Application data processing method and device, electronic equipment and storage medium

Abstract

The invention discloses an application data processing method which is applied to the technical field of computers. According to the method, account behavior link analysis is carried out on application data, so that a representative target account behavior link is mined, and in events related to the target account behavior link, under the condition that an event which is not highly correlated with an index system exists, the index system is corrected based on the event, so that the target account behavior link is corrected. And finally, the indexes in the target index system obtained through correction can be better associated with the events related to the target account behavior link, so that the capability of quantifying application data of the target index system is improved. In the target index system, the information in the application data can be better mined, and the operation condition of the target business is expressed in the form of the index value in the target index system. The indexes of the target index system not only can fully utilize the information content of the application data, but also can comprehensively and reasonably reflect the operation condition of the specific business.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to an application data processing method, apparatus, electronic device, and storage medium. Background Art

[0002] An Indication System refers to an overall entity formed by multiple indicators in a certain relationship. Specifically, an Indication System is an organic whole formed by several indicators that can quantify the operation of a business scenario. Each indicator in the Indication System should have mutual independence and interconnection.

[0003] In the related art, the correspondence between the indicators of the Indication System and the application data collected in the business scenario is not strong, and the ability of the indicator link formed by the relationship between the indicators to describe the event link related to the application data is also not strong. As a result, it is difficult for the Indication System to fully quantify the information of the application data itself, leading to a low utilization rate of the information of the application data, and also reducing the quantification ability and expression ability of the Indication System for the operation of the business scenario. Summary of the Invention

[0004] The embodiments of the present application provide an application data processing method, which solves the technical problems in the related art that the Indication System is difficult to fully quantify the information of the application data itself, resulting in a low utilization rate of the information of the application data, and also reducing the quantification ability and expression ability of the Indication System for the operation of the business scenario.

[0005] According to one aspect of the embodiments of the present application, an application data processing method is provided. The method includes:

[0006] Display a first page for uploading a basic Indication System, where the basic Indication System is a system formed by indicators for quantifying the execution of a target business by a target application, and the directional relationship between the indicators in the basic Indication System matches the execution link of the relevant events in the target business;

[0007] When an instruction for generating an Indication System is obtained, display a second page for presenting a target Indication System, where the target Indication System is the Indication System corresponding to a target scenario in the target business, and the target Indication System is an Indication System obtained by correcting the basic Indication System based on application data;

[0008] Wherein, the application data represents the data obtained by collecting the information generated during the operation of the target application in the target scenario.

[0009] According to one aspect of the embodiments of the present application, an application data processing apparatus is provided. The apparatus includes:

[0010] A display module for displaying a first page for uploading a basic index system, where the basic index system is a system formed by indexes used to quantify the execution of a target service by a target application, and the directional relationship between the indexes in the basic index system matches the execution link of related events in the target service;

[0011] An application data processing module for displaying a second page when an index system generation instruction is obtained. The second page is used to display a target index system, where the target index system is an index system corresponding to a target scenario in the target service and is an index system obtained by correcting the basic index system based on application data;

[0012] Wherein, the application data represents data obtained by collecting information generated during the operation of the target application in the target scenario.

[0013] According to one aspect of the embodiments of the present application, a computer device is provided. The computer device includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the above application data processing method.

[0014] According to one aspect of the embodiments of the present application, a computer-readable storage medium is provided. At least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the above application data processing method.

[0015] According to one aspect of the embodiments of the present application, a computer program product is provided. The computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to enable the computer device to execute to implement the above application data processing method.

[0016] The technical solution provided by the embodiments of the present application can bring the following beneficial effects:

[0017] An embodiment of the present application proposes an application data processing method. This method conducts an analysis of the account behavior link for application data, thereby mining representative target account behavior links. In the case where there are events with a low degree of association with the indicator system among the events related to the target account behavior link, the indicator system is corrected based on such events. Eventually, the indicators in the target indicator system obtained after correction can better establish an association with the events related to the target account behavior link, thereby enhancing the ability of the target indicator system to quantify application data. Within the target indicator system, the information in the application data can be better mined and the operating conditions of the target business are expressed in the form of indicator values within the target indicator system.

[0018] An embodiment of the present application can construct a target indicator system adapted to the application data by correcting the original indicator system. The indicators of the target indicator system can comprehensively index the obtained application data indicators. Each indicator of the target indicator system can not only make full use of the information content of the application data itself but also comprehensively and reasonably reflect the operating conditions of the specific business. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a schematic diagram of the indicator system in an e-commerce scenario provided by an embodiment of the present application;

[0021] Figure 2 It is a schematic diagram of the application program running environment provided by an embodiment of the present application;

[0022] Figure 3 It is a flowchart of the application data processing method provided by an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of the application data processing method in an e-commerce business provided by an embodiment of the present application;

[0024] Figure 5 It is a schematic diagram of the relationship between indicators of the target indicator system provided by an embodiment of the present application;

[0025] Figure 6 It is a schematic diagram of the overall interaction flowchart of the application data processing method provided by an embodiment of the present application;

[0026] Figure 7 It is a schematic diagram of the process flow of the target indicator system generation method provided by an embodiment of the present application;

[0027] Figure 8 It is a schematic flow chart of an account behavior link analysis method provided by an embodiment of the present application;

[0028] Figure 9 It is a block diagram of an application data processing device provided by an embodiment of the present application;

[0029] Figure 10 It is a structural block diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0030] Before introducing the method embodiments provided by the present application, relevant terms or nouns that may be involved in the method embodiments of the present application are briefly introduced first, so as to facilitate the understanding of those skilled in the art of the present application.

[0031] Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or a local area network to achieve data computing, storage, processing, and sharing. Cloud technology is the general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model, and can form a resource pool, which can be used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark and needs to be transmitted to the background system for logical processing. Data at different levels will be processed separately, and various industry data requires a powerful system backup support, which can only be achieved through cloud computing.

