Error popup page guiding method and device based on weak network detection

Abstract

The application provides a weak network detection-based error popup page guidance method and device. The error popup page guidance method comprises the following steps: detecting a current network state of a user in real time, and generating a network detection result according to a preset network detection rule; if the network detection result is network anomaly, obtaining current webpage browsing information of the user; generating a recommended guidance result according to the network detection result, the webpage browsing information of the user, and a preset network monitoring guidance strategy and a popup guidance prediction model; and outputting guidance information according to the recommended guidance result to prompt the user to perform a corresponding operation based on the guidance information. Thus, the function entrances of different users can be analyzed and guided in a popup manner, and the popup guidance for weak networks can be effectively scheduled.

Description

Technical Field

[0001] This invention relates to network detection technologies, and in particular to a method and apparatus for providing error pop-up page guidance based on weak network detection. Background Technology

[0002] With the continuous development of mobile internet and the advancement of fintech, banks not only need to actively transform their businesses but also rapidly iterate their products and innovate. As businesses become increasingly complex and functional, the requirements for accessing multi-terminal systems become more stringent, and service access on each terminal is subject to different constraints and restrictions. Some services are accessible, while others are inaccessible, and response times vary. Mobile banking is not only complex in its own operations but also in its external role; furthermore, mobile banking is a platform business itself and also serves as a platform for the development of new businesses.

[0003] In order to respond promptly to new market demands and changes, and to meet the new financial needs of intelligent and digital mobile banking, the client-side faces an urgent need for architectural and cross-platform component reconstruction.

[0004] In summary, improving efficiency and meeting the needs of marketing and operations personnel for rapid updates and promotion of business across multiple platforms has become an urgent issue to be addressed. Summary of the Invention

[0005] To address the problems in the prior art, this application provides a method and apparatus for providing error pop-up page guidance based on weak network detection.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] Firstly, this application provides a method for providing error pop-up page guidance based on weak network detection, including:

[0008] The system monitors the user's current network status in real time and generates network detection results based on pre-set network detection rules. These results include: network response timeout, network disconnection, slow request status, illegal network segment or Wi-Fi segment status, and whether DNS / domain name resolution is functioning correctly.

[0009] If the network detection result indicates a network anomaly, obtain the user's current webpage browsing information, which includes: current user tags, current user behavior habits, and current user behavior trajectory.

[0010] Recommendation guidance results are generated based on the network detection results, the user's webpage browsing information, and the pre-created network monitoring guidance strategy and pop-up guidance prediction model. The network monitoring guidance strategy is implemented by aggregation analysis based on historical user webpage browsing information, and the pop-up guidance prediction model is implemented by using the training set and test set obtained based on historical user webpage browsing information, based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer.

[0011] Based on the recommended guidance results, output guidance information to prompt the user to perform the corresponding operation based on the guidance information.

[0012] In one embodiment, the real-time detection of the user's current network status and the generation of network detection results according to pre-defined network detection rules include:

[0013] The current network status is detected according to the preset network status strategy;

[0014] Obtain the network detection policy, which is dynamically injected into the local client via the CCB API;

[0015] Based on the network status, query the corresponding network detection rules from the network detection strategy;

[0016] Obtain the network detection parameters of the current network;

[0017] The network detection rules and network detection parameters are used to detect and match the network state to obtain the corresponding network detection results.

[0018] In one embodiment, the step of matching the network detection rules with network detection parameters to detect and match the network state to obtain the corresponding network detection result includes:

[0019] The network detection rules and network detection parameters are used to match the network state.

[0020] The matched network detection rules are compared with the network detection parameters, and the corresponding network detection results are obtained based on the comparison results.

[0021] Obtain the pre-assigned error code from the network detection results.

[0022] In one embodiment, the steps of a pre-created pop-up guidance prediction model include:

[0023] Obtain historical user web browsing information, which includes: user tags, historical user behavior habits, and historical user behavior trajectories;

[0024] The historical user webpage browsing information is preprocessed to obtain a training set and a test set;

[0025] The model is trained using the training and test sets. Based on the random initialization of the hidden layer parameters and the solution of the weights from the hidden layer output to the output layer, a pop-up guidance prediction model is generated.

[0026] In one embodiment, the step of pre-creating the network listening guidance policy includes:

[0027] Obtain historical user web browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory;

[0028] Based on the collaborative filtering recommendation algorithm, the user's preference level is determined according to user tags, user's historical behavior habits, and user's historical behavior trajectory.

[0029] The network monitoring guidance strategy is generated based on the determined level of preference.

[0030] In one embodiment, the step of pre-creating the network listening guidance policy includes:

[0031] Obtain historical user web browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory;

[0032] Based on content recommendation algorithms, user interest tags are obtained according to user tags, user historical behavior habits, and user historical behavior trajectories.

[0033] Based on the interest tags, a network monitoring guidance strategy is derived to guide user preferences.

[0034] In one embodiment, generating recommendation guidance results based on the network detection results, the user's web browsing information, and a pre-created network monitoring guidance strategy includes:

[0035] Based on the network detection results and the user's web browsing information, a corresponding network monitoring guidance strategy is matched and used as the recommendation guidance result.

[0036] In one embodiment, generating recommendation guidance results based on the network detection results, the user's webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model includes:

[0037] A first recommendation guidance result is generated based on the network detection results, the user's webpage browsing information, and the pre-created network monitoring guidance strategy.

[0038] A second recommendation guidance result is generated based on the network detection results, the user's webpage browsing information, and the pre-created pop-up guidance prediction model.

[0039] Obtain the user's preference settings, calculate the relevance between the first recommendation guidance result and the second recommendation guidance result and the preference settings, and take the recommendation guidance result with the higher relevance as the final recommendation guidance result.

[0040] Secondly, this application provides an error pop-up page guidance device based on weak network detection, comprising:

[0041] The detection result generation unit detects the user's current network status in real time and generates network detection results according to pre-set network detection rules. The network detection results include: network response timeout, network disconnection, network slow request, network illegal network segment or WIFI segment, and whether DNS / domain name resolution is normal.

[0042] The information acquisition unit, if the network detection result is a network anomaly, acquires the user's current webpage browsing information, which includes: current user tags, current user behavior habits, and current user behavior trajectory.

[0043] The guidance result generation unit is used to generate recommendation guidance results based on the network detection results, the user's webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model. The network monitoring guidance strategy is implemented based on the aggregation analysis of historical user webpage browsing information, and the pop-up guidance prediction model is implemented by using the training set and test set obtained based on historical user webpage browsing information, based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer.

[0044] The information output unit is used to output guidance information based on the recommendation guidance result to prompt the user to perform the corresponding operation based on the guidance information.

[0045] Thirdly, this application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the relevant steps of the above-mentioned error pop-up page guidance method.

[0046] Fourthly, this application provides a computer program product, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the relevant steps of the above-mentioned error pop-up page guidance method.

[0047] Fifthly, this application provides a computer program product on which a computer program is stored, and when the computer program is executed by a processor, it implements the relevant steps of the above-mentioned error pop-up page guidance method.

