Page monitoring method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a page monitoring method and device, electronic equipment and storage medium, relates to the technical field of data processing, and specifically relates to the field of large models and artificial intelligence. The specific implementation scheme is: receiving sampling data of an application program sent by a client; determining at least one page belonging to the same business function according to function mapping information; performing abnormal function analysis according to the aggregated sampling data of the at least one page, determining an abnormal business function and abnormal information of the abnormal business function; calling a generative large model, and outputting an abnormal repair strategy of the abnormal business function by the generative large model according to the abnormal business function and the abnormal information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, in particular to the field of large models and artificial intelligence, and more particularly to a page monitoring method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, the monitoring of mobile terminals mainly focuses on performance monitoring such as crashes and stalls, and rarely monitors functional abnormalities. It is difficult to comprehensively monitor the page display and function clicks of mobile terminals. The existing code embedding coverage is difficult to achieve full-page and all-click-area coverage, and cannot achieve comprehensive monitoring of abnormalities. SUMMARY

[0003] The present disclosure provides a page monitoring method, device, electronic equipment and storage medium.

[0004] According to an aspect of the present disclosure, a page monitoring method is provided, comprising:

[0005] receiving sampling data of an application program sent by a client, the sampling data comprising aggregated sampling data of a user on a same page and function mapping information corresponding to the same page;

[0006] determining at least one page belonging to a same business function according to the function mapping information;

[0007] performing abnormal function analysis according to the aggregated sampling data of the at least one page to determine an abnormal business function and abnormal information of the abnormal business function;

[0008] calling a generative large model, and outputting an abnormal repair strategy of the abnormal business function by the generative large model according to the abnormal business function and the abnormal information.

[0009] According to a second aspect of the present disclosure, a page monitoring device is provided, comprising:

[0010] a receiving module configured to receive sampling data of an application program sent by a client, the sampling data comprising aggregated sampling data of a user on a same page and function mapping information corresponding to the same page;

[0011] a first obtaining module configured to determine at least one page belonging to a same business function according to the function mapping information;

[0012] a second obtaining module configured to perform abnormal function analysis according to the aggregated sampling data of the at least one page to determine an abnormal business function and abnormal information of the abnormal business function;

[0013] The calling module is configured to call the generative large model, and the generative large model is configured to output an exception repair strategy of the abnormal business function according to the abnormal business function and the abnormal information.

[0014] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect or the second aspect embodiment.

[0015] According to a fourth aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the method of the first aspect or the second aspect embodiment.

[0016] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the first aspect or the second aspect embodiment.

[0017] It should be understood that the contents described in this part are not intended to identify the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0019] Figure 1 is a flowchart of a page monitoring method provided by an embodiment of the present disclosure;

[0020] Figure 2 is a flowchart of another page monitoring method provided by an embodiment of the present disclosure;

[0021] Figure 3 is a flowchart of another page monitoring method provided by an embodiment of the present disclosure;

[0022] Figure 4 is a flowchart of another page monitoring method provided by an embodiment of the present disclosure;

[0023] Figure 5 is a flowchart of another page monitoring method provided by an embodiment of the present disclosure;

[0024] Figure 6 is a logic diagram of a page monitoring method provided by an embodiment of the present disclosure;

[0025] Figure 7 is a structural block diagram of a page monitoring device provided by an embodiment of the present disclosure.

[0026] Figure 8 is a structural block diagram of another page monitoring device provided by an embodiment of the present disclosure.

[0027] Figure 9 shows a schematic block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, which should be considered in their context only. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0029] Data processing is the collection, storage, retrieval, processing, transformation and transmission of data, and the basic purpose is to extract and deduce data that is valuable and meaningful to some specific people from a large amount of data that is possibly disorganized and difficult to understand.

[0030] Large model refers to a machine learning model with a large number of parameters and complex structure, which is pre-trained through massive data and has strong expression and generalization capabilities, and can process massive data and complete various complex tasks.

[0031] Artificial intelligence (AI) is a technology science that studies, develops, simulates, extends and expands human intelligence, and aims to understand the essence of intelligence and produce an intelligent machine that can react in a similar way to human intelligence.

[0032] Figure 1 is a flowchart of a page monitoring method provided by an embodiment of the present disclosure. As Figure 1 shown, the method comprises:

[0033] S101, receiving sampling data of an application program sent by a client.

[0034] Optionally, the client can be a software or a web browser program, and the application program is installed on the client, and the sampling data includes aggregated sampling data of a user on the same page and function mapping information corresponding to the same page.

[0035] In some implementations, the aggregated sampling data of the user on the same page refers to aggregation of the sampling data of one or more users on the page, where the sampling data of the user on the page can be the number of click or page display operation behaviors of the user on the page.

