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

Abstract

The invention provides an error-reporting popup page guiding method and device based on weak network detection, and the method comprises the 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 that the network is abnormal, obtaining current webpage browsing information of the user; generating a recommendation guidance result according to the network detection result, the user webpage browsing information and a pre-created network monitoring guidance strategy and / or a pop-up window guidance prediction model; and outputting guidance information according to the recommended guidance result to prompt the user to execute corresponding operation based on the guidance information. Therefore, aggregation analysis and pop-up window guidance can be carried out on function entrances of different users, and effective scheduling of pop-up window guidance of a weak network is realized.

Description

Technical Field

[0001] The present invention relates to network detection related technologies, and in particular to an error pop-up window page guidance method and device based on weak network detection. Background Art

[0002] With the continuous development of mobile Internet and the continuous advancement of financial technology, banks not only need to actively transform their business, but also need to quickly iterate products and innovate. As the business becomes more and more complex and the functions become more and more numerous, the access requirements for multi-terminal systems become more and more stringent, and the service access of each end is also subject to different constraints and restrictions. Some services can be accessed, while some services cannot be accessed, and the response time of some accesses is also different. Mobile banking is not only complex in itself, but also complex in its external role; in addition, mobile banking itself is a platform business, and it also plays the role of a platform for the development of new businesses.

[0003] In order to respond promptly to new market demands and changes and meet new financial needs for intelligent and digital mobile banking, clients are faced with the urgency of reconstructing their architecture and cross-end components.

[0004] In summary, how to improve efficiency and meet the needs of marketing operations personnel for rapid updates and promotions of business on multiple platforms has become an urgent problem to be solved. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a method and device for guiding an error pop-up page based on weak network detection.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides an error pop-up page guidance method based on weak network detection, comprising:

[0008] Real-time detection of the user's current network status, and generation of network detection results according to 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 WIFI segment, and whether the DNS / domain name resolution is normally accessed;

[0009] If the network detection result is that the network is abnormal, obtain the user's current web browsing information, the current user's web browsing information includes: current user tags, current user behavior habits and current user behavior track;

[0010] Generate a recommendation guidance result according to the network detection result, the user web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up window guidance prediction model; wherein the network monitoring guidance strategy is implemented based on aggregate analysis of historical user web browsing information, and the pop-up window guidance prediction model is implemented by using a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weight of hidden layer output to output layer;

[0011] Output guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0012] In one embodiment, the real-time detection of the user's current network status and the generation of a network detection result according to a preset network detection rule include:

[0013] Detect the network status of the current network according to the preset network status strategy;

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

[0015] Querying a corresponding network detection rule from the network detection strategy according to the network status;

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

[0017] The network detection rule and the network detection parameter are used to detect and match the network status to obtain a corresponding network detection result.

[0018] In one embodiment, detecting and matching the network status with the network detection rule and the network detection parameter to obtain a corresponding network detection result includes:

[0019] Matching the network status with the network detection rule and the network detection parameter;

[0020] Compare the matched network detection rule with the network detection parameter, and obtain the corresponding network detection result according to the comparison result;

[0021] Obtain an error code pre-assigned to the network detection result.

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

[0023] Obtaining historical user web browsing information, the historical user web browsing information including: user tags, historical user behavior habits and historical user behavior tracks;

[0024] Preprocessing the historical user web browsing information to obtain a training set and a test set;

[0025] The training set and the test set are used to perform model training, and a pop-up guidance prediction model is generated based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer.

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

[0027] Obtaining historical user web browsing information, the historical user web browsing information including: user tags, user historical behavior habits and user historical behavior tracks;

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

[0029] The network monitoring guidance strategy is generated according to the determined preference level.

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

[0031] Obtain historical user web browsing information, the historical user web browsing information including: user tags, user historical behavior habits and user historical behavior tracks;

[0032] Based on the content recommendation algorithm, the user's interest tags are obtained according to the user tags, user historical behavior habits and user historical behavior trajectories;

[0033] The network monitoring guidance strategy preferred by the user is obtained according to the interest tag.

[0034] In one embodiment, generating a recommendation guidance result according to the network detection result, the user web browsing information and a pre-created network monitoring guidance strategy includes:

[0035] A corresponding network monitoring guidance strategy is matched according to the network detection result and the user's web browsing information as a recommendation guidance result.

[0036] In one embodiment, generating a recommendation guidance result according to the network detection result, the user web browsing information, and a pre-created network monitoring guidance strategy and / or a pop-up guidance prediction model includes:

[0037] Generate a first recommended guidance result according to the network detection result, the user's web browsing information and a pre-created network monitoring guidance strategy;

[0038] Generate a second recommendation guidance result according to the network detection result, the user's web browsing information and a pre-created pop-up guidance prediction model;

[0039] The user's preference settings are obtained, and the correlation between the first recommended guidance result and the second recommended guidance result and the preference settings is calculated respectively, and the recommended guidance result with the highest correlation is used as the final recommended guidance result.

[0040] In a second aspect, the present application provides an error pop-up page guidance device based on weak network detection, comprising:

[0041] The detection result generating unit detects the current network status of the user in real time and generates a network detection result according to a preset network detection rule; the network detection result includes: 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 the DNS / domain name resolution is normally accessed;

[0042] The information acquisition unit acquires the user's current web browsing information if the network detection result is a network anomaly, wherein the current user's web browsing information includes: the current user's tag, the current user's behavior habits, and the current user's behavior trajectory;

[0043] A guidance result generating unit, used for generating a recommended guidance result according to the network detection result, the user web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up window guidance prediction model; wherein the network monitoring guidance strategy is implemented by aggregate analysis based on historical user web browsing information, and the pop-up window guidance prediction model is implemented by using a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weight of hidden layer output to output layer;

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

[0045] In a third aspect, the present 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] In a fourth aspect, the present 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 implements the relevant steps of the above-mentioned error pop-up page guidance method when executing the program.

[0047] In a fifth aspect, the present application provides a computer program product having a computer program stored thereon, which, when executed by a processor, implements the relevant steps of the above-mentioned error pop-up page guidance method.

