Suggestion decision method and device based on front-end application system user portrait model

Abstract

The present application belongs to the technical field of data processing, and particularly relates to a suggestion decision method and device based on a front-end application system user portrait model, comprising: collecting user behavior data of each user according to a pre-constructed user access behavior monitoring index system; constructing a user portrait model based on the user behavior data; obtaining a user portrait report by using the user portrait model; obtaining a predicted suggestion decision scheme by using a pre-established analysis prediction model based on the user portrait report; and the analysis prediction model being constructed by using historical user portrait reports and historical suggestion decision schemes. The technical scheme provided by the present application can not only efficiently and quickly mine user demand, greatly reducing user research work, but also save labor and quickly distinguish core users, clearly identifying which are key marketing groups and which are key construction directions, thereby relieving the problem of long demand confirmation time caused by many levels within an enterprise.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically relating to a suggestion decision-making method and apparatus based on a user profile model of a front-end application system. Background Technology

[0002] Some enterprises have long suffered from inefficiencies in their IT infrastructure development due to their nature. On the one hand, the design and development of front-end systems generally suffer from vague enterprise-level user needs, multiple layers of communication channels, and short lead times, making it difficult to distinguish core functional requirements and construction value. On the other hand, front-end system evaluation lacks scientific basis, and the system construction and evaluation processes are disconnected, failing to form a virtuous cycle of system construction, system application, system evaluation feedback, and system optimization.

[0003] Therefore, it is necessary to conduct user profiling analysis to help users clarify their functional needs. By constructing a general user profiling indicator model for the State Grid information system, we can deeply explore the value and behavioral characteristics of various users, identify key units for the promotion and application of the middle platform functions, and help the middle platform operation side of the project achieve precise marketing, product evaluation and optimization, user experience improvement, and scientific decision support.

[0004] However, current user profiling theories differ from the actual applications of some enterprises' IT systems, lacking targeted and scientific research methods for user profiling analysis. Current problems with IT systems include: First, frequent short-term, high-frequency use of internal business data often leads to reactive, reactive measures rather than preventative measures based on user profiling. Second, implemented functions lack effective evaluation, user experience feedback channels are limited, and feedback is time-consuming and labor-intensive. Third, precise marketing recommendations based on user preferences are impossible. Fourth, developers, in their pursuit of market expansion and business opportunities, often base their functional design decisions on personal experience, resulting in theoretical discussions that are disconnected from actual user needs.

[0005] Currently, the most common and widely used methodology for approximating user profile analysis is the RFM model. The RFM model is an important tool and method for measuring current user value and potential customer value. It's a methodology specifically designed to study user structure. The model consists of three dimensions: R (Recency), which measures the time since the last purchase (the more recent the purchase, the greater the user value); F (Frequency), which measures how frequently a user makes purchases over a period of time (the higher the purchase frequency, the greater the user value); and M (Monetary), which refers to the total amount spent (the higher the total spending, the greater the user value). The RFM model uses these three dimensions as axes to establish a three-dimensional coordinate system, which then subdivides users into eight different categories to differentiate user value. However, the three dimensions of the RFM model have limitations for B-end IT products with parent-subsidiary relationships. On the one hand, the indicators of the three dimensions are too simplistic and it is difficult to fully and deeply explore user value. On the other hand, the model focuses on evaluating user value but does not explore the value of the objects that users operate on, which is often the key to marketing, i.e., it cannot evaluate the value of marketing items. Summary of the Invention

[0006] To overcome the problems existing in the above-mentioned related technologies, this application provides a suggestion decision-making method and apparatus based on a user profile model of a front-end application system.

[0007] According to a first aspect of the embodiments of this application, a suggestion decision-making method based on a user profile model of a front-end application system is provided, including:

[0008] Based on a pre-built user access behavior monitoring indicator system, collect user behavior data for each user;

[0009] A user profile model is constructed based on the user behavior data;

[0010] Use the user profiling model to obtain a user profile report;

[0011] Based on the user profile report, a predicted decision-making scheme is obtained using a pre-established analysis and prediction model;

[0012] The analytical prediction model is constructed using historical user profile reports and historical suggested decision-making schemes.

[0013] Preferably, the step of collecting user behavior data for each user based on a pre-built user access behavior monitoring indicator system includes:

[0014] Based on a pre-built user access behavior monitoring indicator system, user behavior data of each user is automatically captured by front-end embedding points, and the user behavior data of each user is recorded in a pre-established user footprint log ledger.

[0015] Preferably, the user behavior data includes at least the following nine types:

[0016] Percentage of accessed functions, percentage of access time, percentage of requests, percentage of feasibility study amount, number of users accessing the service, total number of users per unit, user growth rate, user churn rate, and access frequency.

[0017] Preferably, the step of constructing a user profile model based on the user behavior data includes:

[0018] User stickiness, user activity, and user voice power are calculated using the aforementioned user behavior data.

[0019] The user profile model is constructed by utilizing the user stickiness, user activity, and user voice.

[0020] Preferably, the step of calculating user stickiness using the user behavior data includes:

[0021] The user access ratio is calculated using the number of users accessing the service and the total number of users per unit.

[0022] Based on the first preset rule, the user access ratio score is determined according to the user access ratio.

[0023] The user turnover rate is calculated using the user acquisition rate and user churn rate.

[0024] Based on the second preset rule, the user change rate score is determined according to the user change rate.

[0025] Based on the third preset rule, the access frequency score is determined according to the user's access frequency.

[0026] The user stickiness is calculated using the user access ratio score, the user change rate score, and the access frequency score.

[0027] Preferably, the step of calculating user activity using the user behavior data includes:

[0028] The user activity level is calculated using the percentage of accessed functions and the percentage of access time.

[0029] Preferably, the step of calculating user voice authority using the user behavior data includes:

[0030] The user's voice is calculated by using the proportion of demand and the proportion of feasibility study amount.

[0031] Preferably, obtaining the user profile report using the user profile model includes:

[0032] The user profile model is used to determine the user type of each user;

[0033] Based on a preset report template, a user profile report is generated according to the user type of each user.

