CN111737576A - Application function personalized recommendation method and device - Google Patents
Application function personalized recommendation method and device Download PDFInfo
- Publication number
- CN111737576A CN111737576A CN202010574579.8A CN202010574579A CN111737576A CN 111737576 A CN111737576 A CN 111737576A CN 202010574579 A CN202010574579 A CN 202010574579A CN 111737576 A CN111737576 A CN 111737576A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- function
- determining
- list
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an application function personalized recommendation method and device, wherein the method comprises the following steps: acquiring user behavior data, user static data and service system function list data; preprocessing user behavior data, user static data and service system function list data, and determining preprocessed user behavior data, preprocessed user static data and preprocessed service system function list data; determining a user behavior-function matrix according to the preprocessed user behavior data; determining a user similarity recommendation list according to the user behavior-function matrix; determining the module entering data according to the preprocessed user behavior data and the preprocessed user static data; determining a prediction result matrix according to the mode entering data; determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix; and determining a personalized application function list according to the data of the preprocessed service system function list and the function recommendation list. The invention realizes the personalized recommendation of the application function in the service system.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to a personalized recommendation method and device for application functions.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, the service system used by the bank has a plurality of service application functions (Web application), and the use condition of a user presents a long-tail effect. In the prior art, a service and a developer set a typesetting mode of a service application function of a service system according to service needs and experience, so that the arrangement of application function modules is preset, the menu display form is single and fixed, and when the service personnel set a function classification and a function menu typesetting, subjective factors are easily introduced, so that the function classification and the typesetting layout deviate from the actual use preference of a user, and the service quality of the service system is influenced; all users adopt a fixed unified design in advance, and the application function menus seen by all users are the same, so that the individual requirements of different users and different posts on functions cannot be met, and the user experience is reduced; often, a service system is upgraded and modified continuously, and functions are more and more, so that a plurality of application function paths are deep, and functions required by a user are difficult to find; meanwhile, the familiarity of each branch line with the service system is inconsistent, so that part of application functions are only used by a plurality of branch lines.
The service functions required by the user can be difficultly found quickly and effectively under various conditions, and often some service function paths required by the user are deep and can be reached by clicking for many times, even some service function users can not find the position at which the service function users can be placed, so that the convenience requirement of the user on the service function use can not be met, the service quality of a service system is limited, and the user experience and the office efficiency are reduced.
Therefore, how to provide a new solution, which can solve the above technical problems, is a technical problem to be solved in the art.
Disclosure of Invention
The embodiment of the invention provides an application function personalized recommendation method, which realizes the personalized recommendation of service functions and comprises the following steps:
acquiring user behavior data, user static data and service system function list data;
preprocessing user behavior data, user static data and service system function list data, and determining preprocessed user behavior data, preprocessed user static data and preprocessed service system function list data;
determining a user behavior-function matrix according to the preprocessed user behavior data;
determining a user similarity recommendation list according to the user behavior-function matrix;
determining the module entering data according to the preprocessed user behavior data and the preprocessed user static data;
determining a prediction result matrix according to the mode entering data;
determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix;
and determining a personalized application function list according to the data of the preprocessed service system function list and the function recommendation list.
The embodiment of the present invention further provides an application function personalized recommendation device, including:
the data acquisition module is used for acquiring user behavior data, user static data and service system function list data;
the preprocessing module is used for preprocessing the user behavior data, the user static data and the service system function list data and determining the preprocessed user behavior data, the preprocessed user static data and the preprocessed service system function list data;
the user behavior-function matrix determining module is used for determining a user behavior-function matrix according to the preprocessed user behavior data;
the user similarity recommendation list determining module is used for determining a user similarity recommendation list according to the user behavior-function matrix;
the module entering data determining module is used for determining module entering data according to the preprocessed user behavior data and the preprocessed user static data;
the prediction result matrix determining module is used for determining a prediction result matrix according to the mode entering data;
the function recommendation list determining module is used for determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix;
and the personalized application function list determining module is used for determining a personalized application function list according to the preprocessed service system function list data and the function recommendation list.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the application function personalized recommendation method when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program for executing the application function personalized recommendation method.
According to the application function personalized recommendation method and device provided by the embodiment of the invention, historical behavior information and user personal information of a user are comprehensively considered, the user behavior data and user static data are utilized for preprocessing, the current demand degree of the user on a function module is predicted through machine learning, a user similarity recommendation list and a prediction result matrix are constructed, the user similarity recommendation list and the prediction result matrix are fused, a function recommendation list is determined, and finally, a personalized application function list is output by combining with the data of a preprocessing service system function list. The embodiment of the invention can perform personalized recommendation on the service function in the service system by using the existing client information, provide daily required functions for users and improve the office efficiency; the functions which are not found by the user are provided, the potential needs of the user are mined, and the office effectiveness and the service quality and efficiency of the system are further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a schematic diagram of an application function personalized recommendation method according to an embodiment of the present invention.