[0036] In some implementations, the function mapping information corresponding to the same page refers to function information of the current page, and the corresponding function mapping information is determined based on the function corresponding to the page.

[0037] S102, determining at least one page belonging to the same business function according to the function mapping information.

[0038] Optionally, the business function can include different functions such as search, view, marketing, and display; the function corresponding to each page is determined according to the function mapping information of the page, and at least one page belonging to the same business function is determined according to the function corresponding to each page, that is, all pages are classified according to the corresponding business function, and pages of the same business function are divided together.

[0039] S103, performing abnormal function analysis according to the aggregated sampling data of the at least one page to determine an abnormal business function and abnormal information of the abnormal business function.

[0040] In some implementations, feature values can be extracted according to the aggregated sampling data of the at least one page, and the feature values are compared with an abnormal threshold to determine whether the current page is abnormal; for example, the variance of the aggregated sampling data is obtained, and the variance is compared with an abnormal variance threshold to determine that the page is abnormal when the variance is greater than the abnormal variance threshold.

[0041] Further, the business function of the abnormal page is determined as the abnormal business function, and the abnormal information of the abnormal business is determined as the abnormal information of the abnormal business function, and the abnormal information can include the abnormal degree of the comparison between the aggregated sampling data and the abnormal threshold and the abnormal time information.

[0042] S104, calling a generative large model, and outputting an abnormal repair strategy of the abnormal business function by the generative large model according to the abnormal business function and the abnormal information.

[0043] It can be understood that the generative large model refers to a generative model based on a large-scale corpus, which can be trained and generated in an end-to-end manner and can provide problem solving and service support according to input content; in the embodiment, the generative large model can be trained based on the abnormal business function, the abnormal information, and the corresponding abnormal repair strategy, so as to obtain the trained generative large model.

[0044] Further, a pre-trained generative large model is called, and the generative large model outputs an exception repair strategy of the abnormal business function according to the abnormal business function and the exception information, a more perfect exception repair strategy is obtained through the rich expression capability of the generative large model, and the acquisition efficiency of the exception repair strategy is improved.

[0045] In the embodiment, the sampling data of the application program sent by the client is received, and at least one page corresponding to each business function is determined according to the function mapping information in the sampling data; the abnormal function analysis is performed according to the aggregated sampling data of the at least one page, the abnormal business function and the exception information of the abnormal business function are determined, the generative large model is called to acquire the exception repair strategy of the abnormal business function, a more perfect exception repair strategy is obtained through the rich expression capability of the generative large model, an effective solution is provided for the user interaction exception, and the user experience is improved.

[0046] Figure 2 is a flowchart of another page monitoring method provided by the embodiment of the disclosure. As shown in Figure 2 , the method comprises:

[0047] S201, receiving sampling data of an application program sent by a client.

[0048] In the embodiment of the disclosure, the implementation method of step S201 can be realized by any one of the embodiments of the disclosure, which is not limited here and will not be repeated.

[0049] S202, determining at least one page belonging to the same business function according to the function mapping information.

[0050] In the embodiment of the disclosure, the implementation method of step S202 can be realized by any one of the embodiments of the disclosure, which is not limited here and will not be repeated.

[0051] S203, performing statistics on the aggregated sampling data of different users of the page to obtain a second statistical parameter set of the page.

[0052] Optionally, the aggregated sampling data can be the number of page clicks or the number of page displays; the second statistical parameter set of the page can include at least one of the standard deviation, variance, mean and minimum value corresponding to the page, that is, at least one of the standard deviation, variance, mean and minimum value of all aggregated sampling data of the page in a preset time period is obtained.

[0053] In some implementations, the preset time period can be 1 day, that is, the sum, variance or standard deviation of the aggregated sampling data of the page in 1 day is obtained as the second statistical parameter set.

[0054] S204, determining whether there is an abnormal page in the page associated with the service function according to the second statistical parameter and the first statistical parameter set.

[0055] Optionally, sampling information of the sampling data can be determined, and the historical sampling data can be determined according to the sampling information of the sampling data. The sampling information can be sampling position or sampling frequency information, and the historical sampling data is determined based on the same sampling information. The historical sampling data can be sampling data of the page of the previous day and the continuous days before the previous day.

[0056] Further, the historical aggregated sampling data of the page associated with each service function is determined according to the historical sampling data, that is, the historical aggregated sampling data is obtained by aggregating the historical sampling data of all users of the page corresponding to each service function. The first statistical parameter set for abnormal evaluation of the service function is determined by statistically analyzing the historical aggregated sampling data of the page associated with the service function. The first statistical parameter set can include at least one of the standard deviation, the variance, the mean value and the minimum value corresponding to the page. The first statistical parameter set calculated based on the historical sampling data is used as a reference parameter to more accurately determine the data fluctuation and ensure the accuracy of the abnormal identification.