[0034] Preferably, determining the user type of each user using the user profile model includes:

[0035] In the user profile model, users who meet the first preset conditions of user stickiness, user activity, and user voice are considered important development users.

[0036] In the user profile model, users who meet the second preset conditions of user stickiness, user activity, and user voice are core value users.

[0037] In the user profile model, users who meet the third preset conditions of user stickiness, user activity, and user voice are general development users.

[0038] In the user profile model, users who meet the fourth preset condition of user stickiness, user activity, and user voice are the users to be mined;

[0039] In the user profile model, users who meet the fifth preset condition of user stickiness, user activity, and user voice are general retention users;

[0040] In the user profile model, users who meet the sixth preset condition of user stickiness, user activity, and user voice are generally retained users.

[0041] In the user profile model, users who meet the seventh preset condition of user stickiness, user activity, and user voice are considered important users to retain.

[0042] In the user profile model, users who meet the eighth preset condition—user stickiness, user activity, and user voice—are considered important users to retain.

[0043] Preferably, the process of establishing the analytical prediction model includes:

[0044] Collect historical user profile reports and historical suggested decision-making solutions;

[0045] The historical user profile report and the historical suggested decision-making scheme are preprocessed to obtain the processed historical user profile report and the processed historical suggested decision-making scheme.

[0046] A dataset is constructed using the processed historical user profile reports and the suggested decision-making schemes from the processed history;

[0047] The large model is trained using the dataset to obtain the trained large model, which is the analysis and prediction model.

[0048] Preferably, the formula for calculating the user access ratio includes:

[0049] A1 = uv / uvt

[0050] The formula for calculating the user change rate includes:

[0051] A2 = uar - ucr

[0052] The formula for calculating user stickiness includes:

[0053] A = W1*a1 + W2*a2 + W3*a3

[0054] In the above formula, A1 is the user access ratio, uv is the number of users accessing the service, uvt is the total number of users per unit, A2 is the user turnover rate, uar is the new user rate, ucr is the user churn rate, A is the user stickiness, W1 is the weight of the user access ratio score, a1 is the user access ratio score, W2 is the weight of the user turnover rate score, a2 is the user turnover rate score, W3 is the weight of the access frequency score, and a3 is the access frequency score.

[0055] Preferably, the formula for calculating user activity includes:

[0056] B = W4*b1 + W5*b2

[0057] In the above formula, B represents user activity, W4 represents the weight of the percentage of accessed functions, b1 represents the percentage of accessed functions, W5 represents the weight of the percentage of access duration, and b2 represents the percentage of access duration.

[0058] Preferably, the formula for calculating the user's voice power includes:

[0059] C = W6*c1 + W7*c2

[0060] In the above formula, C represents the user's voice, W6 represents the weight of the proportion of demand, c1 represents the proportion of demand, W7 represents the weight of the proportion of feasibility study amount, and c2 represents the proportion of feasibility study amount.

[0061] According to a second aspect of the embodiments of this application, a user profile building apparatus for a front-end application system is provided, comprising:

[0062] The data collection unit is used to collect user behavior data from each user based on a pre-built user access behavior monitoring indicator system.

[0063] The construction unit is used to construct a user profile model based on the user behavior data;

[0064] The acquisition unit is used to acquire a user profile report using the user profile model;

[0065] The prediction unit is used to obtain predicted decision-making schemes based on the user profile report and using a pre-established analysis and prediction model.

[0066] The analytical prediction model is constructed using historical user profile reports and historical suggested decision-making schemes.

[0067] According to a third aspect of the present application, an electronic device is provided, comprising: at least one processor and a memory; wherein the memory and the processor are connected via a bus.

[0068] The memory is used to store one or more programs;

[0069] When the one or more programs are executed by the at least one processor, the suggestion decision method based on the user profile model of the front-end application system is implemented.

[0070] According to a fourth aspect of the embodiments of this application, a readable storage medium is provided, on which an executable program is stored, wherein when the executable program is executed, the suggestion decision method based on the user profile model of the front-end application system is implemented.

[0071] The technical solution provided by this invention has the following beneficial effects:

[0072] This invention provides a suggestion-based decision-making method and apparatus based on a user profile model of a front-end application system, comprising: collecting user behavior data of each user according to a pre-built user access behavior monitoring indicator system; constructing a user profile model based on the user behavior data; obtaining a user profile report using the user profile model; and obtaining a predicted suggestion-based decision-making scheme based on the user profile report using a pre-established analysis and prediction model. The analysis and prediction model is constructed using historical user profile reports and historical suggestion-based decision-making schemes. The technical solution provided by this invention can not only efficiently and quickly uncover user needs, greatly reducing user research work, but also save effort and quickly distinguish core users, clarify which are key marketing groups, and clarify which are key development directions, alleviating the problem of long demand confirmation times caused by multiple internal layers within an enterprise. Attached Figure Description

[0073] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0074] Figure 1 This is a flowchart of a suggestion decision-making method based on a user profile model of a front-end application system provided by an embodiment of the present invention;

[0075] Figure 2 This is a schematic diagram of the user profile model provided in an embodiment of the present invention;

[0076] Figure 3 This is a structural block diagram of a suggestion decision-making device based on a user profile model of a front-end application system provided in an embodiment of the present invention;

[0077] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0078] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the following embodiments are only some embodiments of this invention, not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0079] Example 1

[0080] This invention provides a suggestion decision-making method based on a user profile model of a front-end application system, such as... Figure 1 As shown, it includes the following steps:

[0081] Step 11: Collect user behavior data for each user based on the pre-built user access behavior monitoring indicator system;

[0082] Step 12: Build a user profile model based on user behavior data;

[0083] Step 13: Obtain a user profile report using the user profile model;

[0084] Step 14: Based on the user profile report, use the pre-established analysis and prediction model to obtain the predicted decision-making solutions;

[0085] The analytical predictive model is built using historical user profile reports and historical suggested decision-making schemes.