Fig. 2 is a flowchart of an application function personalized recommendation method according to an embodiment of the present invention.
Fig. 3 is a flowchart of determining a user similarity recommendation list according to an application function personalized recommendation method in an embodiment of the present invention.
Fig. 4 is a schematic diagram of a computer device operating the method for implementing personalized recommendation of application functions according to the present invention.
Fig. 5 is a schematic diagram of an application function personalized recommendation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
As shown in fig. 1, a schematic diagram of an application function personalized recommendation method according to an embodiment of the present invention is provided, an embodiment of the present invention provides an application function personalized recommendation method, which implements personalized recommendation of a service function, and the method includes:
step 101: acquiring user behavior data, user static data and service system function list data;
step 102: preprocessing user behavior data, user static data and service system function list data, and determining preprocessed user behavior data, preprocessed user static data and preprocessed service system function list data;
step 103: determining a user behavior-function matrix according to the preprocessed user behavior data;
step 104: determining a user similarity recommendation list according to the user behavior-function matrix;
step 105: determining the module entering data according to the preprocessed user behavior data and the preprocessed user static data;
step 106: determining a prediction result matrix according to the mode entering data;
step 107: determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix;
step 108: and determining a personalized application function list according to the data of the preprocessed service system function list and the function recommendation list.
The application function personalized recommendation method provided by the embodiment of the invention comprehensively considers the historical behavior information of the user and the personal information of the user, carries out preprocessing by utilizing the behavior data of the user and the static data of the user, predicts the current demand degree of the user on a function module through machine learning, constructs a user similarity recommendation list and a prediction result matrix, fuses the user similarity recommendation list and the prediction result matrix, determines a function recommendation list, and finally outputs a personalized application function list by combining the function list data of a preprocessing service system. The embodiment of the invention can perform personalized recommendation on the service function in the service system by using the existing client information, provide daily required functions for users and improve the office efficiency; the functions which are not found by the user are provided, the potential needs of the user are mined, and the office effectiveness and the service quality and efficiency of the system are further improved.
The aforementioned Long Tail Effect, the English name Long Tail Effect; the "head" and "tail" are two statistical terms. The projection in the middle of the normal curve is called the "head"; the relatively flat parts on both sides are called tail. From the perspective of human demand, most of the demand will be concentrated on the head, and this part we can call popular, while the demand distributed on the tail is personalized, scattered and small demand. This part of the differentiated, small demand creates a long "tail" on the demand curve, and the so-called long tail effect is in its number, adding up all non-popular markets creates a larger market than the popular market. Therefore, in order to enhance the attraction of the bank to the customers distributed in the long tail effect, the personalized function recommendation needs to be carried out on the customers with the long tail effect so as to realize the personalized recommendation on the business functions in the banking system, better serve the 'mainstream' and 'non-mainstream' customer groups of the bank, realize the daily required functions for the users and improve the office efficiency; the functions which are not found by the user are provided, the potential needs of the user are mined, and the office effectiveness and the service quality and efficiency of the system are further improved.
To implement the above functions, as shown in fig. 2, which is a flowchart of an application function personalized recommendation method according to an embodiment of the present invention, an application function personalized recommendation method according to an embodiment of the present invention includes: the method comprises six parts, namely data acquisition, data preprocessing, matrix construction, feature engineering, model school and fusion and function list output; in specific implementation, the work flow of the six parts may include:
acquiring user behavior data, user static data and service system function list data; preprocessing user behavior data, user static data and service system function list data, and determining preprocessed user behavior data, preprocessed user static data and preprocessed service system function list data; determining a user behavior-function matrix according to the preprocessed user behavior data; determining a user similarity recommendation list according to the user behavior-function matrix; determining the module entering data according to the preprocessed user behavior data and the preprocessed user static data; determining a prediction result matrix according to the mode entering data; determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix; and determining a personalized application function list according to the data of the preprocessed service system function list and the function recommendation list.
In the foregoing to obtain the user behavior data, the user static data, and the service system function list data, in an embodiment, the method may include: collecting user behavior data, user static data and service system function list data from service system logs and a database; the service system function list data comprises post information and a service system function list. The user behavior data refers to historical click behaviors and service function records of a user in a service system, and can reflect the use habits of the client in the service system, and the user static data refers to non-user behavior data, namely data which is related to the user and does not change in a short time generally, such as a user address after desensitization processing, user personal information, a user contact way, a user account type and the like.
