CN119128260A - Content recommendation method, device, equipment and medium based on Gaussian mixture model - Google Patents
Content recommendation method, device, equipment and medium based on Gaussian mixture model Download PDFInfo
- Publication number
- CN119128260A CN119128260A CN202411171655.5A CN202411171655A CN119128260A CN 119128260 A CN119128260 A CN 119128260A CN 202411171655 A CN202411171655 A CN 202411171655A CN 119128260 A CN119128260 A CN 119128260A
- Authority
- CN
- China
- Prior art keywords
- user
- index
- gaussian mixture
- mixture model
- index chain
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of machine learning and financial science and technology, and particularly discloses a content recommendation method, device, computer equipment and storage medium based on a Gaussian mixture model. When a user login is detected, user information is acquired, the user information is processed based on a first preset algorithm, a user category is determined, an index chain recommendation template corresponding to the user category is determined based on a preset mapping relation table, wherein the mapping relation table comprises mapping relations between the user category and the index chain recommendation template, and content recommendation of operation indexes is performed based on the index chain recommendation template for users to check. According to the index chain recommendation template corresponding to the user category, accurate content recommendation can be provided for the user, the user does not need to spend time and energy to screen and search interesting operation indexes and signboard contents in the content of the business App, important operation information is prevented from being omitted, and enterprise management efficiency and decision accuracy of the user are improved.
Description
Technical Field
The present application relates to the field of machine learning and financial technology, and in particular, to a content recommendation method, apparatus, computer device and storage medium based on a gaussian mixture model.
Background
With the increasing complexity and increasing informatization of enterprise operations, enterprise managers need to know the operation conditions of enterprises in time in order to make correct decisions and management. Commercial apps (software applications) have become an important channel for employers or high-level businesses to understand business operations as a common enterprise informatization tool. Commercial apps often contain rich business indexes and signage content to help the manager to better understand sales, profits, human resources, inventory, supply chain, etc. of the enterprise. However, as the business indexes and the contents of the signboards in the business App are more and more, the user needs to screen and find the business indexes and the contents of the signboards required by the user from the contents of the business App, for example, when a bank performs business management or evaluates the risk condition of some companies, business personnel are required to acquire business indexes and data related to tasks, such as business income, profit, asset scale, asset profit margin and the like, from a plurality of contents. This not only wastes time and effort, reduces enterprise management efficiency, but also may miss important business information, resulting in inaccurate evaluation results of related businesses, and further reduces decision accuracy. Therefore, how to improve the enterprise management efficiency and the decision accuracy is a problem to be solved.
Disclosure of Invention
The application provides a content recommendation method, a content recommendation device, computer equipment and a storage medium based on a Gaussian mixture model, so that enterprise management efficiency and decision accuracy are improved.
In a first aspect, the present application provides a content recommendation method based on a gaussian mixture model, the method comprising:
When the user login is detected, user information is acquired, the user information is processed based on a first preset algorithm, and the user category is determined;
determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises the mapping relation between the user category and the index chain recommendation template;
And recommending the content of the operation index based on the index chain recommendation template for the user to check.
In a second aspect, the present application further provides a content recommendation device based on a gaussian mixture model, where the device includes:
the user category determining module is used for acquiring user information when the user login is detected, processing the user information based on a first preset algorithm and determining the user category;
the recommendation template determining module is used for determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises the mapping relation between the user category and the index chain recommendation template;
And the content recommendation module is used for recommending the content of the operation index based on the index chain recommendation template so as to be checked by a user.
In a third aspect, the application further provides a computer device, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor is used for executing the computer program and realizing the content recommendation method based on the Gaussian mixture model when executing the computer program.
In a fourth aspect, the present application also provides a computer readable storage medium storing a computer program, which when executed by a processor causes the processor to implement a content recommendation method based on a gaussian mixture model as described above.