[0086] This invention, based on the RFM model, adapts the RFM model for user profiling scenarios of B2B IT products with parent-subsidiary relationships. It establishes a comprehensive indicator system for user profiling analysis and constructs a more adaptable user profiling analysis model and functional value assessment model. For example, the RFM model only focuses on three indicators, which has certain limitations and lacks an analyzable user access behavior monitoring indicator system. Furthermore, previous user profiling research focused on user value classification, lacking product value assessment. This model will consider both marketing targets and marketing items, and due to the specific characteristics of energy industry companies, cost was not a primary consideration when assessing the value of marketing items.

[0087] This invention optimizes the underlying access log association rules to improve user data quality. Currently, user profiling analysis typically relies on large amounts of user data for training and annotation. However, in practical applications, problems such as low data quality and inaccurate annotation often exist, leading to a decline in model performance and thus affecting the accuracy of user profiling. This method pre-plans for functional changes, builds a functional architecture, and establishes version tracking functionality.

[0088] It should be noted that this invention does not limit the "pre-built user access behavior monitoring indicator system," which can be set by those skilled in the art based on experimental data or expert experience. In some embodiments, the user access behavior monitoring indicator system is a six-level indicator system; the first-level indicators include: analysis content and analysis report template chapter settings;

[0089] The secondary indicators corresponding to the analysis content include: analysis direction, analysis indicators, and analysis methods;

[0090] The analysis report template chapters are set with corresponding secondary indicators including: user information profile, user behavior profile, and user segmentation profile;

[0091] The three-level indicators corresponding to the analysis direction include: the logic behind the analysis direction, user attributes, behavioral attributes, resource attributes, and time attributes;

[0092] The three-level indicators corresponding to the analysis metrics include: Activity (i.e., the process of each visit, examining the user's participation; its purpose is to identify resources / features with high user attention), Stickiness (i.e. the user's continued access to and use of the website over a period of time; its purpose is to discover resources / features that enhance user stickiness and reduce user churn), and Voice (i.e., the value output determined by the user based on the website's business; its purpose is to identify the degree to which user needs generate revenue for the project platform).

[0093] The three-level indicators corresponding to the analysis methods include: RFM model expansion (i.e., establishing coordinates, distinguishing user levels, and prioritizing the needs of important development customers and important retention customers), comparative analysis (i.e., through the statistical analysis and comparison of indicator data, to discover resources and functions with high user attention), and other common analysis methods.

[0094] The three-level indicators corresponding to user information profiling include: unit distribution, department distribution, occupational distribution, and specialization distribution; among them, the statistical indicators for unit distribution, department distribution, occupational distribution, and specialization distribution are the number of users, and the statistical time for unit distribution, department distribution, occupational distribution, and specialization distribution is the cumulative time.

[0095] The three-level indicators corresponding to user behavior profiles include: user activity analysis, user stickiness analysis, and user voice analysis.

[0096] The three-level metrics corresponding to user segmentation profiles include: user persistence segmentation, user importance segmentation, and user purchasing power segmentation.

[0097] The four-level indicators corresponding to the logic of the analysis direction include: initiator of behavior, initiating action, initiating object, and initiation time;

[0098] The four-level indicators corresponding to user attributes include: organization, department, position, relevant specialization, gender, age, education level, and personality.

[0099] The four-level indicators corresponding to behavioral attributes include: query, browse, favorites, and data modification;

[0100] The four levels of indicators corresponding to resource attributes include: application type, service type, document type, and function type;

[0101] The four levels of indicators corresponding to the time attribute include: cumulative, this month, and today;

[0102] The four-level metrics corresponding to user activity include: average number of pages visited and average time spent on the page.

[0103] The four levels of metrics corresponding to user stickiness include: number of users, user visit rate, new user ratio (e.g., new user ratio > user churn rate: the product is in the growth stage; new user ratio = user churn rate: the product is in the mature and stable stage; new user ratio < user churn rate: the product is in the decline stage), user churn rate, active user ratio, page views, page view frequency (can identify old users), page view duration, page view interval (identifies the number of active users), first page view time (identifies new users), and last page view time (identifies churned users);

[0104] The four-level indicators corresponding to user voice include: demand (identifying purchasing users and silent users) and feasibility study amount;

[0105] The four levels of indicators corresponding to the comparative analysis method include: resource access ranking, unit access ranking, department access ranking, and peak access period;

[0106] Other common analytical methods with corresponding level 4 indicators include: questionnaire survey method and TF-IDF algorithm;

[0107] The four levels of indicators corresponding to user activity analysis include: statistical indicators (see Activity in the analysis indicators), statistical dimensions (such as by unit / department / position / specialty, by resource, by operation behavior (see the sub-indicators corresponding to the analysis direction)), and statistical time (e.g., cumulative time and this month);

[0108] The four levels of indicators corresponding to user stickiness analysis include: statistical indicators (see stickiness in the analysis indicators), statistical dimensions (such as by unit / department / position / specialty, by resource, by operation behavior) and statistical time (e.g., cumulative time and this month);

[0109] The four levels of indicators corresponding to user discourse power analysis include: statistical indicators (see output in the analysis indicators), statistical dimensions (such as by unit / department / position / specialty) and statistical time (e.g., cumulative time and this month);

[0110] The four-level metrics for user retention segmentation include: new users, returning users, and churned users.

[0111] The four-level indicators corresponding to user importance clusters include: see the RFM model;

[0112] The four-level indicators corresponding to user purchasing power segmentation include: purchasing users and inactive users;

[0113] The five-level indicators corresponding to data modification include: addition (such as request submission and service subscription), deletion, and modification;

[0114] The five-level metrics corresponding to the number of users include: usage persistence category, purchase behavior category, and category by importance;

[0115] The six-level metrics corresponding to the persistence category include: new users (whose corresponding seven-level metrics include: general users and active users), returning users (whose corresponding seven-level metrics include: general users and active users), and churned users.

[0116] The six-level indicators corresponding to the purchase behavior classification include: purchasing users and inactive users;

[0117] The six levels of indicators categorized by importance include: important growth users, important value users, important retention users, important retention users, average retention users, average retention users, average growth users, and average value users.