[0048] Based on the method and device for guiding the pop-up window page of error report based on weak network detection provided in the first specification, when the user uses the network, the user's current network status can be detected in real time, and the network detection result can be generated according to the pre-set network detection rules; if the network detection result is a network anomaly, the current user tag, the current user behavior habits and the current user behavior trajectory are obtained; the recommended guidance result is generated according to the network detection result, the user's web browsing information and the pre-created network monitoring guidance strategy and / or the pop-up window guidance prediction model; the guidance information is output according to the recommended guidance result to prompt the user to perform the corresponding operation based on the guidance information. In this way, the function entrances of different users can be aggregated and analyzed and pop-up window guidance can be performed, so as to realize the effective scheduling of the pop-up window guidance of weak networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

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

[0051] Figure 2 It is a scheduling flow chart of the API corresponding to the full API registration table in an embodiment of the present invention;

[0052] Figure 3 It is a schematic diagram of an embodiment of an error pop-up window page guidance method provided by an embodiment of this specification, in a scenario example;

[0053] Figure 4 It is a schematic diagram of an embodiment of an error pop-up window page guidance method provided by an embodiment of this specification, in a scenario example;

[0054] Figure 5 It is a schematic diagram of an embodiment of an error pop-up window page guidance method provided by an embodiment of this specification, in a scenario example;

[0055] Figure 6 It is a schematic diagram of an embodiment of an error pop-up window page guidance method provided by an embodiment of this specification, in a scenario example;

[0056] Figure 7 It is a schematic diagram of an embodiment of an error pop-up window page guidance method provided by an embodiment of this specification, in a scenario example;

[0057] Figure 8 It is a schematic diagram of an embodiment of an error pop-up window page guidance method provided by an embodiment of this specification, in a scenario example;

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

[0059] Fig.10 This is a schematic diagram of a weak network guide according to an embodiment of this specification;

[0060] Fig.11 is a schematic diagram of the structure of an electronic device provided by an embodiment of this specification;

[0061] Fig.12 It is a schematic diagram of the structural composition of an error pop-up page guidance device provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] It should be noted that the user-related information and data involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by relevant parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances 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. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

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

[0066] APP Application application;

[0067] API Application Programming Interface Application Programming Interface;

[0068] SDK Software Development Kit Software Development Kit;

[0069] WIFI Wireless Fidelity network;

[0070] UI User Interface User Interface;

[0071] URL Uniform Resource Locator Uniform Resource Locator.

[0072] The impact of network performance on user experience will be directly fed back to the operation of the business. Moreover, the inherent weak network problems, DNS problems, and connection performance of mobile networks cannot be compared with traditional fixed networks. Therefore, it is particularly necessary to optimize the mobile terminal network and display friendly reminder pop-up windows. Based on this, the present invention provides.

[0073] like Figure 1 As shown, this specification implements an error pop-up page guidance method based on weak network detection.

[0074] The method is specifically applied to the client side. When implemented, the method may include the following contents:

[0075] S101: Detect the user's current network status in real time and generate a network detection result according to a pre-set network detection rule;

[0076] S102: If the network detection result is that the network is abnormal, obtain the user's current web browsing information, the current user's web browsing information includes: current user tags, current user behavior habits and current user behavior trajectory;

[0077] S103: Generate a recommendation guidance result according to the network detection result, the user's web browsing information, and the pre-created network monitoring guidance strategy and / or pop-up guidance prediction model; wherein the network monitoring guidance strategy is implemented by aggregate analysis based on historical user web 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 web browsing information, based on random initialization of hidden layer parameters and solving the weights of hidden layer output to output layer;

[0078] S104: Outputting guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0079] Among them, the above network detection results may specifically 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 WIFI segment, and whether the DNS / domain name resolution is accessed normally.

[0080] Specifically, in order to meet the needs of business product lines, the client will pre-generate a weak network detection framework (network detection strategy), and based on the pre-set network detection strategy, it can generate corresponding network detection results according to the network to be detected.

[0081] The weak network detection framework can be dynamically injected into the local client through the CCB (Church Community Builder) API. Specifically, it can be dynamically injected into the host APP through the CCB (Church Community Builder) API, and the configuration table and initialization strategy and method can be updated asynchronously online to provide an environment for the next step of network detection.

[0082] In specific implementation, the network detection strategy can be implemented by classifying and defining each stage of the network, fully classifying and defining the status of each network node layer, and extracting the characteristic values ​​of the status to standardize each node. The network detection strategy includes but is not limited to the following 5 network detection rules:

[0083] 1. Network timeout: If the network response time exceeds the set time, it is considered a timeout and the status is recorded as 0.

[0084] The set time length may be, for example, 15 seconds, and may be specifically set as required, and the present invention is not limited to one time.

[0085] 2. Network disconnection: Record status 1 for those without access to the network.

[0086] 3. Slow / weak network: If the monitoring network response time exceeds the set time of 3s, it is considered a slow request and status 2 is recorded.

[0087] The set duration can be set as needed, and can also be determined based on the timeout duration that the users of the big data statistics office can tolerate.

[0088] 4. Network warning: Detect illegal network segments or public insecure WIFI segments and record status 3.

[0089] The unsafe WIFI segment is determined according to a preset relationship table corresponding to the unsafe WIFI segment, and the relationship table can be updated in real time.

[0090] 5. DNS / domain name resolution: Check whether DNS / domain name resolution is accessed normally.

[0091] The network monitoring guidance strategy includes pop-up guidance, network abnormality page prompts, guidance for users to set up themselves or related network detection and viewing, and support for adding application configuration to the management background resource location.

[0092] In order to meet the needs of business product lines, the client will pre-create a pop-up management framework (i.e., network monitoring guidance strategy) and / or 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 through the CCB (ChurchCommunity Builder) API. Specifically, it is dynamically injected into the host APP through the CCB (Church CommunityBuilder) API, and the configuration table and initialization strategy and method are updated asynchronously online to provide an environment for the next step of network monitoring calls. The network monitoring guidance strategy includes but is not limited to the following situations:

[0093] 1. Dynamic detection of network timeout and friendly pop-up prompts: network connection timeout and operation instructions.

[0094] 2. Network disconnection reminder: network connection disconnection reminder and operation instructions.

[0095] 3. Cellular / WiFi switching prompt: Cellular traffic operation guidance is in use.

[0096] 4. Weak network prompt pop-up window: Operation instructions for poor network connection.

[0097] 5. DNS and domain name resolution abnormality reminder: domain name resolution abnormality reminder and operation instructions.

[0098] During the specific implementation, 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 each functional scenario.

[0099] Calls involving network detection and guidance need to be dynamically injected into the code in advance. This call is the business logic that needs to be processed after the APP is started, so that there are input and output of internal and external API methods, including related strategies and error code prompts and other behaviors.

[0100] The network API classification configuration table can be divided into:

[0101] 1. The full API registration form apiconfig.json is used to register all APIs used by various platforms and channels, and to classify and mark them.

[0102] This full API registration table is for the API registration table of network pop-up window scheduling used on multiple terminals and platforms. In the basic API, the SDK is responsible for pop-up window and scheduling. According to needs, a private customized interface can be implemented to implement a custom error pop-up window.

[0103] The full API registration table is a registration of network call layer APIs, which are shared by multiple platforms. Each API has a clear description and scenario-specific usage instructions, including rule permission restrictions, etc.

