Operation method and system based on data analysis

Abstract

The invention relates to the technical field of data processing, in particular to an operation method and system based on data analysis. According to the method, the use behavior data and the use feedback data of the user are obtained, the value label and the preference label are correspondingly distributed, the commercial value level and the scene preference of the user are accurately positioned, the problem that a single label cannot comprehensively describe user attributes is solved, and the user experience is improved. An accurate user data support which is more suitable for a scene is provided for a background operation system; in addition, a marketing strategy matched with the user can be output from the marketing strategy library according to the value label and the preference label, and a personalized function interface is displayed, so that related services are pushed in a targeted manner, the conflict emotion of the user is reduced, and the marketing conversion efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to an operational method and system based on data analysis. Background Technology

[0002] With the increasing prevalence of mobile work and outdoor travel, portable WiFi devices have become a core network dependency for users due to their portability and flexible data usage. Their backend operating systems, as the core carriers of service scheduling, user management, and monetization, directly determine user retention rates and device operational efficiency. Currently, the operational methods of portable WiFi backend systems suffer from significant technical flaws, making it difficult to balance the dual demands of "personalized service provision" and "commercial value conversion."

[0003] On the one hand, existing operating systems mostly formulate strategies based on single-dimensional data, lacking a refined segmentation of portable WiFi user attributes. Some systems rely solely on user device usage behavior data (such as data consumption, connection duration, package renewal frequency, and number of multi-device connections) to push data packages and value-added services (such as speed boosts and targeted data packages), while ignoring users' core preferences in portable WiFi usage scenarios (such as whether they care about roaming charges, whether they need data sharing functions, their preference for package validity periods, and their interface operation habits). This results in a mismatch between the pushed services and users' actual needs—for example, pushing annual packages to users who only need short-term emergency data, and pushing low-priced, speed-limited packages to users who value network speed stability, causing user resistance and significantly reducing the user experience. Other systems only focus on optimizing the interface based on user feedback data (such as feature complaints and satisfaction ratings), without identifying users' commercial value levels (such as high-frequency, high-data-consumption users, business users with a strong willingness to pay, and price-sensitive temporary users). This results in high-value users not receiving customized operations, and low-value users having a low return on marketing investment, failing to effectively stimulate consumption conversion.

[0004] On the other hand, existing systems lack scientific classification of user tags, making it difficult for a single tag system to simultaneously fulfill the dual functions of "contextual demand identification" and "commercial value judgment." Vague user tags fail to accurately depict the contextual preferences of portable WiFi users (such as a preference for daily rental packages in travel scenarios or a need for unlimited data packages in office scenarios), nor can they accurately define the user's commercial value (such as long-term renewal willingness and potential for paying for value-added services). This results in insufficient adaptability between marketing strategies and functional interfaces—either neglecting contextual preferences leads to a decline in user experience, or misjudging user value leads to a waste of marketing resources, ultimately resulting in a "disconnect between experience and conversion," making it difficult to achieve a win-win situation of improved user experience and increased business revenue. Summary of the Invention

[0005] In view of this, this application discloses an operation method based on data analysis. The method includes: acquiring user usage behavior data and user feedback data; assigning value tags to the user based on the usage behavior data; assigning preference tags to the user based on the user feedback data; outputting marketing strategies matching the user from a marketing strategy library based on the value tags and the preference tags; and displaying a functional interface matching the user's preferences to the user.

[0006] In some embodiments, the usage behavior data includes consumption behavior data, data usage data, login behavior data, and plan status data; assigning value tags to the user based on the usage behavior data includes: acquiring the user's consumption behavior data, data usage data, login behavior data, and plan status data; assigning a high-value user tag to the user when the consumption behavior data indicates that the consumption amount within a first preset time period is greater than a first threshold, or when the data usage data indicates that the total data usage is greater than a second threshold; assigning a churn risk user tag to the user when the login behavior data indicates that the interval between two consecutive logins is greater than a third threshold, or when the plan status data indicates that the plan has expired for a longer period than a fourth threshold; and assigning a new user tag to the user when the login behavior data indicates that the time elapsed since the first login is less than a fifth threshold.

[0007] In some embodiments, the feedback data includes log data, work order data, plan change records, search data, login data, and core function usage data; assigning preference tags to the user based on the usage feedback data includes: obtaining the user's log data, work order data, plan change records, search data, login data, and core function usage data; assigning a network speed sensitive tag to the user when the log data indicates that the number of times the network diagnostic function is used within a second preset time period is greater than a sixth threshold, or when the work order data indicates that a slow network speed problem has been reported; assigning a large data tag to the user when the plan change records indicate that the number of times a larger data plan is selected is greater than a seventh threshold, or when excessive data-intensive keywords are searched; assigning a light user tag to the user when the login data indicates that the number of logins within a third preset time period is less than an eighth threshold and the number of times the core function is used is less than a ninth threshold.