[0118] It is understandable that by establishing a user access behavior monitoring indicator system, the logic of user access behavior monitoring indicators can be determined, as shown in Table 1.

[0119] Table 1 Logic of User Access Behavior Monitoring Indicators

[0120]

[0121]

[0122] This invention establishes rules for monitoring user access behavior indicators to determine the user behavior data that needs to be collected. It can also support user behavior analysis applications such as user value and behavioral characteristics. Furthermore, based on user access behavior monitoring indicators, it expands the RFM model and builds a user profile model suitable for state-owned enterprises and B-end products.

[0123] This invention is based on the RFM customer value analysis model theory and a user access behavior monitoring indicator system. It constructs a user profile model from three aspects: user stickiness, user activity, and user voice. This is the main idea behind the research model construction. From a technical perspective, it develops and builds functional identity ledgers and access footprint ledgers to collect user information and support the practical application and implementation of the user profile model.

[0124] Further, step 11 includes:

[0125] Based on a pre-built user access behavior monitoring indicator system, user behavior data of each user is automatically captured by front-end embedding points and recorded in a pre-established user footprint log ledger.

[0126] In some embodiments, a function ledger can also be established to identify function identities through function codes, providing a basis for version statistics for later function iterations and name changes. The function code setting rule is that the function code is 7 digits long, and if it is less than 7, it is padded with 0s at the end. The first digit identifies the first-level function, and the following 2-3, 4-5, and 5-7 digits identify the second-level, third-level, and fourth-level functions, respectively. For example, see the function ID coding example shown in Table 2 and the user footprint log ledger field table shown in Table 3.

[0127] Table 2 Example of Function ID Encoding

[0128]

[0129] Table 3 User Footprint Log Fields Table

[0130]

[0131] This invention improves user data quality by building a functional identity ledger and an access footprint ledger, optimizing the underlying access log association rules, and thus improving user data quality.

[0132] Furthermore, user behavior data includes at least the following nine types:

[0133] Percentage of accessed functions, percentage of access time, percentage of requests, percentage of feasibility study amount, number of users accessing the service, total number of users per unit, user growth rate, user churn rate, and access frequency.

[0134] Understandably, user behavior generally refers to the actions of users clicking on function pages on the system. Once data metrics are available, these actions can be further subdivided into four categories: querying data, adding data, modifying data, and deleting data.

[0135] Further, step 12 includes:

[0136] Step 121: Calculate user stickiness, user activity, and user voice using user behavior data;

[0137] like Figure 2 As shown, step 122: Build a user profile model by utilizing user stickiness, user activity, and user voice.

[0138] It is understandable that the user profile model constructed through the three dimensions of user stickiness, user activity, and user voice is a three-dimensional model.

[0139] Furthermore, step 121 includes: Step 1211: Calculating user stickiness using user behavior data; Step 1211 includes:

[0140] Step 1211a: Calculate the user access ratio using the number of accessing users and the total number of users per unit;

[0141] Specifically, the formula for calculating the user access ratio includes:

[0142] A1 = uv / uvt

[0143] In the above formula, A1 is the user access ratio, uv is the number of accessing users, and uvt is the total number of users per unit.

[0144] Step 1211b: Based on the first preset rule, determine the user access ratio score according to the user access ratio;

[0145] Step 1211c: Calculate the user turnover rate using the user new growth rate and user churn rate;

[0146] Specifically, the formula for calculating the user variability rate includes:

[0147] A2 = uar - ucr

[0148] In the above formula, A2 is the user turnover rate, uar is the new user rate, and ucr is the user churn rate;

[0149] Step 1211d: Based on the second preset rule, determine the user change rate score according to the user change rate;

[0150] Step 1211e: Based on the third preset rule, determine the access frequency score according to the user's access frequency;

[0151] Step 1211f: Calculate user stickiness using user access ratio score, user variability score, and access frequency score;

[0152] Specifically, the formula for calculating user stickiness includes:

[0153] A = W1*a1 + W2*a2 + W3*a3

[0154] A represents user stickiness, W1 represents the weight of the user access ratio score, a1 represents the user access ratio score, W2 represents the weight of the user change rate score, a2 represents the user change rate score, W3 represents the weight of the access frequency score, and a3 represents the access frequency score.

[0155] Understandably, access frequency generally refers to how often an access / click occurs.

[0156] Furthermore, step 121 includes: step 1212: calculating user activity using user behavior data;

[0157] Step 1212 includes: calculating user activity using the percentage of accessed functions and the percentage of access time;

[0158] Specifically, the formula for calculating user activity includes:

[0159] B = W4*b1 + W5*b2

[0160] In the above formula, B represents user activity, W4 represents the weight of the percentage of accessed functions, b1 represents the percentage of accessed functions, W5 represents the weight of the percentage of access duration, and b2 represents the percentage of access duration.

[0161] It is understandable that the number of accessed functions refers to the number of functions clicked by user X within the statistical time interval. The percentage of accessed functions can be, but is not limited to: the number of functions clicked by user X within the statistical time interval / the total number of available functions. Access duration refers to the time a user spends on a specific function's page. The percentage of access duration can be, but is not limited to: the percentage of user A's access duration for function X = user A's access duration for function X / the sum of access durations for all functions X.

[0162] Furthermore, step 121 includes: step 1213: calculating user voice power using user behavior data;

[0163] Step 1213 includes: calculating user bargaining power by using the proportion of demand and the proportion of feasibility study amount;

[0164] Specifically, the formula for calculating user voice includes:

[0165] C = W6*c1 + W7*c2

[0166] In the above formula, C represents the user's voice, W6 represents the weight of the proportion of demand, c1 represents the proportion of demand, W7 represents the weight of the proportion of feasibility study amount, and c2 represents the proportion of feasibility study amount.

[0167] Understandably, user needs generally refer to business requests or management requirements from users to implement a specific business scenario through the development of X product features, ultimately resulting in a feature within the internet product. The percentage of requests is the ratio of the number of requests submitted by a single user to the sum of all requests submitted by all users. Feasibility study funding represents the investment amount from the user side of an internet project, used to assess the user's investment capacity. For example, the percentage of feasibility study funding is the ratio of a single user's investment in project A to the total investment amount from all users in project A.