When the method for recommending an application function in an embodiment of the present invention is specifically implemented, in an embodiment, the pre-processing the user behavior data, the user static data, and the service system function list data to determine the pre-processed user behavior data, the pre-processed user static data, and the pre-processed service system function list data includes:
preprocessing user behavior data and user static data, eliminating data with null values and irregularities, screening data which do not meet modeling requirements according to a set screening rule, and determining preprocessed user behavior data and preprocessed user static data;
preprocessing the service system function list data, and determining the preprocessed service system function list data; wherein, the preprocessing service system function list data comprises: a hot function list and a new function list.
In the embodiment, in the collected user behavior data and user static data, situations such as null values and irregular formats exist, the user behavior data and the user static data need to be removed, the data with null values and irregular formats are removed, then high-quality data needs to be adopted for modeling data during modeling, a data screening rule needs to be set to meet modeling requirements, data which do not meet the modeling requirements are screened according to the set screening rule, and the preprocessed user behavior data and the preprocessed user static data are determined. In the collected service system function list data, service functions are not arranged in order, so that the post information and the service system function list need to be classified according to the condition of unified post user classification, and a hot function list and a new function list under the same post user classification are counted to form preprocessed service system function list data. By preprocessing the function list data of the service system, the new functions of the user service system can be obviously displayed, the new functions can be better popularized, and more users can try to use the functions; meanwhile, the hot function list can further improve the working efficiency of the service system, so that a user can directly click the hot function on the main page, the searching process is reduced, and the working efficiency is improved.
When the method for recommending an application function in an individualized manner according to an embodiment of the present invention is implemented specifically, in an embodiment, the determining a user behavior-function matrix according to the preprocessed user behavior data includes:
performing time attenuation on the preprocessed user behavior data by using a time attenuation model, and determining the preprocessed user behavior data after the time attenuation;
and preprocessing the user behavior data after time attenuation to construct a user behavior-function matrix.
Because the current behavior of the user can better reflect the current demand of the user, the time attenuation model is utilized to process the user behavior data, namely, the influence of the historical behavior data closer to the current time on the model is larger, and otherwise, the influence is smaller; then, constructing a user behavior-function matrix according to the user behavior data after time attenuation;
when the application function personalized recommendation method of the embodiment of the present invention is specifically implemented, in an embodiment, the pre-processing user behavior data after time decay is determined as follows:
wherein, f (x)ij) Preprocessing user behavior data after time decay; t is a click behavior value function; t is t0The time when the click behavior occurs for the first time; k is an attenuation factor; t is the current time; t is tijThe time when the i user last clicked on the j function module.
The foregoing expressions of preprocessing user behavior data after determining the time decay are only examples, and those skilled in the art will understand that the above formulas may be modified in certain forms and other parameters or data may be added or other specific formulas may be provided according to the needs, and such modifications are all within the scope of the present invention.
When the application function personalized recommendation method of the embodiment of the present invention is specifically implemented, in an embodiment, a user behavior-function matrix is constructed as follows:
wherein, CuThe user behavior-function matrix is a matrix of m × n, each row represents a function module clicked by the user iiRepresents the ith user; siRepresents the jth functional module; y isijIndicates the ith user at time tijClicking the jth function module; sijIndicating that the user clicked module j to decay and ∑ f (x)ij) (ii) a M denotes a functional module.
The aforementioned expressions for constructing the user behavior-function matrix are only examples, and those skilled in the art will understand that the above formulas may be modified in some forms and other parameters or data may be added as needed, or other specific formulas may be provided, and such modifications are all within the scope of the present invention.
Fig. 3 is a flowchart of determining a user similarity recommendation list in an application function personalized recommendation method according to an embodiment of the present invention, and as shown in fig. 3, when the application function personalized recommendation method according to the embodiment of the present invention is implemented in detail, in an embodiment, the determining a user similarity recommendation list according to a user behavior-function matrix includes:
step 301: calculating the similarity between every two users according to the user behavior-function matrix through a Pearson correlation coefficient formula, and determining a user similarity matrix;
step 302: sequencing the user similarity matrixes from large to small according to the similarity, and determining the user similarity matrix arrangement;
step 303: and selecting the user similarity matrix from the maximum value in the user similarity matrix arrangement according to the set selection quantity, calculating the user function click condition of the selected user similarity matrix, and determining a user similarity recommendation list.
The Pearson correlation coefficient is a more complex method than the Euclidean distance in the prior art which can judge the interest similarity of people; it may tend to give better results when the data is not very normative.
Assuming there are two variables X, Y, the user similarity between the two variables can be calculated by the Pearson correlation coefficient equation:
where ρ isX,YIs the user similarity between variables X, Y; cov is covariance; e is a mathematical expectation; sigmaXIs the standard deviation of the X variable; sigmaYIs the standard deviation of the Y variable; mu.sXIs the mean of the X variables; mu.sYIs the mean of the Y variables.