[0008] In some embodiments, the step of outputting a marketing strategy matching the user from a marketing strategy library based on the value tag and the preference tag, and displaying a functional interface matching the user's preferences to the user, includes: obtaining a pre-maintained tag-strategy correspondence table; obtaining the marketing strategy corresponding to the value tag and the preference tag from the correspondence table; generating a marketing strategy display control based on the marketing strategy; and combining the marketing strategy display control with inherent interface controls to generate a functional interface for display to the user.

[0009] In some embodiments, the method further includes: constructing a conversion funnel; the conversion funnel includes key steps that prevent users from completing conversions in each operational step from activating the device to completing the first recharge; analyzing the root causes in the key steps; and outputting the key steps and the root causes.

[0010] In some embodiments, the steps from activating the device to completing the first top-up include: powering on; connecting to the network; downloading the App; logging into the App; entering the authentication page; submitting ID card information; facial recognition; authentication result returned; viewing the package; selecting a package; selecting a payment method; initiating payment; and successful payment.

[0011] In some embodiments, constructing the conversion funnel includes: pre-setting embedding points for each operation step; counting the number of first users entering the operation step and the number of second users completing the operation step; and identifying operation steps where the ratio of the number of second users to the number of first users is lower than a ratio threshold as key steps.

[0012] In some embodiments, analyzing the root causes in the critical steps includes: obtaining operation logs for the critical steps; parsing the operation logs to determine the number of operations performed by the user in the critical steps; and identifying operations with a number of operations greater than an operation threshold as root causes.

[0013] This application discloses an operation system based on data analysis. The system includes: an acquisition module for acquiring user behavior data and user feedback data; a first allocation module for assigning value tags to the user based on the usage behavior data; a second allocation module for assigning preference tags to the user based on the user feedback data; and an output module for outputting marketing strategies matching the user from a marketing strategy library based on the value tags and the preference tags, and displaying a functional interface matching the user's preferences to the user.

[0014] In some embodiments, the system further includes a root cause analysis module for: constructing a conversion funnel; the conversion funnel includes key steps that prevent users from completing conversions in each operational step from activating the device to completing the first recharge; analyzing the root causes in the key steps; and outputting the key steps and the root causes.

[0015] In the solutions described in any of the foregoing embodiments, value tags and preference tags can be assigned respectively by acquiring user behavior data and user feedback data. This accurately identifies the user's commercial value level and scenario-based preferences, solving the problem that a single tag cannot fully characterize user attributes and providing more accurate user data support for the back-end operation system. Furthermore, by outputting marketing strategies that match the user from the marketing strategy library based on value tags and preference tags and displaying personalized functional interfaces, relevant services can be pushed in a targeted manner, reducing user resistance and improving marketing conversion efficiency.

[0016] It should be understood that the general description above and the detailed description below are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in one or more embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in one or more embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] The accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below.

[0019] Figure 1 This application illustrates a flowchart of a data analysis-based operational method.

[0020] Figure 2 This is a schematic diagram illustrating a method for analyzing root causes, as described in this application.

[0021] Figure 3 This is a flowchart illustrating the method for constructing a transformation funnel.

[0022] Figure 4 This is a schematic diagram of the method for analyzing root causes in this application.

[0023] Figure 5 This is a schematic diagram illustrating the structure of a data analysis-based operating system as described in this application. Detailed Implementation

[0024] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0025] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items. It should also be understood that the word “if” as used herein, depending on the context, can be interpreted as “when,” “in response to a determination,” or “when…”.

[0026] In view of this, this application proposes an operational method based on data analysis. This method can acquire user behavior data and user feedback data, and assign corresponding value tags and preference tags. This accurately identifies the user's commercial value level and contextual preferences, solving the problem that a single tag cannot comprehensively characterize user attributes, and providing the backend operation system with more precise user data support tailored to specific scenarios. Furthermore, it can output marketing strategies matching users from a marketing strategy library based on value tags and preference tags, and display personalized functional interfaces, thereby targetedly pushing relevant services, reducing user resistance, and improving marketing conversion efficiency.

[0027] The following describes the embodiments in conjunction with the accompanying drawings.

[0028] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating a data analysis-based operational method according to this application. Figure 1 As shown, the method may include steps S102-S108. This method can be applied to terminal devices, such as mobile phones, PDAs, laptops, tablets, servers, etc. The following explanation uses a portable WiFi backend operation system as an example.

[0029] S102, Obtain user behavior data and user feedback data.

[0030] The usage behavior data refers to the objective operation records generated by users when using portable WiFi devices, which can reflect users' spending power, usage frequency, and package status.

[0031] In some embodiments, the usage behavior data may include consumption behavior data, such as user consumption records in the portable WiFi service, including recharge amount, consumption frequency, and payment method. For example, a user recharges 200 yuan within a first preset period (30 days) and has a fixed monthly consumption of 150 yuan. Data usage data includes records of data consumption generated by the user using the portable WiFi service, such as total data usage, average daily data usage, and data consumption rate. For example, a user has a total data usage of 100GB and an average daily data usage of 3.3GB within 30 days. Login behavior data includes records of the user logging into the portable WiFi service platform (APP / mini-program), such as login time, login frequency, and interval between adjacent logins. For example, a user has logged in 5 times in the last 7 days, with the longest interval between two adjacent logins being 3 days. Package status data includes information related to the user's current and historical packages, such as package type, package validity period, and package expiration time. For example, a user is currently using an unlimited data package, and the previous package expired 2 days ago.