The application discloses a content recommendation method, a device, computer equipment and a storage medium based on a Gaussian mixture model, which are used for acquiring user information when a user login is detected, processing the user information based on a first preset algorithm to determine a user category, determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises a mapping relation between the user category and the index chain recommendation template, and recommending content of an operation index based on the index chain recommendation template for the user to check. According to the index chain recommendation template corresponding to the user category, accurate content recommendation can be provided for the user, the user does not need to spend time and energy to screen and search interesting operation indexes and signboard contents in the content of the business App, important operation information is prevented from being omitted, and enterprise management efficiency and decision accuracy of the user are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart illustrating a first embodiment of a content recommendation method based on a Gaussian mixture model provided by an embodiment of the application;
FIG. 2 is a flow chart illustrating a second embodiment of a content recommendation method based on a Gaussian mixture model provided by an embodiment of the application;
FIG. 3 is a flow chart illustrating a third embodiment of a content recommendation method based on a Gaussian mixture model provided by an embodiment of the application;
FIG. 4 is a schematic block diagram of a content recommendation device based on a Gaussian mixture model according to an embodiment of the application;
fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
The embodiment of the application provides a content recommendation method, a content recommendation device, computer equipment and a storage medium based on a Gaussian mixture model. The content recommendation method based on the Gaussian mixture model can be applied to a server, provides accurate content recommendation for users according to index chain recommendation templates corresponding to user types, does not need users to spend time and energy to screen and search interesting operation indexes and billboard contents in the content of a business App, avoids missing important operation information, and improves enterprise management efficiency and decision accuracy of the users. The server may be an independent server or a server cluster.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating a first embodiment of a content recommendation method based on a gaussian mixture model according to an embodiment of the present application. The content recommendation method based on the Gaussian mixture model can be applied to a server and used for providing accurate content recommendation for users according to index chain recommendation templates corresponding to user types, the users do not need to spend time and energy to screen and search interesting operation indexes and billboard contents in the content of a business App, important operation information is prevented from being omitted, and enterprise management efficiency and decision accuracy of the users are improved.
As shown in fig. 1, the content recommendation method based on the gaussian mixture model specifically includes steps S101 to S103.
S101, when a user login is detected, acquiring user information, processing the user information based on a first preset algorithm, and determining a user category;
In one embodiment, the user information may be obtained from an account number logged in by the user, or may be collected by a popup query or the like. By way of example, the user information may include user identity (e.g., bank credit manager, bank risk control officer, business sales manager, business production manager, etc.), user administration (e.g., loan approval, loan risk assessment, sales policy formulation, production policy formulation, etc.).
In one embodiment, the first preset algorithm may be a gaussian mixture model, or may be another crowd clustering algorithm, for grouping users or crowds according to their characteristics, behaviors, or other relevant attributes. By way of example, users may be categorized by user identity and user administration business, with user categories including loan risk assessment personnel, sales policy establishment personnel, and the like.
In a specific embodiment, after a user logs in, cluster analysis is performed on user information based on a first preset algorithm, and a user category of a current user is determined.
S102, determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises the mapping relation between the user category and the index chain recommendation template;
in one embodiment, the mapping table is used to store user categories, index chain recommendation templates, and the mapping of each user category to an index chain recommendation template.
In one embodiment, the index chain refers to a chain in which a plurality of indexes are connected in series according to a certain sequence to form a service change trend. The index chain recommendation template is a standardized framework for constructing and analyzing index chains, and provides a series of combinations and sequences of indexes according to business scenes and targets.
In a specific embodiment, whether the user category of the current user exists is searched in the mapping relation table, if so, an index chain recommendation template corresponding to the user category is obtained, and content recommendation is performed to the user based on the index chain recommendation template in a subsequent process. If the new category of the user belongs to the index chain recommendation template, acquiring the current observation data of the user, processing the current observation data by using a Gaussian mixture model, acquiring the index chain recommendation template corresponding to the new category of the user, and recommending the content to the user by using the index chain recommendation template.
S103, recommending the content of the operation index based on the index chain recommendation template for the user to check.
In one embodiment, according to indexes and index sequences in the index chain recommendation template, corresponding indexes and data recommendation corresponding to the indexes are obtained from the APP logged in by the user and are recommended to the user for viewing.
Illustratively, the index and index order in the index chain recommendation template may be "borrower credit case-borrower income case-borrower liability case-borrower property case", and content is recommended to the bank credit manager in accordance with the index and index order to quickly provide the bank credit manager with effective information.