The expression of the above-mentioned pearson correlation coefficient formula is an example, and those skilled in the art will understand that the above formula may be modified in certain forms and other parameters or data may be added or other specific formulas may be provided according to the needs, and such modifications are within the scope of the present invention.
In the embodiment, the similarity between every two users can be calculated through the Pearson correlation coefficient formula according to the user behavior-function matrix, and then the user similarity matrix is determined; further sorting the user similarity matrixes from large to small according to the similarity, and determining the user similarity matrix arrangement; and finally, selecting the user similarity matrix from the maximum value in the user similarity matrix arrangement according to the set selection quantity, calculating the user function click condition of the selected user similarity matrix, and determining a user similarity recommendation list. In an example, when the set selection number is N (N is a positive integer), the TOP-N user similarity matrices are selected from the user similarity matrix arrangement from the maximum value, and then the user function click conditions of the selected TOP-N user similarity matrices are calculated to determine the user similarity recommendation list.
When the method for recommending an application function in an individualized manner according to an embodiment of the present invention is specifically implemented, in an embodiment, the determining the module entry data according to the pre-processed user behavior data and the pre-processed user static data includes:
and performing feature derivation and feature engineering by combining business knowledge and engineering experience according to the preprocessed user behavior data and the preprocessed user static data, and determining the input-mode data.
In the embodiment, the aforementioned feature engineering, also referred to as variable selection, attribute selection or variable subset selection in machine learning or statistics, is a process of selecting relevant features and constructing feature subsets in model construction, and its essence is an engineering activity, which aims to extract features from raw data to the maximum extent for use by algorithms and models. Further, Collaborative Filtering recommendation (Collaborative Filtering) is rapidly becoming a popular technology in information Filtering and information systems. And (3) analyzing the user interests through collaborative filtering, finding similar (interested) users of the specified user in the user group, and integrating the click conditions of the similar users on a certain article to form preference degree prediction of the specified user on the article. In the embodiment, feature derivation and feature engineering can be performed according to the preprocessed user behavior data and the preprocessed user static data by combining business knowledge and engineering experience, and the modeling data is determined.
In a specific implementation of the method for recommending an application function in an individualized manner according to an embodiment of the present invention, in an embodiment, the determining a prediction result matrix according to the modeling data includes:
and inputting the in-mode data into the XGB OST + LR algorithm model by using a big data distributed computation framework, and determining a prediction result matrix.
The XGBOOST + LR algorithm model comprises two parts, namely XGBOOST and LR.
Wherein XGBOST is based on GBDT, strives to exert speed and efficiency to the utmost, and is called X (extreme) GBoosted; the aforementioned GBDT (Gradient Boosting Decision Tree) is to solve the optimization problem of a general loss function, and the method is to use the negative Gradient of the loss function to simulate the approximate value of the residual error in the regression problem in the current model value, and is a Gradient descent Tree model.
Among them, the aforementioned LR (Logistic Regression) is a Regression problem for processing a dependent variable as a classification variable, and is usually a two-classification or two-term distribution problem, and can also process a multi-classification problem, and belongs to a classification method.
The XGB OST + LR algorithm model combines the XGB OST part and the LR part, and the leaf nodes of the XGB OST tree model are used as the input of the LR algorithm, so that the performance of the model can be improved. Therefore, the model entering data is input into the XGB OST + LR algorithm model by using a big data distributed computing framework, and a prediction result matrix can be determined.
When the method for recommending an application function in an individualized manner according to an embodiment of the present invention is implemented specifically, in an embodiment, the determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix includes:
training the user similarity recommendation list and the prediction result matrix through an LR model, and determining a weighting coefficient;
performing weighted fusion on the user similarity recommendation list and the prediction result matrix by using a weighting coefficient to determine a user-function probability matrix;
and sequencing the user-function probability matrixes from large to small to determine a function recommendation list.
In the embodiment, the user similarity recommendation list and the prediction result matrix are subjected to weighted fusion by using a weighting coefficient to determine a user-function probability matrix according to the following mode:
Pu＝αFu+βEuwherein α + β is 1
Wherein, PuIs a user-function probability matrix; fuTo useA user similarity recommendation list; euα and β are weighting coefficients.
The above mentioned expressions for determining the user-function probability matrix are only examples, and it will be understood by those skilled in the art that the above formulas may be modified in certain forms and other parameters or data may be added or other specific formulas may be provided according to the needs, and such modifications are all within the scope of the present invention.
When the method for recommending an application function in an embodiment of the present invention is implemented specifically, in an embodiment, the determining a personalized application function list according to the pre-processed service system function list data and the function recommendation list includes:
and according to the set recommendation conditions, selecting service functions from the function recommendation list, the hot function list and the new function list, and establishing a personalized application function list.