[0048] Based on the error pop-up guidance method and device for weak network detection provided in this specification, when a user uses the network, the current network status can be detected in real time, and a network detection result can be generated according to pre-set network detection rules. If the network detection result indicates a network anomaly, the current user tag, current user behavior habits, and current user behavior trajectory are obtained. Recommended guidance results are generated based on the network detection results, the user's web browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model. Guidance information is output based on the recommended guidance results to prompt the user to perform corresponding operations. This enables the aggregation analysis and pop-up guidance of different users' functional entry points, achieving effective scheduling of pop-up guidance for weak networks. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0050] Figure 1 This is a flowchart of the error pop-up page guidance method based on weak network detection in the embodiments of this specification;

[0051] Figure 2 This is a flowchart illustrating the scheduling process of the APIs corresponding to the full API registration table in this embodiment of the invention.

[0052] Figure 3 This is a schematic diagram illustrating one embodiment of the error pop-up page guidance method provided in the embodiments of this specification, applied in a scenario example.

[0053] Figure 4 This is a schematic diagram illustrating one embodiment of the error pop-up page guidance method provided in the embodiments of this specification, applied in a scenario example.

[0054] Figure 5 This is a schematic diagram illustrating one embodiment of the error pop-up page guidance method provided in the embodiments of this specification, applied in a scenario example.

[0055] Figure 6 This is a schematic diagram illustrating one embodiment of the error pop-up page guidance method provided in the embodiments of this specification, applied in a scenario example.

[0056] Figure 7 This is a schematic diagram illustrating one embodiment of the error pop-up page guidance method provided in the embodiments of this specification, applied in a scenario example.

[0057] Figure 8This is a schematic diagram illustrating one embodiment of the error pop-up page guidance method provided in the embodiments of this specification, applied in a scenario example.

[0058] Figure 9 This is a schematic diagram of the UI pop-up window in an embodiment of this specification;

[0059] Figure 10 This is a schematic diagram illustrating weak network guidance in an embodiment of this specification;

[0060] Figure 11 This is a schematic diagram of the structural composition of an electronic device provided in one embodiment of this specification;

[0061] Figure 12 This is a schematic diagram of the structural composition of an error pop-up page guidance device provided in one embodiment of this specification. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] It should be noted that the information and data related to users involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by the relevant parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with relevant laws, regulations, and standards, and necessary confidentiality measures have been taken. They do not violate public order and good morals, and corresponding operation entry points are provided for users or relevant parties to choose to authorize or refuse.

[0064] It should also be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0065] The technical terms involved in this invention are as follows:

[0066] APP Application;

[0067] API Application Programming Interface;

[0068] SDK Software Development Kit;

[0069] WIFI Wireless Fidelity network;

[0070] UI (User Interface)

[0071] URL Uniform Resource Locator.

[0072] Because network performance directly impacts user experience, it has a direct impact on business operations. Furthermore, mobile networks inherently suffer from weak network conditions, DNS issues, and connection performance limitations compared to traditional fixed networks. Therefore, optimizing mobile network performance and providing user-friendly notification pop-ups are particularly essential. Based on this, this invention provides…

[0073] like Figure 1 As shown in the figure, this specification embodies a method for providing error pop-up page guidance based on weak network detection. Specifically, this method is applied to the client side. In practical implementation, the method may include the following:

[0074] S101: Real-time detection of the user's current network status, and generation of network detection results based on pre-set network detection rules;

[0075] S102: If the network detection result indicates a network anomaly, obtain the user's current webpage browsing information, which includes: current user tags, current user behavior habits, and current user behavior trajectory.

[0076] S103: Generate recommendation guidance results based on network detection results, user webpage browsing information, and pre-created network monitoring guidance strategy and pop-up guidance prediction model; wherein, the network monitoring guidance strategy is implemented by aggregation analysis based on historical user webpage browsing information, and the pop-up guidance prediction model is implemented by using the training set and test set obtained based on historical user webpage browsing information, based on the random initialization of hidden layer parameters and the solution of the weights from hidden layer output to output layer.

[0077] S104: Output guidance information based on the recommended guidance results to prompt the user to perform the corresponding operation based on the guidance information.

[0078] Specifically, the network detection results mentioned above may include network response timeout, whether the network is disconnected, whether the network is a slow request, whether the network is in an illegal network segment or a WIFI segment, and whether DNS / domain name resolution is normal.

[0079] Specifically, in order to meet the needs of business product lines, the client will pre-generate a weak network detection framework (network detection strategy). Based on the pre-set network detection strategy, the client can generate corresponding network detection results according to the network to be detected.

[0080] The weak network detection framework can be dynamically injected into the local client via the CCB (Church Community Builder) API. Specifically, it is dynamically injected into the host APP via the CCB (Church Community Builder) API, and the configuration table and initialization strategy and method are updated asynchronously online, providing the environment for the next step of network detection.

[0081] In practice, network detection strategies can be implemented by classifying and defining each stage of the network, performing a full classification and definition of the state of each network node layer, and extracting the feature values ​​of the state to standardize each node. Network detection strategies include, but are not limited to, the following five network detection rules:

[0082] 1. Network Timeout: A network response time exceeding a set duration is considered a timeout, and status 0 is recorded. This set duration can be, for example, 15 seconds, and can be set as needed; this invention is not limited to a single setting.

[0083] 2. Network disconnected: Record status 1 for records with no network access relationship.

[0084] 3. Slow / Weak Network: Listen for network response times exceeding the set duration of 3 seconds, classifying them as slow requests, and record status 2.

[0085] The duration can be set as needed, or it can be determined based on the timeout duration that users can tolerate, according to big data statistics.

[0086] 4. Network alert: Detects illegal network segments or public, insecure Wi-Fi segments and records status 3.

[0087] Insecure Wi-Fi segments are determined based on a pre-defined relationship table of insecure Wi-Fi segments, which can be updated in real time.

[0088] 5. DNS / Domain Name Resolution: Check if DNS / domain name resolution is working properly.

[0089] Network monitoring guidance strategies include pop-up guidance, network anomaly page prompts, guidance for users to set up their own networks or check related network detection, and support for adding application configurations in the management backend resource slots.

[0090] To meet the needs of business product lines, the client pre-creates a pop-up management framework (i.e., network monitoring guidance strategy) and a pop-up guidance prediction model. The pop-up management framework and pop-up guidance prediction model can be dynamically injected into the local client via the CCB (Church Community Builder) API. Specifically, they are dynamically injected into the host application via the CCB (Church Community Builder) API, and the configuration table and initialization strategy and methods are updated asynchronously online, providing the environment for the next network monitoring call. The network monitoring guidance strategy includes, but is not limited to, the following:

[0091] 1. Dynamic network timeout detection and user-friendly pop-up notification: Network connection timeout and operation instructions.

[0092] 2. Network Disconnection Alert: Notification of network connection loss and operation instructions.

[0093] 3. Cellular / WiFi switching prompt: Instructions for using cellular data.

[0094] 4. Poor network connection prompt pop-up: Instructions for handling poor network connection.

[0095] 5. DNS and Domain Name Resolution Anomaly Alerts: Domain name resolution anomaly alerts and operation instructions.