[0032] Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, and is a theory, method, technology, and application system that can perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable the machines to have the functions of perception, reasoning, and decision-making.

[0033] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields involved, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0034] Machine Learning (ML) is an interdisciplinary subject that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and rote learning.

[0035] Indicator: An indicator is a measurement standard or quantitative parameter used to measure, evaluate, or describe a specific aspect or goal. It provides a quantitative or qualitative measurement of a specific phenomenon, behavior, or result for comparison, analysis, and monitoring. The quantitative indicators for different businesses are also different.

[0036] Dimension: A dimension is an attribute of an attribute or feature used to classify, group, or describe data. It provides ways to view and segment data from different perspectives to better understand and analyze the data. Classification based on dimensions usually refers to classifying data according to some common characteristics for comparison, screening, and summarization.

[0037] Indicator system: An indicator system (Indication System) refers to an organic whole formed by multiple indicators in a certain relationship. Specifically, an indicator system is an organic whole formed by several indicators that can quantify the operation of a business scenario. These indicators can be absolute numbers, relative numbers, or averages, and they jointly provide a comprehensive reflection of the business scenario. Each indicator in the indicator system should have mutual independence and mutual connection. Mutual independence means that when each indicator reflects the quantitative characteristics of a certain aspect of the business scenario, it does not overlap or repeat with other indicators; mutual connection means that there is a certain logical relationship between each indicator, jointly forming a complete indicator system.

[0038] The K-means algorithm is a common clustering algorithm, and its core idea is a method of finding multiple clusters through iteration. It initializes multiple cluster centers, and then for each sample point, it assigns it to the corresponding cluster based on the nearest cluster center. Subsequently, the cluster centers are recalculated based on the sample points in the clusters. When the cluster centers no longer change, the algorithm terminates.

[0039] The advantages of the K-means algorithm include being simple and easy to understand, having strong interpretability, high computational efficiency, etc. At the same time, it also has some disadvantages, such as being sensitive to the selection of the initial cluster centers and possibly falling into a local optimum.

[0040] K-medoids algorithm: The k-means algorithm (English: k-means clustering) originated from a vector quantization method in signal processing and can be popular as a clustering analysis method in the field of data mining in related technologies. The purpose of k-means clustering is to divide multiple points (which can be an observation of a sample or an instance) into multiple clusters, so that each point belongs to the cluster corresponding to the nearest mean (i.e., the cluster center), and this is used as the standard for clustering. The k-means clustering is similar to the K-means algorithm in related technologies, but the difference lies in the selection of the center point. The center point selected in the K-means algorithm is the centroid of all points in the current class, while the center point selected in the K-medoids (k-means clustering) algorithm is a point existing in the current cluster (cluster), and the criterion function is that the sum of the distances from all other points in the current cluster to this center point is the smallest.

[0041] Before specifically elaborating on the embodiments of the present application, the relevant technical background related to the embodiments of the present application is introduced to facilitate the understanding of those skilled in the art of the present application field.

[0042] The method of constructing an index system in related technologies generally decomposes each index used to analyze a certain business scenario layer by layer in the order from coarser to finer and from macroscopic to detailed, and then forms an index system according to the decomposition results. In the business scenario, according to the different logical levels where the indexes are located, the indexes can be divided into first-level indexes, second-level indexes, third-level indexes, etc. According to the specific indexes in the index system, the application software related to the business scenario is instrumented to obtain application data related to the specific indexes, and the specific index values are calculated based on these application data.

[0043] Please refer to Figure 1, which shows a schematic diagram of an exemplary indicator system in the e-commerce scenario provided by the embodiments of the present application. The indicator system is divided into three logical layers. For the specific business scenario of the e-commerce scenario, the higher the layer of the indicator, the stronger the ability to represent the operation of the business scenario, and the higher the comprehensive representation ability of the indicator itself. The lower the layer, the more the indicator tends to reflect the situation in a certain dimension of the e-commerce scenario, and the higher the ability to represent details. Therefore, an indicator system including upper-layer indicators and lower-layer indicators can not only macroscopically quantify the overall operation of the e-commerce scenario, but also reflect the execution details of the e-commerce scenario in multiple dimensions from all aspects. An indicator system with such an effect is a high-quality indicator system.

[0044] For a business that has not started constructing an indicator system, related technologies usually rely on data analysts to design the indicator system and the instrumentation plan from scratch according to the solutions of related technologies. However, for a business that already has a relatively complex indicator system and instrumentation system, it is relatively difficult for data analysts to quickly clarify the correspondence between the application data obtained through instrumentation during the runtime of the application corresponding to the business and the upper-layer indicators of the business.

[0045] In some cases, the application data may include account behavior data corresponding to the instrumentation location or instrumentation event. For example, the application data may include data information such as the account registering the application at a certain time point, the account logging in to the application at another time point, and the account uninstalling the application at another time point. In many cases, it is unknown what the relationship is between these application data and the specific business indicators. Therefore, a technical solution needs to be designed to enable a better correspondence between the application data and the indicators of the constructed indicator system.

[0046] In the case where sufficient application data has been obtained, the original indicator system can be corrected to construct a target indicator system adapted to the application data. The indicators of the target indicator system can comprehensively index the obtained application data. Each indicator of the target indicator system can not only make full use of the information content of the application data itself, but also comprehensively and reasonably reflect the operation of the specific business. On the basis of using the existing instrumentation results and fully collecting the application data in the application software, automatically generating a high-quality indicator system can improve the utilization rate of application data information, improve the analysis efficiency of the business, and optimize the analysis results.