[0032] The aforementioned user feedback data refers to subjective data provided by users through various channels that reflects their service preferences and user experience, and can reveal users' core needs and pain points.

[0033] In some embodiments, the usage feedback data may include log data, user function usage traces recorded by the portable WiFi service platform, such as the number of times core functions are called and operation paths. For example, using the network diagnostic function 8 times in 30 days. Work order data, records of user-submitted complaints and inquiries, such as problem descriptions and request content. For example, submitting a work order to report "slow internet speed when roaming in other locations". Package change records, historical records of user adjustments to package types, such as package upgrades / downgrades and package change frequency. For example, upgrading from a 10GB package to a 20GB package 3 times in six months. Search data, records of user search keywords within the service platform. For example, searching for "large data monthly package" or "unlimited speed package". Login data, consistent with the "login behavior data" in usage behavior data, used here to help determine the depth of user usage. Core function usage data: records of user usage of the portable WiFi's core functions (such as data usage query, package renewal, and device management). For example, using the data usage query function 2 times in 30 days and not using other core functions besides package renewal.

[0034] In S102, usage behavior data can be automatically collected through the portable WiFi device hardware statistics module and background service logs without user intervention; usage feedback data can be automatically or manually collected through channels such as the work order system, platform search logs, function usage logs, and user feedback entry points.

[0035] This step involves collecting objective and quantifiable usage behavior data and user feedback data reflecting subjective preferences through the portable WiFi backend operation system. This provides a standardized and actionable data source for the subsequent allocation of value tags and preference tags, ensuring that the tag classification is consistent with the user's actual attributes and needs.

[0036] S104, assign value tags to the user based on the usage behavior data.

[0037] This step can analyze the usage behavior data collected by S102 according to preset quantification rules and assign corresponding value tags to users.

[0038] In some embodiments, the usage behavior data includes consumption behavior data, data usage data, login behavior data, and plan status data. Assigning value tags to the user based on the usage behavior data includes: Acquire user consumption behavior data, data usage data, login behavior data, and plan status data; If the consumption behavior data indicates that the consumption amount exceeds a first threshold within a first preset time period, or if the traffic usage data indicates that the total traffic exceeds a second threshold, a high-value user tag is assigned to the user. If the login behavior data indicates that the interval between two consecutive logins is greater than a third threshold, or if the package status data indicates that the package has expired for a longer period than a fourth threshold, a churn risk user label will be assigned to the user. If the login behavior data indicates that the time elapsed since the first login is less than a fifth threshold, a new user tag is assigned to the user.

[0039] The above thresholds and time periods are values ​​set according to business needs, and this application does not impose any special limitations. The following are merely illustrative examples.

[0040] The value tag can be a business value identifier based on user behavior data. It can be divided into high-value user tags, churn-risk user tags, and new user tags, which are used to distinguish the user's business contribution and operational priority to the portable WiFi operation.

[0041] The high-value user tag refers to users with strong spending power and high data usage demand. The allocation rule is "spending amount within a first preset period exceeds a first threshold" or "data usage data indicates total data usage exceeds a second threshold". The first preset period and the first and second thresholds are preset values. For example, if the first preset period is 30 days, the first threshold is 100 yuan / 30 days, and the second threshold is 50GB / 30 days, a user who spends 180 yuan (greater than 100 yuan) within 30 days is assigned the "high-value user tag".

[0042] The "churn risk user" tag refers to users with low activity levels and whose plans are about to expire or have already expired. The assignment rule is either "the interval between two consecutive logins is greater than a third threshold" or "the plan status data indicates the plan has expired for a period greater than a fourth threshold." The third and fourth thresholds are preset, such as 7 days for the third threshold and 3 days for the fourth threshold. Users with a churn risk user tag are assigned a tag if the interval between two consecutive logins is 9 days (greater than 7 days).

[0043] The "new user" tag refers to a user who has just registered and is assigned the tag based on the rule that "the time since the first login is less than a fifth threshold," where the fifth threshold is a preset value, such as 30 days. A user is assigned the "new user" tag if the time since their first login is 15 days (less than 30 days).

[0044] It should be noted that the backend system automatically compares user behavior data with preset thresholds. If the conditions for any tag are met, tag allocation is triggered. If multiple tag conditions are met at the same time (such as new user and spending amount reaches the target), the higher priority tag (such as high-value user tag) will be allocated first.

[0045] S106, Assign preference tags to the user based on the usage feedback data.

[0046] This step can analyze the usage feedback data collected in S102 according to the rules preset in the claims, extract the user's core preferences in terms of network speed, data usage, and usage depth, and assign corresponding preference tags to the user.