[0096] In practice, it is necessary to configure strategies for the indicators and nodes at each stage of the network to meet the process guidance and pop-up error reminders required by various functional scenarios.

[0097] The calls involving network detection and guidance need to be dynamically injected into the code in advance. These calls are the business logic that needs to be processed after the APP starts, so that it has input and output for internal and external API methods, including related strategies and error code prompts.

[0098] The network API classification configuration table can be further divided into:

[0099] 1. The full API registration form apiconfig.json registers all APIs used across various platforms and channels, and categorizes and tags them.

[0100] This full API registry is for network pop-up scheduling used across multiple devices and platforms. Within the basic API, the SDK is responsible for both pop-ups and scheduling. Custom, private interfaces can be implemented to create custom error pop-ups as needed.

[0101] This full API registry registers network call layer APIs for use across multiple platforms. Each API includes a clear description and usage instructions for specific scenarios, including rule permissions and other relevant information.

[0102] The data structure fields of apiconfig.json and the descriptions of each parameter in the fields are as follows:

[0103] Unique Identifier (id): "0001" is a unique identifier defined by the category to ensure the uniqueness of this API interface in the system.

[0104] Description (des): "Scan API", used to briefly explain the function or purpose of this interface.

[0105] Platform: "ios / android" indicates that this API is applicable to mobile platforms, including the Android and iOS operating systems.

[0106] Channel type: "ccbmobile / ccblife" indicates the specific channel through which the API is used, such as mobile banking or CCB Life application platforms.

[0107] The Android class name (android_classname): "com.ccb.home.appscene.CCBBridge" is the fully qualified name of the class that implements this API functionality on the Android platform.

[0108] The iOS class name (ios_classname): "CCBSceneBridge" is the class name that implements the API functionality on the iOS platform.

[0109] API Name: "startSceneAPI" This is the name of the API used to identify its functionality.

[0110] The parameter (params): "key1=value&key2=value2" represents the parameters and their corresponding values ​​required when calling this API, and supports passing them in the form of key-value pairs.

[0111] The permission rule (rule): "tag:_00028||branchid:440000000" defines the permission rule required to trigger the pop-up. The example rule indicates that customers must meet specific tag and line number conditions to use the relevant functionality.

[0112] This data structure is used to describe a specific API interface. Through the fields mentioned above, this data structure provides a comprehensive definition, covering the API's basic information, applicable platforms, class name, parameter configuration, and permission requirements, to facilitate development and use.

[0113] Figure 2The scheduling flowchart for the APIs corresponding to this full API registration table is as follows: Figure 2 As shown, the process scheduling process includes:

[0114] S201: API call.

[0115] S202: The CCBH5 Bridge layer is encapsulated; it serves as an intermediate layer, used to indicate how to display pop-ups and prompts, and to distribute tasks to the scheduling layer.

[0116] S203: Distribute to the CCBH5 Operation scheduling strategy layer.

[0117] S204: Determine if the user has the necessary permissions; if there is a corresponding calling method; and if each pilot has their own implementation method, etc.

[0118] S205: If yes, trigger the corresponding method call and callback; otherwise, proceed to S206.

[0119] S206: End.

[0120] 2. The rule configuration file ruleconfig.json specifies the usage details such as the type, rules, and parameters associated with the API that need to be configured.

[0121] The rule fields for a certain scenario are as follows:

[0122] "params":"key1=value1",

[0123] "des":"Scan API, for mobile banking only"

[0124] "rule":"",

[0125] The above fields are for the registration and description of a specific API, and different rules are used for different scenarios.

[0126] Based on the above-configured strategy, by searching, calculating, and monitoring each network node, the current network status value of the user can be determined, and user guidance can be provided, achieving a complete closed loop of user network pop-up guidance process and achieving a better user interaction experience.

[0127] Let's take web scraping as an example:

[0128] JSON data records specific information about network requests, facilitating analysis and troubleshooting. Each request is identified by a unique event ID and includes the start and end times (in milliseconds) to calculate request latency. The scenario ID defines the specific environment in which the request occurred, such as the network or an advertisement.

[0129] The request result is represented by a response code; a successful request returns a status code of 200, while a failed request is identified by a 404. The error description field provides detailed information about the network layer exception, and the status code field further indicates whether the request was successful (0 for success, 1 for failure). Additionally, the response status code and message fields provide supplementary information about the request result.

[0130] The requested URL and its parameters contain the specific content of the request. The trace section records the request's performance at different processing nodes (such as HTTP, DNS, and TCP), including the processing time at each stage, corresponding error messages, and their success status. This structured record makes network request performance monitoring and problem analysis clearer and more transparent, helping the team identify specific points of latency or error, thereby enabling effective optimization and adjustments.

[0131] The above examples of network data collection mainly focus on network performance monitoring and related indicators and explanations. Specifically, they specify indicators such as the type of machine, the time point, the type of error message, and the duration of the error to comprehensively evaluate network performance and provide error guidance.

[0132] In some embodiments, such as Figure 3 As shown, the above-mentioned real-time detection of the user's current network status and generation of network detection results based on pre-set network detection rules may include the following in specific implementation:

[0133] S301: Detect the current network status according to the preset network status policy;

[0134] S302: Obtain the network detection policy, which is dynamically injected into the local client via the CCB API;

[0135] S303: Query the corresponding network detection rule from the network detection policy based on the current network status;

[0136] S304: Obtain the network detection parameters of the current network;

[0137] S305: Detect and match the network status according to the network detection rules and network detection parameters to obtain the corresponding network detection results.

[0138] Specifically, the aforementioned network status can include normal network and abnormal network. Under normal network conditions, this invention generally does not require operational guidance. Abnormal network conditions can include network timeouts, network disconnections, slow / weak network conditions, network alerts, and checks on whether DNS / domain name resolution is functioning correctly.

[0139] It should be noted that in S301, detecting the current network status can be regarded as a preliminary detection method for network detection, which aims to query and verify the network detection rules based on the preliminary detection results.

[0140] Preliminary detection can be performed based on preset network status policies, which include network connection time being too long (exceeding the set time), network being unable to connect, network speed being slow (below the preset minimum network speed), indicating potential network risks, and DNS / domain name resolution failures (DNS server failure, domain name expiration, DNS setting errors, etc.).

[0141] As mentioned above, the network detection policy stores multiple network detection rules. Based on the abnormal situations in the current network state, the client can query one or more possible corresponding network detection rules from the network detection policy.

[0142] Specifically, network detection parameters for the current network may include, for example, a network connection duration exceeding 30 seconds or a network speed below 50kbps.

[0143] In some embodiments, such as Figure 4 As shown, the above method detects and matches network status based on network detection rules and parameters to obtain corresponding network detection results. In practice, this can include the following:

[0144] S401: Match the network detection rules with the network detection parameters to determine the network status;

[0145] S402: Compare the matched network detection rules with the network detection parameters, and obtain the corresponding network detection results based on the comparison results;

[0146] S403: Obtain the pre-assigned error code for the network detection results.