In the embodiment, one set recommendation condition is to take TOP-N service functions from the function recommendation list, the hit function list and the new function list respectively, and establish a personalized application function list of the client. Further, another set recommendation condition is provided in the embodiments of the present invention: assuming that the length of all service system function lists in a service system is L, the first N function lists are taken, the first m function lists are taken, and the TOP-N function recommendation list is taken, namely the first N function recommendation lists are taken; and (4) eliminating the front L-N-m hot function lists and the front L-N-m new function lists, and establishing a personalized application function list by combining N function recommendation lists.
The embodiment of the invention forms user behavior data by utilizing the user function click behavior data; forming user static data by utilizing user personal information, post information and the like, and automatically learning the demand degree and preference of the user for different functions by combining a function list, a new function list and a hot function list of a service system; learning a recommendation model based on user behavior similarity by using a click behavior of a user on a service system function; a recommendation model based on user behavior similarity, a prediction model of XGB OST + LR based on user behavior and static information and a fusion scheme thereof; in the internal business system of the bank, the hot function list, the dynamically variable function recommendation list and the new function recommendation list are combined for use. By utilizing a big data distributed computing framework and a data mining method, the personalized requirements of users on a bank internal business system are automatically mined, and a personalized application function list is automatically generated; the embodiment of the invention comprehensively considers factors in various aspects such as historical behavior information of a user, personal information of the user, hot functions of different posts, new functions and the like, eliminates subjective factors, objectively provides a function list suitable for different users, and obviously provides a function which is not used by a certain user but is frequently used by the user on the same post. And providing a personalized display scheme of the function list of the business system in the bank. By the scheme, daily required functions can be obviously provided for users, and the office efficiency is improved; the method has the advantages that good functions which are not found by the user are provided, the potential needs of the user are mined, and the office effectiveness and the service quality and efficiency of the system are further improved; the new function of the user service system is provided, so that the user requirement is met, and the popularization cost of the new function by a demander can be saved.
Fig. 4 is a schematic diagram of a computer device operating the method for implementing personalized recommendation of application functions according to the present invention, and as shown in fig. 4, an embodiment of the present invention further provides a computer device including a memory, a processor, and a computer program stored in the memory and operable on the processor, where the processor implements the method for implementing personalized recommendation of application functions when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program for implementing the personalized recommendation method for application functions.
The embodiment of the invention also provides an application function personalized recommendation device, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to the application function personalized recommendation method, the implementation of the device can refer to the implementation of the application function personalized recommendation method, and repeated parts are not described again.
Fig. 5 is a schematic diagram of an application function personalized recommendation device according to an embodiment of the present invention, and as shown in fig. 5, an application function personalized recommendation device according to an embodiment of the present invention further includes:
a data obtaining module 501, configured to obtain user behavior data, user static data, and service system function list data;
a preprocessing module 502, configured to preprocess the user behavior data, the user static data, and the service system function list data, and determine preprocessed user behavior data, preprocessed user static data, and preprocessed service system function list data;
a user behavior-function matrix determining module 503, configured to determine a user behavior-function matrix according to the preprocessed user behavior data;
a user similarity recommendation list determining module 504, configured to determine a user similarity recommendation list according to the user behavior-function matrix;
a module entering data determining module 505, configured to determine module entering data according to the pre-processing user behavior data and the pre-processing user static data;
a prediction result matrix determining module 506, configured to determine a prediction result matrix according to the mode entry data;
a function recommendation list determining module 507, configured to determine a function recommendation list according to the user similarity recommendation list and the prediction result matrix;
and the personalized application function list determining module 508 is configured to determine a personalized application function list according to the pre-processed service system function list data and the function recommendation list.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the preprocessing module is specifically configured to:
preprocessing user behavior data and user static data, eliminating data with null values and irregularities, screening data which do not meet modeling requirements according to a set screening rule, and determining preprocessed user behavior data and preprocessed user static data;
preprocessing the service system function list data, and determining the preprocessed service system function list data; wherein, the preprocessing service system function list data comprises: a hot function list and a new function list.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the user behavior-function matrix determination module is specifically configured to:
performing time attenuation on the preprocessed user behavior data by using a time attenuation model, and determining the preprocessed user behavior data after the time attenuation;
and preprocessing the user behavior data after time attenuation to construct a user behavior-function matrix.
In an embodiment of the application function personalized recommendation device according to an embodiment of the present invention, the user behavior-function matrix determination module is further configured to determine the preprocessed user behavior data after time decay according to the following manner:
wherein, f (x)ij) Preprocessing user behavior data after time decay; t is a click behavior value function; t is t0The time when the click behavior occurs for the first time; k is an attenuation factor; t is the current time; t is tijThe time when the i user last clicked on the j function module.