[0047] In some embodiments, the feedback data includes log data, work order data, package change records, search data, login data, and core function usage data; Assigning preference tags to the user based on the usage feedback data includes: Acquire user log data, work order data, package change records, search data, login data, and core function usage data; If the number of times the network diagnostic function is used within the second preset time period indicated by the log data is greater than the sixth threshold, or if the work order data indicates that a slow network speed problem has been reported, a network speed sensitive label will be assigned to the user. If the number of times the user selects a larger data plan in the package change record exceeds the seventh threshold, or if the user searches for excessive data-intensive keywords, assign a large data plan tag to the user. If the number of logins within the third preset time period indicated by the login data is less than the eighth threshold and the number of times the core functions are used is less than the ninth threshold, a "light user" label will be assigned to the user.

[0048] The above thresholds and time periods are values ​​set according to business needs, and this application does not impose any special limitations. The following are merely illustrative examples.

[0049] The preference tags can be demand preference identifiers based on user feedback data, and may include tags such as network speed sensitive tags, high data usage tags, and light user tags, used to match users' personalized service needs.

[0050] The "network speed sensitive tag" refers to users who are concerned about network speed stability and have high requirements for network speed. The assignment rule is either "the number of times the network diagnostic function is used within a second preset time period exceeds a sixth threshold" or "a work order indicates a slow network speed issue." The second preset time period and the sixth threshold are preset values, such as 30 days for the second preset time period and 5 times for the sixth threshold. For example, if a user uses the network diagnostic function 6 times (more than 5 times) within 30 days, they will be assigned a "network speed sensitive tag."

[0051] The "high data usage" tag refers to users with high data usage needs who tend to choose high data plans. The allocation rule is either "the number of times the plan change record indicates a higher data usage plan is greater than the seventh threshold" or "the user has searched for high data usage keywords." The seventh threshold is a preset value, such as 2 times. For example, if a user upgrades to a high data usage plan twice within six months (more than twice), or has searched for "unlimited data," they are assigned the "high data usage" tag.

[0052] The "light user" tag refers to users with low usage frequency and simple functional needs. The allocation rule is "login frequency within a third preset time period is less than the eighth threshold, and core function usage frequency is less than the ninth threshold." The third preset time period, the eighth, and the ninth threshold are preset values, such as a third preset time period of 30 days, an eighth threshold of 3 times, and a ninth threshold of 2 times. For example, if a user logs in 2 times (less than 3 times) and uses the core function 1 time (less than 2 times) within 30 days, they are assigned the "light user" tag.

[0053] It should be noted that the backend system can automatically map users to corresponding preference tags by analyzing usage frequency, keyword matching (work orders / search data), and conditional combinations. This allows for the assignment of multiple preference tags to a single user. For example, a user may simultaneously possess the tags "Speed-Sensitive + High Data Usage".

[0054] S108, based on the value tag and the preference tag, output a marketing strategy matching the user from the marketing strategy library, and display a functional interface matching the user's preferences to the user.

[0055] This step can, based on the "tag-strategy" mapping logic, combine the value tags of S104 and the preference tags of S106 to select suitable marketing content from the marketing strategy library, and at the same time generate a functional interface that fits user preferences, so as to achieve "precision marketing + personalized experience".

[0056] In some embodiments, the step of outputting a marketing strategy matching the user from a marketing strategy library based on the value tag and the preference tag, and displaying a functional interface matching the user's preferences to the user, includes: Obtain the pre-maintained table of tag-policy mappings; Retrieve the marketing strategies corresponding to the value tags and the preference tags from the correspondence table; Generate a marketing strategy display control based on the aforementioned marketing strategy; The marketing strategy display control is combined with the inherent interface controls to generate a functional interface, which is then displayed to the user.

[0057] The aforementioned marketing strategy library refers to a standardized set of marketing strategies pre-established by the portable WiFi operator. It includes marketing content corresponding to different combinations of value tags and preference tags, such as package discounts, value-added services, and retention activities. For example, the strategy library includes strategies such as "High-value users + high data usage tag - 20% off annual unlimited data packages," "At-risk users + light users tag - 30 RMB discount on package renewals," and "New users + speed-sensitive tags - free speed upgrade service for the first month."

[0058] The tag-strategy mapping table refers to a standardized mapping table pre-maintained by the operator, which clarifies the marketing strategies and interface display rules corresponding to different combinations of value tags and preference tags, ensuring that the matching logic is consistent and reusable. For example, the mapping table clarifies that "high-value user tag + high traffic tag" corresponds to the strategy of "20% off annual subscription package + free activation of traffic sharing function", and the interface displays "fast renewal entrance for annual subscription package + traffic sharing function at the top".

[0059] The marketing strategy display controls refer to visual elements generated based on the matched marketing strategy, such as pop-ups, banners, and button entries. For example, for the "20% off annual subscription packages" strategy, a banner control that says "Apply for an annual subscription package now and enjoy a 20% discount" and a "One-click renewal" button control are generated.

[0060] Interface-defined controls refer to controls that form the original interface, such as traffic query and device management entry.

[0061] Combining marketing strategy display controls with inherent interface controls can generate personalized interfaces. This not only retains the necessary original controls but also prioritizes displaying user-preferred function entry points and matching marketing content. For example, the interface for "light user tags + churn-risk user tags" retains the inherent controls for "package renewal" and "data usage inquiry," while overlaying the "30 yuan discount on renewal" marketing control and hiding complex function entry points.