[0057] In some implementations, for each page, the abnormal determination condition of each type of statistical parameter can be obtained. For example, when the statistical parameter is the mean value, the standard deviation or the variance, the abnormal determination condition can be to determine whether the second statistical parameter of the page of the day exceeds a certain multiple of the first statistical parameter. The multiple is a set value, for example, 2. The mean value, the standard deviation or the variance of the page of the day satisfies the abnormal determination condition if it exceeds 2 times the mean value, the standard deviation or the variance of the historical aggregated sampling data. When the statistical parameter is the minimum value, the abnormal determination condition can be to determine whether the deviation between the minimum value of the second statistical parameter set and the minimum value of the first statistical parameter set is greater than a threshold value. For example, the threshold value is 10. The minimum value of the second statistical parameter set satisfies the abnormal determination condition if the deviation between the minimum value of the second statistical parameter set and the minimum value of the first statistical parameter set is greater than 10.

[0058] In response to at least one type of statistical parameter in the first statistical parameter set satisfying the corresponding abnormal determination condition, the page is determined to be an abnormal page. That is, any one of the mean value, the standard deviation, the variance or the minimum value satisfies the abnormal determination condition, and the page is an abnormal page with large click or display fluctuation, thereby improving the accuracy of the abnormal analysis.

[0059] S205, in response to the existence of the abnormal page, determining that the service function is an abnormal service function, and determining the abnormal information of the abnormal service function according to the abnormal information of the abnormal page.

[0060] In some implementations, the abnormal alarm information of the application program can be generated according to the abnormal business function and the corresponding abnormal information, the abnormal alarm information at least including the abnormal business function and the abnormal information, and the abnormal alarm information can be sent to the corresponding user equipment through an email to remind the user to process the abnormal situation in time.

[0061] In the embodiment of the present disclosure, the implementation method of step S205 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0062] S206, calling a generative large model, and outputting an abnormal repair strategy of the abnormal business function from the generative large model according to the abnormal business function and the abnormal information.

[0063] In the embodiment of the present disclosure, the implementation method of step S206 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0064] In the embodiment, the sampling data of the application program sent by the client is received, and at least one page belonging to the same business function is determined according to the function mapping information of the sampling data. The aggregated sampling data of different users of the page is counted to obtain a second statistical parameter set of the page. The second statistical parameter set is used as a feature parameter of the aggregated sampling data of the user for abnormal analysis. The first statistical parameter set is obtained through the historical aggregated sampling data. The first statistical parameter set is used as a reference feature parameter. The comparison between the current feature parameter and the reference feature parameter is analyzed to determine whether the abnormal determination condition is met, thereby improving the accuracy of the abnormal analysis. The abnormal page is determined based on whether the abnormal determination condition is met, and the abnormal business function and the abnormal information of the abnormal business function are determined according to the business function of the abnormal page, thereby providing an accurate basis for generating the abnormal repair strategy and ensuring the stability and accuracy of the subsequent abnormal repair strategy generation.

[0065] Figure 3 is a flowchart of another page monitoring method provided by the embodiment of the present disclosure. As shown in Figure 3 , the method comprises:

[0066] S301, receiving sampling data of an application program sent by a client.

[0067] In the embodiment of the present disclosure, the implementation method of step S301 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0068] S302, determining at least one page belonging to the same business function according to the function mapping information.

[0069] In the embodiments of the present disclosure, the implementation method of step S302 can be implemented by any one of the embodiments of the present disclosure, and the present disclosure does not limit this and will not be repeated here.

[0070] S303, counting the aggregated sampling data of different users of the page to obtain a second statistical parameter set of the page.

[0071] In the embodiments of the present disclosure, the implementation method of step S303 can be implemented by any one of the embodiments of the present disclosure, and the present disclosure does not limit this and will not be repeated here.

[0072] S304, determining whether there is an abnormal page in the page associated with the business function according to the second statistical parameter and the first statistical parameter set.

[0073] In the embodiments of the present disclosure, the implementation method of step S304 can be implemented by any one of the embodiments of the present disclosure, and the present disclosure does not limit this and will not be repeated here.

[0074] S305, in response to the existence of the abnormal page, determining that the business function is an abnormal business function, and determining the abnormal information of the abnormal business function according to the abnormal information of the abnormal page.

[0075] In the embodiments of the present disclosure, the implementation method of step S305 can be implemented by any one of the embodiments of the present disclosure, and the present disclosure does not limit this and will not be repeated here.

[0076] S306, calling a generative large model to obtain a repair prompt prompt.