[0047] To achieve the foregoing technical objectives, the embodiments of the present application propose an application data processing method, which is a method for automatically generating an index system by means of data mining. For some typical business scenarios, these business scenarios often have their own corresponding basic index systems. For example, in the e-commerce scenario, the most common business logic in this scenario is a business funnel of user browsing - adding to cart - clicking to purchase - returning goods, and the index link formed by the corresponding index system is such as the number of views -> the number of items added to the cart -> the number of clicks to purchase -> the number of returns. Of course, for some detailed businesses in this e-commerce scenario, additional specific indexes may be added on the basis of the basic index system. The embodiments of the present application can perform data mining in the direction of the behavior link on the application data generated by instrumentation on the basis of the basic index system, such as the index system in the e-commerce scenario, and combine the semantic understanding of the basic index system to automatically generate an index system unique to a specific business, so as to comprehensively reflect the operation of the specific business and assist in improving the data analysis efficiency.

[0048] To make the objectives, technical solutions, and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0049] Please refer to Figure 2 , which shows a schematic diagram of an application program running environment provided by an embodiment of the present application. The application program running environment may include: a terminal 10 and a server 20.

[0050] The terminal 10 includes, but is not limited to, electronic devices such as mobile phones, computers, intelligent voice interaction devices, intelligent home appliances, vehicle-mounted terminals, game consoles, e-book readers, multimedia playback devices, and wearable devices. A client of the application program may be installed in the terminal 10.

[0051] In the embodiments of the present application, the foregoing application program may be any application program that provides or uses application data processing services. Typically, the application program may be a media content recommendation type application program. Of course, in addition to media content recommendation type application programs, application data processing services may also be provided or used in other types of application programs. For example, news type application programs, social type application programs, interactive entertainment type application programs, browser application programs, shopping type application programs, content sharing type application programs, virtual reality (VR) type application programs, augmented reality (AR) type application programs, application store type application programs, etc., and the embodiments of the present application do not make any limitations in this regard. The embodiments of the present application do not make any limitations in this regard. Optionally, a client of the foregoing application program runs in the terminal 10.

[0052] The server 20 is used to provide background services for the clients of the applications in the terminal 10. For example, the server 20 may be the background server of the above-mentioned application. The server 20 may be a single server or a server cluster composed of multiple physical servers, that is, any server in the distributed cluster. The distributed cluster can concurrently respond to requests from multiple clients 10, and it can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0053] Optionally, the terminal 10 and the server 20 can communicate with each other through the network 30. The terminal 10 and the server 20 can be directly or indirectly connected through wired or wireless communication methods, and the present application does not limit this.

[0054] Please refer to Figure 3 , which shows a flowchart of an application data processing method provided by an embodiment of the present application. This method can be applied to a computer device, and the above-mentioned computer device refers to an electronic device with data calculation and processing capabilities. For example, the execution subject of each step can be Figure 2 any terminal 10 or server 20 in the application program running environment shown. This method may include the following steps:

[0055] S301. Display a first page, where the first page is used to upload a basic index system. The basic index system is a system formed by indexes used to quantify the execution of the target business by the target application, and the directional relationship between the indexes in the basic index system matches the execution link of related events in the target business.

[0056] In the embodiments of the present application, the target business is not limited. The target business can be any business, such as e-commerce business, game business, payment business, etc. The target application is an application used to run the target business, and the basic index system is an index system that describes the operation of the target business. Please refer to Figure 1 , Figure 1 shows the basic index system corresponding to the e-commerce business in an implementation manner. There is a correlation relationship, that is, a directional relationship, between the multiple indexes included in the basic index system. These relationships enable the basic index system formed by the multiple indexes to be expressed as a chain or a graph.

[0057] Please refer to FIG. 4, which shows a schematic diagram of the application data processing method in the e-commerce business in the embodiments of the present application. FIG. 4(a) shows the first page, and the basic index system corresponding to the e-commerce business can be uploaded under this page. FIG. 4(b) shows the specific content of the basic index system of the e-commerce business. It can be seen that the basic index system can be described as a chain, so there is a clear directional relationship between adjacent indexes. This directional relationship can also be understood as an upstream and downstream relationship. For example, the index of "number of registrations / number of registration times" is the upstream index of the index of "number of starts / number of start-up people". Similarly, the index of "number of starts / number of start-up people" is the downstream index of the index of "number of registrations / number of registration times". The directional relationship between the indexes in the above basic index system matches the execution link of the relevant events in the above target business. For example, the relevant event corresponding to the index of "number of registrations / number of registration times" is to register the target application, and the relevant event corresponding to the index of "number of starts / number of start-up people" is to start the target application. Corresponding to the upstream and downstream relationship between the indexes, the event of registering the target application is also the upstream event of the event of starting the target application, and the event of starting the target application is the downstream event of the event of registering the target application.

[0058] S302. When an index system generation instruction is obtained, display the second page. The second page is used to display the target index system. The target index system is the index system corresponding to the target scenario in the target business, and the target index system is the index system obtained by correcting the basic index system based on the application data; wherein, the application data represents the data obtained by collecting the information generated during the operation of the target application in the target scenario.

[0059] The embodiments of the present application do not limit the target scenario, which can be any subordinate scenario in the target business. Taking the target business as an e-commerce business as an example, the target scenario can be a certain activity scenario of the e-commerce business. The target scenario is also the scenario during the operation of the target application. Collecting the data generated or obtained during the operation of the target application can obtain application data. The embodiments of the present application do not limit the collection method. For example, the collection of application data can be completed through forms such as instrumentation, callback, and questionnaire. Among them, instrumentation is also called logging, which is to collect some information in specific processes of the target application to collect the usage status of the target application, and then use it to further optimize the target application or provide data support for operation. Many information can be obtained through logging, such as the number of visits, the number of visitors, the time on site, the number of page views, and the bounce rate. What to log depends on what information is desired. For example, the basic attribute information or account behavior information of the account can be obtained. The basic attribute information of the account mainly includes the city, address, age, gender, longitude and latitude, account type, operator, network, device, etc. The account behavior information is the click behavior and browsing behavior of the user, such as data on which user clicked which button, browsed which page, and the browsing duration at what time.