[0104] The data structure fields of apiconfig.json and the descriptions of the parameters in the fields are as follows:

[0105] Unique ID (id): "0001", which is a unique identifier defined by a category and is used to ensure the uniqueness of the API interface in the system.

[0106] Description (des): "Scan API", which is used to briefly describe the function or purpose of the interface.

[0107] Platform: "ios / android", indicating that the API interface is applicable to mobile platforms, including Android and iOS operating systems.

[0108] Channel type (type): "ccbmobile / ccblife", indicating the specific usage channel of the API, such as mobile banking or CCB Life application platforms.

[0109] Android class name (android_classname): "com.ccb.home.appscene.CCBBridge", which is the full name of the class that implements the API function on the Android platform.

[0110] iOS class name (ios_classname): "CCBSceneBridge", which is the class name that implements the API function on the iOS platform.

[0111] API name: "startSceneAPI", which is the name of the API to identify its function.

[0112] Parameters (params): "key1=value&key2=value2", which indicates the parameters and their corresponding values ​​required when calling the API, and can be passed in the form of key-value pairs.

[0113] Permission rule (rule): "tag:_00028||branchid:440000000", this field defines the permission rule required to initiate the pop-up window. The rule in the example indicates that customers must meet the conditions of specific tags and branch numbers to use the relevant functions.

[0114] This data structure is used to describe a specific API interface. Through the above fields, the data structure provides a comprehensive definition that covers the basic information of the API, applicable platforms, class names, parameter configurations, and permission requirements to facilitate development and use.

[0115] Figure 2 The scheduling flow chart of the API corresponding to the full API registration table is as follows: Figure 2 As shown in the figure, the process scheduling process includes:

[0116] S201: API call.

[0117] S202: CCBH5 Bridge is encapsulated in the middle layer, which is used to instruct how to pop up a window, how to prompt, and distribute tasks to the scheduling layer.

[0118] S203: Distribute to the CCBH5 Operation scheduling strategy layer.

[0119] S204: Determine whether the authority is available; whether there is a corresponding calling method; whether the pilots have their own implementation methods, etc.

[0120] S205: If yes, trigger the corresponding method call and callback; if no, go to S206.

[0121] S206: End.

[0122] 2. The rule permission configuration table ruleconfig.json contains the usage details such as the type, rules, parameters, etc. of the specific API that needs to be configured.

[0123] The rule fields for a scenario are as follows:

[0124] "params":"key1=value1",

[0125] "des":"Scan API, dedicated to mobile banking",

[0126] "rule":"",

[0127] The above fields are partial registration and description of a specific API, and different rules are used in different scenarios.

[0128] According to the above configured strategy, by searching, calculating and monitoring each network node, the network status value of the current user can be clarified and user guidance can be given, thus achieving a complete closed loop of the user network pop-up guidance process and achieving a better user interaction experience.

[0129] Take network collection as an example to illustrate:

[0130] The JSON data records the specific information of the network request for easy analysis and troubleshooting. Each request is identified by a unique event ID and contains the start and end time of the request (in milliseconds) to calculate the latency of the request. The scenario ID defines the specific environment in which the request occurs, such as network or advertising.

[0131] The request result is indicated by the response code. A successful request returns a status code of 200, while a failed request is marked with 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 and 1 for failure). In addition, the response status code and message fields provide additional information about the request result.

[0132] The requested URL and its parameters contain the specific content of the request. In the trace section, the performance of the request in different processing nodes (such as HTTP, DNS, and TCP) is recorded, including the processing time of each stage, the corresponding error information, and its success status. This structured record makes the performance monitoring and problem analysis of network requests clearer, helping the team identify the specific links of delays or errors, so as to make effective optimization and adjustments.

[0133] The above network collection examples are mainly for network performance monitoring and collection related indicators and instructions, specific to a certain indicator, such as which model, which time point, which error message, how long it takes, etc., to comprehensively judge network performance and error guidance.

[0134] In some embodiments, Figure 3 As shown, the above real-time detection of the user's current network status generates a network detection result according to a preset network detection rule. When implemented specifically, it may include the following contents:

[0135] S301: Detecting the network status of the current network according to a preset network status strategy;

[0136] S302: Obtain a network detection policy, which is dynamically injected into the local client through the CCB API;

[0137] S303: querying corresponding network detection rules from the network detection policy according to the current network status;

[0138] S304: Obtain network detection parameters of the current network;

[0139] S305: Detect and match the network status according to the network detection rule and the network detection parameter to obtain a corresponding network detection result.

[0140] The above network status may specifically include normal network and abnormal network. In the normal network state, the present invention generally does not need to provide operation instructions. Network abnormality may include network timeout, network disconnection, slow / weak network, network warning, and detection of whether DNS / domain name resolution is normally accessed.

[0141] It should be noted that in S301, detecting the current network status can be regarded as a preliminary detection method of network detection, which aims to query and verify the network detection rules based on the preliminary detection results.

[0142] Preliminary detection can be performed based on preset network status strategies, which include long network connection time (exceeding the set time), network inability to connect, slow network speed (lower than the preset minimum speed), prompts that the network may have risks, DNS / domain name resolution cannot be accessed normally (DNS server failure, domain name expired, DNS setting error, etc.), etc.

[0143] As described above, a plurality of network detection rules are stored in the network detection policy. Based on an abnormal situation in the current network state, the client can query one or more possible corresponding network detection rules from the network detection policy.

[0144] Specifically, the network detection parameters of the current network may include, for example, a network connection time exceeding 30 seconds, a network speed lower than 50 k / s, and the like.

[0145] In some embodiments, Figure 4 As shown, the above-mentioned network status is detected and matched according to the network detection rules and network detection parameters to obtain the corresponding network detection result. When implemented specifically, it may include the following contents:

[0146] S401: Matching the network status with the network detection rule and the network detection parameter;

[0147] S402: Compare the matched network detection rule with the network detection parameter, and obtain a corresponding network detection result according to the comparison result;

[0148] S403: Obtain the error code pre-assigned by the network detection result.

[0149] In S401, the network detection rules in the network detection strategy need to be matched with the network detection parameters respectively to obtain network detection rules related to the network detection parameters. For example, if the network transmission speed is low, for example, one of the network detection parameters is 5k / s, then there may be a slow / weak network problem, and the network detection rule "slow / weak network: the monitoring network response time that exceeds the set time of 3s is a slow request, and status 2 is recorded" can be matched. It should be noted that the network detection parameters may include multiple ones, and the matched network detection rules may also be multiple.

[0150] The matched network detection rules are compared with the network detection parameters, and the corresponding network detection results can be obtained according to whether the comparison results meet the preset conditions. For example, if the current network connection time is 30 seconds, and the preset setting time is 15 seconds, the network detection result is a network response timeout.

[0151] Specifically, each network detection result may be assigned an error code to be used as an error code prompt during operation guidance.