[0077] Optionally, the repair prompt prompt can include an abnormal business function and abnormal information of the abnormal business function, for example, the repair prompt is that the search result point number decreases, and a repair idea is given; wherein the abnormal business function is a search function, and the abnormal information is a decrease in the number of search results.

[0078] S307, inputting the repair prompt, the abnormal business function and the abnormal information into the large model.

[0079] It can be understood that the abnormal business function and the abnormal information include more detailed and specific abnormal conditions, so that the large model can output more accurate abnormal repair strategies based on more detailed and specific abnormal information.

[0080] S308, generating an abnormal repair strategy by the large model according to the abnormal business function and the abnormal information, in combination with a pre-configured output reference example.

[0081] In some implementations, the pre-configured output reference example refers to a reasonable abnormality repair strategy output template, that is, a more comprehensive and detailed abnormality repair strategy output based on the output reference example as a reference template.

[0082] In some implementations, after determining the abnormality repair strategy, the abnormal page in the abnormal business function can be determined; the abnormal page abnormality repair information is extracted from the abnormality repair strategy; and the page repair task of the abnormal page is generated according to the abnormal page and the corresponding abnormality repair information; that is, the abnormality repair information related to the abnormal page is determined from the abnormality repair strategy, and the page repair task is generated according to the abnormal page and the corresponding abnormality repair information, which is used to repair the abnormal page based on the abnormality repair information.

[0083] Further, the page repair task is sent to the first associated object corresponding to the abnormal page; the first associated object can be a developer corresponding to the abnormal page, and the page repair task is sent to the first associated object, which executes the page repair task to complete the repair of the abnormal page, ensures the repair effect of the abnormal page, and improves the abnormality repair efficiency.

[0084] In some implementations, the repair task set of the abnormal business function can also be generated according to the abnormality repair strategy; that is, the repair task of each abnormal page corresponding to the abnormal business function is generated based on the abnormality repair strategy, and the repair task set is composed of the repair tasks of all abnormal pages corresponding to the abnormal business function.

[0085] The repair task set is sent to the second associated object corresponding to the abnormal business function, and the tasks in the repair task set are distributed to the first associated object corresponding to the abnormal page through the second associated object; wherein the second associated object can be a manager corresponding to the abnormal business function, and the manager distributes the repair tasks of the abnormal pages of the abnormal business function to the corresponding first associated object, that is, the corresponding developer performs the execution of the repair task to repair the abnormal page, uniformly allocates the abnormal task, more clearly controls the page repair task, and improves the abnormality repair efficiency.

[0086] In this embodiment, the sampling data of the application program sent by the client is received, and at least one page belonging to the same business function is determined according to the function mapping information of the sampling data. The aggregated sampling data and the historical aggregated sampling data of different users of the page are respectively counted to obtain corresponding characteristic parameters. Whether the abnormal judgment condition is met is determined through comparison and analysis between the current characteristic parameters and the reference characteristic parameters, thereby improving the accuracy of the abnormal analysis. After determining the existence of the abnormal page, the repair prompt is obtained, and the abnormal business function, the abnormal information and the repair prompt are input into the large model to generate the abnormal repair strategy, thereby improving the accuracy and efficiency of the generation of the abnormal repair strategy. Based on the abnormal repair strategy, the corresponding page repair task or the repair task set of the abnormal business function is generated and sent to the corresponding associated object for execution of the repair task, so as to realize the repair of the abnormal page and ensure the repair effect of the abnormal page while improving the abnormal repair efficiency.

[0087] Figure 4 is a flowchart of another page monitoring method provided by the embodiments of the present disclosure. As shown in Figure 4 , the method comprises:

[0088] S401, globally monitoring the pages of the application program.

[0089] Optionally, the pages of the application program can be fully instrumented to realize global monitoring. Full instrumentation refers to adding data tracking code in each page and interaction of the application program to collect the behavior and usage of the user and obtain detailed data.

[0090] S402, aggregating the operations of the user on the same page in a set time unit to obtain the aggregated sampling data of the user on the same page.

[0091] In some implementations, the set time unit can be 1 day or multiple days. If the set time unit is 1 day, the operations of the user on the same page in 1 day are aggregated to obtain the aggregated sampling data of the user on the same page. The user operations can include page clicking and page displaying.

[0092] S403, obtaining the function mapping information corresponding to the same page.

[0093] Optionally, the page identifier or the page code can be obtained, and the function mapping information corresponding to the page is determined according to the mapping relationship between the page identifier or the page code and the function. The function can include marketing, display or search functions. The function mapping information of the page at least includes the function corresponding to the page.

[0094] In some implementations, the importance and urgency of the exception identification can also be determined according to the function mapping information. For example, in a function page related to advertising marketing or a cash register, the page exception will directly affect the business transaction, and therefore the corresponding exception identification has higher urgency and needs to be processed urgently.