[0147] In S401, the network detection rules in the network detection strategy need to be matched with the network detection parameters to obtain the network detection rules related to the network detection parameters. For example, if the network transmission speed is low, such as one of the network detection parameters being 5k / s, then there may be a slow / weak network problem, and the network detection rule "Slow / weak network: Listen for network response times exceeding the set duration of 3 seconds, which are considered slow requests, and record state 2" can be matched. It should be noted that there may be multiple network detection parameters, and there may also be multiple matched network detection rules.

[0148] The matched network detection rules are compared with the network detection parameters. The corresponding network detection result can be obtained based on whether the comparison result meets the preset conditions. For example, if the current network connection duration is 30 seconds and the preset duration is 15 seconds, the network detection result is network response timeout.

[0149] Specifically, each network test result can be assigned an error code, which can be used to provide error code prompts when providing operational guidance.

[0150] Specifically, to meet the needs of business product lines, the aforementioned preset network status policies and network detection policies will be generated in advance. These preset network status policies and network detection policies can be dynamically injected into the host APP of the local client via CCBAPI, and the configuration table and initialization policies and methods will be updated asynchronously online.

[0151] In some embodiments, such as Figure 5 As shown, the steps of the pre-created pop-up guidance prediction model described above can include the following in practice:

[0152] S501: Obtain historical user webpage browsing information, which includes: user tags, historical user behavior habits, and historical user behavior trajectory;

[0153] Specifically, the client obtains historical web browsing information of multiple users from the server as training samples for the model. The historical data includes user tags, historical user behavior habits, and historical user behavior trajectories, which are used to train the model to obtain the pop-up guidance prediction model.

[0154] S502: Preprocess historical user web browsing information to obtain training and test sets;

[0155] Specifically, the client preprocesses historical user web browsing information, including data cleaning, data normalization, data completion, and data partitioning, to remove low-quality data and obtain corresponding high-quality training and testing sets. The high-quality training and testing sets are then used to train the model and generate a pop-up guidance prediction model.

[0156] S503: Use the training set and test set to train the model, and generate a pop-up guidance prediction model based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer.

[0157] Specifically, the client uses training and testing sets obtained from processing historical user web browsing information to train a pop-up guidance prediction model. This model is based on neural network training. The client first randomly initializes the weights and biases from the input layer to the hidden layer, then performs a non-linear transformation on the input data through the hidden layer to obtain the hidden layer output matrix. Finally, it uses the hidden layer output matrix and the target output of the training data to solve for the weights from the hidden layer output to the output layer. The inputs to the pop-up guidance prediction model include user tags, historical user behavior habits, and historical user behavior trajectories; the output is the recommendation guidance result.

[0158] Specifically, user tags can include factors such as gender, age, role, and region; historical user behavior habits include factors such as user preferences, browsing time, and user behavior data points; and historical user behavior trajectories include data such as user clicks and browsing trajectories. User tags and historical user behavior habits are generally static attributes of users, while historical user behavior trajectories are generally dynamic attributes of users.

[0159] In one embodiment, the client selects data from historical user web browsing information for different age groups (e.g., 10 years per age group), with 2000 sets of data selected for each age group, and obtains a pop-up guidance prediction model for each age group through training.

[0160] In one embodiment, the client trains the model based on a single-layer feedforward neural network (SLFN). The SLFN consists of an input layer, a hidden layer, and an output layer, including perceptrons, multi-layer perceptrons (MLPs), radial basis function networks (RBFNs), self-organizing maps (SOMs), and extreme learning machines (ELMs), etc. This application is not limited to these.

[0161] In one embodiment, the client trains a pop-up guidance prediction model based on an Extreme Learning Machine (ELM), the structure of which is as follows: Figure 11 As shown, the input weights and hidden layer thresholds are randomly generated and independent of the training sample data, and the output layer weight matrix is ​​obtained through one-step analytical calculation.

[0162] For the observed sample (x) i ,t i ), where the input vector x i =[x i1 ,x i2 ,x i3 ,…x in ] T ∈R n ,(i=1,2,3,…,N), where N is the number of observed samples, n is the dimension of the sample input vector, and t is the output vector. i =[t i1 ,t i2 ,…t im ] T ∈R m,m represents the output sample dimension, i.e., the number of nodes in the output layer of the ELM model. Let the number of hidden layer nodes be l, and the activation function be g(·), then the ELM model is:

[0163]

[0164] In the formula, β i =[b i1 ,b i2 ,…,b im ] T w represents the weights from the i-th node in the hidden layer to the output layer of the model. i =[w i1 ,w i2 ,…,w in ] T Let b be the weight of the i-th node in the input layer and the hidden layer of the model. i This represents the threshold value for the i-th node in the hidden layer. The output value of the ELM model can fit the sample with zero error, i.e.:

[0165]

[0166] That is, b exists. i w i and b i satisfy:

[0167]

[0168] It can be abbreviated as:

[0169] Hβ=T (4)

[0170] in:

[0171]

[0172] In the formula, H is called the hidden layer output matrix. During the model training phase, the input weights and biases of the feedforward neural network are randomly set. By calculating the output matrix H, the ELM learning and training problem is transformed into solving the least squares norm problem of the output weight matrix β, that is:

[0173]

[0174] In the formula H + Let H be the generalized inverse of matrix H.

[0175] The client uses training and testing sets obtained from processing historical web browsing information of users of different age groups to train models, resulting in pop-up guidance prediction models for different age groups. The inputs to the pop-up guidance prediction models for different age groups include user tags, historical user behavior habits, and historical user behavior trajectories, and the output is the recommendation guidance result.

[0176] The above training examples categorized users by age group, but this application is not limited to this, and age group categorization may not be required in specific implementations.

[0177] In some embodiments, recommended guidance results can be generated based on network detection results, user webpage browsing information, and pop-up guidance prediction models. Guidance information can then be output based on the recommended guidance results to prompt the user to perform corresponding operations. Specifically, this includes the following:

[0178] 1. Format of output guidance information

[0179] Recommendation guidance results are transformed into user-friendly information formats, such as pop-up notifications, mobile app message alerts, in-web page card styles, or email notifications.

[0180] 2. Operation prompt design

[0181] Each notification includes a clear call to action, such as "Try reloading the page," "Check your network settings," or "We recommend you visit this link," encouraging users to take specific action.

[0182] Ideally, a user feedback mechanism can also be integrated, allowing users to evaluate the recommended guidance information in order to further optimize the recommendation model and improve the user experience.

[0183] The network monitoring guidance strategy is implemented based on the aggregation and analysis of historical user web browsing information, and may specifically include the following:

[0184] User tags, user history behavior habits, and user history behavior patterns

[0185] 1. User behavior analysis

[0186] Statistical analysis methods can be used to analyze users' browsing habits and behavioral patterns. For example, cluster analysis can be used to group users according to similar browsing behaviors, identifying different types of users. Time series analysis can also be used to analyze users' access patterns in different time periods, identifying high-frequency access periods and abnormal behaviors.

[0187] 2. Problem Identification

[0188] Based on a user's browsing history, potential network problems can be identified. For example, for network timeout issues, it's possible to analyze whether the user experiences frequent delays when accessing certain websites. For network outages, it's possible to check whether the user is unable to access the network during specific time periods. For domain name errors, analysis can be performed on 404 error pages appearing in the user's access records.