[0152] Specifically, in order to meet the needs of business product lines, the above-mentioned preset network status strategy and network detection strategy will be generated in advance. The preset network status strategy and network detection strategy can be dynamically injected into the host APP of the local client through CCBAPI, and the configuration table and the initialization strategy and method are updated asynchronously online.

[0153] In some embodiments, Figure 5 As shown, the steps of the above-pre-created pop-up window guidance prediction model may include the following contents when implemented:

[0154] S501: Acquire historical user web browsing information, wherein the historical user web browsing information includes: user tags, historical user behavior habits and historical user behavior tracks;

[0155] Specifically, the client obtains historical user web browsing information of multiple users from the server as model training samples. The historical data includes user tags, historical user behavior habits and historical user behavior trajectories, which are used for model training to obtain a pop-up guidance prediction model.

[0156] S502: Preprocess the historical user web browsing information to obtain a training set and a test set;

[0157] Specifically, the client preprocesses historical user web browsing information, including data cleaning, data normalization, data completion and data partitioning, removes low-quality data, and obtains corresponding high-quality training sets and test sets, respectively, so as to use the high-quality training sets and test sets for model training to generate a pop-up guidance prediction model.

[0158] S503: Perform model training using the training set and the test set, 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.

[0159] Specifically, the client uses the training set and test set obtained by processing historical user web browsing information to perform model training respectively, and obtains the pop-up guidance prediction model. The pop-up guidance prediction model is obtained based on neural network training. The client first randomly initializes the weights and biases from the input layer to the hidden layer, and then performs a nonlinear transformation on the input data through the hidden layer to obtain the hidden layer output matrix. Finally, the hidden layer output matrix and the target output of the training data are used to solve the weights from the hidden layer output to the output layer. The input of the pop-up guidance prediction model includes user labels, historical user behavior habits and historical user behavior trajectories, and the output is the recommendation guidance result.

[0160] Among them, user tags may specifically 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, and historical user behavior trajectories are generally dynamic attributes of users.

[0161] In one embodiment, the client selects data of different age groups (for example, 10 years as one age group) from historical user web browsing information, selects 2000 sets of data for each age group, and obtains a pop-up guidance prediction model for each age group through training.

[0162] In one embodiment, the client performs model training based on a single hidden layer feedforward neural network (SLFN), which consists of an input layer, a hidden layer and an output layer, including a perceptron, a multi-layer perceptron (MLP), a radial basis function network (RBFN), a self-organizing map (SOM) and an extreme learning machine (ELM), etc., but the present application is not limited to this.

[0163] In one embodiment, the client obtains a pop-up window guidance prediction model based on extreme learning machine (ELM) training, and its structure is as follows: Fig.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 by one-step analytical calculation.

[0164] 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), N is the number of observed samples, n is the dimension of the sample input vector, and the output vector t i =[t i1 ,t i2 ,…t im ] T ∈R m, m is the output sample dimension, that is, the number of nodes in the output layer of the ELM model. Assuming the number of nodes in the hidden layer of the model is l, and the activation function is g(·), the ELM model is:

[0165]

[0166] In the formula, β i =[β i1 ,β i2 ,…,β im ] T is the weight from the i-th node in the hidden layer of the model to the output layer, w i =[w i1 ,w i2 ,…,w in ] T is the weight of the i-th node in the model input layer and hidden layer, b i represents the threshold of the i-th node in the hidden layer. The output value of the ELM model can fit the sample with zero error, that is:

[0167]

[0168] That is, there is β i , w i and b i satisfy:

[0169]

[0170] It can be shortened to:

[0171] Hβ=T (4)

[0172] in:

[0173]

[0174] In the formula, H is called the hidden layer output matrix. In the model training stage, the input weights and bias values ​​of the feedforward neural network are randomly set. By calculating the output matrix H, the ELM learning and training problem is transformed into a least squares norm problem for solving the output weight matrix β, that is:

[0175]

[0176] Where H + is the generalized inverse matrix of the matrix H.

[0177] The client uses the training set and test set obtained by processing the historical web browsing information of users of different age groups to train the model respectively, and obtains the pop-up guidance prediction model for different age groups. The input of the pop-up guidance prediction model for different age groups includes user labels, historical user behavior habits and historical user behavior trajectories, and the output is the recommendation guidance result.

[0178] In the above training embodiment, users are divided into age groups, but the present application is not limited thereto, and age groups may not be divided during specific implementation.

[0179] In some embodiments, a recommended guidance result can be generated according to the network detection result, the user's web browsing information and the pop-up guidance prediction model, and guidance information can be output according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information. The specific implementation includes the following contents:

[0180] 1. Output guidance information format

[0181] The recommendation guidance results are converted into user-friendly information formats, such as pop-up notifications, message reminders of mobile applications, card styles within web pages, or email notifications.

[0182] 2. Operation prompt design

[0183] Each prompt message contains a clear call to action, such as "Try to reload the page", "Check network settings", "Recommend you to visit this link", etc., to encourage users to take specific actions.

[0184] Preferably, a user feedback mechanism may also be integrated to allow users to evaluate the recommended guidance information, so as to further optimize the recommendation model and enhance the user experience.

[0185] The network monitoring guidance strategy is implemented based on the aggregate analysis of historical user web browsing information, which can include the following:

[0186] User tags, user historical behavior habits and user historical behavior tracks

[0187] 1. User behavior analysis

[0188] Analyze users' browsing habits and behavior patterns through statistical analysis methods. For example, through cluster analysis, users with similar browsing behaviors can be grouped to identify different types of users. Time series analysis can also be used to analyze users' access patterns in different time periods to identify high-frequency access periods and abnormal behaviors.

[0189] 2. Problem identification

[0190] Identify potential network problems based on the user's browsing history. For example, for network timeouts, you can analyze whether users frequently experience delays when accessing certain specific websites. For network disconnections, you can check whether users cannot access the network within a specific time period. For domain name errors, you can analyze the 404 error pages that appear in the user's access records.

[0191] 3. Generate guidance strategy

[0192] For the identified problems, we generate personalized operation instructions based on the user's historical behavior and tags. For example, for a specific user, if it is detected that a timeout occurs when the user frequently visits a certain website, we can recommend the user to choose a more stable network connection or change the DNS settings. For users who frequently experience network disconnection problems, we can recommend them to check their router settings or contact their network service provider.

[0193] Preferably, after implementing the guidance strategy, user feedback is collected to evaluate the effectiveness of the guidance, and the analysis model and guidance strategy are continuously optimized and adjusted based on the feedback data. In addition, the accuracy and pertinence of the aggregate analysis can be improved by continuously tracking the user's browsing behavior and network conditions, and the data model can be updated in real time, thereby realizing a dynamic network monitoring guidance strategy.