[0095] S404, generating the sampling data of the application program according to the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page.

[0096] It can be understood that the sampling data of the application program includes the aggregated sampling data and the function mapping information, so that the page exception can be analyzed based on more comprehensive sampling data, and the reliability of the exception identification is improved.

[0097] S405, sending the sampling data of the application program to the server.

[0098] In the embodiment, the pages of the application program are comprehensively monitored in the full-buried point manner, so that more comprehensive aggregated sampling data is obtained, the function mapping information of the page is further acquired, the function mapping information and the aggregated sampling data are combined to form the sampling data of the application program, and the sampling data is sent to the server, so that the server can analyze the page exception based on more comprehensive sampling data, and the reliability of the exception identification analysis is improved.

[0099] Figure 5 is a flowchart of another page monitoring method provided by the embodiment of the disclosure. As shown in Figure 5 , the method includes:

[0100] S501, globally monitoring the pages of the application program.

[0101] In the embodiment of the disclosure, the implementation method of step S501 can be implemented in any one of the embodiments of the disclosure, and here it is not limited, and will not be repeated.

[0102] S502, aggregating the operations of the user on the same page in a set time unit to obtain the aggregated sampling data of the user on the same page.

[0103] In the embodiment of the disclosure, the implementation method of step S502 can be implemented in any one of the embodiments of the disclosure, and here it is not limited, and will not be repeated.

[0104] S503, determining the code class of the same page, and determining the target business component to which the code class belongs.

[0105] In some implementations, the code class of a page can reflect basic attribute information of the page, and the target business component to which it belongs is determined based on the code information in the code class. The business component is a component corresponding to different business functions.

[0106] S504: Generate function mapping information corresponding to the same page according to the code class and the target business component.

[0107] Optionally, you can perform a function query based on the code class and the target business component, for example, by querying the function mapping information corresponding to the code class and the target business component from a mapping file. The mapping file can be a file that automatically maps the class and function generated by placing the code class into its corresponding target business component and performing binary packaging.

[0108] S505 : Generate sampling data of the application program according to the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page.

[0109] In the embodiment of the present disclosure, the implementation method of step S505 can be implemented by using any of the methods in the embodiments of the present disclosure, which is not limited here and will not be described in detail.

[0110] S506: Send the sampled data of the application to the server.

[0111] Optionally, the aggregated sampling data of some users can be sampled from the aggregated sampling data corresponding to the same page as the target aggregated sampling data; in some implementations, the aggregated sampling data of some users can be randomly sampled or the aggregated sampling data of some users can be sampled according to pre-configured rules as the target sampling data.

[0112] Based on the target aggregated sampling data and the function mapping information corresponding to the same page, the sampling data of the application is generated and sent to the server, avoiding the sampling data occupying a large amount of memory and increasing the storage burden, thereby reducing the storage cost of the server.

[0113] In this embodiment, the application pages are fully monitored by a full-point embedding method, thereby obtaining more comprehensive aggregated sampling data, and the accurate functional mapping information of the page is determined according to the code class and the target business component to which the code class belongs. The functional mapping information reflects the urgency of abnormality identification and improves the recognition effect of abnormality identification. The aggregated sampling data of some users can also be randomly sampled from the aggregated sampling data as the target aggregated sampling data, and the sampling data of the application is generated by the target aggregated sampling data and the functional mapping information for sending, so as to avoid the sampling data occupying a large amount of memory and increasing the storage burden, thereby reducing the storage cost of the server.

[0114] Based on the above embodiments, Figure 6is a logic schematic diagram of a page monitoring method provided by an embodiment of the disclosure. As shown in Figure 6 The client collects the page display and click operation of the user to obtain the aggregated sampling data of the user, randomly samples the user to obtain target aggregated sampling data, generates sampling data in combination with the function mapping information and sends the sampling data to the server, the server stores the sampling data and performs abnormal analysis, analyzes whether the statistical parameter set (minimum value, mean value, variance or standard deviation) meets the abnormal judgment condition through calculation, thereby determining whether there is an abnormal page, and obtaining the abnormal business function and abnormal information corresponding to the abnormal page, calling the generative large model based on the abnormal business function and the abnormal information, outputting the abnormal repair strategy and the abnormal alarm, providing an effective solution for user interaction abnormality and improving user experience.

[0115] Figure 7 is a structural block diagram of a page monitoring device provided by an embodiment of the disclosure. As shown in Figure 7 The page monitoring device 700 includes:

[0116] The receiving module 701 is configured to receive the sampling data of the application program sent by the client, and the sampling data includes the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page.