[0060] Based on the fact that in the related art, it is difficult for data analysts to establish a correspondence between the actually collected application data and the existing indicator system, resulting in the relative separation of the indicator system and the application data, and it is difficult to correct the indicator system from the perspective of application data. The embodiments of the present application obtain a target indicator system that is more suitable for describing the target scenario by correcting the above basic indicator system based on the application data.

[0061] Please refer to FIG. 4(c), which shows a schematic diagram of the target indicator system displayed on the second page. It can be seen that the target indicator system includes both the indicators in the basic indicator system and newly added other indicators with a high degree of relevance to the target scenario, such as "the number of activities / the number of people in the activity". Therefore, compared with the basic indicator system, the target indicator system has a more powerful and targeted description ability and quantification ability for the target scenario. Moreover, this target indicator system is obtained by correcting the basic system from the perspective of application data, and can make better use of the information of the application data itself, improving the information utilization rate. Of course, the directional relationship between the indicators in the above target indicator system matches the execution link of the relevant events in the target scenario of the above target business.

[0062] In one embodiment, the display of the second page includes: displaying the relationship between the indicators in the above-mentioned target indicator system, where the relationship between the indicators is a graph relationship or a link relationship; displaying the execution link of the target event, where the target event is an event associated with the indicators in the above-mentioned target indicator system. Please refer to FIG. 4(c). The upper box shows the execution link of the target event, and the lower box shows the relationship between the indicators in the target indicator system. The upstream and downstream relationships of the target event are consistent with the upstream and downstream relationships between the indicators.

[0063] The target indicator system can also be expressed in the form of a graph. Please refer to Figure 5 , which shows a schematic diagram of the relationship between the indicators in the target indicator system in an embodiment of the present application. The target indicator system can be identified as a graph structure, and the arrow points from the upstream indicator to the downstream indicator.

[0064] Please refer to Figure 6 , which shows an overall interaction flowchart of the application data processing method in an embodiment of the present application. First, the user opens the indicator system generation interface - the first page. Under this first page, the user uploads the basic indicator system to the server. The server uploads the application data collected by business data tracking in the recent period and the basic indicator system to the algorithm module that is communicatively connected to itself. The algorithm module generates a complete target indicator system (business indicator system), and the server returns the complete target indicator system to the user. Of course, the algorithm module can also be regarded as a part of the server.

[0065] Next, the generation process of the target indicator system in the embodiment of the present application will be described in detail.

[0066] In one embodiment, the aforementioned application data includes account behavior sequences corresponding to multiple accounts respectively. Any one of the above-mentioned account behavior sequences is composed of account behavior data collected in chronological order. Any one of the above-mentioned account behavior data includes a time point and an account behavior entry corresponding to the time point. An example of an account behavior sequence corresponding to one account is used in the embodiment of the present application to illustrate this. Taking this account as U1, the account behavior sequence can be expressed as U1: [{t1: [f11, f21..]}, {t2: [f21, f22…]}…], where {t1: [f11, f21..]}, {t2: [f21, f22…]} are two account behavior data. At different time points t1, t2…, the account behavior entries occurring at this time point are collected at each time point. For example, f11 is the behavior of clicking a button, and the number of times of clicking the button… f21 is the behavior of browsing a page, and f22 is the browsing duration starting from opening the target application, etc. Based on such multiple account behavior sequences, the target indicator system can be automatically generated. Please refer to Figure 7 , which shows a schematic flowchart of the method for generating the target indicator system provided in the embodiment of the present application. The above-mentioned target indicator system is generated by the following method:

[0067] S701. Analyze the account behavior link based on the above application data to obtain multiple target account behavior links. The above target account behavior links are account behavior links whose occurrence frequency meets the preset requirements.

[0068] The process of account behavior link analysis can be understood as an automated process of behavior link mining. Its technical purpose is to mine target behavior links with high frequencies, so that the relevant events in such target behavior links establish a strong correlation with the indicators in the target indicator system, which is beneficial to enhancing the expression ability of the target indicator system for the target scenario. The embodiments of the present application do not limit the preset requirements and can be set according to actual situations, as long as the occurrence frequency of the target account behavior link in the application data meets the requirements of data analysts in the target scenario. Of course, the embodiments of the present application do not limit the number of target account behavior links, and any account behavior link that meets the preset requirements can be used as a target account behavior link.

[0069] Please refer to Figure 8 , which shows a schematic flowchart of the account behavior link analysis method in the embodiments of the present application. The above analysis of the account behavior link based on the application data to obtain multiple target account behavior links includes:

[0070] S801. For any account behavior sequence, divide the account behavior data in the above account behavior sequence based on a time interval to obtain multiple account behavior subsequences.

[0071] According to the foregoing, for example, U1: [{t1: [f11, f21..]}, {t2: [f21, f22…]}…

[0072] , {t1: [f11, f21..]}, {t2: [f21, f22…]} are two account behavior data respectively. If t1 and t2 are in the same time interval, then {t1: [f11, f21..]}, {t2: [f21, f22…]} can be divided into the same account behavior subsequence, otherwise they will be divided into different account behavior subsequences. Of course, the embodiments of the present application do not set the size and specific range of the time interval, as long as the account behavior sequence can be divided into several account behavior subsequences from the perspective of the time interval. Taking the account U1 as an example, the corresponding account behavior subsequence is expressed as U1 = [p1, p2, p3…]. Divide each account behavior sequence based on the time interval, and all the obtained account behavior subsequences can be expressed as [p1…pm]. m is a positive integer, and its size is not limited.

[0073] Cluster all the above account behavior subsequences to obtain multiple clusters, and determine the account behavior subsequence corresponding to the center of each cluster as the central sequence; use the link formed by the events corresponding to the account behavior entries of the above central sequence as the above target account behavior link.

