A data processing method and apparatus

Abstract

The application provides a data processing method and device, wherein the method comprises: obtaining session behavior data of a target application; screening session behavior data associated with a target index from the session behavior data as target behavior data; decomposing the target behavior data into behavior data represented by a plurality of dimensional sub-rules; and adjusting the target behavior data corresponding to each sub-rule one by one to optimize the target index of the target application. Through the above scheme, the user abnormal behavior data is split into a plurality of dimensional sub-rules, so that each sub-rule can be optimized and adjusted, so that the application can be adjusted according to the direction of target index optimization, thereby realizing effective optimization of the application and improving the use rate of the application.

Description

Technical Field

[0001] This application belongs to the field of electronic digital data processing technology, and in particular relates to a data processing method and apparatus. Background Technology

[0002] With the continuous development of internet technology, various mobile applications have begun to appear in people's lives. For application providers, the goal is to increase application usage through promotion and improved user experience. This requires continuous optimization of the application.

[0003] Currently, no effective solution has been proposed for how to optimize the application. Summary of the Invention

[0004] The purpose of this application is to provide a data processing method and apparatus that can improve the utilization rate of applications, thereby achieving efficient optimization of applications.

[0005] This application provides a data processing method and apparatus implemented as follows:

[0006] A data processing method, the method comprising:

[0007] Obtain session behavior data of the target application;

[0008] Filter out the conversation behavior data that is associated with the target metric from the conversation behavior data, and use it as the target behavior data;

[0009] The target behavior data is broken down into behavior data represented by sub-rules of multiple dimensions;

[0010] Adjustments are made one by one according to the adjustment behavior data corresponding to each sub-rule in order to optimize the target indicators of the target application.

[0011] A data processing method, the method comprising:

[0012] Obtain conversational behavior data for prescription drug inquiry form completion;

[0013] From the prescription drug inquiry and form filling session behavior data, session behavior data associated with negative bounce rate are filtered out as target behavior data;

[0014] The target behavior data is broken down into behavior data represented by sub-rules of multiple dimensions;

[0015] Adjustments are made one by one according to the adjustment behavior data corresponding to each sub-rule in order to optimize the negative bounce rate of the target application.

[0016] A data processing apparatus, comprising:

[0017] The acquisition module is used to acquire session behavior data of the target application;

[0018] The filtering module is used to filter out the session behavior data that is associated with the target metric from the session behavior data, and use it as the target behavior data;

[0019] The decomposition module is used to decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions;

[0020] The adjustment module is used to adjust the target indicators of the target application one by one according to the adjustment behavior data corresponding to each sub-rule.

[0021] An electronic device includes a processor and a memory for storing processor-executable instructions, wherein the processor executes the instructions as described in the steps of the method above.

[0022] A computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0023] The data processing method and apparatus provided in this application acquire session behavior data associated with target indicators, and then decompose and analyze the data to form behavioral data represented by sub-rules in multiple dimensions. Because the abnormal behavior data is decomposed into sub-rules in multiple dimensions, optimization and adjustment can be made based on each sub-rule, so that the application can be adjusted in the direction of target indicator optimization, thereby achieving effective optimization of the application and improving the application's usage rate. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the architecture of one embodiment of the data processing system provided in this application;

[0026] Figure 2 This is a logical diagram of the application optimization process provided in this application;

[0027] Figure 3 This is a logical diagram illustrating the determination of abnormal behavior indicators by application indicators, provided in this application.

[0028] Figure 4 This is a schematic diagram illustrating the breakdown of the negative bounce rate provided in this application;

[0029] Figure 5 This is a flowchart of one embodiment of the data processing method provided in this application;

[0030] Figure 6 This is a hardware structure block diagram of an electronic device for a data processing method provided in this application;

[0031] Figure 7 This is a schematic diagram of the module structure of one embodiment of the data processing device provided in this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0033] Considering the issue of user engagement retention for various applications—for example, if a user quits midway, the session is often interrupted—if this situation is not addressed, it will lead to a decrease in application usage. To optimize the application, improve user experience, and increase usage, this example provides a data processing system to achieve application optimization and updates. For example... Figure 1 As shown, this example provides a data processing system that may include: multiple user terminals 101 (101-1, 101-2, 101-3), a server 102, a memory 103, and an analysis processor 104.