[0062] The solutions described in S102-S108 can acquire user behavior data and user feedback data, and assign corresponding value tags and preference tags. This accurately identifies the user's commercial value level and contextual preferences, solving the problem that a single tag cannot fully characterize user attributes. It provides the back-end operation system with more accurate user data support that fits the scenario. Furthermore, by outputting marketing strategies that match users from the marketing strategy library based on value tags and preference tags, and displaying personalized functional interfaces, relevant services can be pushed in a targeted manner, reducing user resistance and improving marketing conversion efficiency.

[0063] In some embodiments, analyzing user behavior on the system can help identify the root causes of low user conversion rates, thereby facilitating solutions to fundamental problems and improving user conversion rates.

[0064] Please see Figure 2 , Figure 2 This is a schematic flowchart illustrating a method for analyzing root causes, as described in this application. Figure 2 As shown, the method may include steps S202-S206.

[0065] S202, Construct the transformation funnel.

[0066] The conversion funnel includes key stages that hinder users from completing the conversion process, from device activation to the completion of the first recharge. The conversion funnel can simulate a streamlined analytical model of the user's journey from initial action to target conversion (first recharge), using user retention rates at each stage as the core indicator to visually represent the points of user churn throughout the entire process.

[0067] The steps from device activation to first-time top-up cover the entire process from device activation to first payment. In some embodiments, this may include powering on the device, connecting to the network, downloading the corresponding service app, logging into the app account, entering the real-name authentication page, submitting identity information, completing facial recognition, receiving authentication results, viewing available data plans, selecting a target plan, choosing a payment method, initiating a payment request, and successful payment.

[0068] The critical stage refers to the operational steps in the conversion process where the user churn rate is high and seriously hinders the overall conversion efficiency. This can be determined by the ratio of "number of users entering the stage" to "number of users completing the stage" (conversion rate). If the conversion rate is lower than a preset threshold (e.g., 50%), it is considered a critical stage. For example, if 1000 users enter the "facial recognition" stage, but only 300 complete the recognition, the conversion rate is 30% < 50%, making the "facial recognition" stage a critical stage.

[0069] This step can analyze the entire process from activating a portable WiFi device to completing the first top-up. Through data collection and quantitative analysis, it can identify key steps with high user churn and low conversion rates, build a visual conversion funnel, and provide a clear direction for subsequent precise identification of the root causes.

[0070] In some embodiments, a conversion funnel can be constructed by embedding probes. See also Figure 3 , Figure 3 This is a flowchart illustrating the method for constructing a transformation funnel. For example... Figure 3 As shown, the method may include S302-S306.

[0071] S302, Pre-set embedded points for each of the aforementioned operational steps.

[0072] The aforementioned data collection points refer to data collection code embedded in system functions or pages, which can capture specific user behavior events (such as "opening the page", "clicking the button", "operation successful") and send the data back to the backend database in real time.

[0073] Each of the aforementioned operational steps refers to the entire process of "activation-first charge" for portable WiFi, which may include powering on, connecting to the network, downloading the App, logging into the App, entering the authentication page, submitting ID information, facial recognition, receiving authentication results, viewing the plan, selecting a plan, selecting a payment method, initiating payment, and successful payment.

[0074] This step can be divided into two types of event tracking based on the characteristics of each stage: page-level event tracking is embedded in the page loading code to record the "entering the stage" event (such as being triggered when the authentication page is opened); operation-level event tracking is embedded in the key button click code to record the "completing the stage" event (such as being triggered after clicking "submit ID card" and the information is verified).

[0075] For example, in the "Submit ID Card Information" step, the "Enter ID Card Submission Step" event is automatically triggered when the page loads. After the user fills in the information and clicks the "Submit" button, and the system verifies the information, the "Complete ID Card Submission" event is triggered. In the "Face Recognition" step, the "Enter Face Recognition Step" event is triggered when the user clicks the "Start Recognition" button. After successful recognition, the "Complete Face Recognition" event is triggered.

[0076] S304, count the number of first users entering each operation step and the number of second users completing each operation step.

[0077] The first number of users refers to the total number of different users who successfully entered a certain operation stage. It is obtained by deduplicating the number of times the "entry event" event is triggered in that stage to avoid counting the same user repeatedly. For example, if the "enter authentication page" event is triggered 1200 times in 24 hours, after deduplication, it is confirmed that there are 1200 different users. Therefore, the first number of users in this stage is 1200.

[0078] The second user count refers to the total number of different users who successfully completed a certain operation step. It is obtained by deduplicating the trigger count of the "completion event" event for that step, and the statistical range is the same user pool as the first user count. For example, if the "complete ID card submission" event is triggered 900 times within 24 hours, after deduplication, it corresponds to 900 different users, so the second user count for that step is 900.

[0079] S306, the operation step in which the ratio of the number of second users to the number of first users is lower than the ratio threshold is identified as a critical step.

[0080] The percentage threshold can be preset according to business needs to distinguish between "normal conversion stage" and "severe loss stage", for example, 50%.