[0074] In one embodiment, for each of the above account behavior data, extract the account behavior performance characteristics associated with the corresponding time point; based on each of the above account behavior performance characteristics, obtain the sequence performance characteristics corresponding to each of the above account behavior subsequences; perform clustering of the account behavior subsequences based on each of the above sequence performance characteristics to obtain the above multiple clusters.

[0075] Taking the account behavior data {t1: [f11, f21..]} as an example, the account behavior performance characteristics associated with t1 can be extracted. Organize the account behavior performance characteristics at each time point into features with the same dimension, such as [whether clicked, number of clicks, whether browsed, number of views, browsing duration..]. After normalizing and standardizing these features, the final target account behavior performance characteristics can be obtained. Each account behavior data has its corresponding target account behavior performance characteristics. Organize the target account behavior performance characteristics corresponding to each account behavior data in the account behavior subsequence in order to obtain the sequence performance characteristics corresponding to the account behavior subsequence. Perform clustering of the account behavior subsequences based on each of the above sequence performance characteristics to obtain the above multiple clusters.

[0076] Of course, the embodiment of the present application does not limit the clustering method for sequences. For example, the K-medoids algorithm or the K-means algorithm mentioned above can be used. Specifically, cluster multiple account behavior subsequences into k clusters. k is a positive integer greater than 1. During the specific clustering process, the DTW algorithm can be used to calculate the similarity between two sequences, and then the K-medoids algorithm is used to perform clustering based on the similarity calculation results to obtain k clusters and the central sequences of the k clusters. Among them, DTW (Dynamic Time Warping) is a dynamic time warping algorithm, and the embodiment of the present application will not elaborate on this.

[0077] S702. In the case where the semantic relevance between the first application event and the above basic index system is lower than the relevance threshold, determine new indexes based on the above first application event, update the above basic index system to obtain the current index system; where the above first application event is the application event corresponding to the first account behavior, the above first account behavior is any account behavior of the first target account behavior link, and the above first target account behavior link is any target behavior link among the above multiple target account behavior links.

[0078] In some embodiments, when the semantic relevance between the second application event and the current metric system is lower than the relevance threshold, new metrics are determined based on the second application event to update the current metric system; the second application event is an application event corresponding to a second account behavior, and the second account behavior is any account behavior in the first target account behavior link other than the first account behavior. In some embodiments, when the semantic relevance between the third application event and the current metric system is lower than the relevance threshold, new metrics are determined based on the third application event to update the current metric system; the third application event is an application event corresponding to a third account behavior, and the third account behavior is any account behavior in a second target account behavior link, and the second target behavior link is any behavior link among the multiple target account behavior links other than the first target behavior link.

[0079] Simply put, if the basic metric system is used as the update basis, that is, the initial current metric system, the current metric system can be updated according to any application event in any target account link that meets the preset relevance requirements. Specifically, the application event that meets the relevance threshold requirements can be directly abstracted as or used as new metrics, so as to continuously update the current metric system and finally obtain the target metric system.

[0080] The preset relevance requirement is that the semantic relevance between the application event and the current metric system is lower than the relevance threshold. The embodiments of the present application do not limit the relevance threshold, which can be set according to actual situations, nor do they limit the calculation method of semantic relevance. For example, a semantic similarity calculation model can be used to calculate the relevance. In this regard, the embodiments of the present application will not elaborate. In one embodiment, the corresponding semantic relevance can be calculated for each metric of the application event and the current metric system, and the highest value of the semantic relevance is used as the semantic relevance between the application event and the current metric system. In another embodiment, taking the first application event as an example, the semantic similarity can also be calculated between the first application event and each metric of the basic metric system to obtain the similarity value corresponding to each metric; when each of the above similarity values is lower than the relevance threshold, it is determined that the semantic relevance between the first application event and the basic metric system is lower than the relevance threshold. Of course, the judgment methods for whether other application events meet the above preset relevance requirements are also based on the same inventive concept.

[0081] For example, if k target behavior link sequences are obtained, and by using a similarity model, the buried point events (application events) in each target behavior link sequence that meet the above-mentioned preset requirements for relevance are abstracted into metrics, new metrics can be obtained. Taking the event link corresponding to the target behavior link sequence as the event sequence of opening a mini-program -> browsing the mini-program -> closing the mini-program, the semantic similarity (relevance) between each event in it and each metric in the current metric system is calculated respectively. If there is a situation where the calculated similarity is greater than the similarity threshold, then this event belongs to the corresponding metric. For example, opening a mini-program belongs to the startup metric. If all the calculated similarities are less than the similarity threshold, then this event is abstracted into a new metric (newly added metric) and inserted into the current metric system. The specific method is to insert this newly added metric between the metric corresponding to the upstream event and the metric corresponding to the downstream event of this event, and update the upstream and downstream relationships of this newly added metric. Finally, the target metric system is formed.

[0082] S703. Based on the above current metric system, obtain the above target metric system;

[0083] The basic metric system can be expressed as a graph structure. The process of modifying the metric system not only adds new metrics but also synchronously adds the topology of the newly added metrics. Therefore, the finally obtained target metric system can still be expressed as a graph structure, not only with richer metric quantities and metric meanings, but also with a very clear metric topology.

[0084] The embodiment of the present application proposes an application data processing method. Based on the basic metric system of the target business, combined with the application data collected by business buried points, account behavior link mining is carried out, and the basic metric system is updated according to the mining results to obtain the target metric system unique to the target scenario in the target business. It can assist data analysts to more quickly clarify the target metric system of the target business and greatly improve work efficiency.