[0117] The first obtaining module 702 is configured to determine at least one page belonging to the same business function according to the function mapping information.

[0118] The second obtaining module 703 is configured to perform abnormal function analysis according to the aggregated sampling data of the at least one page to determine the abnormal business function and the abnormal information of the abnormal business function.

[0119] The calling module 704 is configured to call the generative large model, and the generative large model outputs the abnormal repair strategy of the abnormal business function according to the abnormal business function and the abnormal information.

[0120] In some implementations, the calling module 704 includes:

[0121] Obtain the repair prompt word prompt;

[0122] Input the repair prompt, the abnormal business function and the abnormal information into the large model;

[0123] The large model generates the abnormal repair strategy according to the abnormal business function and the abnormal information in combination with the pre-configured output reference example.

[0124] In some implementations, the calling module 704 further includes:

[0125] Determine the abnormal page in the abnormal business function;

[0126] extracting the abnormal page exception repair information from the exception repair strategy;

[0127] generating a page repair task of the abnormal page according to the abnormal page and the corresponding abnormal page exception repair information, and sending the page repair task to the first associated object corresponding to the abnormal page.

[0128] In some implementations, the calling device 704 further includes:

[0129] According to the exception repair strategy, a repair task set of the abnormal service function is generated; the repair task set is sent to the second associated object corresponding to the abnormal service function, and the tasks in the repair task set are distributed to the first associated object corresponding to the abnormal page through the second associated object.

[0130] In some implementations, the second acquisition module 703 further includes:

[0131] determining the sampling information of the sampling data, and determining the historical sampling data according to the sampling information of the sampling data;

[0132] According to the historical sampling data, the historical aggregated sampling data of the page associated with each service function is determined;

[0133] statistical analysis is performed on the historical aggregated sampling data of the page associated with the service function to determine a first statistical parameter set of the service function for exception evaluation.

[0134] In some implementations, the second acquisition module 703 includes:

[0135] statistical analysis is performed on the historical aggregated sampling data of the page associated with the service function to determine a first statistical parameter set of the service function for exception evaluation.

[0136] According to the second statistical parameter and the first statistical parameter set, it is determined whether there is an abnormal page in the page associated with the service function;

[0137] In response to the existence of the abnormal page, the service function is determined as an abnormal service function, and the abnormal information of the abnormal service function is determined according to the abnormal information of the abnormal page.

[0138] In some implementations, after determining the abnormal service function and the abnormal information of the abnormal service function, the device 700 further includes:

[0139] According to the abnormal service function and the corresponding abnormal information, an exception alarm information of the application program is generated.

[0140] In some implementations, the statistical parameter set includes at least one of the standard deviation, variance, mean and minimum value corresponding to the page, and the device 700 further includes:

[0141] For each page, obtain the abnormality determination condition of each type of statistical parameter;

[0142] In response to at least one type of statistical parameter in the first set of statistical parameters satisfying the corresponding abnormality determination condition, determine that the page is an abnormal page.

[0143] In this embodiment, the sampling data of the application program sent by the client is received, and at least one page corresponding to each business function is determined according to the function mapping information in the sampling data; abnormal function analysis is performed according to the aggregated sampling data of the at least one page, the abnormal business function and the abnormal information of the abnormal business function are determined, the generative large model is called to obtain the abnormal repair strategy of the abnormal business function, and the more perfect abnormal repair strategy is obtained through the rich expression ability of the generative large model, so as to provide an effective solution to the user interaction abnormality and improve the user experience.

[0144] Figure 8 is another structural block diagram of a page monitoring device provided by the embodiments of the present disclosure. As shown in Figure 8 The page monitoring device 800 further includes:

[0145] The monitoring module 801 is configured to globally monitor the pages of the application program.

[0146] The third obtaining module 802 is configured to aggregate the operations of the user on the same page within a set time unit to obtain aggregated sampling data of the user on the same page.

[0147] The fourth obtaining module 803 is configured to obtain function mapping information corresponding to the same page.

[0148] The fifth obtaining module 804 is configured to generate sampling data of the application program according to the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page.

[0149] In some implementations, the fourth obtaining module 803 includes:

[0150] Determine the code class of the same page, and determine the target business component to which the code class belongs;

[0151] According to the code class and the target business component, the function mapping information corresponding to the same page is generated.

[0152] In some implementations, the fifth obtaining module 804 includes:

[0153] Sample the aggregated sampling data of part of the users from the aggregated sampling data corresponding to the same page as the target aggregated sampling data;

[0154] According to the target aggregated sampling data and the function mapping information corresponding to the same page, the sampling data of the application program is generated.