In an embodiment of the application function personalized recommendation device according to an embodiment of the present invention, the user behavior-function matrix determining module is further configured to construct a user behavior-function matrix according to the following manner:
wherein, CuThe user behavior-function matrix is a matrix of m × n, each row represents a function module clicked by the user iiRepresents the ith user; siRepresents the jth functional module; y isijIndicates the ith user at time tijClicking the jth function module; sijIndicating that the user clicked module j to decay and ∑ f (x)ij) (ii) a M denotes a functional module.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the user similarity recommendation list determining module is specifically configured to:
calculating the similarity between every two users according to the user behavior-function matrix through a Pearson correlation coefficient formula, and determining a user similarity matrix;
sequencing the user similarity matrixes from large to small according to the similarity, and determining the user similarity matrix arrangement;
and selecting the user similarity matrix from the maximum value in the user similarity matrix arrangement according to the set selection quantity, calculating the user function click condition of the selected user similarity matrix, and determining a user similarity recommendation list.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the module for determining the module entry data is specifically configured to:
and performing feature derivation and feature engineering by combining business knowledge and engineering experience according to the preprocessed user behavior data and the preprocessed user static data, and determining the input-mode data.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the prediction result matrix determination module is specifically configured to:
and inputting the in-mode data into the XGB OST + LR algorithm model by using a big data distributed computation framework, and determining a prediction result matrix.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the function recommendation list determining module is specifically configured to:
training the user similarity recommendation list and the prediction result matrix through an LR model, and determining a weighting coefficient;
performing weighted fusion on the user similarity recommendation list and the prediction result matrix by using a weighting coefficient to determine a user-function probability matrix;
and sequencing the user-function probability matrixes from large to small to determine a function recommendation list.
In an embodiment of the invention, when the application function personalized recommendation device according to the embodiment of the invention is specifically implemented, the personalized application function list determination module is specifically configured to:
and according to the set recommendation conditions, selecting service functions from the function recommendation list, the hot function list and the new function list, and establishing a personalized application function list.
To sum up, the application function personalized recommendation method and apparatus provided by the embodiments of the present invention comprehensively consider the historical behavior information of the user and the personal information of the user, perform preprocessing by using the user behavior data and the user static data, predict the current degree of demand of the user on the function module through machine learning, construct a user similarity recommendation list and a prediction result matrix, fuse the user similarity recommendation list and the prediction result matrix, determine a function recommendation list, and finally output a personalized application function list by combining the data of the function list of the pre-processing service system. The embodiment of the invention can perform personalized recommendation on the service function in the service system by using the existing client information, provide daily required functions for users and improve the office efficiency; the functions which are not found by the user are provided, the potential needs of the user are mined, and the office effectiveness and the service quality and efficiency of the system are further improved. The embodiment of the invention comprehensively considers the factors in various aspects such as user static data such as user behavior data, user personal information and the like, hot functions of different posts, new functions and the like, eliminates subjective factors, and objectively provides a function list suitable for different users. Considering the personalized requirements of different users on the function list, establishing a personalized recommendation model of each user, displaying the respective required functions for each user, improving the user experience and improving the office efficiency; the new functions of the user service system are obviously displayed, the new functions are better popularized, and more users can try to use the functions. The user behavior data is combined with a machine learning algorithm, the function use preferences of different users on the same post are mined, a function list meeting the user requirements is automatically generated, the functions used by other people are provided for the user, and the improvement of the office efficiency of the user is promoted.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may 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, and the like) having computer-usable program code embodied therein.
The present 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 flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (13)
1. An application function personalized recommendation method is characterized by comprising the following steps:
acquiring user behavior data, user static data and service system function list data;
preprocessing user behavior data, user static data and service system function list data, and determining preprocessed user behavior data, preprocessed user static data and preprocessed service system function list data;
determining a user behavior-function matrix according to the preprocessed user behavior data;
determining a user similarity recommendation list according to the user behavior-function matrix;
determining the module entering data according to the preprocessed user behavior data and the preprocessed user static data;
determining a prediction result matrix according to the mode entering data;
determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix;
and determining a personalized application function list according to the data of the preprocessed service system function list and the function recommendation list.
2. The method of claim 1, wherein pre-processing the user behavior data, the user static data, and the business system function manifest data to determine pre-processed user behavior data, pre-processed user static data, and pre-processed business system function manifest data, comprises:
preprocessing user behavior data and user static data, eliminating data with null values and irregularities, screening data which do not meet modeling requirements according to a set screening rule, and determining preprocessed user behavior data and preprocessed user static data;
preprocessing the service system function list data, and determining the preprocessed service system function list data; wherein, the preprocessing service system function list data comprises: a hot function list and a new function list.