[0168] It should be noted that this invention does not limit the weights of the "user access ratio score," "user change rate score," "access frequency score," "access function number percentage," "access duration percentage," "demand number percentage," and "feasibility study amount percentage," which can be set by those skilled in the art based on experimental data or expert experience. In some embodiments, the weights can be set using the analytic hierarchy process (AHP) based on qualitative and quantitative analysis combined with fuzzy comprehensive evaluation, making it easier and faster to construct a multi-objective, multi-criteria, and multi-structural data health evaluation index system.

[0169] For example, the weights of the following percentages obtained through the Analytic Hierarchy Process (AHP) are: 0.2 for the percentage of demand, 0.8 for the percentage of feasibility study amount, 0.3 for the percentage of accessed functions, 0.7 for the percentage of access duration, 0.15 for the user access ratio, 0.15 for the user change rate, and 0.7 for the access frequency.

[0170] It should be noted that the embodiments of the present invention do not limit the "first preset rule," "second preset rule," and "third preset rule," which can be set by those skilled in the art according to engineering needs, experimental data, or expert experience. In some embodiments, the first preset rule includes:

[0171] If the user access ratio falls within the first threshold range, then the user access ratio score is the first score.

[0172] If the user access ratio falls within the second threshold range, then the user access ratio score is the second score.

[0173] If the user access ratio falls within the third threshold range, then the user access ratio score is the third score.

[0174] If the user access ratio falls within the fourth threshold range, then the user access ratio score is the fourth score.

[0175] If the user access ratio falls within the fifth threshold range, then the user access ratio score is the fifth score.

[0176] For example, a user access ratio of 0 is scored as 0 points; a user access ratio ∈ (0, 0.2] is scored as 1 point; a user access ratio ∈ (0.2, 0.4] is scored as 2 points; a user access ratio ∈ (0.4, 0.6] is scored as 3 points; a user access ratio ∈ (0.6, 0.8] is scored as 4 points; and a user access ratio ∈ (0.8, 1] is scored as 5 points.

[0177] In some embodiments, the second preset rule includes:

[0178] If the user variability rate falls within the sixth threshold range, then the user variability rate score is the sixth score.

[0179] If the user variability rate falls within the seventh threshold range, then the user variability rate score is the seventh score.

[0180] If the user variability rate falls within the eighth threshold range, then the user variability rate score is the eighth score.

[0181] If the user variability rate falls within the ninth threshold range, then the user variability rate score is the ninth score.

[0182] If the user change rate falls within the tenth threshold range, then the user change rate score is the tenth value.

[0183] If the user variability rate falls within the eleventh threshold range, then the user variability rate score is the eleventh score.

[0184] If the user change rate falls within the twelfth threshold range, then the user change rate score is the twelfth score.

[0185] If the user variability rate falls within the thirteenth threshold range, then the user variability rate score is the thirteenth value.

[0186] If the user change rate falls within the fourteenth threshold range, then the user change rate score is the fourteenth score.

[0187] For example, a user change rate ∈ (∞, -0.2] is worth -5 points; a user change rate ∈ (-0.2, -0.1] is worth -3 points; a user change rate ∈ (-0.1, -0.05] is worth -2 points; a user change rate ∈ (-0.05, 0] is worth -1 point; a user change rate = 0 is worth 0 points; a user change rate ∈ (0, 0.05] is worth 1 point; a user change rate ∈ (0.05, 0.1] is worth 2 points; a user change rate ∈ (0.1, 0.2] is worth 3 points; and a user change rate ∈ (0.1, 0.2] is worth 5 points.

[0188] In some embodiments, the third preset rule includes:

[0189] If the user's access frequency falls within the fifteenth threshold range, then the access frequency score is the fifteenth score.

[0190] If the user's access frequency falls within the sixteenth threshold range, then the access frequency score is the sixteenth score.

[0191] If the user's access frequency falls within the seventeenth threshold range, then the access frequency score is the seventeenth score.

[0192] If the user's access frequency falls within the eighteenth threshold range, then the access frequency score is the eighteenth score.

[0193] If the user's access frequency falls within the nineteenth threshold range, then the access frequency score is the nineteenth score.

[0194] If the user's access frequency falls within the twentieth threshold range, the access frequency score is the twentieth tenth value.

[0195] If the user access frequency falls within the twenty-first threshold range, then the access frequency score is the twenty-first score.

[0196] If the user's access frequency falls within the twenty-second threshold range, then the access frequency score is the twenty-second score.

[0197] If the user's access frequency falls within the 23rd threshold range, then the access frequency score is the 23rd score.

[0198] If the user's access frequency falls within the twenty-fourth threshold range, then the access frequency score is the twenty-fourth score.

[0199] If the user's access frequency falls within the 25th threshold range, then the access frequency score is the 25th score.

[0200] For example, access frequency ∈ (365 days / time, ∞) is scored as follows: -5 points; access frequency ∈ (180 days / time, 365 days / time) is scored as follows: -4 points; access frequency ∈ (150 days / time, 180 days / time) is scored as follows: -3 points; access frequency ∈ (120 days / time, 150 days / time) is scored as follows: -2 points; access frequency ∈ (90 days / time, 120 days / time) is scored as follows: -1 point; access frequency = 90 days / time is scored as follows: 0 points; access frequency ∈ (30 days / time, 90 days / time) is scored as follows: 1 point; access frequency ∈ (1 day / time, 30 days / time) is scored as follows: 2 points; access frequency ∈ (1 hour / time, 1 day / time) is scored as follows: 3 points; access frequency ∈ (1 minute / time, 1 hour / time) is scored as follows: 4 points; access frequency ∈ (0, 1 minute / time) is scored as follows: 5 points.

[0201] Further, step 13 includes:

[0202] Step 131: Use the user profile model to determine the user type of each user;

[0203] Step 132: Based on the preset report template, generate a user profile report according to the user type of each user.