[0194] In some embodiments, Figure 6 As shown, the above step of pre-creating the network monitoring guidance strategy may include the following contents when implemented specifically:

[0195] S601: Acquire historical user web browsing information, wherein the historical user web browsing information includes user tags, user historical behavior habits, and user historical behavior tracks;

[0196] S602: Based on the collaborative filtering recommendation algorithm, determine the user's preference according to the user's tags, the user's historical behavior habits and the user's historical behavior trajectory;

[0197] S603: Generate a network monitoring guidance strategy according to the determined preference level.

[0198] The specific method of obtaining the above user tags may include: collecting tags during the user registration process and information input process. In addition, based on the user's online behavior (such as clicks, purchases, etc.), the user tags can be dynamically adjusted to maintain the accuracy and relevance of the information.

[0199] User historical behavior habits can be the user's behavior over a period of time, including browsing time, page visit frequency, click behavior, etc. You can use website analysis tools (such as Google Analytics) or custom tracking codes to record various user behavior habits in real time. User historical behavior habits can be stored in a time series format to form a user behavior log for subsequent use.

[0200] The user's historical behavior track can be the user's browsing path within a specific time period, including the pages visited, timestamps, event types, etc. The user's historical behavior track can be recorded using an event-driven method. When a user visits a page or clicks a link, the relevant information is recorded in real time and uploaded to the backend database. The user's historical behavior track is regularly sorted and cleaned to optimize storage and search efficiency, and a certain amount of historical records are retained for model training and analysis.

[0201] Among them, when determining the user's preference, the collaborative filtering recommendation algorithms that can be based on include user-based collaborative filtering algorithms, item-based collaborative filtering algorithms, etc. In the user-based collaborative filtering algorithm, content can be recommended by comparing the similarities between different users. For example, by looking at the browsing records of user A and user B, if they have the same interests, then content that user B is interested in but user A has not seen can be recommended; in the item-based collaborative filtering algorithm, the items that users liked in the past can be analyzed, and then other items similar to these items can be recommended.

[0202] Then, similarity calculation methods (such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc.) are used to calculate the similarity between users and users, and between items and items. Based on the known user behavior records, the user's potential rating for unvisited content is predicted, and the preference rating is generated by weighted average to achieve the rating preset. After that, the preference level needs to be classified, the calculated rating is standardized, and a threshold is set to distinguish between high-, medium-, and low-preference content in order to better generate a recommendation strategy.

[0203] The network monitoring guidance strategy is implemented based on the aggregate analysis of historical user web browsing information. When generating the network monitoring guidance strategy based on the determined preference level, a personalized network monitoring guidance strategy can be formulated based on the analysis results of the user's tags, historical behavior habits, and behavior trajectories. Clearly define the recommended behavior in a specific situation. For example, if the user's preference level is higher than a certain threshold, recommend the update of this type of content. Preferably, the present application can also design adjustable parameters to allow the strategy to be dynamically adjusted based on real-time user feedback (such as user behavior changes, preference shifts).

[0204] Based on the network monitoring guidance strategy obtained above, a recommendation guidance result can be generated according to the network detection result, the user's web browsing information and the network monitoring guidance strategy, which can be specifically achieved in the following ways:

[0205] 1. The process of generating recommendation guidelines

[0206] Data integration: Obtain the current user's network status data and online behavior, combined with previously obtained user browsing history information and formulated guidance strategies.

[0207] Effect evaluation mechanism: Use real-time data input to perform effect analysis on the generated guidance results, such as calculating the click-through rate and user engagement of actual recommended content to evaluate the effectiveness and rationality of the guidance strategy.

[0208] 2. Generation and optimization of recommendation results

[0209] Personalized recommendation results: Based on the generated network monitoring guidance strategy, a list of recommended content is generated for each user, including text information, pictures, videos and other forms to increase attractiveness.

[0210] Continuous optimization mechanism: Regularly analyze historical data and user feedback, optimize recommendation algorithms and strategies, and ensure that recommendation results are always consistent with user needs.

[0211] Based on the recommended guidance results obtained above, guidance information can be output to prompt the user to perform corresponding operations based on the guidance information, which can be specifically achieved in the following ways:

[0212] 1. Display format of guidance information

[0213] There are various ways to express recommended content, including pop-up prompts, page navigation bar recommendations, email notifications, etc., to ensure that users see the recommended information at the appropriate time.

[0214] 2. User operation guidance

[0215] Provide clear and concise operation instructions, connect them with the recommended content, ensure that users understand the meaning and role of the recommendation, and encourage them to take corresponding actions (such as clicking on links, purchasing recommended products, etc.).

[0216] 3. User feedback collection and circulation

[0217] A user feedback form is added after each recommendation, allowing users to evaluate the recommended content (such as like, dislike, suggestion), and this data is fed back to the recommendation algorithm for TM optimization to continuously improve the user's personalized experience.

[0218] The network monitoring guidance strategy is implemented based on the aggregate analysis of historical user web browsing information. In some embodiments, such as Figure 7 As shown, the above step of pre-creating the network monitoring guidance strategy may include the following contents when implemented specifically:

[0219] S701: Acquire historical user web browsing information, wherein the historical user web browsing information includes: user tags, user historical behavior habits and user historical behavior tracks;

[0220] S702: Based on the content recommendation algorithm, obtain the user's interest tags according to the user tags, the user's historical behavior habits and the user's historical behavior trajectory;

[0221] S703: Obtaining a network monitoring guidance strategy preferred by the user according to the interest tag.

[0222] Among them, obtaining user tags, user historical behavior habits and user historical behavior tracks is Figure 6 The corresponding embodiments have been described in detail above and will not be repeated here.

[0223] In the process of forming interest tags, the user's tags, behavior habits and historical tracks can be integrated to generate user interest tags using content recommendation algorithms. For example, if a user frequently browses web pages in the categories of "technology" and "travel", relevant interest tags (such as "technology enthusiast" and "travel explorer") will be generated for them. Interest tags can be regularly verified and optimized through A / B testing or user feedback to ensure their accuracy and real-time performance.

[0224] Specifically, the network monitoring guidance strategy of obtaining user preferences based on interest tags can be implemented by the following method:

[0225] 1. Development of network monitoring strategy

[0226] Based on the generated interest tags, a specific network monitoring strategy is formulated to monitor content changes and information updates that are highly relevant to the user's interests. Strategy elements may include the type of content to be monitored (such as news, product updates, social media trends), specific websites or platforms to follow, and the frequency of information updates (such as real-time monitoring, scheduled queries).

[0227] 2. Application of Personalization Strategy

[0228] Personalized implementation, for example, if the user's tag shows that he is interested in "healthy living", the strategy will focus on monitoring information on related web pages such as health products, fitness activities and dietary advice. In addition, the network monitoring strategy can be dynamically adjusted according to changes in user behavior and updates to interest tags to ensure that it always meets the user's latest needs.