[0189] 3. Generate guidance strategy

[0190] For identified issues, personalized instructions are generated based on the user's historical behavior and tags. For example, if a specific user experiences timeouts when frequently accessing a certain website, the system can suggest choosing a more stable network connection or changing DNS settings. For users who frequently experience network outages, the system can advise them to check their router settings or contact their internet service provider.

[0191] Ideally, after implementing the guidance strategy, user feedback should be collected to evaluate its effectiveness, and the analysis model and guidance strategy should be continuously optimized and adjusted based on the feedback data. Additionally, by continuously tracking user browsing behavior and network conditions, the data model can be updated in real time, thereby improving the accuracy and relevance of aggregated analysis and enabling a dynamic network monitoring guidance strategy.

[0192] In some embodiments, such as Figure 6 As shown, the steps for pre-creating the network monitoring guidance policy described above can, in practice, include the following:

[0193] S601: Obtain historical user webpage browsing information, which includes user tags, user historical behavior habits, and user historical behavior trajectory;

[0194] S602: Based on the collaborative filtering recommendation algorithm, the user's preference level is determined according to user tags, user's historical behavior habits and user's historical behavior trajectory;

[0195] S603: Generate network monitoring guidance strategy based on the determined preference level.

[0196] The specific methods for obtaining the aforementioned user tags may include collecting tags during the user registration process and information input. Furthermore, user tags can be dynamically adjusted based on user online behavior (such as clicks and purchases) to maintain the accuracy and relevance of the information.

[0197] User behavior history can track a user's actions over a period of time, including browsing duration, page visit frequency, and click behavior. Website analytics tools (such as Google Analytics) or custom tracking code can be used to record various user behaviors in real time. User behavior history can be stored in a time-series format to form a user behavior log for later use.

[0198] User historical behavior can be a user's browsing path within a specific time period, including visited pages, timestamps, and event types. Recording user historical behavior can utilize an event-driven approach, recording relevant information and uploading it to the backend database in real time when a user visits a page or clicks a link. User historical behavior is periodically organized and cleaned to optimize storage and retrieval efficiency, while retaining a certain amount of historical data for model training and analysis.

[0199] When determining user preferences, collaborative filtering recommendation algorithms can be used, including user-based collaborative filtering and item-based collaborative filtering. User-based collaborative filtering recommends content by comparing the similarity between different users. For example, by reviewing the browsing history of users A and B, if they share similar interests, content that user B might be interested in but user A hasn't seen can be recommended. Item-based collaborative filtering analyzes items a user has previously liked and then recommends other similar items.

[0200] Then, similarity calculation methods (such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc.) are used to calculate the similarity between users and between items. Based on known user behavior records, potential ratings for unvisited content are predicted, and a weighted average is used to generate preference ratings, thus achieving the pre-set rating. Afterwards, preference levels need to be categorized, the calculated ratings are standardized, and thresholds are set to distinguish between high, medium, and low preference content, in order to better generate recommendation strategies.

[0201] The network monitoring guidance strategy is implemented based on the aggregation and analysis of historical user web browsing information. When generating the network monitoring guidance strategy according to a determined level of preference, personalized network monitoring guidance strategies can be formulated based on the analysis results of user tags, historical behavioral habits, and behavioral patterns. The recommended behavior under specific circumstances is clearly defined; for example, if the user's preference level is higher than a certain threshold, updates of that type of content are recommended. Preferably, this application can also design adjustable parameters, allowing the strategy to be dynamically adjusted based on real-time user feedback (such as changes in user behavior or shifts in preferences).

[0202] Based on the network monitoring guidance strategy obtained above, recommended guidance results can be generated according to network detection results, user web browsing information, and the network monitoring guidance strategy. This can be achieved in the following way:

[0203] 1. The process of generating recommendation guidelines

[0204] Data integration: Obtain current user network status data and online behavior, and combine it with previously obtained user browsing history information and established guidance strategies.

[0205] Effectiveness evaluation mechanism: Real-time data input is used to analyze the effectiveness of the generated guidance results, such as calculating the click-through rate of the actual recommended content and the user engagement level, in order to evaluate the effectiveness and rationality of the guidance strategy.

[0206] 2. Generation and optimization of recommendation results

[0207] Personalized recommendation results: Based on the generated network monitoring guidance strategy, a list of recommended content is generated for each user, including various forms such as text information, images, and videos, to enhance attractiveness.

[0208] Continuous optimization mechanism: Regularly analyze historical data and user feedback to optimize recommendation algorithms and strategies, ensuring that recommendation results always remain consistent with user needs.

[0209] Based on the recommendation guidance results obtained above, guidance information can be output to prompt users to perform corresponding operations based on the guidance information. This can be achieved in the following way:

[0210] 1. Display format of guidance information

[0211] Diverse ways of presenting recommended content, including pop-up notifications, page navigation bar recommendations, and email notifications, ensure that users see recommended information at the appropriate time.

[0212] 2. User operation guidance

[0213] Provide clear and concise operation guidance, linked to the recommended content, to ensure that users understand the meaning and function of the recommendations and encourage them to take corresponding actions (such as clicking links, purchasing recommended products, etc.).

[0214] 3. User feedback collection and iteration

[0215] After each recommendation, a user feedback form is added, allowing users to rate the recommended content (such as liking, disliking, or providing suggestions). This data is fed back to the recommendation algorithm for TM optimization, in order to continuously improve the user's personalized experience.

[0216] Network monitoring guidance strategies are implemented based on the aggregation and analysis of historical user web browsing information. In some embodiments, such as... Figure 7 As shown, the steps for pre-creating the network monitoring guidance policy described above can, in practice, include the following:

[0217] S701: Obtain historical user webpage browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory;

[0218] S702: Based on content recommendation algorithms, user interest tags are obtained according to user tags, user historical behavior habits, and user historical behavior trajectories;

[0219] S703: Obtain a network monitoring guidance strategy based on the user's preferences according to the interest tags.

[0220] Among these, obtaining user tags, user history behavior habits, and user history behavior trajectories is crucial. Figure 6 The corresponding embodiments described above have been explained in detail and will not be repeated here.

[0221] The formation of interest tags involves combining user tags, behavioral habits, and historical data, and using content recommendation algorithms to generate user interest tags. For example, if a user frequently browses web pages in the categories of "technology" and "travel," relevant interest tags (such as "technology enthusiast" or "travel explorer") will be generated for them. Interest tags can be periodically verified and optimized through A / B testing or user feedback to ensure their accuracy and timeliness.

[0222] Specifically, a network monitoring guidance strategy based on interest tags to obtain user preferences can be implemented through the following methods:

[0223] 1. Formulation of network monitoring strategy

[0224] Based on the generated interest tags, specific network monitoring strategies are developed to monitor content changes and information updates highly relevant to user interests. Strategy elements may include the type of content to be monitored (e.g., news, product updates, social media trends), specific websites or platforms to follow, and the frequency of information updates (e.g., real-time monitoring, scheduled queries).

[0225] 2. Application of Personalization Strategies

[0226] Personalized implementation is possible. For example, if a user's tags indicate an interest in "healthy living," the strategy will focus on monitoring information on web pages related to health products, fitness activities, and dietary advice. Furthermore, the web monitoring strategy can be dynamically adjusted based on changes in user behavior and updates to interest tags to ensure it always aligns with the user's latest needs.