[0081] The ratio is a core indicator reflecting the user retention efficiency of a single stage. The lower the ratio, the more serious the user churn at that stage, and the greater the obstacle to overall conversion.

[0082] For example, in the "Submit ID Card Information → Facial Recognition" step, the number of second users is 240, the number of first users is 600, and the conversion rate is 40%. Since 40% is lower than the preset first threshold of 50%, the "Submit ID Card Information → Facial Recognition" step is identified as a key step.

[0083] The solutions described in S302-S306 allow for the pre-installation of data collection probes at each stage of the user's "device activation - first recharge" process. This automatically captures user behavior data at the "entry stage" and "completion stage," statistically calculates the conversion rate at each stage, identifies key stages with high user churn, and constructs a quantifiable conversion funnel.

[0084] S204, Analyze the root causes in the key process.

[0085] The root cause can refer to the core reason for the low conversion efficiency in key links. It is necessary to go beyond the surface problems (such as "user has not completed authentication") and dig out the underlying essence (such as complex operation, system failure, unclear information, etc.).

[0086] For example, the "Submit Identity Information" step requires users to manually enter multiple pieces of information such as their ID number and address, and lacks a photo recognition function, making the process cumbersome and causing users to give up; the "Face Recognition" step frequently prompts "Recognition Failed," which is actually due to poor system compatibility with some mobile phone models or network interface response delays; the "Package Selection" step does not clearly indicate the validity period of the package and the data speed limit rules, causing users to hesitate and exit due to unclear information; and the "Connect to Network" step relies on other WiFi networks, and users cannot continue downloading the app if there is no available network.

[0087] In some methods, root cause tracing can be performed by maintaining a knowledge base. For example, various key nodes can be maintained and connected through relationships (edges). After identifying a key node, the root cause can be traced back to a key node without a parent node through the edge.

[0088] This application proposes a simpler and more efficient root cause analysis method, particularly effective for operational systems. Please see [link to relevant documentation]. Figure 4 Figure 4 is a schematic diagram of the root cause analysis method of this application. Figure 4 As shown, the method may include S402-S406.

[0089] S402, Obtain the operation log for the key step.

[0090] The key links mentioned refer to the operational links with high user churn identified through the conversion funnel, such as the "face recognition" link in the "activation-first charge" process of portable WiFi (conversion rate 30% < threshold 50%).

[0091] The operation log refers to the user's operation trajectory at each key stage, automatically recorded by the system. It is structured text data containing fields such as user ID, operation behavior description, operation result, and operation timestamp. For example, "User ID: 10086; Operation behavior: Initiate face recognition; Operation result: Recognition failed (prompt 'Face not aligned with the box'); Operation time: 2024-05-20 14:30:22" and "User ID: 10086; Operation behavior: Initiate face recognition; Operation result: Recognition failed (prompt 'Insufficient lighting'); Operation time: 2024-05-20 14:31:05".

[0092] S404, parse the operation log to obtain the number of operations performed by the user in the critical stage.

[0093] The aforementioned operational behavior refers to the specific actions performed by the user in key stages. The same key stage may contain multiple operational behaviors, such as the operational behaviors in the "face recognition" stage, including "initiating face recognition", "initiating recognition after changing the shooting angle", and "initiating recognition after adjusting the lighting".

[0094] The number of operations refers to the total frequency of a certain operation in the operation logs of all users, reflecting the prevalence of the operation.

[0095] For example, analyzing 3,000 operation logs in the "face recognition" process revealed a total of 2,800 "initiate face recognition" operations. Among these, 1,500 operations resulted in the message "face not aligned with frame" being displayed after initiating recognition, 800 operations resulted in the message "insufficient lighting" being displayed after initiating recognition, and 500 operations resulted in "successful recognition on the first attempt".

[0096] S406, the operation whose number of operations exceeds the operation threshold is identified as the root cause.

[0097] The operation threshold is used to define the critical value between "high-frequency abnormal operation" and "normal operation". It is set by the operator based on the normal operation frequency of key links. For example, the preset operation threshold for the "face recognition" link is 1000 times.

[0098] The root cause is the system design flaw or user experience problem underlying high-frequency operations. For example, if the operation threshold for "face recognition" is set to 1000 times, the number of operations that "prompt 'face not aligned with the frame' after initiating recognition" is 1500 times > 1000 times, while the number of operations that "prompt 'insufficient lighting' after initiating recognition" is 800 times < 1000 times. Therefore, the problem corresponding to "face not aligned with the frame" (such as unclear recognition frame guidance and lack of real-time alignment prompts) is identified as the root cause.

[0099] The solutions described in S402-S406 allow for the extraction of user operation logs at this stage, analysis and statistical analysis of the number of various user operations at this stage, and identification of operations with more than a preset threshold as the root cause. The process is simple, efficient, and meets the needs of the operation system for quickly locating problems.

[0100] S206, output the key link and the root cause.

[0101] The root cause can be output in a structured way on the interface, making it easier to solve problems.

[0102] The solutions described in S202-S206 can pinpoint the root cause of low conversion rates at the system level based on user actions. Resolving the root cause can improve user experience and thus increase conversion rates.