[0155] In this embodiment, the pages of the application program are comprehensively monitored by full burying, so that more comprehensive sampling data is obtained, the operations of the user on the same page are aggregated to obtain aggregated sampling data, the function mapping information of the page is further acquired, the function mapping information and the aggregated sampling data are combined to form the sampling data of the application program, and the sampling data is sent to the server, so that the server can analyze the page exception based on more comprehensive sampling data, and the reliability of the exception identification analysis is improved.

[0156] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0157] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0158] Figure 9 A schematic block diagram of an electronic device for implementing embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the present disclosure described and / or claimed in this document.

[0159] As shown in Figure 9 The device 900 includes a computing unit 901 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0160] A plurality of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0161] The computing unit 901 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 901 performs various methods and processes described above, such as the page monitoring method. For example, in some embodiments, the page monitoring method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded to the RAM 903 and executed by the computing unit 901, one or more steps of the page monitoring method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the page monitoring method by other any appropriate means, such as by means of firmware.

[0162] Various implementations of the systems and techniques described above herein can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0163] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package, or entirely on a remote machine or server.

[0164] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0165] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0166] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0167] The computer system can include clients and servers. This relationship can be. The servers are typically remote from the clients with the interactions between them occurring over a communication network. The relationship between a client and a server is one of client-server. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0168] It should be understood that the various forms of flow shown above can be used with reordering, additions, or removals of steps. For example, each of the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, unless otherwise specifically noted, and is not limited to the order recited in this document.

[0169] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Any further modifications, equivalents, alternatives, and / or improvements made to the specific embodiments described above are intended to fall within the scope of the disclosure.

Claims

1. A page monitoring method, wherein: The method comprises: Receive sampled data of an application sent by a client, the sampled data including aggregated sampled data of users on the same page and function mapping information corresponding to the same page, the aggregated sampled data being obtained by aggregating operations of one or more users on the same page, and the function mapping information being generated based on a code class of the same page and a target business component to which the code class belongs; Determining, based on the function mapping information, at least one page belonging to the same business function; Performing statistical analysis on historical aggregated sampling data of pages associated with the business function to determine a first statistical parameter set for anomaly assessment of the business function; Performing statistics on the aggregated sampling data of different users of the page to obtain a second statistical parameter set of the page; determining, based on the second statistical parameter set and the first statistical parameter set, whether there is an abnormal page among the pages associated with the business function; In response to the presence of the abnormal page, determining that the business function is an abnormal business function, and determining abnormal information of the abnormal business function based on abnormal information of the abnormal page; The generative big model is called, and the generative big model outputs an abnormal repair strategy for the abnormal business function according to the abnormal business function and the abnormal information.

2. The method according to claim 1, wherein The generative large model outputs an abnormality repair strategy for the abnormal business function based on the abnormal business function and the abnormal information, including: Get the repair prompt word prompt; Inputting the repair prompt word prompt, the abnormal business function and the abnormal information into the large model; The big model generates the exception repair strategy based on the abnormal business function and the abnormal information in combination with a pre-configured output reference example.

3. The method according to claim 2, wherein: After outputting the abnormality repair strategy for the abnormal business function, the method further includes: Determining an abnormal page in the abnormal business function; Extracting the abnormal page abnormality repair information from the abnormality repair strategy; A page repair task for the abnormal page is generated according to the abnormal page and corresponding abnormal repair information, and the page repair task is sent to a first associated object corresponding to the abnormal page.

4. The method according to claim 2, wherein: After outputting the abnormality repair strategy for the abnormal business function, the method further includes: According to the abnormal repair strategy, a repair task set for the abnormal business function is generated; the repair task set is sent to the second associated object corresponding to the abnormal business function, and the tasks in the repair task set are distributed to the first associated object corresponding to the abnormal page in the abnormal business function through the second associated object.

5. The method according to any one of claims 1 to 4, wherein Before performing statistical analysis on the historical aggregated sampling data of the pages associated with the business function to determine the first statistical parameter set for abnormality assessment of the business function, the method further includes: Determining sampling information of the sampled data, and determining historical sampling data based on the sampling information of the sampled data; According to the historical sampling data, historical aggregated sampling data of pages associated with each business function is determined.

6. The method according to any one of claims 1 to 4, wherein After determining the abnormal business function and abnormal information of the abnormal business function, the method further includes: Generate abnormal alarm information of the application program according to the abnormal business function and the corresponding abnormal information.

7. The method according to any one of claims 1 to 4, wherein The statistical parameter set includes at least one of a standard deviation, a variance, a mean, and a minimum value corresponding to the page, and the method further includes: For each page, obtain the abnormality judgment conditions for each type of statistical parameter; In response to at least one type of statistical parameter in the first statistical parameter set satisfying a corresponding abnormality determination condition, the page is determined to be an abnormal page.