[0227] When generating recommendation guidance results based on network detection results, user web browsing information, and network monitoring guidance strategies, data integration and processing can be performed first, followed by the generation of recommendation guidance results. During data integration, real-time data (such as price changes, user reviews, new product releases, etc.), historical user web browsing information, and network monitoring guidance strategies are integrated into a comprehensive dataset. During data processing, big data processing frameworks (such as Apache Spark or Hadoop) are used for data cleaning, transformation, and analysis to extract valuable information. When generating recommendation guidance results, personalized recommendation guidance results can be generated using recommendation algorithms (such as collaborative filtering or content filtering) based on the integrated data. Preferably, a real-time feedback mechanism can be introduced to evaluate the effectiveness of the recommendation results based on user click-through rates and interaction levels, thereby continuously optimizing the recommendation algorithm.

[0228] Based on the recommended guidance results, guidance information is output to prompt users to perform corresponding operations. This output can take various forms, including but not limited to push notifications, in-app messages, emails, and social media sharing, to ensure the timeliness and effectiveness of the information. A user-friendly interface is designed to present the recommended guidance information in an intuitive and easy-to-understand manner.

[0229] When prompting users to perform corresponding operations based on the guidance information, operation prompts can be designed, and the output information should include clear operation prompts, such as "Click to view details" or "Buy now", to encourage users to interact further based on the recommendations.

[0230] Ideally, a user feedback option can be included in the recommendation results output to assess user satisfaction with the recommended content. By collecting user evaluation data, the recommendation algorithm and guidance strategy can be optimized. Combining user feedback with behavioral data serves as the basis for the next round of interest tag generation and network monitoring strategy formulation, creating a virtuous cycle that continuously improves the user experience.

[0231] Specifically, generating the recommended guidance result based on the network detection results, the user's webpage browsing information, and the pre-created network monitoring guidance strategy may include: matching the corresponding network monitoring guidance strategy based on the network detection results and the user's webpage browsing information, and using this as the recommended guidance result. In one embodiment, matching the corresponding network monitoring guidance strategy based on the network detection results and the user's webpage browsing information can calculate the similarity between the network detection results and the user's webpage browsing information and the webpage browsing information of each user. This similarity can be cosine similarity, Euclidean distance, Pearson correlation coefficient, etc., which will not be elaborated on in this application.

[0232] The above Figures 5 to 7The corresponding embodiments describe generating recommendation guidance results based on network detection results, user webpage browsing information, and network monitoring guidance strategies, as well as generating recommendation guidance results based on network detection results, user webpage browsing information, and pop-up guidance prediction models. In this application, recommendation guidance results can also be generated based on network detection results, user webpage browsing information, network monitoring guidance strategies, and pop-up guidance prediction models.

[0233] Recommended guidance results can be generated based on this network monitoring guidance strategy, and also based on the pop-up guidance prediction model. Furthermore, a superior recommended guidance result can be obtained from both the network monitoring guidance strategy and the pop-up guidance prediction model. For example, the superior recommended guidance result can be output to the user based on their preferences.

[0234] In some embodiments, such as Figure 8 As shown, the above-mentioned recommendation guidance results are generated based on network detection results, user web browsing information, network monitoring guidance strategies, and pop-up guidance prediction models. In specific implementation, this may include the following:

[0235] S801: Generate a first recommendation guidance result based on the network detection result, the user's webpage browsing information, and the pre-created network monitoring guidance strategy;

[0236] S802: Generate a second recommendation guidance result based on the network detection result, the user's webpage browsing information, and the pre-created pop-up guidance prediction model;

[0237] S803: Obtain the user's preference settings, calculate the relevance between the first recommendation guidance result and the second recommendation guidance result and the preference settings respectively, and take the recommendation guidance result with high relevance as the final recommendation guidance result.

[0238] The results of the first recommendation guideline mentioned above can be referenced. Figure 6 and Figure 7 In the corresponding embodiments, the results of the second recommendation guidance described above can be referred to. Figure 5 The corresponding implementation examples will not be described in detail here.

[0239] In S803, user preferences can be obtained through various methods. Options are provided to users upon initial system launch, user registration, or in the user settings interface. User preferences are collected through questionnaires, multiple-choice questions, or sliders. Preference settings may include, but are not limited to: content type (e.g., news, entertainment, technology, sports), language preference, price range (for e-commerce recommendations), brand preference, and update frequency (e.g., daily, weekly). Preference settings are stored in the user profile database and associated with the user's unique identifier (e.g., user ID) for subsequent retrieval and use.

[0240] In practice, relevance calculation techniques (such as cosine similarity, Jaccard similarity coefficient, or Euclidean distance) can be used to calculate the relevance between each first recommendation result and the user's preference settings, and the relevance between each second recommendation result and the user's preference settings. For example, for each recommended content, features (such as category and keywords) are extracted and compared with user preferences. The calculation results are saved as scores, with higher scores indicating greater relevance.

[0241] After determining the relevance between the first and second recommendation guidance results and the user's preferences, the relevance scores can be integrated. The relevance scores of the first and second recommendation guidance results can be combined and compared. A weighted average method can be used, assigning weights to different recommendation sources (e.g., giving higher weight to the first recommendation result) to emphasize more reliable sources. When determining highly relevant recommendation guidance results, a threshold can be set to filter out recommendations exceeding a certain relevance threshold as the final recommendation guidance results. The final recommendations should not only meet the user's preferences but also match their interests. The final recommended guidance results are then displayed to the user. At this point, the system can inform the user of the detected match between user preferences and recommended content, enhancing the user experience and increasing system transparency and user trust.

[0242] Figure 9 This is a schematic diagram of the UI pop-up guidance in an embodiment of this specification; Figure 10 This is a schematic diagram of weak network guidance in an embodiment of this specification; network guidance and pop-up guidance may include the following: classifying network timeout, disconnection, weak network, DNS, connection, domain name resolution, etc.; designing corresponding error codes and pop-up guidance prompts; network abnormality page prompts; guiding users to set up themselves or check related network tests; adding application configuration support to the management backend resource slots, etc., but this invention is not limited to these.

[0243] As can be seen from the above, based on the error pop-up guidance method provided in the embodiments of this specification, when a user uses the network, the current network status of the user can be detected in real time, and a network detection result can be generated according to a pre-set network detection rule. If the network detection result indicates a network anomaly, the current user tag, current user behavior habits, and current user behavior trajectory are obtained. Recommended guidance results are generated based on the network detection results, the user's web browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model. Guidance information is output based on the recommended guidance results to prompt the user to perform corresponding operations based on the guidance information. This enables the aggregation analysis and pop-up guidance of different users' functional entry points, achieving effective scheduling of pop-up guidance for weak networks.

[0244] This specification provides an electronic device through its embodiments. (See attached document.) Figure 11 As shown. The electronic device includes a network communication port 1101, a processor 1102, and a memory 1103. These structures are connected by internal cables so that they can perform specific data interaction.