3. The method of claim 1, wherein determining a user behavior-function matrix from the pre-processed user behavior data comprises:
performing time attenuation on the preprocessed user behavior data by using a time attenuation model, and determining the preprocessed user behavior data after the time attenuation;
and preprocessing the user behavior data after time attenuation to construct a user behavior-function matrix.
4. The method of claim 3, wherein the pre-processed user behavior data after time decay is determined as follows:
wherein, f (x)ij) Preprocessing user behavior data after time decay; t is a click behavior value function; t is t0The time when the click behavior occurs for the first time; k is an attenuation factor; t is the current time; t is tijThe time when the i user last clicked on the j function module.
5. The method of claim 4, wherein the user behavior-function matrix is constructed as follows:
wherein, CuThe user behavior-function matrix is a matrix of m × n, each row represents a function module clicked by the user iiRepresents the ith user; siRepresents the jth functional module; y isijIndicates the ith user at time tijClicking the jth function module; sijIndicating that the user clicked module j to decay and ∑ f (x)ij) (ii) a M denotes a functional module.
6. The method of claim 1, wherein determining a user similarity recommendation list based on a user behavior-function matrix comprises:
calculating the similarity between every two users according to the user behavior-function matrix through a Pearson correlation coefficient formula, and determining a user similarity matrix;
sequencing the user similarity matrixes from large to small according to the similarity, and determining the user similarity matrix arrangement;
and selecting the user similarity matrix from the maximum value in the user similarity matrix arrangement according to the set selection quantity, calculating the user function click condition of the selected user similarity matrix, and determining a user similarity recommendation list.
7. The method of claim 1, wherein determining the modelled data based on the pre-processed user behavior data and the pre-processed user static data comprises:
and performing feature derivation and feature engineering by combining business knowledge and engineering experience according to the preprocessed user behavior data and the preprocessed user static data, and determining the input-mode data.
8. The method of claim 1, wherein determining a prediction matrix based on the modulo-in data comprises:
and inputting the in-mode data into the XGB OST + LR algorithm model by using a big data distributed computation framework, and determining a prediction result matrix.
9. The method of claim 1, wherein determining the function recommendation list based on the user similarity recommendation list and the prediction result matrix comprises:
training the user similarity recommendation list and the prediction result matrix through an LR model, and determining a weighting coefficient;
performing weighted fusion on the user similarity recommendation list and the prediction result matrix by using a weighting coefficient to determine a user-function probability matrix;
and sequencing the user-function probability matrixes from large to small to determine a function recommendation list.
10. The method of claim 2, wherein determining the personalized application function list based on the pre-processed business system function list data and the function recommendation list comprises:
and according to the set recommendation conditions, selecting service functions from the function recommendation list, the hot function list and the new function list, and establishing a personalized application function list.
11. An application function personalized recommendation device, comprising:
the data acquisition module is used for acquiring user behavior data, user static data and service system function list data;
the preprocessing module is used for preprocessing the user behavior data, the user static data and the service system function list data and determining the preprocessed user behavior data, the preprocessed user static data and the preprocessed service system function list data;
the user behavior-function matrix determining module is used for determining a user behavior-function matrix according to the preprocessed user behavior data;
the user similarity recommendation list determining module is used for determining a user similarity recommendation list according to the user behavior-function matrix;
the module entering data determining module is used for determining module entering data according to the preprocessed user behavior data and the preprocessed user static data;
the prediction result matrix determining module is used for determining a prediction result matrix according to the mode entering data;
the function recommendation list determining module is used for determining a function recommendation list according to the user similarity recommendation list and the prediction result matrix;
and the personalized application function list determining module is used for determining a personalized application function list according to the preprocessed service system function list data and the function recommendation list.
12. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 10 when executing the computer program.
13. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing a method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010574579.8A CN111737576B (en) | 2020-06-22 | 2020-06-22 | Application function personalized recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010574579.8A CN111737576B (en) | 2020-06-22 | 2020-06-22 | Application function personalized recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111737576A true CN111737576A (en) | 2020-10-02 |
| CN111737576B CN111737576B (en) | 2023-09-19 |
Family
ID=72650425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010574579.8A Active CN111737576B (en) | 2020-06-22 | 2020-06-22 | Application function personalized recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111737576B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344744A (en) * | 2021-08-02 | 2021-09-03 | 广东电网有限责任公司中山供电局 | Personalized business function calculation method and device for power system |
| CN114706624A (en) * | 2022-03-29 | 2022-07-05 | 中国建设银行股份有限公司 | Method and device for recommending mobile application service function entrance |
| CN114860918A (en) * | 2022-05-25 | 2022-08-05 | 重庆邮电大学 | Mobile application recommendation method and device fusing multi-source reliable information |
| CN115604049A (en) * | 2022-12-14 | 2023-01-13 | 忆月启函（盐城）科技有限公司（Cn） | Intelligent communication network system for household multifunctional monitoring |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130185292A1 (en) * | 2012-01-04 | 2013-07-18 | Trustgo Mobile, Inc. | Application recommendation system |
| CN105893609A (en) * | 2016-04-26 | 2016-08-24 | 南通大学 | Mobile APP recommendation method based on weighted mixing |
| CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video content recommending method, device and system |
| CN106874355A (en) * | 2016-12-28 | 2017-06-20 | 浙江浙大网新集团有限公司 | The collaborative filtering method of social networks and user's similarity is incorporated simultaneously |
| CN107562818A (en) * | 2017-08-16 | 2018-01-09 | 中国工商银行股份有限公司 | Information recommendation system and method |
| US20180174218A1 (en) * | 2016-12-19 | 2018-06-21 | Sap Se | Recommendation optmization with a dynamic mixture of frequent and occasional recommendations |
-
2020
- 2020-06-22 CN CN202010574579.8A patent/CN111737576B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130185292A1 (en) * | 2012-01-04 | 2013-07-18 | Trustgo Mobile, Inc. | Application recommendation system |
| CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video content recommending method, device and system |
| CN105893609A (en) * | 2016-04-26 | 2016-08-24 | 南通大学 | Mobile APP recommendation method based on weighted mixing |
| US20180174218A1 (en) * | 2016-12-19 | 2018-06-21 | Sap Se | Recommendation optmization with a dynamic mixture of frequent and occasional recommendations |
| CN106874355A (en) * | 2016-12-28 | 2017-06-20 | 浙江浙大网新集团有限公司 | The collaborative filtering method of social networks and user's similarity is incorporated simultaneously |
| CN107562818A (en) * | 2017-08-16 | 2018-01-09 | 中国工商银行股份有限公司 | Information recommendation system and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344744A (en) * | 2021-08-02 | 2021-09-03 | 广东电网有限责任公司中山供电局 | Personalized business function calculation method and device for power system |
| CN114706624A (en) * | 2022-03-29 | 2022-07-05 | 中国建设银行股份有限公司 | Method and device for recommending mobile application service function entrance |
| CN114860918A (en) * | 2022-05-25 | 2022-08-05 | 重庆邮电大学 | Mobile application recommendation method and device fusing multi-source reliable information |
| CN115604049A (en) * | 2022-12-14 | 2023-01-13 | 忆月启函（盐城）科技有限公司（Cn） | Intelligent communication network system for household multifunctional monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111737576B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111737576A (en) | Application function personalized recommendation method and device | |
| US9405427B2 (en) | Adaptive user interface using machine learning model | |
| CN111143655B (en) | Method for calculating news popularity | |
| CN103198086A (en) | Information processing device, information processing method, and program | |
| US20210019213A1 (en) | Systems and methods for the analysis of user experience testing with ai acceleration | |
| CN112633962B (en) | Service recommendation method and device, computer equipment and storage medium | |
| CN111061962A (en) | Recommendation method based on user score analysis | |
| US20100223099A1 (en) | Method and apparatus for a multi-dimensional offer optimization (mdoo) | |
| CN106557558A (en) | A kind of data analysing method and device | |
| WO2019061664A1 (en) | Electronic device, user's internet surfing data-based product recommendation method, and storage medium | |
| US10191985B1 (en) | System and method for auto-curation of Q and A websites for search engine optimization | |
| CN112153426A (en) | Content account management method and device, computer equipment and storage medium | |
| CN111967971A (en) | Bank client data processing method and device | |
| Antonyuk et al. | Medical news aggregation and ranking of taking into account the user needs | |
| CN111611488A (en) | Information recommendation method and device based on artificial intelligence and electronic equipment | |
| CN117829914B (en) | Digital media advertisement effect evaluation system | |
| US11909100B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
| CN110502639B (en) | Information recommendation method and device based on problem contribution degree and computer equipment | |
| CN112417267A (en) | User behavior analysis method and device, computer equipment and storage medium | |
| CN115983900A (en) | Method, apparatus, device, medium, and program product for constructing user marketing strategy | |
| CN115063035A (en) | Customer evaluation method, system, equipment and storage medium based on neural network | |
| CN110807676A (en) | Long-tail user mining method and device, electronic equipment and storage medium | |
| Zhou et al. | MMSE: A multi-model stacking ensemble learning algorithm for purchase prediction | |
| Ulian et al. | Exploring the effects of different Clustering Methods on a News Recommender System | |
| CN117271905A (en) | Crowd image-based lateral demand analysis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |