A prediction method, information push method and device

Abstract

The present disclosure relates to a prediction method, a push method and a device, wherein the prediction method includes collecting a user's behavior log in real time; determining a potential problem in a problem set according to the behavior log; and pushing relevant knowledge information of the potential problem. By actively pushing relevant knowledge information of the potential problem to the user's terminal, the prediction method, the push method and the device according to the embodiments of the present disclosure can achieve the timeliness and personalization of the prediction service, thereby improving user stickiness and user retention rate.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a prediction method, an information push method and a device. Background Art

[0002] Users may encounter various problems during online shopping, such as "how to refund", "how to exchange goods" and "how to change the delivery address", etc. Users can consult through the online shopping assistant or voice hotline provided by the shopping website.

[0003] In the related art, after a user opens an online shopping assistant or dials a voice hotline, the online shopping assistant or voice hotline can predict the user's problem based on the user's rights protection dispute consultation history data. This prediction method has the following problems: users who are not familiar with the consultation channels may not be able to find the consultation channels, resulting in the problem not being solved; users who are familiar with the consultation channels will only consult after the problem has occurred or has affected the user, resulting in a poor user experience. Summary of the invention

[0004] In view of this, the present disclosure proposes a prediction method, an information push method and a device.

[0005] According to a first aspect of the present disclosure, a prediction method is provided, the method comprising: collecting user behavior logs in real time; determining potential problems in a problem set based on the behavior logs; and pushing relevant knowledge information of the potential problems.

[0006] According to a second aspect of the present disclosure, an information push method is provided, the method comprising: determining a user to whom a message is to be pushed; obtaining a behavior log of the user; determining the information to be pushed based on the behavior log, and pushing the information to the user.

[0007] According to a third aspect of the present disclosure, a prediction device is provided, which includes: a behavior log collection module, used to collect user behavior logs in real time; a problem determination module, used to determine potential problems in a problem set based on the behavior logs; and an information push module, used to push relevant knowledge information of the potential problems.

[0008] According to the fourth aspect of the present disclosure, an information push device is provided, characterized in that it includes: a user determination module, used to determine the user to whom the message is to be pushed; a behavior log acquisition module, used to obtain the behavior log of the user; an information determination module, used to determine the information to be pushed based on the behavior log, and push it to the user.

[0009] According to a fifth aspect of the present disclosure, a prediction device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the method of the first aspect above.

[0010] According to a sixth aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the method of the above-mentioned first aspect when executed by a processor.

[0011] According to a seventh aspect of the present disclosure, a prediction device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute the method of the second aspect above.

[0012] According to an eighth aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the method of the above second aspect when executed by a processor.

[0013] In the embodiments of the present disclosure, by predicting the problems that users may encounter based on their behavior logs and proactively pushing relevant knowledge information about potential problems to the user's terminal, the timeliness and personalization of the prediction service are achieved, which facilitates improving user experience and user satisfaction, thereby increasing user stickiness and user retention rate.

[0014] On the one hand, the embodiments of the present disclosure perform timely problem prediction and proactive push based on real-time behavior logs, thereby realizing timely and proactive prediction services. Compared with the passive prediction services in related technologies, the proactive prediction services of the embodiments of the present disclosure save the user the process of searching for consultation channels, simplify user operations, and guide users before problems occur, which can reduce the impact on users when problems occur, improve the timeliness of prediction services, and thus improve user experience and user satisfaction.

[0015] On the other hand, the embodiments of the present disclosure perform personalized problem prediction based on the user's behavior log, implement personalized prediction services, and improve the accuracy of predictions, thereby improving user experience and user satisfaction.

[0016] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0018] Figure 1 A flowchart of a prediction method according to an embodiment of the present disclosure is shown.

[0019] Figure 2 A schematic diagram of a prediction system according to an embodiment of the present disclosure is shown.

[0020] Figure 3 A flow chart of an information push method according to an embodiment of the present disclosure is shown.

[0021] Figure 4 A schematic diagram of a push system according to an embodiment of the present disclosure is shown.

[0022] Figure 5 A block diagram of a prediction device according to an embodiment of the present disclosure is shown.

[0023] Figure 6 A block diagram of an information push device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0024] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0025] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0026] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0027] Figure 1 FIG. 1 is a flowchart of a prediction method according to an embodiment of the present disclosure. Figure 1 As shown, the prediction method may include:

[0028] Step S11, collecting user behavior logs in real time.