[0229] When generating recommendation guidance results based on network detection results, the user's web browsing information and network monitoring guidance strategies, data integration and processing can be performed first, and then the recommendation guidance results are generated. When performing data integration, the acquired 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 data set. When performing data processing, a big data processing framework (such as Apache Spark or Hadoop) is used to clean, convert and analyze the data to extract valuable information. When generating recommendation guidance results, a recommendation algorithm (such as collaborative filtering or content filtering) can be used based on the integrated data to generate personalized recommendation guidance results. Preferably, a real-time feedback mechanism can also be introduced to evaluate the effectiveness of the recommendation results based on user click-through rates and interactions, thereby continuously optimizing the recommendation algorithm.

[0230] In the process of outputting guidance information based on the recommended guidance results to prompt the user to perform corresponding operations based on the guidance information, the guidance information can be output in a variety of forms, including but not limited to push notifications, in-site messages, emails, and social media sharing, etc., to ensure the timeliness and effectiveness of the information. By designing a user-friendly interface, the recommended guidance information is presented in an intuitive and easy-to-understand manner.

[0231] When prompting users to perform corresponding operations based on guidance information, operation prompts can be designed. The output information contains clear operation prompts, such as "click to view details" and "buy now", etc., to encourage users to further interact based on the recommendation results.

[0232] Preferably, a user feedback option can be added to the output of the recommendation results to evaluate the satisfaction of the recommended content. By collecting user evaluation data, the recommendation algorithm and guidance strategy can be optimized. User feedback is combined with behavioral data as the basis for the next round of interest tag generation and network monitoring strategy formulation, forming a virtuous circle and continuously improving user experience.

[0233] Among them, generating a recommended guidance result according to the network detection result, the user web browsing information and the pre-created network monitoring guidance policy can specifically include: matching the corresponding network monitoring guidance policy according to the network detection result and the user web browsing information as the recommended guidance result. In one embodiment, according to matching the corresponding network monitoring guidance policy according to the network detection result and the user web browsing information, the similarity between the network detection result and the user web browsing information and the web browsing information of each user can be calculated, and the similarity can be cosine similarity, Euclidean distance, Pearson correlation coefficient, etc., which will not be elaborated in detail in this application.

[0234] Above Figures 5 to 7The corresponding embodiments describe generating recommended guidance results based on network detection results, user web browsing information, and network monitoring guidance strategies, and generating recommended guidance results based on network detection results, user web browsing information, and pop-up guidance prediction models. In the present application, recommended guidance results can also be generated based on network detection results, user web browsing information, network monitoring guidance strategies, and pop-up guidance prediction models.

[0235] A recommended guidance result can be generated based on the network monitoring guidance strategy, and a recommended guidance result can also be generated based on the pop-up guidance prediction model. In addition, a better recommended guidance result can be obtained based on the recommended guidance result generated by the network monitoring guidance strategy and the recommended guidance result generated by the pop-up guidance prediction model. For example, the better recommended guidance result can be output to the user based on the user's preference.

[0236] In some embodiments, Figure 8 As shown, the above-mentioned recommendation guidance results are generated based on the network detection results, the user's web browsing information, the network monitoring guidance strategy and / or the pop-up guidance prediction model. When implemented specifically, it may include the following contents:

[0237] S801: Generate a first recommended guidance result according to the network detection result, the user's web browsing information and a pre-created network monitoring guidance strategy;

[0238] S802: Generate a second recommendation guidance result according to the network detection result, the user's web browsing information and a pre-created pop-up guidance prediction model;

[0239] S803: Obtain the user's preference settings, calculate the relevance of the first recommended guidance result and the second recommended guidance result to the preference settings respectively, and use the recommended guidance result with the highest relevance as the final recommended guidance result.

[0240] Among them, the above first recommended guidance results can refer to Figure 6 and Figure 7 For the corresponding embodiment, the second recommendation guide result can refer to Figure 5 The corresponding embodiments are not described in detail.

[0241] In S803, user preferences can be obtained in a variety of ways, such as providing options to users when the system is first run, user registration, or user settings interface, and collecting user preferences through questionnaires, multiple-choice questions, or sliders. Preferences may include, but are not limited to: content type (such as news, entertainment, technology, sports, etc.), language preference, price range (for e-commerce recommendations), brand preference, and update frequency (such as daily, weekly, etc.). Preferences are stored in the user profile database and associated with the user's unique identifier (such as user ID) so that they can be retrieved and used later.

[0242] In specific implementation, a correlation calculation technique (such as cosine similarity, Jaccard similarity coefficient or Euclidean distance) can be used to calculate the correlation between each first recommendation guidance result and the user preference setting, and the correlation between each second recommendation guidance result and the user preference setting. For example, for each recommended content, extract features (such as categories, keywords) and compare them with user preferences, and save the calculation results in the form of scores, where the higher the score, the more relevant it is.

[0243] After the correlation between the first recommendation guidance result and the user's preference setting and the correlation between the second recommendation guidance result and the user's preference setting, the correlation scores can be integrated, the correlation scores of the first recommendation guidance result and the second recommendation guidance result can be sorted, and the scores of the corresponding recommendation results can be compared. A weighted average method can be used to set weights for different recommendation sources (for example, the first recommendation result has a higher weight) so as to emphasize more reliable recommendation sources. When determining the recommendation guidance results with high correlation, a threshold can be set to filter out the recommended content with a correlation exceeding a certain threshold as the final recommendation guidance result. The final recommendation result not only needs to meet the user's preference settings, but also match the user's interests. The final recommendation guidance results that are filtered out are displayed to the user. At this time, the system can tell the user the matching of the detected user preferences and the recommended content to enhance the user experience, while improving the transparency of the system and user trust.

[0244] Fig. 9 This is a UI pop-up window guide schematic diagram of an embodiment of this specification; Fig.10 This is a schematic diagram of the weak network guidance of the embodiment of this specification; the network guidance and pop-up guidance may include the following: classification of network timeout, disconnection, weak network, DNS, link, domain name resolution, etc.; design of corresponding error codes and pop-up guidance prompts; network abnormality page prompts; guiding users to set up by themselves or check related network detection; managing background resource positions to add application configuration support, etc., the present invention is not limited to this.

[0245] As can be seen from the above, based on the error pop-up page guidance method provided in the embodiment of this specification, when the user uses the network, the user's current network status can be detected in real time, and the network detection result can be generated according to the pre-set network detection rules; if the network detection result is a network anomaly, the current user tag, the current user behavior habits and the current user behavior trajectory are obtained; based on the network detection result, the user's web browsing information and the pre-created network monitoring guidance strategy and / or pop-up guidance prediction model, a recommended guidance result is generated; according to the recommended guidance result, guidance information is output to prompt the user to perform corresponding operations based on the guidance information. In this way, the function entrances of different users can be aggregated and analyzed and pop-up guidance can be performed, so as to realize effective scheduling of pop-up guidance for weak networks.