[0204] It should be noted that the present invention does not limit the "preset report template", which can be set by those skilled in the art based on experimental data or expert experience.

[0205] Further, step 131 includes:

[0206] In the user profile model, users who meet the first preset conditions of user stickiness, user activity, and user voice are considered important development users.

[0207] In the user profile model, users who meet the second preset conditions of user stickiness, user activity, and user voice are considered core value users.

[0208] In the user profile model, users who meet the third preset condition of user stickiness, user activity, and user voice are considered general development users.

[0209] In the user profile model, users who meet the fourth preset condition of user stickiness, user activity, and user voice are the users to be explored;

[0210] In the user profile model, users who meet the fifth preset condition—user stickiness, user activity, and user voice—are considered general retention users.

[0211] In the user profile model, users who meet the sixth preset condition of user stickiness, user activity, and user voice are considered general retention users.

[0212] In the user profile model, users who meet the seventh preset condition—user stickiness, user activity, and user voice—are considered important users to retain.

[0213] In the user profile model, users who meet the eighth preset condition—user stickiness, user activity, and user voice—are considered important users to retain.

[0214] It should be noted that the present invention does not limit the "first preset condition, second preset condition, third preset condition, fourth preset condition, fifth preset condition, sixth preset condition, seventh preset condition, and eighth preset condition," which can be limited by those skilled in the art based on experimental data or expert experience. For example, the first preset condition, second preset condition, third preset condition, fourth preset condition, fifth preset condition, sixth preset condition, seventh preset condition, and eighth preset condition can be, but are not limited to, set as threshold ranges corresponding to user stickiness, user activity, and user voice power, thereby limiting the user type.

[0215] Furthermore, the method also includes: Step 10: Establishing an analytical prediction model; Step 10 includes:

[0216] Step 101: Collect historical user profile reports and historical suggested decision-making solutions;

[0217] Step 102: Preprocess the historical user profile reports and historical suggested decision-making schemes to obtain processed historical user profile reports and processed historical suggested decision-making schemes;

[0218] In some embodiments, "preprocessing historical user profile reports and historical suggested decision schemes" means preprocessing the collected data before model training. This can include, but is not limited to, cleaning, labeling, and formatting the collected historical user profile reports and historical suggested decision schemes to ensure that the large model can learn useful information from them.

[0219] Step 103: Construct a dataset using the processed historical user profile reports and the processed historical suggested decision-making schemes;

[0220] Step 104: Train the large model using the dataset to obtain the trained large model, which is the analysis and prediction model.

[0221] In some embodiments, datasets can also be used to train deep learning models such as deep neural network models.

[0222] It should be noted that the method of "training a large model using a dataset" involved in this invention is well known to those skilled in the art, therefore, its specific implementation will not be described in detail.

[0223] In practical applications, the suggestion-based decision-making method based on a user profile model of a front-end application system proposed in this invention can be used to obtain predicted suggestion-based decision-making schemes, which can then be directly used to guide actual construction work. The predicted suggestion-based decision-making schemes can also be adjusted based on actual needs or expert experience. By comparing user data from different periods, the effectiveness of the management methods in the report and suggestion-based decision-making schemes can be evaluated. If deviations are found from reality, the applicability of the weights of demand percentages, feasibility study amount percentages, access function percentages, access duration percentages, user access ratio scores, user change rate scores, and access frequency scores can be adjusted, or statistical indicators can be adjusted or corrected. This allows for the re-collection of user behavior data and the construction of a new user profile model.

[0224] In some embodiments, after the actual construction work is guided by the predicted suggested decision scheme, user behavior will change, that is, the user footprint will change. This requires the re-collection of user behavior data and the construction of a new user profile model, thereby forming a new user profile report.

[0225] This invention proposes a suggestion-based decision-making method based on a user profile model of a front-end application system. Based on the RFM customer value analysis model theory, it performs statistical analysis on user access behavior data of the front-end system, conducts research on user behavior profile analysis technology for the project's middle-end operation portal system, analyzes various user values ​​and behavioral characteristics, supports the identification of key users for the promotion and application of middle-end functions, and clarifies the direction for the planning and construction of hot functions and the optimization and improvement of low-access functions, laying the foundation for further improving user experience, optimizing product functions, and achieving business growth.

[0226] This invention addresses the shortcomings of existing technologies: the lack of a comprehensive user access behavior monitoring indicator system, the lack of adaptability to user profile analysis for B2B products, the lack of functional value assessment, and the analysis scope being limited to users. Furthermore, existing functional value assessment techniques generally employ cost-benefit analysis, which is unsuitable for state-owned enterprises in the energy industry that prioritize information security. This invention proposes a suggestion-based decision-making method based on a user profile model of a front-end application system. It collects user behavior data from each user according to a pre-built user access behavior monitoring indicator system, constructs a user profile model based on this data, generates user profile reports using these models, and then uses a pre-established analysis and prediction model based on these reports to obtain predicted suggestion-based decision-making solutions. The analysis and prediction model is built using historical user profile reports and historical suggestion-based decision-making solutions, enabling efficient and rapid discovery of user needs, significantly reducing user research work; effortlessly and quickly identifying core users and key marketing groups; and effortlessly and quickly identifying popular functions and key development directions. It also alleviates the problem of long requirement confirmation times caused by internal enterprise hierarchies.

[0227] Example 2

[0228] This invention also provides a suggestion decision-making device based on a user profile model of a front-end application system, such as... Figure 3 As shown, it includes:

[0229] Based on a pre-built user access behavior monitoring indicator system, collect user behavior data for each user;

[0230] The data collection unit is used to collect user behavior data from each user based on a pre-built user access behavior monitoring indicator system.

[0231] Building units are used to construct user profile models based on user behavior data;

[0232] The acquisition unit is used to obtain user profile reports using the user profile model.

[0233] The prediction unit is used to obtain predicted decision-making solutions based on user profile reports and using pre-established analytical prediction models.

[0234] The analytical predictive model is built using historical user profile reports and historical suggested decision-making schemes.