[0103] Corresponding to any of the preceding embodiments, this application also proposes an operation system based on data analysis. Please see [link to relevant documentation]. Figure 5 , Figure 5 This is a schematic diagram illustrating the structure of a data analysis-based operating system, as shown in this application. Figure 5As shown, the data analysis-based operation system 500 includes: Module 510 is used to acquire user behavior data and user feedback data. The first allocation module 520 is used to allocate value tags to the user based on the usage behavior data; The second allocation module 530 is used to allocate preference tags to the user based on the usage feedback data; The output module 540 is used to output a marketing strategy matching the user from the marketing strategy library based on the value tag and the preference tag, and to display a functional interface matching the user's preferences to the user.

[0104] In some embodiments, the usage behavior data includes consumption behavior data, data usage data, login behavior data, and plan status data; The first allocation module 520 is further configured to: Acquire user consumption behavior data, data usage data, login behavior data, and plan status data; If the consumption behavior data indicates that the consumption amount exceeds a first threshold within a first preset time period, or if the traffic usage data indicates that the total traffic exceeds a second threshold, a high-value user tag is assigned to the user. If the login behavior data indicates that the interval between two consecutive logins is greater than a third threshold, or if the package status data indicates that the package has expired for a longer period than a fourth threshold, a churn risk user label will be assigned to the user. If the login behavior data indicates that the time elapsed since the first login is less than a fifth threshold, a new user tag is assigned to the user.

[0105] In some embodiments, the feedback data includes log data, work order data, package change records, search data, login data, and core function usage data; The second allocation module 530 is further configured to: Acquire user log data, work order data, package change records, search data, login data, and core function usage data; If the number of times the network diagnostic function is used within the second preset time period indicated by the log data is greater than the sixth threshold, or if the work order data indicates that a slow network speed problem has been reported, a network speed sensitive label will be assigned to the user. If the number of times the user selects a larger data plan in the package change record exceeds the seventh threshold, or if the user searches for excessive data-intensive keywords, assign a large data plan tag to the user. If the number of logins within the third preset time period indicated by the login data is less than the eighth threshold and the number of times the core functions are used is less than the ninth threshold, a "light user" label will be assigned to the user.

[0106] In some embodiments, the output module 540 is further configured to: Obtain the pre-maintained table of tag-policy mappings; Retrieve the marketing strategies corresponding to the value tags and the preference tags from the correspondence table; Generate a marketing strategy display control based on the aforementioned marketing strategy; The marketing strategy display control is combined with the inherent interface controls to generate a functional interface, which is then displayed to the user.

[0107] In some embodiments, the system 500 further includes a root cause analysis module, configured to: Construct a conversion funnel; the conversion funnel includes the key steps that prevent users from completing the conversion process from activating the device to completing the first recharge. Analyze the root causes in the aforementioned key processes; Output the key links and the root causes.

[0108] In some embodiments, the steps from activating the device to completing the first top-up include: powering on; connecting to the network; downloading the App; logging into the App; entering the authentication page; submitting ID card information; facial recognition; authentication result returned; viewing the package; selecting a package; selecting a payment method; initiating payment; and successful payment.

[0109] In some embodiments, the root cause analysis module is further configured to: Pre-set embedding points for each of the aforementioned operational steps; Count the number of first users entering each operation step and the number of second users completing each operation step; Operations where the ratio of the second user to the first user is lower than a certain threshold are identified as critical operations.

[0110] In some embodiments, the root cause analysis module is further configured to: Obtain the operation logs for the aforementioned key steps; The operation log is used to parse the number of times the user performs all operations at the critical stage; Operations whose number of operations exceeds the operation threshold are identified as root causes.

[0111] In the above systems, by acquiring user behavior data and user feedback data, value tags and preference tags can be assigned accordingly. This accurately identifies the user's commercial value level and contextual preferences, solving the problem that a single tag cannot fully characterize user attributes. It provides the back-end operation system with more accurate user data support that fits the scenario. Furthermore, by outputting marketing strategies that match users from the marketing strategy library based on value tags and preference tags and displaying personalized functional interfaces, relevant services can be pushed in a targeted manner, reducing user resistance and improving marketing conversion efficiency.

[0112] Those skilled in the art will understand that one or more embodiments of this application can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this application can take the form of a computer program product implemented on one or more computer-usable storage media (which may include, but are not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] In this application, “and / or” means having at least one of two options. For example, “A and / or B” can include three options: A, B, and “A and B”.

[0114] The various embodiments in this application 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, the data processing device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0115] The specific embodiments of this application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The subject matter and functional implementations described in this application can be implemented as digital electronic circuits, tangibly embodied computer software or firmware, computer hardware that may include the structures disclosed in this application and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this application can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions loaded onto a tangible, non-transitory program carrier for execution by a data processing apparatus or to control the data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0117] The processing and logic flow described in this application can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by loading input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGA (Field-Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit)—and the device can also be implemented as dedicated logic circuitry.