[0034] The aforementioned user terminal 101 can be a terminal device or software used by a customer. Specifically, the user terminal can be a smartphone, tablet, laptop, desktop computer, smartwatch, or other wearable device. Of course, the user terminal can also be software that can run on the aforementioned terminal devices.

[0035] For users, user terminal 101 can call the target application from server 102 and perform operations on the target application. Each user operation can be stored as a user session in memory 103. In this way, the operation actions of multiple users on the target application can be stored in memory 103, thereby storing multiple session data. Analysis processor 104 can perform anomaly analysis on the application based on the session data, thereby breaking down the abnormal session data into sub-rules of multiple dimensions and setting adjustment schemes for each sub-rule. The adjustment schemes are then applied to the target application one by one, and the application indicators are observed to see if the target application's performance is optimized after the adjustment schemes are applied, thereby achieving gradual optimization of the application.

[0036] In other words, to improve application conversion rates, the analysis processor 104 can analyze user behavior data to optimize the application, thereby improving the user experience and enhancing the performance metrics of various application components. Specifically, based on user behavior data analysis, problems within the application can be accurately identified, allowing for targeted solutions and improved application iteration efficiency. For example, session behavior data of the target application can be acquired; session behavior data associated with target metrics can be filtered from this data as target behavior data. The target metrics can be abnormal behavior metrics, and the associated session behavior data can be abnormal behavior data. For instance, taking the negative bounce rate as an abnormal behavior metric, which refers to the percentage of users who leave without any clicks or input, the corresponding associated abnormal behavior data would be: session data from the target application's session data that shows users leaving without any clicks or input. After obtaining this abnormal behavior data, the behavior data can be decomposed into multiple dimensions, thereby breaking it down into behavior data represented by sub-rules of multiple dimensions. Then, the behavior data corresponding to each sub-rule is adjusted one by one to optimize the target indicators of the target application.

[0037] In this example, the target session behavior data (i.e., abnormal behavior data) can be integrated according to the time sequence of user execution to obtain the operation path of each user; then, the operation path of each user is jointly decomposed to obtain sub-rules of each dimension under multiple dimensions; the sub-rules under each dimension are accumulated to serve as the behavior data represented by the sub-rules of multiple dimensions obtained from the decomposition.

[0038] The aforementioned dimensions can include: ability, motivation, and cue. Ability refers to the capacity to fulfill a motivation, such as time, financial resources, physical strength, or mental capacity. Motivation represents the user's level of willingness, such as feelings, expectations, and mental states. Cue represents the trigger point that prompts the user to take action, such as getting up when the alarm rings. Accordingly, in this example, motivation can represent attraction, ability can represent the capacity to fulfill the motivation, and cue can represent the trigger for action.

[0039] That is, the target session behavior data (B) can be represented by three dimensions: ability (A), motivation (M), and cue (T). Therefore, the user behavior model can be expressed as: B = MAT. In this example, the user's abnormal behavior (B1) is broken down into multiple ability sub-rules, motivation sub-rules, and cue sub-rules. Correspondingly, the abnormal behavior data can be represented as:

[0040]

[0041] Where B1 represents abnormal behavior data, A k Represents capability sub-rules, M k Indicates the motivational sub-rule, T k The sub-rules are: x represents the number of capability sub-rules, y represents the number of motivation sub-rules, and z represents the number of prompt sub-rules.

[0042] Because the abnormal behavior data is broken down into a set of multiple sub-rules, it is only necessary to set the corresponding adjustment plan for each sub-rule to investigate and handle the causes of abnormal behavior, thereby improving the target application's metrics and optimizing the application.

[0043] Specifically, the aforementioned target metrics can be determined as follows: First, obtain application metrics. Then, through drill-down analysis of these application metrics, identify anomalous behavioral metrics and use these identified anomalous behavioral metrics as the target metrics. For example, the application metric could be the abandonment rate, where the abandonment rate refers to the percentage of users who abandon their operation and leave the site. Through drill-down analysis, the anomalous behavioral metric could be identified as the negative bounce rate, where the negative bounce rate is the percentage of users who leave the site without clicking or inputting any data. Therefore, the negative bounce rate identified through drill-down analysis would be used as the target metric.