8. The method according to claim 1, wherein The method comprises: Perform global monitoring of application pages; Aggregate the user's operations on the same page within a set time unit to obtain aggregated sampling data of the user on the same page; Obtaining function mapping information corresponding to the same page; The sampling data of the application is generated according to the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page.

9. The method according to claim 8, characterized in that The obtaining of function mapping information corresponding to the same page includes: Determining the code class of the same page, and determining the target business component to which the code class belongs; Function mapping information corresponding to the same page is generated according to the code class and the target business component.

10. The method according to claim 8 or 9, wherein: Generating the sampling data of the application according to the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page includes: Sampling aggregated sampling data of some users from the aggregated sampling data corresponding to the same page as target aggregated sampling data; The sampling data of the application is generated according to the target aggregated sampling data and the function mapping information corresponding to the same page.

11. A page monitoring device, comprising: a receiving module, configured to receive sampled data of an application sent by a client, the sampled data including aggregated sampled data of users on the same page and function mapping information corresponding to the same page, the aggregated sampled data being obtained by aggregating operations of one or more users on the same page, and the function mapping information being generated based on a code class on the same page and a target business component to which the code class belongs; A first acquisition module is configured to determine at least one page belonging to the same business function according to the function mapping information; A second acquisition module is configured to perform statistical analysis on historical aggregated sampling data of the page associated with the business function to determine a first statistical parameter set for abnormality assessment of the business function; and to perform statistics on the aggregated sampling data of different users of the page to obtain a second statistical parameter set for the page; determining, based on the second statistical parameter set and the first statistical parameter set, whether there is an abnormal page among the pages associated with the business function; In response to the presence of the abnormal page, determining that the business function is an abnormal business function, and determining abnormal information of the abnormal business function based on abnormal information of the abnormal page; The calling module is used to call the generative big model, and the generative big model outputs the abnormal repair strategy of the abnormal business function according to the abnormal business function and the abnormal information.

12. The device according to claim 11, wherein The calling module includes: Get the repair prompt word prompt; Inputting the repair prompt word prompt, the abnormal business function and the abnormal information into the large model; The big model generates the exception repair strategy based on the abnormal business function and the abnormal information in combination with a pre-configured output reference example.

13. The device according to claim 12, wherein The calling module further includes: Determining an abnormal page in the abnormal business function; Extracting the abnormal page abnormality repair information from the abnormality repair strategy; A page repair task for the abnormal page is generated according to the abnormal page and corresponding abnormal repair information, and the page repair task is sent to a first associated object corresponding to the abnormal page.

14. The device according to claim 12, wherein The calling module further includes: According to the abnormal repair strategy, a repair task set for the abnormal business function is generated; the repair task set is sent to the second associated object corresponding to the abnormal business function, and the tasks in the repair task set are distributed to the first associated object corresponding to the abnormal page in the abnormal business function through the second associated object.

15. The device according to any one of claims 11 to 14, wherein: The second acquisition module further includes: Determining sampling information of the sampled data, and determining historical sampling data based on the sampling information of the sampled data; According to the historical sampling data, historical aggregated sampling data of pages associated with each business function is determined.

16. The device according to any one of claims 11 to 14, wherein: After determining the abnormal service function and abnormal information of the abnormal service function, the apparatus further includes: Generate abnormal alarm information of the application program according to the abnormal business function and the corresponding abnormal information.

17. The device according to any one of claims 11 to 14, wherein: The statistical parameter set includes at least one of a standard deviation, a variance, a mean, and a minimum value corresponding to the page, and the apparatus further includes: For each page, obtain the abnormality judgment conditions for each type of statistical parameter; In response to at least one type of statistical parameter in the first statistical parameter set satisfying a corresponding abnormality determination condition, the page is determined to be an abnormal page.

18. The device according to claim 11, wherein The device further comprises: Monitoring module, used to perform global monitoring of application pages; A third acquisition module is used to aggregate the user's operations on the same page within a set time unit to obtain aggregated sampling data of the user on the same page; A fourth acquisition module is used to acquire function mapping information corresponding to the same page; The fifth acquisition module is configured to generate the sampling data of the application program according to the aggregated sampling data of the user on the same page and the function mapping information corresponding to the same page.

19. The device according to claim 18, wherein The fourth acquisition module includes: Determining the code class of the same page, and determining the target business component to which the code class belongs; Function mapping information corresponding to the same page is generated according to the code class and the target business component.

20. The device according to claim 18 or 19, wherein The fifth acquisition module includes: Sampling aggregated sampling data of some users from the aggregated sampling data corresponding to the same page as target aggregated sampling data; The sampling data of the application is generated according to the target aggregated sampling data and the function mapping information corresponding to the same page.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

Images