[0246] This specification embodiment provides an electronic device, referring to Fig.11 The electronic device includes a network communication port 1101, a processor 1102 and a memory 1103, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0247] The network communication port 1101 may be specifically used to receive the user's current web browsing information, wherein the current user's web browsing information includes: the current user's tag, the current user's behavior habits, and the current user's behavior track.

[0248] The processor 1102 can be specifically used to generate a network detection result according to a pre-set network detection rule; if the network detection result is a network anomaly, obtain the user's current web browsing information; generate a recommended guidance result according to the network detection result, the user's web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up guidance prediction model; wherein the network monitoring guidance strategy is implemented based on an aggregate analysis of historical user web browsing information, and the pop-up guidance prediction model is implemented using a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weights of the hidden layer output to the output layer; output guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0249] The memory 1103 may be specifically used to store corresponding instruction programs, target processing rules and other related data.

[0250] Based on the above method, the relevant structural performance of the server can be effectively utilized, the data processing speed of the electronic equipment can be improved, and the data processing of the market management bill can be efficiently realized.

[0251] In this embodiment, the network communication port 1101 can be a virtual port that is bound to different communication protocols so that different data can be sent or received. 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. In addition, 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, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0252] In this embodiment, the processor 1102 may be implemented in any appropriate manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not limit this.

[0253] In this embodiment, the memory 1103 may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function that has 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.

[0254] The embodiments of the present specification also provide a computer-readable storage medium for an error pop-up page guidance method, wherein the computer-readable storage medium stores computer program instructions, which, when executed, achieve: generating a network detection result according to a pre-set network detection rule; if the network detection result is a network anomaly, obtaining the user's current web browsing information; generating a recommended guidance result according to the network detection result, the user's web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up guidance prediction model; wherein the network monitoring guidance strategy is implemented by performing aggregate analysis based on historical user web browsing information, and the pop-up guidance prediction model is implemented by utilizing a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weights of the hidden layer output to the output layer; outputting guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0255] In this embodiment, the storage medium includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD), or a memory card. The memory may be used to store computer program instructions. The network communication unit may be an interface for network connection communication set in accordance with the standard specified by the communication protocol.

[0256] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be described in detail here.

[0257] The embodiments of the present specification also provide a computer program product, which at least includes a computer program, and when the computer program is executed by a processor, it implements the following method steps: generating a network detection result according to a pre-set network detection rule; if the network detection result is a network anomaly, obtaining the user's current web browsing information; generating a recommended guidance result according to the network detection result, the user's web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up guidance prediction model; wherein the network monitoring guidance strategy is implemented based on an aggregate analysis of historical user web browsing information, and the pop-up guidance prediction model is implemented based on a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weights of the hidden layer output to the output layer; outputting guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0258] See also Fig.12 As shown, the embodiment of this specification also provides an error pop-up page guidance device based on weak network detection, and the device may specifically include the following structural units:

[0259] The detection result generating unit 1201 is used to detect the current network status of the user in real time and generate a network detection result according to a preset network detection rule; the network detection result includes: 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 the DNS / domain name resolution is normally accessed;

[0260] The information acquisition unit 1202 detects the current network status of the user in real time, and is used to generate a network detection result according to a preset network detection rule; the network detection result includes: 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 the DNS / domain name resolution is normally accessed;

[0261] The guidance result generating unit 1203 is used to generate a recommended guidance result according to the network detection result, the user web browsing information and the pre-created network monitoring guidance strategy and / or the pop-up window guidance prediction model; wherein the network monitoring guidance strategy is implemented by aggregate analysis based on the historical user web browsing information, and the pop-up window guidance prediction model is implemented by using the training set and the test set obtained based on the historical user web browsing information, based on the random initialization of the hidden layer parameters and the solution of the weight of the hidden layer output to the output layer;

[0262] The information output unit 1204 is used to output guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

[0263] In one embodiment, the detection result generating unit includes: a state detection module, a policy acquisition module, a rule query module parameter acquisition module and a detection matching module.

[0264] The status detection module is used to detect the network status of the current network according to the preset network status strategy;

[0265] The policy acquisition module is used to acquire the network detection policy, and the network detection policy is dynamically injected into the local client through the CCB API;

[0266] The rule query module is used to query the corresponding network detection rule from the network detection strategy according to the network status;

[0267] The parameter acquisition module is used to obtain the network detection parameters of the current network;

[0268] The detection and matching module is used to detect and match the network status with the network detection rule and the network detection parameter to obtain a corresponding network detection result.

[0269] In one embodiment, the detection and matching module includes: a state matching submodule, a comparison submodule and an error code allocation module.

[0270] The state matching submodule is used to match the network state with the network detection rule and the network detection parameter;

[0271] The comparison submodule is used to compare the matched network detection rule with the network detection parameter, and obtain the corresponding network detection result according to the comparison result;

[0272] The error code allocation module is used to obtain the error code pre-allocated by the network detection result.

[0273] In one embodiment, the error pop-up page guidance device further includes: a model creation unit, and the model creation unit includes: a historical information acquisition module, a preprocessing module and a model generation module.

[0274] The historical information acquisition module is used to acquire historical user web browsing information, and the historical user web browsing information includes: user tags, historical user behavior habits and historical user behavior tracks;

[0275] The preprocessing module is used to preprocess the historical user web browsing information to obtain a training set and a test set;

[0276] The model generation module is used to perform model training using the training set and the test set, and to 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.

[0277] In one embodiment, the error pop-up page guidance device further includes: a history information acquisition unit, a user preference determination unit and a strategy generation unit.

[0278] The historical information acquisition unit is used to acquire historical user web browsing information, wherein the historical user web browsing information includes: user tags, user historical behavior habits and user historical behavior tracks;

[0279] The user preference determination unit is used to determine the user's preference level based on the collaborative filtering recommendation algorithm according to the user tag, the user's historical behavior habits and the user's historical behavior trajectory;

[0280] The policy generating unit is used to generate the network monitoring guidance policy according to the determined preference degree.

[0281] In one embodiment, the error pop-up page guiding device further includes: a history information acquisition unit, a label generation unit and a label generation unit.

[0282] The historical information acquisition unit is used to acquire historical user web browsing information, wherein the historical user web browsing information includes: user tags, user historical behavior habits and user historical behavior tracks;

[0283] The tag generation unit is used to obtain the user's interest tag based on the content recommendation algorithm and the feature description event of the user's business product;

[0284] The policy determination unit is used to obtain the network monitoring guidance policy preferred by the user according to the interest tag.

