posts.

[0057] In practical applications, during the collection and transmission of front-end events, the front-end event receiving interface 1021 may experience event omissions. When the intelligent inference module 1023 in the server 102 receives the front-end and back-end events, it infers the missing events based on preset inference rules, thereby further completing the user's event sequence. Since there are causal and dependency relationships between front-end and back-end events, the preset inference rules can be set according to the correspondence between them.

[0058] Specifically, the correspondence between front-end events and back-end events can be divided into 1:1 correspondence, 1:N correspondence, N:1 correspondence, M:N correspondence, etc.

[0059] A 1:1 correspondence means that one front-end event corresponds to one back-end event. This is the simplest correspondence, and a front-end event can be directly deduced from a back-end event.

[0060] A 1:N correspondence means that one front-end event corresponds to multiple back-end events. In this case, it is necessary to deduce the front-end event from the combination of multiple back-end events.

[0061] The N:1 correspondence means that multiple front-end events correspond to one back-end event. This means that multiple front-end events can be deduced from one back-end event. If some of these front-end events are already collected and reported by the front-end, the credibility of this inference can be greatly increased.

[0062] The M:N correspondence means that multiple front-end events can be inferred from the combination of multiple back-end events. Similarly, if some front-end events have been collected and reported, the credibility of this inference can be increased.

[0063] In the above correspondence, N refers to a combination of multiple events occurring together. In reality, there may also be cases where multiple events occur separately. For example, N front-end events may correspond to one back-end event, and these N events occur independently. That is to say, the front-end may have multiple different user behaviors that produce the same back-end event. In this case, it is not possible to make inferences based solely on the mapping relationship between front-end events and back-end events. It is necessary to comprehensively consider other events in the entire user behavior sequence, temporal relationships, etc., in order to make a more accurate inference.

[0064] It should be noted that the correspondence between front-end events and back-end events in the preset inference rules can be flexibly adjusted according to actual needs. For example, one or more hybrid inference rules can be adopted, and different inference rules can be set according to different events. This application does not impose specific limitations on this. In addition, the modules, devices, etc. used in this application can be set up independently or integrated with other modules or devices. This application does not impose limitations on this.

[0065] In this embodiment, the intelligent inference module 1023 can infer missing events based on the received front-end events and back-end events, as well as preset inference rules, thereby completing the user behavior sequence and greatly improving the accuracy of user behavior analysis.

[0066] Furthermore, in this embodiment, the intelligent inference module 1023 may further include:

[0067] Event pool 10231 is used to store the front-end events and the back-end events;

[0068] The time window processing module 10232 is used to process the front-end events and the back-end events within a preset time interval, and input the processed front-end events and back-end events into the rule engine 10233;

[0069] The rule engine 10233 is used to infer missing events based on the front-end events, the back-end events, and preset inference rules, and generate inferred events.

[0070] Specifically, the event pool 10231 stores front-end and back-end events, enabling subsequent event processing within a certain timeframe and preventing event loss during later transmission or processing, thus improving system stability. The time window processing module 10232 performs preprocessing before front-end and back-end events are input into the rule engine, such as grouping potentially related events together and eliminating events that don't require prediction, significantly reducing the processing load on the rule engine 10233 and improving data processing efficiency. Upon receiving front-end events and back-end times, the rule engine 10233 uses preset inference rules to predict missing times and generate predicted events, thereby further completing the user behavior sequence.

[0071] Furthermore, in this embodiment, the intelligent inference module 1023 may further include:

[0072] The deduplication processing module 10234 is used to receive the inferred event sent by the rule engine 10233, perform deduplication processing on the inferred event, and output the target inferred event.

[0073] Specifically, since the rule engine 10233 may output duplicate predicted events, the deduplication module 10234 is used to deduplicatize the predicted time, eliminating duplicate events such as existing events in the input events, thereby avoiding multiple duplicate events from interfering with the final user behavior sequence and improving the accuracy of user behavior analysis.

[0074] In the embodiments of this application, the rule engine 10233 may include any one or more of the following: a logic-based rule engine, a neural network-based rule engine, and a probability calculation-based rule engine.

[0075] Specifically, the logic rules included in the logic-based rule engine can be AND, OR, NOT, and other logical rules. In practical applications, different logical rules can be set according to different events, and logical rules can also be mixed. This application does not limit this. Logical rules can be set manually. In practice, based on business knowledge and system experience, various rules are manually configured, generally for relatively obvious rules and rules based on logical operations.