[0245] Specifically, the network communication port 1101 can be used to receive the user's current webpage browsing information, which includes: current user tags, current user behavior habits, and current user behavior trajectory.

[0246] The processor 1102 is specifically configured to generate network detection results according to pre-defined network detection rules; if the network detection result indicates a network anomaly, it acquires the user's current webpage browsing information; and generates recommended guidance results based on the network detection results, the user's webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model. The network monitoring guidance strategy is implemented through aggregation analysis of historical user webpage browsing information, and the pop-up guidance prediction model is implemented using a training set and a test set obtained from historical user webpage browsing information, based on random initialization of hidden layer parameters and solving for the weights from the hidden layer output to the output layer. Based on the recommended guidance results, it outputs guidance information to prompt the user to perform corresponding operations based on the guidance information.

[0247] The memory 1103 can be used to store the corresponding instruction program, target processing rules and other related data.

[0248] Based on the above method, the relevant structural performance of the server can be effectively utilized to improve the data processing speed of electronic devices and efficiently realize the data processing of market management bills.

[0249] In this embodiment, the network communication port 1101 can be a virtual port bound to different communication protocols, thereby enabling the sending or receiving of different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM or CDMA; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.

[0250] In this embodiment, the processor 1102 can be implemented in any suitable manner. For example, the processor can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc. This specification is not limiting.

[0251] In this embodiment, the memory 1103 may include multiple layers. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with storage function but no physical form is also called a memory, such as RAM, FIFO, etc. In a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0252] This specification also provides a computer-readable storage medium for an error pop-up page guidance method. The computer-readable storage medium stores computer program instructions that, when executed, implement the following: generating a network detection result based on pre-defined network detection rules; if the network detection result indicates a network anomaly, obtaining the user's current webpage browsing information; generating a recommended guidance result based on the network detection result, the user's webpage browsing information, a pre-created network monitoring guidance strategy, and a pop-up guidance prediction model; wherein the network monitoring guidance strategy is implemented based on aggregated analysis of historical user webpage browsing information, and the pop-up guidance prediction model is implemented using a training set and a test set obtained based on historical user webpage browsing information, based on random initialization of hidden layer parameters and solving for the weights from hidden layer output to output layer; and outputting guidance information based on the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0253] In this embodiment, the storage medium includes, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), cache, hard disk drive (HDD), or memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured according to standards specified in the communication protocol for network connection communication.

[0254] In this embodiment, the specific functions and effects implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other embodiments, and will not be repeated here.

[0255] This specification also provides a computer program product, comprising at least a computer program, which, when executed by a processor, implements the following method steps: generating a network detection result according to pre-set network detection rules; if the network detection result indicates a network anomaly, obtaining the user's current webpage browsing information; generating a recommendation guidance result based on the network detection result, the user's webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model; wherein the network monitoring guidance strategy is implemented based on aggregate analysis of historical user webpage browsing information, and the pop-up guidance prediction model is implemented using a training set and a test set obtained based on historical user webpage browsing information, based on random initialization of hidden layer parameters and solving for the weights from hidden layer output to output layer; and outputting guidance information based on the recommendation guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0256] See Figure 12 As shown in the embodiments of this specification, an error pop-up page guidance device based on weak network detection is also provided. This device may specifically include the following structural units:

[0257] The detection result generation unit 1201 is used to detect the user's current network status in real time and generate network detection results according to the pre-set network detection rules. The network detection results include: network response timeout, whether the network is disconnected, whether the network is a slow request, whether the network is in an illegal network segment or a WIFI segment, and whether DNS / domain name resolution is normal.

[0258] The information acquisition unit 1202, if the network detection result is a network anomaly, acquires the user's current webpage browsing information, which includes: current user tags, current user behavior habits and current user behavior trajectory;

[0259] The guidance result generation unit 1203 is used to generate recommendation guidance results based on network detection results, user webpage browsing information, and pre-created network monitoring guidance strategy and pop-up guidance prediction model. The network monitoring guidance strategy is implemented by aggregation analysis based on historical user webpage browsing information, and the pop-up guidance prediction model is implemented by using training set and test set obtained based on historical user webpage browsing information, based on random initialization of hidden layer parameters and solving for the weights from hidden layer output to output layer.

[0260] The information output unit 1204 is used to output guidance information based on the recommendation guidance results to prompt the user to perform the corresponding operation based on the guidance information.

[0261] In one embodiment, the detection result generation unit includes: a state detection module, a strategy acquisition module, a rule query module, a parameter acquisition module, and a detection matching module.

[0262] The status detection module is used to detect the current network status according to a preset network status strategy;

[0263] The policy acquisition module is used to acquire the network detection policy, which is dynamically injected into the local client via the CCB API.

[0264] The rule query module is used to query the corresponding network detection rules from the network detection strategy based on the network status;

[0265] The parameter acquisition module is used to acquire the network detection parameters of the current network;

[0266] The detection and matching module is used to detect and match the network state with the network detection rules and network detection parameters to obtain the corresponding network detection results.

[0267] In one embodiment, the detection matching module includes: a state matching submodule, a comparison submodule, and an error code allocation module.

[0268] The state matching submodule is used to match the network detection rules with the network detection parameters to the network state;

[0269] The comparison submodule is used to compare the matched network detection rules with the network detection parameters, and obtain the corresponding network detection results based on the comparison results;

[0270] The error code allocation module is used to obtain the pre-assigned error codes of the network detection results.

[0271] In one embodiment, the error pop-up page guidance device further includes a model creation unit, which includes a historical information acquisition module, a preprocessing module, and a model generation module.

[0272] The historical information acquisition module is used to acquire historical user web browsing information, which includes: user tags, historical user behavior habits, and historical user behavior trajectories.

[0273] The preprocessing module is used to preprocess the historical user webpage browsing information to obtain training and test sets;

[0274] The model generation module is used to train the model using the training set and the test set. Based on the random initialization of the hidden layer parameters and the solution of the weights from the hidden layer output to the output layer, it generates a pop-up guidance prediction model.

[0275] In one embodiment, the error pop-up page guidance device further includes: a historical information acquisition unit, a user preference determination unit, and a strategy generation unit.

[0276] The historical information acquisition unit is used to acquire historical user webpage browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory.

[0277] The user preference determination unit is used to determine the degree of user preference based on collaborative filtering recommendation algorithms, user tags, user historical behavior habits, and user historical behavior trajectories.

[0278] The policy generation unit is used to generate the network monitoring guidance policy based on a determined level of preference.

[0279] In one embodiment, the error pop-up page guidance device further includes: a historical information acquisition unit, a tag generation unit, and a tag generation unit.

[0280] The historical information acquisition unit is used to acquire historical user webpage browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory.

[0281] The tag generation unit is used to obtain users' interest tags based on the feature description events of users' business products, using content recommendation algorithms.

[0282] The strategy determination unit is used to obtain the network monitoring guidance strategy based on the user's preferences according to the interest tags.

[0283] In one embodiment, the guidance result generation unit 1203 is specifically used to match the corresponding network monitoring guidance strategy based on the network detection result and the user's webpage browsing information, as a recommended guidance result.

[0284] In one embodiment, the guidance result generation unit 1203 includes: a first result generation module, a second result generation module, and a guidance result generation module.

[0285] The first result generation module is used to generate a first recommendation guidance result based on the network detection result, the user's webpage browsing information, and the pre-created network monitoring guidance strategy.

[0286] The second result generation module is used to generate a second recommendation guidance result based on the network detection result, the user's webpage browsing information, and the pre-created pop-up guidance prediction model.

[0287] The guidance result generation module is used to obtain the user's preference settings, calculate the relevance between the first and second recommended guidance results and the preference settings, and take the recommended guidance result with high relevance as the final recommended guidance result.

[0288] As can be seen from the above, based on the error pop-up page guidance device provided in the embodiments of this specification, when a user uses the network, the current network status of the user can be detected in real time, and a network detection result can be generated according to the pre-set network detection rules. If the network detection result indicates a network anomaly, the current user tag, current user behavior habits, and current user behavior trajectory are obtained. Recommended guidance results are generated based on the network detection results, the user's webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model. Guidance information is output based on the recommended guidance results to prompt the user to perform corresponding operations based on the guidance information. This enables the aggregation analysis and pop-up guidance of different users' functional entry points, achieving effective scheduling of pop-up guidance for weak networks.

[0289] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0290] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will 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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0291] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function 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.

[0292] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable 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.

[0293] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0294] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for providing error pop-up page guidance based on weak network detection, characterized in that, include: Real-time detection of the user's current network status, and generation of network detection results based on pre-defined network detection rules; The network detection results include: network response timeout, network disconnection, network slow request, network being in an illegal network segment or WIFI segment, and whether DNS / domain name resolution is normal. If the network detection result indicates a network anomaly, obtain the user's current webpage browsing information, which includes: current user tags, current user behavior habits, and current user behavior trajectory. Recommendation guidance results are generated based on the network detection results, the user's webpage browsing information, and the pre-created network monitoring guidance strategy and pop-up guidance prediction model. The network monitoring guidance strategy is implemented by aggregation analysis based on historical user webpage browsing information, and the pop-up guidance prediction model is implemented by using the training set and test set obtained based on historical user webpage browsing information, based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer. Based on the recommended guidance results, output guidance information to prompt the user to perform the corresponding operation based on the guidance information; The steps of the pre-created pop-up guidance prediction model include: Obtain historical user web browsing information, which includes: user tags, historical user behavior habits, and historical user behavior trajectories; The historical user webpage browsing information is preprocessed to obtain a training set and a test set; The model is trained using the training and test sets. Based on the random initialization of the hidden layer parameters and the solution of the weights from the hidden layer output to the output layer, a pop-up guidance prediction model is generated. The steps for pre-creating the network listening guidance policy include: Obtain historical user web browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory; Based on the collaborative filtering recommendation algorithm, the user's preference level is determined according to user tags, user's historical behavior habits, and user's historical behavior trajectory. The network monitoring guidance strategy is generated based on the determined level of preference; or Obtain historical user web browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory; Based on content recommendation algorithms, user interest tags are obtained according to user tags, user historical behavior habits, and user historical behavior trajectories. Based on the interest tags, a network monitoring guidance strategy is derived to guide user preferences.

2. The error pop-up page guidance method according to claim 1, characterized in that, The real-time detection of the user's current network status and the generation of network detection results based on pre-defined network detection rules include: The current network status is detected according to the preset network status strategy; Obtain the network detection policy, which is dynamically injected into the local client via the CCB API; Based on the network status, query the corresponding network detection rules from the network detection strategy; Obtain the network detection parameters of the current network; The network detection rules and network detection parameters are used to detect and match the network state to obtain the corresponding network detection results.

3. The error pop-up page guidance method according to claim 2, characterized in that, The step of matching the network detection rules with the network detection parameters to detect and match the network state to obtain the corresponding network detection result includes: The network detection rules and network detection parameters are used to match the network state. The matched network detection rules are compared with the network detection parameters, and the corresponding network detection results are obtained based on the comparison results. Obtain the pre-assigned error code from the network detection results.

4. The error pop-up page guidance method according to claim 1, characterized in that, Based on the network detection results, the user's web browsing information, and the pre-created network monitoring guidance strategy, a recommendation guidance result is generated, including: Based on the network detection results and the user's web browsing information, a corresponding network monitoring guidance strategy is matched and used as the recommendation guidance result.

5. The error pop-up page guidance method according to claim 1, characterized in that, The step of generating recommendation guidance results based on the network detection results, the user's webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model includes: A first recommendation guidance result is generated based on the network detection results, the user's webpage browsing information, and the pre-created network monitoring guidance strategy. A second recommendation guidance result is generated based on the network detection results, the user's webpage browsing information, and the pre-created pop-up guidance prediction model. Obtain the user's preference settings, calculate the relevance between the first recommendation guidance result and the second recommendation guidance result and the preference settings, and take the recommendation guidance result with the higher relevance as the final recommendation guidance result.

6. A pop-up error message guidance device based on weak network detection, characterized in that, include: The detection result generation unit is used to detect the user's current network status in real time and generate network detection results according to pre-set network detection rules. The network detection results include: network response timeout, network disconnection, network slow request, network being in an illegal network segment or WIFI segment, and whether DNS / domain name resolution is normal. The information acquisition unit, if the network detection result is a network anomaly, acquires the user's current webpage browsing information, which includes: current user tags, current user behavior habits, and current user behavior trajectory. The guidance result generation unit is used to generate recommendation guidance results based on the network detection results, user webpage browsing information, and a pre-created network monitoring guidance strategy and pop-up guidance prediction model. The network monitoring guidance strategy is implemented by aggregation analysis based on historical user webpage browsing information, and the pop-up guidance prediction model is implemented by using a training set and a test set obtained based on historical user webpage browsing information, based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer. An information output unit is used to output guidance information based on the recommendation guidance result to prompt the user to perform corresponding operations based on the guidance information; The model creation unit includes: a historical information acquisition module for acquiring historical user webpage browsing information, including user tags, historical user behavior habits, and historical user behavior trajectories; a preprocessing module for preprocessing the historical user webpage browsing information to obtain a training set and a test set; and a model generation module for training the model using the training set and the test set, generating a pop-up guidance prediction model based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer. The historical information acquisition unit is used to acquire historical user webpage browsing information, which includes: user tags, user historical behavior habits, and user historical behavior trajectory. The error pop-up page guidance device further includes: a user preference determination unit and a strategy generation unit, or a tag generation unit and a strategy determination unit; The user preference determination unit is used to determine the user's preference level based on the collaborative filtering recommendation algorithm, according to user tags, user historical behavior habits, and user historical behavior trajectory. The strategy generation unit is used to generate the network monitoring guidance strategy based on a determined degree of preference. The tag generation unit is used to obtain user interest tags based on the feature description events of user business products, using a content recommendation algorithm. The strategy determination unit is used to obtain a network monitoring guidance strategy based on the user's preferences according to the interest tags.

7. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the error pop-up page guidance method according to any one of claims 1 to 5.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the error pop-up page guidance method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the error pop-up page guidance method according to any one of claims 1 to 5.

Images