[0235] Furthermore, the acquisition unit is specifically used for:

[0236] Based on a pre-built user access behavior monitoring indicator system, user behavior data of each user is automatically captured by front-end embedding points and recorded in a pre-established user footprint log ledger.

[0237] Furthermore, user behavior data includes at least the following nine types:

[0238] Percentage of accessed functions, percentage of access time, percentage of requests, percentage of feasibility study amount, number of users accessing the service, total number of users per unit, user growth rate, user churn rate, and access frequency.

[0239] Furthermore, the building blocks include:

[0240] The calculation module is used to calculate user stickiness, user activity, and user voice power using user behavior data.

[0241] The module is used to build user profile models by leveraging user stickiness, user activity, and user voice.

[0242] Furthermore, the computing module includes:

[0243] The first calculation submodule is used to calculate the user access ratio using the number of accessing users and the total number of users per unit.

[0244] The first determining submodule is used to determine the user access ratio score based on the first preset rule and the user access ratio.

[0245] The second calculation submodule is used to calculate the user turnover rate using the user new growth rate and user churn rate;

[0246] The second determination submodule is used to determine the user change rate score based on the second preset rule and the user change rate.

[0247] The third determination submodule is used to determine the access frequency score based on the third preset rule and the user access frequency.

[0248] The third calculation submodule is used to calculate user stickiness using user access ratio score, user change rate score, and access frequency score.

[0249] Furthermore, the computing module also includes:

[0250] The fourth calculation submodule is used to calculate user activity by using the percentage of accessed functions and the percentage of access time.

[0251] Furthermore, the computing module also includes:

[0252] The fifth calculation submodule is used to calculate the user's voice by using the proportion of demand and the proportion of feasibility study amount.

[0253] Furthermore, the acquisition unit includes:

[0254] The fourth submodule is used to determine the user type of each user using the user profile model;

[0255] The generation submodule is used to generate user profile reports based on preset report templates and user types for each user.

[0256] Furthermore, the fourth determination submodule is specifically used for:

[0257] In the user profile model, users who meet the first preset conditions of user stickiness, user activity, and user voice are considered important development users.

[0258] In the user profile model, users who meet the second preset conditions of user stickiness, user activity, and user voice are considered core value users.

[0259] In the user profile model, users who meet the third preset condition of user stickiness, user activity, and user voice are considered general development users.

[0260] In the user profile model, users who meet the fourth preset condition of user stickiness, user activity, and user voice are the users to be explored;

[0261] In the user profile model, users who meet the fifth preset condition—user stickiness, user activity, and user voice—are considered general retention users.

[0262] In the user profile model, users who meet the sixth preset condition of user stickiness, user activity, and user voice are considered general retention users.

[0263] In the user profile model, users who meet the seventh preset condition—user stickiness, user activity, and user voice—are considered important users to retain.

[0264] In the user profile model, users who meet the eighth preset condition—user stickiness, user activity, and user voice—are considered important users to retain.

[0265] Furthermore, the device also includes: a model building unit for building an analysis and prediction model; the model building unit is specifically used for:

[0266] Collect historical user profile reports and historical suggested decision-making solutions;

[0267] The historical user profile reports and historical suggested decision-making schemes are preprocessed to obtain the processed historical user profile reports and processed historical suggested decision-making schemes;

[0268] A dataset is constructed using processed historical user profile reports and suggested decision-making schemes.

[0269] A large model is trained using the dataset to obtain a trained large model, which serves as the analysis and prediction model. Furthermore, the formula for calculating the user access ratio includes:

[0270] A1 = uv / uvt

[0271] The formula for calculating the user change rate includes:

[0272] A2 = uar - ucr

[0273] The formula for calculating user stickiness includes:

[0274] A = W1*a1 + W2*a2 + W3*a3

[0275] In the above formula, A1 is the user access ratio, uv is the number of users accessing the service, uvt is the total number of users per unit, A2 is the user turnover rate, uar is the new user rate, ucr is the user churn rate, A is the user stickiness, W1 is the weight of the user access ratio score, a1 is the user access ratio score, W2 is the weight of the user turnover rate score, a2 is the user turnover rate score, W3 is the weight of the access frequency score, and a3 is the access frequency score.

[0276] Furthermore, the formula for calculating user activity includes:

[0277] B = W4*b1 + W5*b2

[0278] In the above formula, B represents user activity, W4 represents the weight of the percentage of accessed functions, b1 represents the percentage of accessed functions, W5 represents the weight of the percentage of access duration, and b2 represents the percentage of access duration.

[0279] Furthermore, the formula for calculating user voice includes:

[0280] C = W6*c1 + W7*c2

[0281] In the above formula, C represents the user's voice, W6 represents the weight of the proportion of demand, c1 represents the proportion of demand, W7 represents the weight of the proportion of feasibility study amount, and c2 represents the proportion of feasibility study amount.

[0282] It is understood that the system embodiments provided above correspond to the method embodiments described above, and the specific details can be referred to each other, which will not be repeated here.

[0283] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0284] Example 3

[0285] like Figure 4 As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0286] The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to implement the corresponding method flow or corresponding function, so as to realize the steps of the suggestion decision method based on the user profile model of the front-end application system in the above embodiments.

[0287] Example 4

[0288] Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). This readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both built-in storage media within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of a suggestion decision-making method based on a user profile model of a front-end application system in the above embodiments.

[0289] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0290] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0291] 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.

[0292] 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.