[0285] In one embodiment, the guidance result generating unit 1203 is specifically configured to match a corresponding network monitoring guidance strategy according to the network detection result and the user web browsing information as a recommended guidance result.

[0286] In one embodiment, the guidance result generating unit 1203 includes: a first result generating module, a second result generating module and a guidance result generating module.

[0287] The first result generating module is used to generate a first recommendation guidance result according to the network detection result, the user web browsing information and the pre-created network monitoring guidance strategy;

[0288] The second result generating module is used to generate a second recommendation guidance result according to the network detection result, the user web browsing information and a pre-created pop-up guidance prediction model;

[0289] The guidance result generation module is used to obtain the user's preference settings, calculate the correlation between the first recommended guidance result and the second recommended guidance result and the preference settings, and use the recommended guidance result with the highest correlation as the final recommended guidance result.

[0290] As can be seen from the above, based on the error pop-up page guidance device provided in the embodiment of this specification, when the user uses the network, the user's current network status can be detected in real time, and the network detection result can be generated according to the pre-set network detection rules; if the network detection result is a network anomaly, the current user tag, the current user behavior habits and the current user behavior trajectory are obtained; the recommended guidance result is generated according to the network detection result, the user's web browsing information and the pre-created network monitoring guidance strategy and / or pop-up guidance prediction model; according to the recommended guidance result, the guidance information is output to prompt the user to perform the corresponding operation based on the guidance information. In this way, the function entrances of different users can be aggregated and analyzed and pop-up guidance can be performed, so as to realize the effective scheduling of the pop-up guidance of weak networks.

[0291] 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 in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0292] The present application 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 application. 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.

[0293] 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.

[0294] 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 1 A step that specifies a function in one or more boxes.

[0295] In the description of this specification, the description with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0296] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for guiding an error pop-up page based on weak network detection, characterized in that: include: Detect the user's current network status in real time and generate network detection results based on 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 WIFI segment, and whether the DNS / domain name resolution is normally accessed; If the network detection result is that the network is abnormal, obtain the user's current web browsing information, the current user's web browsing information includes: current user tags, current user behavior habits and current user behavior track; Generate a recommendation guidance result according to the network detection result, the user web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up window guidance prediction model; wherein the network monitoring guidance strategy is implemented based on aggregate analysis of historical user web browsing information, and the pop-up window guidance prediction model is implemented by using a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weight of hidden layer output to output layer; Output guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

2. The error pop-up window page guidance method according to claim 1, characterized in that: The real-time detection of the user's current network status and generation of a network detection result according to a preset network detection rule include: Detect the network status of the current network according to the preset network status strategy; Obtain a network detection policy, where the network detection policy is dynamically injected into the local client via the CCB API; Querying a corresponding network detection rule from the network detection strategy according to the network status; Get the network detection parameters of the current network; The network detection rule and the network detection parameter are used to detect and match the network status to obtain a corresponding network detection result.

3. The error pop-up page guidance method according to claim 2, characterized in that: The detecting and matching the network status with the network detection rule and the network detection parameter to obtain a corresponding network detection result includes: Matching the network status with the network detection rule and the network detection parameter; Compare the matched network detection rule with the network detection parameter, and obtain the corresponding network detection result according to the comparison result; Obtain an error code pre-assigned to the network detection result.

4. The error pop-up page guidance method according to claim 1, characterized in that: The steps of the pre-created pop-up guidance prediction model include: Obtaining historical user web browsing information, the historical user web browsing information including: user tags, historical user behavior habits and historical user behavior tracks; Preprocessing the historical user web browsing information to obtain a training set and a test set; The training set and the test set are used to perform model training, and a pop-up guidance prediction model is generated based on the random initialization of hidden layer parameters and the solution of the weights from the hidden layer output to the output layer.

5. The error pop-up page guidance method according to claim 1, characterized in that: The steps of pre-creating the network monitoring guidance strategy include: Obtaining historical user web browsing information, the historical user web browsing information including: user tags, user historical behavior habits and user historical behavior tracks; Based on collaborative filtering recommendation algorithm, the user's preference is determined according to user tags, user historical behavior habits and user historical behavior trajectory; The network monitoring guidance strategy is generated according to the determined preference level.

6. The error pop-up page guidance method according to claim 1, characterized in that: The steps of pre-creating the network monitoring guidance strategy include: Obtain historical user web browsing information, the historical user web browsing information including: user tags, user historical behavior habits and user historical behavior tracks; Based on the content recommendation algorithm, the user's interest tags are obtained according to the user tags, user historical behavior habits and user historical behavior trajectories; The network monitoring guidance strategy preferred by the user is obtained according to the interest tag.

7. The error pop-up page guidance method according to claim 5 or 6, characterized in that: Generate a recommendation guidance result according to the network detection result, the user web browsing information and a pre-created network monitoring guidance strategy, including: A corresponding network monitoring guidance strategy is matched according to the network detection result and the user's web browsing information as a recommendation guidance result.

8. The error pop-up page guidance method according to claim 1, characterized in that: The generating of the recommendation guidance result according to the network detection result, the user web browsing information and the pre-created network monitoring guidance strategy and / or the pop-up guidance prediction model includes: Generate a first recommended guidance result according to the network detection result, the user's web browsing information and a pre-created network monitoring guidance strategy; Generate a second recommendation guidance result according to the network detection result, the user's web browsing information and a pre-created pop-up guidance prediction model; The user's preference settings are obtained, and the correlation between the first recommended guidance result and the second recommended guidance result and the preference settings is calculated respectively, and the recommended guidance result with the highest correlation is used as the final recommended guidance result.

9. A device for guiding an error pop-up page based on weak network detection, characterized in that: include: A detection result generating unit, used to detect the user's current network status in real time and generate a network detection result according to a preset network detection rule; 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 WIFI segment, and whether the DNS / domain name resolution is normally accessed; The information acquisition unit detects the user's current network status in real time and is used to generate network detection results according to 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 WIFI segment, and whether the DNS / domain name resolution is normally accessed; A guidance result generating unit, used for generating a recommended guidance result according to the network detection result, the user web browsing information and a pre-created network monitoring guidance strategy and / or a pop-up window guidance prediction model; wherein the network monitoring guidance strategy is implemented by aggregate analysis based on historical user web browsing information, and the pop-up window guidance prediction model is implemented by using a training set and a test set obtained based on historical user web browsing information, based on random initialization of hidden layer parameters and solving the weight of hidden layer output to output layer; The information output unit is used to output guidance information according to the recommended guidance result to prompt the user to perform corresponding operations based on the guidance information.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the error pop-up window page guidance method described in any one of claims 1 to 8 are implemented.

11. 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, the steps of the error pop-up page guidance method described in any one of claims 1 to 8 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the error pop-up window page guidance method described in any one of claims 1 to 8 are implemented.

Images