[0085] Specifically, this method conducts account behavior link analysis on application data to thus mine representative target account behavior links. And in the events related to the target account behavior link, if there are events with a low degree of association with the metric system, the metric system is corrected based on such events. Thus, finally, the metrics in the target metric system obtained after correction can better establish an association with the events related to the target account behavior link, thereby enhancing the ability of the target metric system to quantify application data. Within the target metric system, the information in the application data can be better mined and the operation situation of the target business is expressed in the form of metric values within the target metric system.

[0086] In the embodiments of the present application, the original index system can be corrected to construct a target index system adapted to the application data. The indicators of the target index system can comprehensively index the obtained application data indicators. Each indicator of the target index system can not only make full use of the information content of the application data itself, but also comprehensively and reasonably reflect the operation of the specific business.

[0087] Please refer to Figure 9 , which shows a block diagram of an application data processing device provided by an embodiment of the present application. The device has the function of implementing the above application data processing method. The above function can be implemented by hardware or by hardware executing corresponding software. The device can be a computer device or can be set in a computer device. The above device includes:

[0088] A display module 901, configured to display a first page, where the first page is used to upload a basic index system, and the basic index system is a system formed by indicators for quantifying the execution of a target service by a target application, and the directional relationship between the indicators in the basic index system matches the execution link of relevant events in the target service;

[0089] An application data processing module 902, configured to display a second page when an index system generation instruction is obtained, where the second page is used to display a target index system, and the target index system is an index system corresponding to a target scenario in the target service, and the target index system is an index system obtained by correcting the basic index system based on application data;

[0090] Wherein, the above application data represents data obtained by collecting information generated during the operation of the target application in the target scenario.

[0091] In one embodiment, the above application data processing module 902 is configured to perform the following operations:

[0092] Display the relationship between the indicators of the target index system, where the relationship between the indicators is a graph relationship or a link relationship;

[0093] Display the target event execution link, where the target event is an event associated with the indicators in the target index system.

[0094] In one embodiment, the above application data includes account behavior sequences corresponding to multiple accounts respectively, and any one of the above account behavior sequences is composed of account behavior data collected in chronological order. The above application data processing module 902 is configured to perform the following operations:

[0095] Perform account behavior link analysis based on the above application data to obtain multiple target account behavior links, where the target account behavior links are account behavior links whose occurrence frequency meets the preset requirements;

[0096] When the semantic relevance between the first application event and the above-mentioned basic index system is lower than the relevance threshold, new indexes are determined based on the first application event, and the above-mentioned basic index system is updated to obtain the current index system;

[0097] Based on the above-mentioned current index system, the above-mentioned target index system is obtained;

[0098] Among them, the first application event is an application event corresponding to the first account behavior, the first account behavior is any account behavior in the first target account behavior link, and the first target account behavior link is any target behavior link among the above-mentioned multiple target account behavior links.

[0099] In one embodiment, the above-mentioned application data processing module 902 is used to perform the following operations:

[0100] When the semantic relevance between the second application event and the above-mentioned current index system is lower than the above-mentioned relevance threshold, new indexes are determined based on the second application event, and the above-mentioned current index system is updated; the second application event is an application event corresponding to the second account behavior, and the second account behavior is any account behavior in the first target account behavior link except the first account behavior.

[0101] In one embodiment, the above-mentioned application data processing module 902 is used to perform the following operations:

[0102] When the semantic relevance between the third application event and the above-mentioned current index system is lower than the above-mentioned relevance threshold, new indexes are determined based on the third application event, and the above-mentioned current index system is updated; the third application event is an application event corresponding to the third account behavior, the third account behavior is any account behavior in the second target account behavior link, and the second target behavior link is any behavior link among the above-mentioned multiple target account behavior links except the first target behavior link.

[0103] In one embodiment, the above-mentioned application data processing module 902 is used to perform the following operations:

[0104] The semantic similarity between the first application event and each index of the above-mentioned basic index system is calculated respectively to obtain the similarity value corresponding to each index;

[0105] When each of the above-mentioned similarity values is lower than the above-mentioned relevance threshold, it is determined that the semantic relevance between the first application event and the above-mentioned basic index system is lower than the above-mentioned relevance threshold.

[0106] In one embodiment, any of the above-mentioned account behavior data includes a time point and an account behavior entry corresponding to the time point. The application data processing module 902 is configured to perform the following operations:

[0107] For any account behavior sequence, divide the account behavior data in the account behavior sequence based on a time interval to obtain a plurality of account behavior subsequences;

[0108] Cluster all the above-mentioned account behavior subsequences to obtain a plurality of clusters, and determine the account behavior subsequence corresponding to the center of each cluster as the center sequence;

[0109] Use the link formed by the events corresponding to the account behavior entries of the above-mentioned center sequence as the target account behavior link.

[0110] In one embodiment, the above-mentioned application data processing module 902 is configured to perform the following operations:

[0111] For each of the above-mentioned account behavior data, extract the account behavior performance characteristics associated with the corresponding time point;

[0112] According to the above-mentioned account behavior performance characteristics, obtain the sequence performance characteristics corresponding to each of the above-mentioned account behavior subsequences;

[0113] Perform clustering of the account behavior subsequences based on the above-mentioned sequence performance characteristics to obtain the above-mentioned plurality of clusters.

[0114] It should be noted that when the device provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and the method embodiment belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be repeated here.

[0115] Please refer to Figure 10 , which shows a structural block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server for executing the above-mentioned application data processing method. Specifically:

[0116] The computer device 1100 includes a Central Processing Unit (CPU) 1101, a system memory 1104 including a Random Access Memory (RAM) 1102 and a Read Only Memory (ROM) 1103, and a system bus 1105 connecting the system memory 1104 and the central processing unit 1101. The computer device 1100 also includes a Basic Input / Output System (I / O (Input / Output) system) 1106 that helps transfer information between various components within the computer, and a mass storage device 1107 for storing an operating system 1113, application programs 1114, and other program modules 1115.

[0117] The Basic Input / Output System 1106 includes a display 1108 for displaying information and input devices 1109 such as a mouse, keyboard, etc. for user input. The display 1108 and the input devices 1109 are both connected to the central processing unit 1101 through an input / output controller 1110 connected to the system bus 1105. The Basic Input / Output System 1106 may also include an input / output controller 1110 for receiving and processing inputs from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1110 also provides output to a display screen, printer, or other types of output devices.

[0118] The mass storage device 1107 is connected to the central processing unit 1101 through a mass storage controller (not shown) connected to the system bus 1105. The mass storage device 1107 and its associated computer-readable medium provide non-volatile storage for the computer device 1100. That is, the mass storage device 1107 may include computer-readable media (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0119] Without loss of generality, computer-readable media can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes RAM, ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other solid-state memory technologies, CD-ROM, DVD (Digital Video Disc) or other optical storage, magnetic tape cartridges, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that computer storage media is not limited to the above several types. The above-mentioned system memory 1104 and mass storage device 1107 can be collectively referred to as memory.

[0120] According to various embodiments of the present application, the computer device 1100 can also run on a remote computer on the network through a network such as the Internet. That is, the computer device 1100 can be connected to the network 1112 through the network interface unit 1111 connected to the system bus 1105, or in other words, the network interface unit 1111 can also be used to connect to other types of networks or remote computer systems (not shown).

[0121] The above memory further includes a computer program, which is stored in the memory and is configured to be executed by one or more processors to implement the above application data processing method.

[0122] In an exemplary embodiment, a computer-readable storage medium is further provided. At least one instruction, at least one segment of program, code set or instruction set is stored in the above storage medium. When the at least one instruction, the at least one segment of program, the code set or the instruction set is executed by the processor, the above application data processing method is implemented.

[0123] Specifically, the application data processing method includes:

[0124] Display a first page, where the first page is used to upload a basic indicator system. The basic indicator system is a system formed by indicators for quantifying the execution of a target service by a target application. The directional relationship between the indicators in the basic indicator system matches the execution link of relevant events in the target service;

[0125] When receiving an instruction for generating an index system, display a second page. The above-mentioned second page is used to display a target index system. The above-mentioned target index system is the index system corresponding to the target scenario in the above-mentioned target business, and the above-mentioned target index system is an index system obtained by correcting the above-mentioned basic index system based on application data;

[0126] Among them, the above-mentioned application data represents the data obtained by collecting the information generated during the operation of the above-mentioned target application in the above-mentioned target scenario.

[0127] In one embodiment, the above-mentioned display of the second page includes:

[0128] Display the relationship between the indexes of the above-mentioned target index system. The above-mentioned relationship between the indexes is a graph relationship or a link relationship;

[0129] Display the execution link of the target event. The above-mentioned target event is an event associated with the indexes in the above-mentioned target index system.

[0130] In one embodiment, the above-mentioned application data includes account behavior sequences corresponding to multiple accounts respectively. Any one of the above-mentioned account behavior sequences is composed of account behavior data collected in chronological order. The above-mentioned target index system is generated by the following method:

[0131] Based on the above-mentioned application data, perform account behavior link analysis to obtain multiple target account behavior links. The above-mentioned target account behavior links are account behavior links whose occurrence frequencies meet the preset requirements;

[0132] When the semantic relevance between the first application event and the above-mentioned basic index system is lower than the relevance threshold, determine new indexes based on the above-mentioned first application event, update the above-mentioned basic index system, and obtain the current index system;

[0133] Based on the above-mentioned current index system, obtain the above-mentioned target index system;

[0134] Among them, the above-mentioned first application event is the application event corresponding to the first account behavior. The above-mentioned first account behavior is any account behavior of the first target account behavior link, and the above-mentioned first target account behavior link is any target behavior link among the above-mentioned multiple target account behavior links.

[0135] In one embodiment, before obtaining the above-mentioned target index system based on the above-mentioned current index system, the above-mentioned method further includes:

[0136] In the case that the semantic relevance between the second application event and the current indicator system is lower than the above-mentioned relevance threshold, new indicators are determined based on the second application event, and the current indicator system is updated; the second application event is an application event corresponding to a second account behavior, and the second account behavior is any account behavior other than the first account behavior in the first target account behavior link.

[0137] In one embodiment, before obtaining the target indicator system based on the current indicator system, the method further includes:

[0138] In the case that the semantic relevance between the third application event and the current indicator system is lower than the above-mentioned relevance threshold, new indicators are determined based on the third application event, and the current indicator system is updated; the third application event is an application event corresponding to a third account behavior, and the third account behavior is any account behavior in a second target account behavior link, and the second target behavior link is any behavior link other than the first target behavior link among the multiple target account behavior links.

[0139] In one embodiment, before determining new indicators based on the first application event, updating the basic indicator system, and obtaining the current indicator system, the method further includes:

[0140] Semantic similarity calculations are respectively performed between the first application event and each indicator of the basic indicator system to obtain a similarity value corresponding to each indicator;

[0141] In the case that all the above similarity values are lower than the above-mentioned relevance threshold, it is determined that the semantic relevance between the first application event and the basic indicator system is lower than the above-mentioned relevance threshold.

[0142] In one embodiment, any of the above account behavior data includes a time point and an account behavior entry corresponding to the time point, and the above-mentioned account behavior link analysis based on the application data to obtain multiple target account behavior links includes:

[0143] For any account behavior sequence, the account behavior data in the account behavior sequence is divided based on a time interval to obtain multiple account behavior subsequences;

[0144] Cluster all the above account behavior subsequences to obtain multiple clusters, and determine the account behavior subsequence corresponding to the center of each cluster as the center sequence;

[0145] The link formed by the events corresponding to the account behavior entries of the above center sequence is used as the above target account behavior link.