[0044] When filtering conversation behavior data that is associated with a target metric from conversation behavior data as target behavior data, the process can involve: obtaining the target metric; performing key item statistics on each conversation in the conversation behavior data; and selecting conversations whose key item statistics match the target metric as target behavior data. For example, if the target metric is the bounce rate, then any conversation data where the user did not click or input anything can be selected from the conversation behavior data as target behavior data.

[0045] The key items mentioned above may include, but are not limited to, at least one of the following: number of actions, duration of page stay, session start time, session end time, user's region, and user's device.

[0046] In practice, adjustments are made one by one according to the adjustment behavior data corresponding to each sub-rule to optimize the target metrics of the target application. This can be done by retrieving the adjustment behavior data that has been pre-set for each sub-rule; applying the adjustment behavior data to the target application one by one and obtaining the session behavior data of the target application to which the adjustment behavior data has been applied; and determining whether the target metrics have been optimized based on the session behavior data of the target application to which the adjustment behavior data has been applied.

[0047] For example, such as Figure 2 As shown, the application optimization process can involve acquiring application metrics, then performing drill-down session analysis to identify anomalous behavior metrics. Session data related to these metrics is obtained through behavior replication and designated as anomalous behavior data. This anomalous behavior data is then divided into x capability sub-rules, y motivation sub-rules, and z prompt sub-rules. Solutions can then be set for each of these sub-rules. The solutions are then deployed online, and it is further determined whether the target metric (e.g., bounce rate) decreases after applying the solution. If it does decrease, the corresponding sub-rule and solution are considered effective optimization instances.

[0048] Taking the target metric of bounce rate as an example, motivation can be the attraction of users, such as the attractiveness of the text content in the application, the psychological cues of color, etc. Capabilities can be providing richer user-operable capabilities, such as expanding the range of interactive elements, making it easier for users to click or input, and providing timely feedback on user clicks and inputs. Tips can be timely and effective reminders to users in key scenarios, such as strong pop-up reminders, SMS message reminders, etc.

[0049] In the example above, abnormal user behavior was broken down into multiple sub-rules from the perspectives of ability, motivation, and prompts. Each sub-rule then corresponds to a specific ability characteristic, motivation characteristic, or display characteristic as a solution. Each characteristic is then applied one by one to the corresponding application implementation plan to optimize the application. During application implementation, this process can in turn influence the behavior analysis process, allowing us to observe changes in application metrics and abnormal behavior metrics after the application solution is implemented, thus forming a closed loop for application optimization. In other words, by combining user behavior analysis with behavior metric data analysis to optimize the application, each analysis of behavior data can effectively optimize application performance.

[0050] When implementing this approach, combining user behavior analysis with behavioral metric data analysis to optimize the application can include the following steps:

[0051] S1: Behavioral Analysis

[0052] Starting with application metrics, feature mining of user behavior is performed, and drill-down analysis of application metrics based on user behavior data is conducted to identify abnormal behavior indicators. Specifically, this may include:

[0053] 1) Session Analysis: By calculating key information of each session in the target application or a specific function of the target application (e.g., number of actions in the session, page dwell time, user's location, user's device, etc.), a list of valuable sessions under the application metrics is compiled; that is, all user actions on the target page are counted.

[0054] 2) Reproduce user behavior. Specifically, you can display a list of user behavior logs in chronological order as the key path for drill-down analysis; that is, summarize the behavior process of each individual user.

[0055] 3) Drill-down analysis: Abnormal user behavior is identified by behavioral replication, thereby determining abnormal behavior indicators.

[0056] S2: Behavioral Model Rule Design:

[0057] Using identified abnormal behavior indicators as input, user behavior is decomposed to determine the corresponding capability sub-rules, motivation sub-rules, and prompt sub-rules, and a solution is set for each sub-rule.