[0293] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A suggestion-based decision-making method based on a user profile model of a front-end application system, characterized in that, include: Based on a pre-built user access behavior monitoring indicator system, collect user behavior data for each user; A user profile model is constructed based on the user behavior data; Use the user profiling model to obtain a user profile report; Based on the user profile report, a predicted decision-making scheme is obtained using a pre-established analysis and prediction model; The analytical prediction model is constructed using historical user profile reports and historical suggested decision-making schemes; The user behavior data includes at least the following nine types: Percentage of accessed functions, percentage of access time, percentage of requests, percentage of feasibility study amount, number of users accessing the service, total number of users per unit, user growth rate, user churn rate, and access frequency. The process of constructing a user profile model based on the user behavior data includes: User stickiness, user activity, and user voice power are calculated using the aforementioned user behavior data. The user profile model is constructed using the user stickiness, user activity, and user voice. The calculation of user stickiness using the user behavior data includes: The user access ratio is calculated using the number of users accessing the service and the total number of users per unit. Based on the first preset rule, the user access ratio score is determined according to the user access ratio. The user turnover rate is calculated using the user acquisition rate and user churn rate. Based on the second preset rule, the user change rate score is determined according to the user change rate. Based on the third preset rule, the access frequency score is determined according to the user's access frequency. The user stickiness is calculated using the user access ratio score, the user change rate score, and the access frequency score. The calculation of user voice authority using the user behavior data includes: The user's voice is calculated by using the proportion of demand and the proportion of feasibility study amount.

2. The method according to claim 1, characterized in that, The process involves collecting user behavior data from each user based on a pre-built user access behavior monitoring indicator system, including: Based on a pre-built user access behavior monitoring indicator system, user behavior data of each user is automatically captured by front-end embedding points, and the user behavior data of each user is recorded in a pre-established user footprint log ledger.

3. The method according to claim 1, characterized in that, The calculation of user activity using the user behavior data includes: The user activity level is calculated using the percentage of accessed functions and the percentage of access time.

4. The method according to claim 1, characterized in that, The process of obtaining a user profile report using the user profile model includes: The user profile model is used to determine the user type of each user; Based on a preset report template, a user profile report is generated according to the user type of each user.

5. The method according to claim 4, characterized in that, The process of determining the user type of each user using the user profile model includes: In the user profile model, users who meet the first preset conditions of user stickiness, user activity, and user voice are considered important development users. In the user profile model, users who meet the second preset conditions of user stickiness, user activity, and user voice are core value users. In the user profile model, users who meet the third preset conditions of user stickiness, user activity, and user voice are general development users. In the user profile model, users who meet the fourth preset condition of user stickiness, user activity, and user voice are the users to be mined; In the user profile model, users who meet the fifth preset condition of user stickiness, user activity, and user voice are general retention users; In the user profile model, users who meet the sixth preset condition of user stickiness, user activity, and user voice are generally retained users. In the user profile model, users who meet the seventh preset condition of user stickiness, user activity, and user voice are considered important users to retain. In the user profile model, users who meet the eighth preset condition—user stickiness, user activity, and user voice—are considered important users to retain.

6. The method according to claim 1, characterized in that, The process of establishing the analytical prediction model includes: Collect historical user profile reports and historical suggested decision-making solutions; The historical user profile report and the historical suggested decision-making scheme are preprocessed to obtain the processed historical user profile report and the processed historical suggested decision-making scheme. A dataset is constructed using the processed historical user profile reports and the suggested decision-making schemes from the processed history; The large model is trained using the dataset to obtain the trained large model, which is the analysis and prediction model.

7. The method according to claim 1, characterized in that, The formula for calculating the user access ratio includes: A1 = uv / uvt The formula for calculating the user change rate includes: A2 = uar - ucr The formula for calculating user stickiness includes: A = W1*a1 + W2*a2 + W3*a3 In the above formula, A1 is the user access ratio, uv is the number of users accessing the service, uvt is the total number of users per unit, A2 is the user turnover rate, uar is the new user rate, ucr is the user churn rate, A is the user stickiness, W1 is the weight of the user access ratio score, a1 is the user access ratio score, W2 is the weight of the user turnover rate score, a2 is the user turnover rate score, W3 is the weight of the access frequency score, and a3 is the access frequency score.

8. The method according to claim 3, characterized in that, The formula for calculating user activity includes: B = W4*b1 + W5*b2 In the above formula, B represents user activity, W4 represents the weight of the percentage of accessed functions, b1 represents the percentage of accessed functions, W5 represents the weight of the percentage of access duration, and b2 represents the percentage of access duration.

9. The method according to claim 4, characterized in that, The formula for calculating the user's voice power includes: C = W6*c1 + W7*c2 In the above formula, C represents the user's voice, W6 represents the weight of the proportion of demand, c1 represents the proportion of demand, W7 represents the weight of the proportion of feasibility study amount, and c2 represents the proportion of feasibility study amount.

10. A user profile building device for a front-end application system, characterized in that, include: The data collection unit is used to collect user behavior data from each user based on a pre-built user access behavior monitoring indicator system. The construction unit is used to construct a user profile model based on the user behavior data; The acquisition unit is used to acquire a user profile report using the user profile model; The prediction unit is used to obtain predicted decision-making schemes based on the user profile report and using a pre-established analysis and prediction model. The analytical prediction model is constructed using historical user profile reports and historical suggested decision-making schemes; The user behavior data includes at least the following nine types: Percentage of accessed functions, percentage of access time, percentage of requests, percentage of feasibility study amount, number of users accessing the service, total number of users per unit, user growth rate, user churn rate, and access frequency. The building unit includes: The calculation module is used to calculate user stickiness, user activity, and user voice power using user behavior data. The building module is used to construct user profile models by leveraging user stickiness, user activity, and user voice. The computing module includes: The first calculation submodule is used to calculate the user access ratio using the number of accessing users and the total number of users per unit. The first determining submodule is used to determine the user access ratio score based on the first preset rule and the user access ratio. The second calculation submodule is used to calculate the user turnover rate using the user new growth rate and user churn rate; The second determination submodule is used to determine the user change rate score based on the second preset rule and the user change rate. The third determination submodule is used to determine the access frequency score based on the third preset rule and the user access frequency. The third calculation submodule is used to calculate user stickiness using user access ratio score, user change rate score and access frequency score; The computing module further includes: The fifth calculation submodule is used to calculate the user's voice by using the proportion of demand and the proportion of feasibility study amount.

11. An electronic device, characterized in that, include: At least one processor and memory; The memory and processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the front-end application system user profile construction method as described in any one of claims 1 to 9 is implemented.

12. A readable storage medium, characterized in that, It contains an executable program, which, when executed, implements the front-end application system user profile construction method as described in any one of claims 1 to 9.

Images