[0118] A computer suitable for executing computer programs may include, for example, a general-purpose and / or special-purpose microprocessor, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer may include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer may also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer may be loadably coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer may be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0119] Computer-readable media suitable for storing computer program instructions and data can include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0120] While this application contains numerous specific implementation details, these should not be construed as limiting the scope of any disclosure or the scope of the claims, but rather are primarily used to describe the features of specific embodiments of a particular disclosure. Certain features described in the multiple embodiments of this application may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0121] Similarly, although loads are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these loads to be executed in the specific order shown or sequentially, or requiring all illustrated loads to be executed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the described embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0122] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0123] The above are merely preferred embodiments of one or more embodiments of this application and are not intended to limit the scope of one or more embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this application should be included within the scope of protection of one or more embodiments of this application.

Claims

1. A data-driven operational method, characterized in that, The method includes: Acquire user behavior data and user feedback data; Assign value tags to the users based on the usage behavior data; Assign preference tags to the users based on the usage feedback data; Based on the value tags and preference tags, output marketing strategies that match the user from the marketing strategy library, and display a functional interface that matches the user's preferences to the user.

2. The data analysis-based operation method according to claim 1, characterized in that, The usage behavior data includes consumption behavior data, data usage data, login behavior data, and plan status data; Assigning value tags to the user based on the usage behavior data includes: Acquire user consumption behavior data, data usage data, login behavior data, and plan status data; If the consumption behavior data indicates that the consumption amount exceeds a first threshold within a first preset time period, or if the traffic usage data indicates that the total traffic exceeds a second threshold, a high-value user tag is assigned to the user. If the login behavior data indicates that the interval between two consecutive logins is greater than a third threshold, or if the package status data indicates that the package has expired for a longer period than a fourth threshold, a churn risk user label will be assigned to the user. If the login behavior data indicates that the time elapsed since the first login is less than a fifth threshold, a new user tag is assigned to the user.

3. The data analysis-based operation method according to claim 1, characterized in that, The feedback data includes log data, work order data, package change records, search data, login data, and core function usage data; Assigning preference tags to the user based on the usage feedback data includes: Acquire user log data, work order data, package change records, search data, login data, and core function usage data; If the number of times the network diagnostic function is used within the second preset time period indicated by the log data is greater than the sixth threshold, or if the work order data indicates that a slow network speed problem has been reported, a network speed sensitive label will be assigned to the user. If the number of times the user selects a larger data plan in the package change record exceeds the seventh threshold, or if the user searches for excessive data-intensive keywords, assign a large data plan tag to the user. If the number of logins within the third preset time period indicated by the login data is less than the eighth threshold and the number of times the core functions are used is less than the ninth threshold, a "light user" label will be assigned to the user.

4. The data analysis-based operation method according to claim 2, characterized in that, The step of outputting a marketing strategy matching the user from the marketing strategy library based on the value tag and the preference tag, and displaying a functional interface matching the user's preferences to the user, includes: Obtain the pre-maintained table of tag-policy mappings; Retrieve the marketing strategies corresponding to the value tags and the preference tags from the correspondence table; Generate a marketing strategy display control based on the aforementioned marketing strategy; The marketing strategy display control is combined with the inherent interface controls to generate a functional interface, which is then displayed to the user.

5. The data analysis-based operation method according to claim 1, characterized in that, The method further includes: Construct a conversion funnel; the conversion funnel includes the key steps that prevent users from completing the conversion process from activating the device to completing the first recharge. Analyze the root causes in the aforementioned key processes; Output the key links and the root causes.

6. The data analysis-based operation method according to claim 5, characterized in that, The steps from activating the device to completing the first top-up include: powering on; connecting to the network; downloading the App; logging into the App; entering the authentication page; submitting ID information; facial recognition; authentication result returned; viewing the plan; selecting a plan; selecting a payment method; initiating payment; payment successful.

7. The data analysis-based operation method according to claim 6, characterized in that, The construction of the transformation funnel includes: Pre-set embedding points for each of the aforementioned operational steps; Count the number of first users entering each operation step and the number of second users completing each operation step; Operations where the ratio of the second user to the first user is lower than a certain threshold are identified as critical operations.

8. The data analysis-based operation method according to claim 5, characterized in that, The analysis of the root causes in the key processes includes: Obtain the operation logs for the aforementioned key steps; The operation log is used to parse the number of times the user performs all operations at the critical stage; Operations whose number of operations exceeds the operation threshold are identified as root causes.

9. An operating system based on data analysis, characterized in that, The system includes: The acquisition module is used to acquire user behavior data and user feedback data; The first allocation module is used to assign value tags to the user based on the usage behavior data; The second allocation module is used to allocate preference tags to the user based on the usage feedback data; The output module is used to output marketing strategies that match the user from the marketing strategy library based on the value tags and the preference tags, and to display a functional interface that matches the user's preferences to the user.

10. The data analysis-based operating system according to claim 9, characterized in that, The system also includes a root cause analysis module, used for: Construct a conversion funnel; the conversion funnel includes the key steps that prevent users from completing the conversion process from activating the device to completing the first recharge. Analyze the root causes in the aforementioned key processes; Output the key links and the root causes.

Images