[0058] That is, the target session behavior data (B) can be represented by three dimensions: ability (A), motivation (M), and cue (T). Therefore, the user behavior model can be expressed as: B = MAT. In this example, the user's abnormal behavior (B1) is broken down into multiple ability sub-rules, motivation sub-rules, and cue sub-rules. Correspondingly, the abnormal behavior data can be represented as:

[0059]

[0060] Where B1 represents abnormal behavior data, A k Represents capability sub-rules, M k Indicates the motivational sub-rule, T k The sub-rules are: x represents the number of capability sub-rules, y represents the number of motivation sub-rules, and z represents the number of prompt sub-rules.

[0061] For example, such as Figure 3 As shown, the applied metric is the abandonment rate (i.e., the percentage of users who abandon their operation and leave). Analysis reveals that the abandonment rate corresponds to: frustrated bounce rate (i.e., the percentage of sessions that ultimately bounce after clicking submit), abandoned bounce rate after attempting to fill in information (i.e., the percentage of sessions that filled in information but did not submit), abandoned bounce rate after attempting to click (i.e., the percentage of sessions that clicked but did not submit), and negative bounce rate (i.e., the percentage of users who abandon their operation without clicking or inputting anything). Drill-down analysis determined that among these bounce rates, the negative bounce rate is an indicator of abnormal behavior.

[0062] Then, based on the model, the abnormal behavior data is broken down into three dimensions: "motivation," "ability," and "cues," resulting in multiple sub-rules. A corresponding solution is then set for each sub-rule, for example: Figure 4 As shown, the negative bounce rate can be broken down as follows:

[0063] 1) Motivational sub-rules and their corresponding solutions:

[0064] [Prompt Text Rules]: The page prompt text should read "Please fill in your medication information";

[0065] [Placeholder Rules]: Add text information for name placeholders;

[0066] [Background Color Rule]: Set the page background color to red;

[0067] 2) Capability sub-rules and their corresponding solutions:

[0068] [Clickable Sub-rules for Areas]: The "Confirm Medication Use" form items are now clickable;

[0069] [Interactive Validation Sub-rule]: Set up interactive validation for errors in the "ID Card" form field;

[0070] 3) Prompt for some rules and solutions for each sub-rule:

[0071] [Pop-up Notification Rules]: Set up pop-up notifications for verification errors.

[0072] S3: Application Practice Process:

[0073] In the process of application practice, corresponding solutions were designed for "motivation sub-rules", "ability sub-rules" and "hint sub-rules" respectively. After going online, the impact on the abnormal behavior indicator "abandonment rate" was observed. If the abandonment rate was reduced, then the corresponding sub-rules and solutions were determined to be effective application practice solutions.

[0074] That is, the solution is applied to the application practice process, and then it is fed back into the behavior analysis process, so that the changes in the corresponding application indicators and abnormal behavior indicators can be observed, thus forming an application closed loop.

[0075] The example above illustrates the scenario of filling out a form during a medical consultation. However, it is worth noting that this is only an illustrative representation. In actual implementation, it can be applied to other scenarios to optimize other application metrics and achieve effective application optimization.

[0076] Figure 5 This is a flowchart of one embodiment of the data processing method provided in this application. Although this application provides method operation steps or apparatus structures as shown in the following embodiments or figures, more or fewer operation steps or module units may be included in the method or apparatus based on conventional or non-inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure described in the embodiments and figures of this application. When the method or module structure is applied in actual devices or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0077] Specifically, such as Figure 5 As shown, the data processing method described above may include the following steps:

[0078] Step 501: Obtain session behavior data of the target application;

[0079] Specifically, session behavior data can be obtained from user behavior logs.

[0080] Step 502: Filter out the conversation behavior data that is associated with the target metric from the conversation behavior data, and use it as the target behavior data;

[0081] When filtering, you can obtain key information from the session data and then select valuable session behavior data under the target metric as the target behavior data.

[0082] For example, a target metric can be obtained, and then key item statistics can be performed on each session in the session behavior data; sessions whose key item statistics match the target metric are used as target behavior data. The key items may include, but are not limited to, at least one of the following: number of behavioral operations, page dwell time, session start time, session end time, user's location, and the device used by the user.

[0083] The determination of the target metric can be achieved by acquiring application metrics, performing drill-down analysis on these metrics to identify anomalous behavior indicators, and then using these identified anomalous behavior indicators as the target metric. For example, the application metric could be the abandonment rate, where the abandonment rate refers to the percentage of users who abandon their interaction and leave the platform. Through drill-down analysis, the anomalous behavior indicator could be identified as the negative bounce rate, where the negative bounce rate is the percentage of users who leave the platform without clicking or inputting any data. Therefore, the negative bounce rate identified through drill-down analysis can be used as the target metric. Correspondingly, session behavior data that is valuable for the negative bounce rate metric can be acquired as the target behavior data.

[0084] Step 503: Decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions;

[0085] In implementation, the target session behavior data can be integrated according to the user's execution time sequence to obtain each user's operation path; the operation paths of each user can be jointly decomposed to obtain sub-rules for each dimension; and the sub-rules under each dimension can be accumulated to obtain the behavioral data represented by the decomposed sub-rules of multiple dimensions. Dimensions can include: representing the motivation of attraction, representing the ability to complete the motivation, and representing the prompts that trigger the action. Each dimension can correspond to one or more sub-rules, and the decomposition result is obtained by accumulating the sub-rules.

[0086] For example, if abnormal behavior data is divided into x capability sub-rules, y motivation sub-rules, and z prompt sub-rules, then solutions can be set for each of these sub-rules. Next, the solutions are deployed online, and it is further determined whether the target metrics have improved after applying the solutions, thus confirming whether the sub-rules and solutions are effective optimization instances.

[0087] Step 504: Adjust the behavior data corresponding to each sub-rule one by one to optimize the target indicators of the target application.

[0088] Specifically, the system can retrieve the adjustment behavior data that has been pre-set for each sub-rule; apply the adjustment behavior data to the target application one by one, and obtain the session behavior data of the target application to which the adjustment behavior data has been applied; and determine whether the target metric has been optimized based on the session behavior data of the target application to which the adjustment behavior data has been applied.

[0089] This example also provides a data processing method for optimizing the online consultation and form filling process, which may include:

[0090] S1: Obtain conversational behavior data for prescription drug inquiry form filling;

[0091] S2: Filter out the conversation behavior data associated with the negative bounce rate from the prescription drug inquiry form filling conversation behavior data, and use it as the target behavior data;

[0092] S3: Decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions;

[0093] S4: Adjust the behavior data corresponding to each sub-rule one by one to optimize the negative bounce rate of the target application.

[0094] The methods and embodiments provided in the above-described embodiments of this application can be executed in a mobile terminal, computer terminal, or similar computing device. Taking operation on an electronic device as an example... Figure 6 This is a hardware structure block diagram of an electronic device for a data processing method provided in this application. (See diagram for example.) Figure 6 As shown, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (processors 02 may include, but are not limited to, processing devices such as microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 04 for storing data, and a transmission module 06 for communication functions. Those skilled in the art will understand that... Figure 6 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, electronic device 10 may also include... Figure 6 The more or fewer components shown, or having the same Figure 6 The different configurations shown.

[0095] The memory 04 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the data processing method in this embodiment. The processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, thereby implementing the data processing method of the application described above. The memory 04 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 04 may further include memory remotely located relative to the processor 02, and these remote memories can be connected to the electronic device 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0096] The transmission module 06 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 10. In one example, the transmission module 06 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 06 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0097] At the software level, data processing devices can be like... Figure 7 As shown, it includes:

[0098] The acquisition module 701 is used to acquire session behavior data of the target application;

[0099] The filtering module 702 is used to filter out the session behavior data associated with the target indicator from the session behavior data, and use it as the target behavior data;

[0100] The decomposition module 703 is used to decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions;

[0101] The adjustment module 704 is used to adjust the target indicators of the target application one by one according to the adjustment behavior data corresponding to each sub-rule.

[0102] In one implementation, the data processing device may obtain application metrics before filtering out session behavior data associated with the target metric from the session behavior data and using it as the target behavior data; perform drill-down analysis on the application metrics to identify abnormal behavior metrics; and use the identified abnormal behavior metrics as the target metric.

[0103] In one implementation, the decomposition module 703 can be specifically used to integrate the target session behavior data according to the time sequence of user execution to obtain the operation path of each user; to jointly decompose the operation path of each user to obtain sub-rules of each dimension under multiple dimensions; and to accumulate the sub-rules under each dimension as the behavior data represented by the sub-rules of the multiple dimensions obtained by decomposition.

[0104] In one implementation, the multiple dimensions may include: motivations that characterize attraction, abilities that characterize the motivation to complete, and cues that characterize action triggers.

[0105] In one embodiment, the filtering module 702 can be specifically used to obtain target indicators; perform key item statistics on each session in the session behavior data; and take the sessions whose key item statistics results match the target indicators as target behavior data.

[0106] In one implementation, the aforementioned key items may include, but are not limited to, at least one of the following: number of actions, page dwell time, session start time, session end time, user's region, and user's device.

[0107] In one implementation, the adjustment module 704 can be specifically used to retrieve adjustment behavior data pre-set for each sub-rule; apply the adjustment behavior data to the target application one by one, and obtain the session behavior data of the target application to which the adjustment behavior data has been applied; and determine whether the target metric has been optimized based on the session behavior data of the target application to which the adjustment behavior data has been applied.

[0108] This example also provides a data processing device for optimizing the application process of online prescription drug inquiry and form filling. It may include: an acquisition module for acquiring session behavior data of prescription drug inquiry and form filling; a filtering module for filtering session behavior data associated with negative bounce rate from the prescription drug inquiry and form filling session behavior data as target behavior data; a decomposition module for decomposing the target behavior data into behavior data characterized by sub-rules of multiple dimensions; and an adjustment module for adjusting the behavior data according to each sub-rule to optimize the negative bounce rate of the target application.

[0109] This application also provides a specific implementation of an electronic device capable of implementing all steps of the data processing method in the above embodiments. The electronic device specifically includes: a processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the processor is used to call a computer program in the memory, and when the processor executes the computer program, it implements all steps of the data processing method in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0110] Step 1: Obtain session behavior data of the target application;

[0111] Step 2: Filter out the conversation behavior data that is associated with the target metric from the conversation behavior data, and use it as the target behavior data;

[0112] Step 3: Decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions;

[0113] Step 4: Adjust the behavior data corresponding to each sub-rule one by one to optimize the target indicators of the target application.

[0114] As can be seen from the above description, the embodiments of this application obtain session behavior data associated with the target indicator, and then decompose and analyze the data to form behavior data represented by sub-rules in multiple dimensions. Because the abnormal behavior data is decomposed into sub-rules in multiple dimensions, optimization and adjustment can be made based on each sub-rule, so that the application can be adjusted in the direction of target indicator optimization, thereby achieving effective optimization of the application and improving the application's usage rate.

[0115] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the data processing method in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the data processing method in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0116] Step 1: Obtain session behavior data of the target application;

[0117] Step 2: Filter out the conversation behavior data that is associated with the target metric from the conversation behavior data, and use it as the target behavior data;

[0118] Step 3: Decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions;

[0119] Step 4: Adjust the behavior data corresponding to each sub-rule one by one to optimize the target indicators of the target application.

[0120] As can be seen from the above description, the embodiments of this application obtain session behavior data associated with the target indicator, and then decompose and analyze the data to form behavior data represented by sub-rules in multiple dimensions. Because the abnormal behavior data is decomposed into sub-rules in multiple dimensions, optimization and adjustment can be made based on each sub-rule, so that the application can be adjusted in the direction of target indicator optimization, thereby achieving effective optimization of the application and improving the application's usage rate.

[0121] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0122] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0123] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0124] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, an in-vehicle human-machine interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0125] While this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or end product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded.

[0126] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0127] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0128] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0132] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0133] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0134] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0136] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0137] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A data processing method, characterized in that, The method includes: Obtain session behavior data of the target application; Filter out the conversation behavior data that is associated with the target metric from the conversation behavior data, and use it as the target behavior data; The target behavior data is decomposed into behavior data represented by sub-rules of multiple dimensions, including: integrating the target session behavior data according to the time sequence of user execution to obtain the operation path of each user; jointly decomposing the operation path of each user to obtain sub-rules of each dimension; and accumulating the sub-rules of each dimension as the behavior data represented by the decomposed sub-rules of multiple dimensions; wherein, the multiple dimensions include: motivation representing attraction, ability representing completion motivation, and prompts representing action triggers; The adjustment behavior data corresponding to each sub-rule is adjusted one by one to optimize the target metrics of the target application. This includes: retrieving the adjustment behavior data that has been pre-set for each sub-rule; applying the adjustment behavior data to the target application one by one and obtaining the session behavior data of the target application to which the adjustment behavior data has been applied; and determining whether the target metrics have been optimized based on the session behavior data of the target application to which the adjustment behavior data has been applied.

2. The method according to claim 1, characterized in that, Before filtering out the session behavior data associated with the target metric from the session behavior data, the process further includes: Obtain application metrics; Drill down the application metrics to identify abnormal behavior indicators; The identified abnormal behavior indicators will be used as the target indicators.

3. The method according to claim 1, characterized in that, Filtering conversation behavior data that is associated with the target metric from the conversation behavior data, as the target behavior data, includes: Obtain target metrics; Perform key item statistics on each session in the aforementioned session behavior data; Sessions that match the key statistical results with the target metrics are used as target behavior data.

4. The method according to claim 3, characterized in that, The key items include at least one of the following: number of actions, duration of page stay, session start time, session end time, user's region, and user's device.

5. A data processing method, characterized in that, The method includes: Obtain conversational behavior data for prescription drug inquiry form completion; From the prescription drug inquiry and form filling session behavior data, session behavior data associated with negative bounce rate are filtered out as target behavior data; The target behavior data is decomposed into behavior data represented by sub-rules across multiple dimensions, including: integrating the prescription drug inquiry and form-filling session behavior data according to the user's execution time sequence to obtain the operation path of each user; jointly decomposing the operation path of each user to obtain sub-rules for each dimension; and accumulating the sub-rules under each dimension to obtain the behavior data represented by the decomposed sub-rules across multiple dimensions; wherein, the multiple dimensions include: motivation representing attraction, ability representing completion motivation, and prompts representing action triggers; Adjustments are made one by one according to the adjustment behavior data corresponding to each sub-rule to optimize the negative bounce rate of the target application. This includes: retrieving the adjustment behavior data that has been pre-set for each sub-rule; applying the adjustment behavior data to the target application one by one and obtaining the session behavior data of the target application to which the adjustment behavior data has been applied; and determining whether the target metric has been optimized based on the session behavior data of the target application to which the adjustment behavior data has been applied.

6. A data processing apparatus, characterized in that, include: The acquisition module is used to acquire session behavior data of the target application; The filtering module is used to filter out the session behavior data that is associated with the target metric from the session behavior data, and use it as the target behavior data; The decomposition module is used to decompose the target behavior data into behavior data represented by sub-rules of multiple dimensions, including: integrating the target session behavior data according to the time sequence of user execution to obtain the operation path of each user; jointly decomposing the operation path of each user to obtain sub-rules of each dimension under multiple dimensions; and accumulating the sub-rules under each dimension as the behavior data represented by the decomposed sub-rules of multiple dimensions; wherein, the multiple dimensions include: motivation representing attraction, ability representing completion motivation, and prompts representing action triggers; The adjustment module is used to adjust the target metrics of the target application one by one according to the adjustment behavior data corresponding to each sub-rule. The adjustment module includes: retrieving the adjustment behavior data that has been set in advance for each sub-rule; applying the adjustment behavior data to the target application one by one and obtaining the session behavior data of the target application to which the adjustment behavior data has been applied; and determining whether the target metrics have been optimized based on the session behavior data of the target application to which the adjustment behavior data has been applied.

7. An electronic device comprising a processor and a memory for storing processor-executable instructions, characterized in that, When the processor executes the instructions, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1 to 4.

Images