[0029] Step S12: determining potential problems in the problem set according to the behavior log.

[0030] Step S13: Push relevant knowledge information of the potential problem.

[0031] In the embodiments of the present disclosure, by predicting the problems that users may encounter based on their behavior logs and proactively pushing relevant knowledge information about potential problems to the user's terminal, the timeliness and personalization of the prediction service are achieved, which facilitates improving user experience and user satisfaction, thereby increasing user stickiness and user retention rate.

[0032] On the one hand, the embodiments of the present disclosure perform timely problem prediction and proactive push based on real-time behavior logs, thereby realizing timely and proactive prediction services. Compared with the passive prediction services in related technologies, the proactive prediction services of the embodiments of the present disclosure save the user the process of searching for consultation channels, simplify user operations, and guide users before problems occur, which can reduce the impact on users when problems occur, improve the timeliness of prediction services, and thus improve user experience and user satisfaction.

[0033] On the other hand, the embodiments of the present disclosure perform personalized problem prediction based on the user's behavior log, implement personalized prediction services, and improve the accuracy of predictions, thereby improving user experience and user satisfaction.

[0034] Figure 2 A schematic diagram of a prediction system according to an embodiment of the present disclosure is shown. Figure 1 The forecasting method shown can be applied to Figure 2 The prediction system shown in Figure 2 As shown, the prediction system may include a behavior log collection module, a problem determination module and an information push module. Among them, the behavior log collection module can be used to collect the user's behavior log in real time (corresponding to step S11), and store the collected behavior log in the log storage platform. The problem determination module can subscribe to the user's behavior log in real time from the log storage system, and determine the problems that the user may encounter, that is, potential problems, in the problem set based on the subscribed behavior log (corresponding to step S12). Afterwards, the problem determination module can obtain relevant knowledge information of the potential problem and send the relevant knowledge information to the information push module. When the information push module receives the relevant knowledge information sent by the problem determination module, it can push the relevant knowledge to the terminal that the user is using (corresponding to step S13) for the user's reference.

[0035] In step S11, the user's behavior log is used to record the user's behavior information. The user's behavior information can describe the user's behavior. In one example, the user's behavior information may include: time, location, person, behavior, and content corresponding to the behavior. For example, at time A, user B visits a web page, and the specific content is product details page C.

[0036] The behavior log collection module can collect the user's behavior logs from each terminal or server in real time, and store the collected behavior logs in a log storage platform. In one example, the log storage platform can be a kafka cluster.

[0037] In step S12, the question set may represent a set of various problems that users may encounter, such as how to refund, how to protect rights, and how to exchange goods. The question set may be set as needed, and the present disclosure does not limit this.

[0038] In one example, a problem set can be determined based on the business type. Different types of businesses can be applied to different scenarios to meet the needs of different business parties. For example, the after-sales business type can be applied to the scenario after payment. In this business type, the problems in the problem set may include: what if the seller does not ship for a long time, what if the courier has signed for but not received the goods, how to refund, and what if the seller refuses to compensate. For another example, the pre-sales business type can be applied to the scenario before the user pays. In this business type, the problems in the problem set may include: how to get coupons, how to find similar products, and what to do if the wrong order is placed. The above is only one way to divide the business types. In the embodiment of the present disclosure, other division methods can also be used. The business types can be divided into refunds, shipments, disputes, and rights protection. It should be noted that the same problems can exist between the problem sets corresponding to different business types. It is only necessary to establish an association relationship between the business type and the problem set to ensure that the problem set can be found according to the business type.

[0039] A potential problem is a problem in the problem set. A potential problem may represent a problem that a user may encounter as determined by the problem determination module based on the user's behavior log. A potential problem may include one or more problems.

[0040] The problem determination module can determine potential problems based on user behavior. In one example, when a user browses the “rights protection refund list page”, it means that the user may want a refund. At this time, the problem determination module can determine that the potential problem is “how to refund.” When a user browses the “rights protection refund list page” and the “product details page”, it means that the user may want to exchange the product. At this time, the problem determination module can determine that the potential problem is “how to exchange the product.”

[0041] In a possible implementation, step S12 may include: obtaining, based on the behavior log, page information browsed by the user in a first time period adjacent to the current moment; inputting the page information into a prediction model to obtain the potential problem, wherein the output result of the prediction model corresponds to the problem in the problem set.

[0042] The problem determination module can obtain the user's behavior log from the log storage platform in real time, and can determine the page information browsed by the user in the first time period adjacent to the current moment based on the obtained behavior log. The first time period can represent a time period adjacent to the current moment, and the length of the first time period can be set as needed, such as 10 minutes or 15 minutes. For example, the problem determination module can determine the page information browsed by the user in the last 10 minutes based on the obtained behavior log.

[0043] like Figure 2 As shown, the problem determination module may include a real-time computing platform and a prediction platform. The real-time computing platform may determine the page information browsed by the user in the first time period adjacent to the current moment based on the obtained behavior log, input the page information into the prediction model, and obtain the potential problem. Afterwards, the real-time computing platform obtains the relevant knowledge information of the potential problem and stores it in the message queue for the prediction platform to call. The prediction platform may subscribe to the relevant knowledge information of the potential problem from the message queue and send the relevant knowledge information to the information push module.

[0044] The input of the prediction model is the page information browsed by the user in the first time period, and the output result of the prediction model corresponds to the questions in the question set. The real-time computing platform can call the prediction model from the model training deployment platform through the calling module.

[0045] Figure 2 The database shown is mainly used to produce offline training data for the prediction model, which can be Oracle, MySQL, etc., and this disclosure does not limit this. The model training deployment platform is mainly used for the deployment and operation of the prediction model. The model training deployment platform can use the training data in the database to train the prediction model (i.e., establish the correspondence between page information and questions), and then publish the trained prediction model online for the real-time computing platform to call.

[0046] In one example, the real-time computing platform may first splice the acquired page information together; then input the spliced ​​page information into the prediction model to obtain the potential problem, thereby inputting the page information into the prediction model to obtain the potential problem. Specifically, the real-time computing platform may splice the addresses of the acquired pages into a string, and send the string to the calling module. The calling module may obtain the page information according to the string, and input the page information into the prediction model.

[0047] In a possible implementation, the prediction model may include a feature extraction model and a classification model, wherein the feature extraction model may be used to extract feature vectors of page information, and the classification model may be used to classify feature vectors. Inputting the page information into the prediction model to obtain the potential problem may include: calling the feature extraction model to extract feature vectors of page information browsed by the user in the first time period, classifying the feature vectors through the classification model to obtain classification results; and determining the problem in the problem set corresponding to the classification result as the potential problem.

[0048] It should be noted that different business types correspond to different problem sets and corresponding prediction models. The business type is determined by the business party.

[0049] In this way, by collecting user behavior logs in real time and then processing them with algorithm models, we can obtain the problems that users may encounter at the moment, and write the relevant knowledge information of the problems to the message queue, which can facilitate subscription by the prediction platform and realize the active push of information.

[0050] In a possible implementation, step S12 may include: based on the behavior log, obtaining page information browsed by the user in a second time period adjacent to the current moment; preprocessing the page information and obtaining static information of the user; searching for rules that match the preprocessed page information and the static information of the user in a rule set; and determining the problems in the problem set that correspond to the found rules as the potential problems.

[0051] The problem determination module can obtain the user's behavior log from the log storage platform in real time, and can determine the page information browsed by the user in a second time period adjacent to the current moment based on the obtained behavior log. Among them, the second time period can represent a time period adjacent to the current moment, and the length of the second time period can be set as needed. The length of the second time period can be the same as the first time period or different, and this disclosure does not limit this. For example, the problem determination module can determine the page information browsed by the user in the last 15 minutes based on the obtained behavior log.

[0052] like Figure 2As shown, the problem determination module may include a real-time computing platform and a rule configuration system. Among them, the real-time computing platform can determine the page information browsed by the user in the first time period adjacent to the current moment based on the acquired behavior log, and pre-process the page information. Afterwards, the real-time computing platform can store the pre-processed page information in the log storage platform. The rule configuration system can subscribe to the processed page information from the log storage platform, and search for rules that match the pre-processed page information and the static information of the user in the rule set, and then determine the problem corresponding to the found rule in the problem set as the potential problem. After the rule matching system obtains the relevant knowledge information of the current problem, it can send the relevant knowledge information to the information push module.

[0053] Preprocessing the page information may include: cleaning, filtering and aggregating the page information based on the rule set. For example, removing page information of pages with errors or failed access; filtering out page information of pages not covered by the rule set such as the home page and product details page; aggregating pages of the same type (such as refund, rights protection, etc.). The user's static information may include: one or more of the user's personal information (such as age, gender, etc.), order information, logistics status information and rights protection status information.

[0054] In an example, suppose there is a rule that the user browses the order logistics details page (determined by the behavior log), and the logistics status of the user's order is paid but not shipped (determined by the user's static information), then the potential problems are: why the order has not been shipped, what to do if it is not shipped within the time limit, etc.

[0055] In this way, by collecting user behavior logs in real time, preprocessing and matching rules, we can obtain the problems that users may encounter at the moment, and write the relevant knowledge information of the problems to the message queue, which can facilitate the prediction platform to subscribe and realize the active push of information.

[0056] In step S13, the relevant knowledge information of the potential problem can be actively pushed. Figure 2 As shown, after receiving the relevant knowledge information of the potential problem sent by the rule configuration system or the prediction platform, the information push module can actively push the relevant knowledge information to the terminal to which the user belongs.

[0057] In an example, the knowledge information related to the potential problem may include: the potential problem and a method for solving the potential problem, or a link between the potential problem and the method for solving the potential problem, etc., which is not limited in the present disclosure.

[0058] Figure 3 FIG. 1 is a flow chart showing an information push method according to an embodiment of the present disclosure. Figure 3As shown, the method may include:

[0059] Step S21, determining the user to whom the message is to be pushed.

[0060] Step S22, obtaining the user's behavior log.

[0061] Step S23, determining the information to be pushed based on the behavior log, and pushing it to the user.

[0062] In the embodiments of the present disclosure, a real-time information push service can be provided to target users, so as to improve user experience and user satisfaction, thereby increasing user stickiness and user retention rate.

[0063] Figure 4 A schematic diagram of a push system according to an embodiment of the present disclosure is shown. Figure 3 The information push method shown can be applied to Figure 4 The push system shown. Figure 4 As shown, the push system may include a user determination module and Figure 2 The prediction system shown.

[0064] Among them, the user determination module can be used to determine the users to whom messages are to be pushed (corresponding to step S21). These users have certain characteristics, such as member users, elderly users, etc. The users to whom messages are to be pushed may also be other users, which is not limited by the present disclosure. The prediction system can be used to obtain the user's behavior log, determine the information to be pushed based on the obtained behavior log, and push the determined information to the user to whom the message is to be pushed (corresponding to steps S22 and S23). The message to be pushed may be relevant knowledge information of potential problems. The method of obtaining the user's behavior log, the method of determining potential problems, and the method of determining relevant knowledge information can refer to steps S11 to S13, which will not be repeated here.

[0065] For example, the user to whom the message is to be pushed is a member user. Figure 2 and Figure 4 First, the user determination module determines the member user and sends the user ID of the member user to the inference system. Then, Figure 2The behavior log collection module in the prediction system shown can collect the behavior logs of each member user in real time according to the received user identifier, and store the collected behavior logs in the log storage platform. The problem determination module of the prediction system can subscribe to the behavior logs of each member user in real time from the log storage system, and determine the problems that each member user may encounter in the problem set based on the subscribed behavior logs, that is, potential problems. Afterwards, the problem determination module can obtain relevant knowledge information of the potential problems corresponding to each member user. The information determination module (not shown) can determine the relevant knowledge information of each member user as the information to be pushed, and send the relevant knowledge information to the information push module. The information push module can push the relevant knowledge information to the corresponding member users for user reference.

[0066] Figure 5 FIG. 4 is a block diagram of a prediction device according to an embodiment of the present disclosure. Figure 5 As shown, the device 30 may include:

[0067] The behavior log collection module 31 is used to collect the user's behavior log in real time;

[0068] A problem determination module 32, configured to determine potential problems in a problem set based on the behavior log;

[0069] The information push module 33 is used to push the relevant knowledge information of the potential problem.

[0070] In a possible implementation, the problem determination module 32 may be specifically used to:

[0071] According to the behavior log, obtaining page information browsed by the user in a first time period adjacent to the current time;

[0072] The page information is input into a prediction model to obtain the potential problem, and the output result of the prediction model corresponds to the problem in the problem set.

[0073] In a possible implementation, the prediction model includes a feature extraction model and a classification model, and the page information is input into the prediction model to obtain the potential problem, including:

[0074] Calling a feature extraction model to extract a feature vector of the page information;

[0075] Classify the feature vector using a classification model to obtain a classification result;

[0076] The problem in the problem set corresponding to the classification result is determined as the potential problem.

[0077] In a possible implementation, the page information is input into a prediction model to obtain the potential problem, including:

[0078] Splice the obtained page information together;

[0079] The spliced ​​page information is input into the prediction model to obtain the potential problem.

[0080] In a possible implementation, the problem determination module 32 may be specifically used to:

[0081] According to the behavior log, obtaining page information browsed by the user in a second time period adjacent to the current time;

[0082] Preprocessing the page information and obtaining static information of the user;

[0083] In the rule set, searching for a rule that matches the preprocessed page information and the static information of the user;

[0084] The problem in the problem set corresponding to the found rule is determined as the potential problem.

[0085] In a possible implementation, preprocessing the page information includes:

[0086] The page information is cleaned, filtered and aggregated based on the rule set.

[0087] In a possible implementation, the user's static information includes: one or more of the user's personal information, order information, logistics status information, and rights protection status information.

[0088] In a possible implementation, the device 30 may further include:

[0089] The set determination module is used to determine the problem set according to the business type.

[0090] In the embodiments of the present disclosure, by predicting the problems that users may encounter based on their behavior logs and proactively pushing relevant knowledge information about potential problems to the user's terminal, the timeliness and personalization of the prediction service are achieved, which facilitates improving user experience and user satisfaction, thereby increasing user stickiness and user retention rate.

[0091] Figure 6 FIG. 2 is a block diagram of an information push device according to an embodiment of the present disclosure. Figure 6 As shown, the information push device 40 may include:

[0092] A user determination module 41, used to determine the user to whom the message is to be pushed;

[0093] A behavior log acquisition module 42, used to acquire the behavior log of the user;

[0094] The information determination module 43 is used to determine the information to be pushed based on the behavior log and push it to the user.

[0095] In the embodiments of the present disclosure, a real-time information push service can be provided to target users, so as to improve user experience and user satisfaction, thereby increasing user stickiness and user retention rate.

[0096] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may 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.

[0097] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0100] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0101] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0102] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0103] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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.) that contain computer-usable program code.

[0105] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A prediction method, It is characterized in that The method comprises: Collect user behavior logs in real time; According to the behavior log, obtain information about pages browsed by the user in a time period adjacent to the current time; Preprocessing the page information and obtaining static information of the user; In the rule set, searching for a rule that matches the preprocessed page information and the static information of the user; Identify the problems in the problem set that correspond to the found rules as potential problems; Push relevant knowledge information about the potential problem.

2. The method according to claim 1, It is characterized in that Preprocessing the page information includes: The page information is cleaned, filtered and aggregated based on the rule set.

3. The method according to claim 1, It is characterized in that The user's static information includes: one or more of the user's personal information, order information, logistics status information and rights protection status information.

4. The method according to claim 1, It is characterized in that The method further comprises: The problem set is determined according to the business type.

5. A prediction device, It is characterized in that The device comprises: Behavior log collection module, used to collect user behavior logs in real time; A problem determination module is used to obtain, based on the behavior log, page information of pages browsed by the user in a time period adjacent to the current moment; preprocess the page information and obtain static information of the user; search for a rule matching the preprocessed page information and the static information of the user in a rule set; and determine a problem in the problem set corresponding to the found rule as a potential problem; The information push module is used to push relevant knowledge information of the potential problem.

6. The device according to claim 5, It is characterized in that Preprocessing the page information includes: The page information is cleaned, filtered and aggregated based on the rule set.

7. The device according to claim 5, It is characterized in that The user's static information includes: one or more of the user's personal information, order information, logistics status information and rights protection status information.

8. The device according to claim 5, It is characterized in that The device also includes: The set determination module is used to determine the problem set according to the business type.

9. A prediction device, It is characterized in that include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method according to any one of claims 1 to 4.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, It is characterized in that When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images