[0146] In one embodiment, clustering all the above-mentioned account behavior subsequences to obtain multiple clusters, including:

[0147] For each of the above-mentioned account behavior data, extract the account behavior performance characteristics associated with the corresponding time point;

[0148] According to the above-mentioned account behavior performance characteristics, obtain the sequence performance characteristics corresponding to each of the above-mentioned account behavior subsequences;

[0149] Based on the above-mentioned sequence performance characteristics, perform clustering of the account behavior subsequences to obtain the above-mentioned multiple clusters.

[0150] Optionally, the computer-readable storage medium may include: ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drives), or optical discs, etc. Among them, the random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0151] In an exemplary embodiment, a computer program product or a computer program is further provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned application data processing method.

[0152] It should be understood that "a plurality of" mentioned herein refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the front and rear associated objects. In addition, the step numbers described in this article only exemplarily show a possible execution sequence between steps. In some other embodiments, the above steps may not be executed in the order of the numbers. For example, two steps with different numbers are executed simultaneously, or two steps with different numbers are executed in the reverse order of the illustration. The embodiments of the present application do not limit this.

[0153] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0154] In addition, in the specific implementation manners of the present application, for data related to user information, etc., when the above embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of the relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0155] The above are only exemplary embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for processing application data, characterized in that, The method includes: Displaying a first page for uploading a basic indicator system, where the basic indicator system is a system formed by indicators for quantifying the execution of a target service by a target application, and the directional relationship between the indicators in the basic indicator system matches the execution link of relevant events in the target service; When an indicator system generation instruction is obtained, displaying a second page for presenting a target indicator system, where the target indicator system is an indicator system corresponding to a target scenario in the target service and is an indicator system obtained by correcting the basic indicator system based on application data; Wherein, the application data represents data obtained by collecting information generated during the operation of the target application in the target scenario.

2. The method according to claim 1, characterized in that, The displaying of the second page includes: Displaying the relationship between the indicators of the target indicator system, where the relationship between the indicators is a graph relationship or a link relationship; Displaying the execution link of a target event, where the target event is an event associated with the indicators in the target indicator system.

3. The method according to claim 1 or 2, characterized in that, The application data includes account behavior sequences corresponding to multiple accounts, and any one of the account behavior sequences is composed of account behavior data collected in chronological order. The target indicator system is generated by the following method: Performing account behavior link analysis based on the application data to obtain multiple target account behavior links, where the target account behavior links are account behavior links whose occurrence frequency meets a preset requirement; When the semantic relevance between a first application event and the basic indicator system is lower than a relevance threshold, determining new indicators based on the first application event and updating the basic indicator system to obtain a current indicator system; Based on the current indicator system, obtaining the target indicator system; Wherein, the first application event is an application event corresponding to a first account behavior, the first account behavior is any account behavior of a first target account behavior link, and the first target account behavior link is any one of the multiple target account behavior links.

4. The method according to claim 3, wherein Before obtaining the target indicator system based on the current indicator system, the method further includes: When the semantic relevance between a second application event and the current indicator system is lower than the relevance threshold, determining new indicators based on the second application event and updating the current indicator system; the second application event is an application event corresponding to a second account behavior, and the second account behavior is any account behavior other than the first account behavior in the first target account behavior link.

5. The method according to claim 4, wherein Before obtaining the target indicator system based on the current indicator system, the method further includes: In the case where the semantic relevance between the third application event and the current metric system is lower than the relevance threshold, new metrics are determined based on the third application event, and the current metric system is updated; the third application event is an application event corresponding to a third account behavior, and the third account behavior is any account behavior in the second target account behavior link, and the second target behavior link is any behavior link other than the first target behavior link among the multiple target account behavior links.

6. The method according to claim 3, characterized in that, Before determining new metrics based on the first application event, updating the basic metric system, and obtaining the current metric system, the method further includes: Performing semantic similarity calculation on the first application event and each metric of the basic metric system respectively to obtain a similarity value corresponding to each metric. In the case where each of the similarity values is lower than the relevance threshold, it is determined that the semantic relevance between the first application event and the basic metric system is lower than the relevance threshold.

7. The method according to claim 3, characterized in that, Any of the account behavior data includes a time point and an account behavior entry corresponding to the time point. The account behavior link analysis based on the application data to obtain multiple target account behavior links includes: For any account behavior sequence, dividing the account behavior data in the account behavior sequence based on a time interval to obtain multiple account behavior subsequences. Clustering all the account behavior subsequences to obtain multiple clusters, and determining the account behavior subsequence corresponding to the center of each cluster as the center sequence. Taking the link formed by the events corresponding to the account behavior entries of the center sequence as the target account behavior link.

8. The method according to claim 7, wherein The clustering of all the account behavior subsequences to obtain multiple clusters includes: For each of the account behavior data, extracting the account behavior performance characteristics associated with the corresponding time point. According to each of the account behavior performance characteristics, obtaining the sequence performance characteristics corresponding to each of the account behavior subsequences. Performing clustering of the account behavior subsequences based on each of the sequence performance characteristics to obtain the multiple clusters.

9. An application data processing device, characterized in that, The device includes: A display module for displaying a first page, where the first page is used to upload a basic metric system, and the basic metric system is a system formed by metrics for quantifying the situation of a target application executing a target service, and the directional relationship between the metrics in the basic metric system matches the execution link of relevant events in the target service. An application data processing module for displaying a second page in the case of obtaining a metric system generation instruction, where the second page is used to display a target metric system, and the target metric system is a metric system corresponding to a target scenario in the target service, and the target metric system is a metric system obtained by correcting the basic metric system based on application data. Wherein, the application data represents data obtained by collecting information generated during the operation of the target application in the target scenario.

10. A computer device, characterized in that, The computer device includes a processor and a memory, and at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the application data processing method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, At least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the application data processing method according to any one of claims 1 to 8.

Images