[0076] A rule engine based on neural networks includes rules set through neural networks. Specifically, it uses historical data to learn rules for neural network computation. The training set for neural network learning comes from historical data of front-end and back-end events. One or more events are extracted from a complete sequence of front-end events, and the remaining front-end and back-end events are used as input to the training set. The extracted front-end events are used as the results of the training set, and the neural network is trained using this training set. Neural network learning can continuously optimize the model based on accumulated data, improving inference performance.

[0077] The learning process of a neural network can be divided into two stages: the pre-training stage and the learning stage. The pre-training stage involves converting discrete user events into a vector, which is then used for the neural network's learning. This conversion process is also known as embedding. Here, discrete user events can be considered as a sequence of events, and the order of events in the sequence is related; therefore, the embedding method should be a time-series-based embedding method. In practice, training methods such as Word2rec and BERT can be used.

[0078] Word2rec originates from natural language processing. Natural language itself is a sequentially related stream of events, so word2rec's embedding methods can be used to embed user events. Word2rec is characterized by its concepts of event sequence and time windows, which are very similar to user event processing. One training method for Word2rec is the CBOW model, because the CBOW model's starting point is predicting the center word from surrounding words, which is similar to predicting missing user events.

[0079] BERT is a relatively new model for training word embeddings. Compared to word2rec, BERT can better utilize context and extract more contextual features. It is more suitable when the data features have a wide range of correlations. In BERT training methods, the Masked LM model can be chosen. The Masked LM model randomly masks the input token sequence, allowing the model to identify the masked tokens. This model also aligns with the goal of predicting missing user events.

[0080] Both Word2vec and BERT belong to self-supervised learning, which does not require manual labeling of the training data. Therefore, it can use continuously accumulated historical data for automated learning and gradually improve the training effect.

[0081] The result of pre-training is a vector encoding library for user events. Subsequent machine learning requires encoding user events based on this library before inputting them into the neural network for learning. Here, an LSTM (Longshort-term memory) model can be used for learning. LSTM models are suitable for processing time-series data and have both long-term and short-term memory models, allowing for the extraction of short-term and long-term feature associations respectively, thus better handling time-series events. The LSTM model can be tuned with various parameters to achieve learning results that better suit the business scenario.

[0082] The entire learning architecture of the neural network is as follows Figure 4 As shown, historically collected user event data is first pre-trained using word2rec / BERT, resulting in an event encoding library. Then, user events are encoded chronologically according to the encoding library, and event extraction is performed on the encoded events to form training data and label data. This data is then used to train an LSTM neural network, and the trained model serves as the working model for the rule inference engine.

[0083] The above training methods are only illustrative examples. In practical applications, specific training methods can be adjusted according to different situations, and this application does not impose any specific limitations on them.

[0084] In this application, a rule engine based on probability calculation is used to infer events through probability models. For example, a Bayesian probability model can be applied for calculation. The formula for the Bayesian probability model is as follows:

[0085]

[0086] Where A is the front-end event, B is the back-end event, P(A) is the probability of the front-end event occurring, P(B) is the probability of the back-end event occurring, P(B|A) is the probability of the back-end event occurring given the front-end event, and P(A|B) is the probability of the front-end event occurring given the back-end event. Based on historical data, P(A), P(B), and P(B|A) are statistically determined, and P(A|B) can be calculated using Bayes' theorem, which is the probability of inferring the front-end event from the back-end event. Using this probability data, the reliability of various inferences can be calculated. In practical applications, the probability model can be continuously optimized with the accumulation of data to improve the inference effect. The above is only an example; the probability model can be flexibly adjusted according to the actual situation, and this application does not impose specific limitations on it.

[0087] By using one or more of the aforementioned rule engines, the success rate and accuracy of event prediction can be greatly increased, thereby significantly improving the accuracy of user behavior analysis. Furthermore, other rule engines can be introduced in this application as needed, and this application does not impose any limitations on this.

[0088] In this embodiment of the application, the server 102 may include a user event processing module 1024, which is used to uniformly process the front-end event, the back-end event and the target missing event.

[0089] Specifically, the user event processing module 1024 can uniformly process and store the collected user events and the inferred and supplemented user events. For example, it can analyze user behavior based on the collected and supplemented user events, and can also output user behavior, thereby facilitating other operations or settings for user behavior in the later stage.

[0090] In this embodiment of the application, the server 102 may include a user event storage module 1025, which is used to uniformly store the front-end events, the back-end events and the target missing events.

[0091] By unifying the storage of front-end events, back-end events, and missing events, the system can prevent events from being lost during subsequent processing, thereby improving system stability.

[0092] In this embodiment of the application, the server 102 may include a rule base 1026, which includes preset inference rules; the rule base 1026 is used to send the preset inference rules to the intelligent inference module 1023 and generate a corresponding rule engine.

[0093] Specifically, in this application, a rule base 1026 can be set up separately in server 102, and the rule base 1026 stores preset inference rules. The rule base 1026 can send the preset inference rules to the intelligent inference module 1023 and generate a corresponding rule engine, so that the intelligent inference module 1023 can process events based on the preset inference rules and infer missing events. By setting up an independent rule base, it is convenient to update the preset inference rules, thereby improving the convenience in actual operation.

[0094] Furthermore, the attribute information corresponding to the preset inference rules in the rule base 1023 may include any one or a combination of the following: event combination, event sequence order, logical relationship between events, event occurrence time constraint, event interval time constraint, and event occurrence frequency constraint.

[0095] Based on this attribute information, we can develop logic-based rule engines, neural network-based rule models, and probability-based rule models. Combining these various attribute information for inference can greatly increase the accuracy and success rate of event prediction.

[0096] The second embodiment of this application relates to an event prediction system, such as... Figure 8 As shown, Figure 8 This is a schematic diagram of another event prediction system according to an exemplary embodiment.

[0097] Specifically, the front-end event collection program collects user events from the human-computer interaction interface and reports them to the front-end event receiving interface on the server via network communication. However, some events may be missing during the collection and transmission process. After receiving the front-end event data, the front-end event receiving interface passes it to both the user event handling program for unified processing and the intelligent inference program for inferring and supplementing user behavior events. The back-end event collection program collects various back-end events from the server and passes them to the intelligent inference program for inferring and supplementing user behavior events.

[0098] The intelligent inference program loads various inference rules from the rule base, infers missing user behavior events based on front-end and back-end events, and outputs the inference results to the user event handling program for unified processing. The user event handling program processes and stores the collected user events and the inferred and supplemented user events in a unified manner. The core of the system is the intelligent inference program, which integrates various attributes of front-end and back-end events, performs intelligent inference based on the rule base, obtains missing events, and thus completes the user behavior sequence, improving the accuracy of user behavior analysis.

[0099] Intelligent inference programs such as Figure 9 As shown, after front-end and back-end events are input into the inference program, they enter a unified event pool. Events in the event pool are processed through a time window and then input into the rule engine. During rule engine initialization, the rule library is loaded, and inference is performed based on the rule library and the input events. The inference results are deduplicated, for example, by excluding events that already exist in the input events, before the event results are output.

[0100] In this embodiment of the application, the intelligent inference program can infer events based on front-end events, back-end events, and rule bases to obtain missing events and complete the user behavior sequence, thereby greatly improving the accuracy of user behavior analysis.

[0101] It should be noted that in practical applications, the above-mentioned program or intermediate processing items can be made into a separate module or integrated into a module or device as a program. The specific adjustments can be made according to actual needs, and this application does not limit this.

[0102] The third embodiment of this application relates to an event prediction method, such as... Figure 7 As shown, Figure 7 This is a flowchart illustrating an event prediction method according to an exemplary embodiment, including:

[0103] Collect front-end events from a preset interactive interface;

[0104] If a frontend event is detected, retrieve the backend event;

[0105] The missing events are inferred based on the front-end events, the back-end events, and the preset inference rules.

[0106] As the method embodiments are basically similar to the device embodiments, the description is relatively simple, and relevant details can be found in the description of the method embodiments.

[0107] Furthermore, based on the same inventive concept, a specific embodiment of this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method steps in any of the above embodiments.

[0108] Based on the same inventive concept, in specific embodiments of this application, the processor can implement any of the methods in the embodiments of this application when executing the computer program.

[0109] Since the electronic devices described in the specific embodiments of this application are devices used to implement the methods of the embodiments of this application, those skilled in the art can understand the specific structure and variations of the devices based on the methods described in the embodiments of this application, and therefore will not be described in detail here. All devices used in the methods of the embodiments of this application fall within the scope of protection of this application.

[0110] Based on the same inventive concept, this application also provides a storage medium corresponding to the method in the embodiment: This embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method steps in any of the above embodiments.

[0111] In practice, when the computer program is executed by the processor, it can implement any of the methods in the specific embodiments of this application.

[0112] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0113] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, storable media, and processors. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] In a typical configuration, the computer device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media. Computer-readable media includes both permanent and non-persistent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in this article, computer-readable media do not include transient media, such as modulated data signals and carrier waves.

[0115] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0119] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0120] The above provides a detailed description of the event prediction system, method, electronic device, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An event prediction system, characterized in that, include: The front-end event acquisition terminal, and the server; The front-end event acquisition terminal is used to acquire front-end events from a preset interactive interface and upload the front-end events to the front-end event receiving interface in the server. The server includes the front-end event receiving interface, the back-end event acquisition module, and the intelligent inference module; The front-end event receiving interface is used to send the front-end event to the intelligent inference module; The backend event collection module is used to collect backend events and send the backend events to the intelligent inference module. The backend events are business events, resource events or content events that occur on the backend server and are related to the user. The intelligent inference module is used to infer missing events based on the front-end events, the back-end events, and preset inference rules. There is a causal and dependency relationship between the front-end events and the back-end events, and the preset inference rules are set according to the correspondence between the front-end events and the back-end events. The correspondence between the front-end events and the back-end events can be categorized into 1:1 correspondence, 1:N correspondence, N:1 correspondence, and M:N correspondence. The server further includes: a rule base, the rule base including the preset inference rules; The rule base is used to send the preset inference rules to the intelligent inference module and generate the corresponding rule engine; The attribute information corresponding to the preset inference rule in the rule base includes any one or a combination of the following: Event combination, event sequence order, logical relationship between events, event occurrence time constraint, event interval time constraint, and event occurrence frequency constraint.

2. The event prediction system according to claim 1, characterized in that, The intelligent inference module includes: an event pool, a time window processing module, and a rule engine; The event pool is used to store the front-end events and the back-end events; The time window processing module is used to process the front-end events and the back-end events within a preset time interval, and input the processed front-end events and back-end events into the rule engine; The rule engine is used to infer missing events based on the front-end events, the back-end events, and the preset inference rules, and generate inferred events.

3. The event prediction system according to claim 2, characterized in that, The intelligent inference module also includes: a deduplication processing module; The deduplication processing module is used to receive the speculative events sent by the rule engine, perform deduplication processing on the speculative events, and output the target speculative event.

4. The event prediction system according to claim 2, characterized in that, The rule engine includes any of the following: Rule engines based on logic, rule engines based on neural networks, and rule engines based on probability calculation.

5. The event prediction system according to claim 1, characterized in that, The server also includes a user event processing module; The user event processing module is used to process the front-end events, the back-end events, and the target missing events in a unified manner.

6. The event prediction system according to claim 1, characterized in that, The server also includes a user event storage module; The user event storage module is used to uniformly store the front-end events, the back-end events, and the target missing events.

7. A method for predicting events, characterized in that, The event prediction system according to claim 1 includes: Collect front-end events from a preset interactive interface; Upon detecting a front-end event, obtain the back-end event, which is a business event, resource event, or content event that occurs on the back-end server and is relevant to the user. Missing events are inferred based on the front-end events, the back-end events, and preset inference rules. There is a causal and dependency relationship between the front-end events and the back-end events. The preset inference rules are set according to the correspondence between the front-end events and the back-end events. The correspondence between the front-end events and the back-end events can be categorized into 1:1 correspondence, 1:N correspondence, N:1 correspondence, and M:N correspondence. The server further includes: a rule base, the rule base including the preset inference rules; The rule base is used to send the preset inference rules to the intelligent inference module and generate the corresponding rule engine; The attribute information corresponding to the preset inference rule in the rule base includes any one or a combination of the following: Event combination, event sequence order, logical relationship between events, event occurrence time constraint, event interval time constraint, and event occurrence frequency constraint.

8. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of claim 7.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method as described in claim 7.

Images