The embodiment provides a content recommendation method, device, computer equipment and storage medium based on a Gaussian mixture model, wherein when a user login is detected, user information is acquired, the user information is processed based on a first preset algorithm, a user category is determined, an index chain recommendation template corresponding to the user category is determined based on a preset mapping relation table, the mapping relation table comprises a mapping relation between the user category and the index chain recommendation template, and content recommendation of operation indexes is performed based on the index chain recommendation template for users to check. According to the index chain recommendation template corresponding to the user category, accurate content recommendation can be provided for the user, the user does not need to spend time and energy to screen and search interesting operation indexes and signboard contents in the content of the business App, important operation information is prevented from being omitted, and enterprise management efficiency and decision accuracy of the user are improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating a second embodiment of a content recommendation method based on a gaussian mixture model according to an embodiment of the present application. The content recommendation method based on the Gaussian mixture model can be applied to a server, and is used for generating a mapping relation table of user categories and index chain recommendation templates according to user information and historical observation indexes of historical users, determining the index chain recommendation templates corresponding to the users based on the mapping relation table, further providing accurate content recommendation for the users according to the index chain recommendation templates, and the users do not need to spend time and effort to screen and search interesting operation indexes and billboard contents in the content of a business App, so that important operation information is avoided being omitted, and enterprise management efficiency and decision accuracy of the users are improved.
As shown in fig. 2, before the step S103, the content recommendation method based on the gaussian mixture model specifically further includes steps S201 to S204.
S201, acquiring user information and historical observation indexes of at least one historical user;
In one embodiment, the historical user is a user who has used the current business APP, and the historical observation index is obtained by analyzing the user's behavioral data during use of the business APP. Specifically, the behavior data of the user is analyzed, and the operation index (such as user activity, order quantity, sales and the like) which is checked by the user is extracted as the historical observation index.
S202, converting the historical observation index into a feature vector;
Further, the step S202 includes performing abnormal index screening on the historical observation indexes to obtain an observation index set, processing the observation index set based on a preset dimension to obtain a target index chain, and performing word vector conversion on the target index chain to obtain the feature vector.
Further, the processing of the observation index set based on the preset dimension to obtain a target index chain comprises the steps of analyzing the observation index set based on the preset dimension to generate an initial index chain, and deleting each operation index in the initial index chain based on a preset rule to obtain the target index chain.
In one embodiment, the historical observation index is subjected to anomaly detection, an anomaly index is determined, and the anomaly index is deleted to obtain an observation index set.
In one embodiment, the preset dimensions include a session dimension and a day dimension. The conversation dimension focuses on the behavior mode of the user in single interaction, comprising a behavior sequence, residence time, event triggering frequency and the like of the user in one conversation, analyzes a conversion path of the user in the conversation, identifies key behavior nodes such as page browsing, adding commodities to shopping carts, completing purchase and the like, and identifies abnormal behaviors in the conversation such as sudden jump-out or long-time inactivity. The day dimension focuses on the behavior mode of a user in a certain time period (such as one day), including the daily active user number, the user retention rate, the daily average transaction amount and the like, analyzes the daily trend and the periodic change of the user behavior, such as the difference between a weekday and a weekend, the flow peak of a holiday and the like, identifies the user behavior mode of a specific date, and evaluates the influence of a marketing activity or a special event.
In one embodiment, the set of observation indicators is processed through a session dimension and a day dimension to obtain an indicator chain. Specifically, the data is grouped according to the dimension of the session, and index values in each session, such as the number of active users, the order quantity, sales, etc., of each session are counted. The data are grouped according to the day dimension, and data index values of each day, such as the number of active users, the order quantity, the sales and the like, are counted. According to the service requirement, proper indexes are selected and connected in series according to a certain sequence to form an index chain. For example, three indexes of the number of active users, the order quantity and the sales can be selected and connected in series according to the time sequence to form an initial index chain reflecting the business change trend.
In one embodiment, the index i that is repeated in adjacent positions of the index chain is eliminated by the following formula.
In one embodiment, abnormal indexes in the initial index chain are removed, and indexes with poor timeliness (history index names) are mapped to the latest operation index names to obtain the target index chain.
In one embodiment, the target index chains are subjected to word vector conversion to obtain feature vectors, specifically, through construction Embedding (embedding), each target index chain is converted into feature vectors conforming to word semantic relations, and Input required by the model is obtained, namely input= Emebdding ([ ind1, ind2,.. indn ]).
S203, processing the user information and the feature vector based on a Gaussian mixture model, and determining at least one user category and an index chain recommendation template corresponding to each user category;
Further, before the step S203, the method further includes obtaining target parameter data related to the gaussian mixture model based on a second preset algorithm and the historical observation index, generating an initial gaussian mixture model based on the target parameter data, obtaining a verification data set, obtaining classification accuracy of the initial gaussian mixture model based on the verification data set, and taking the initial gaussian mixture model as the gaussian mixture model when the classification accuracy is greater than or equal to a preset accuracy threshold.
Further, the verification data set comprises index observation data of at least one user and an actual observation index chain, and the classification accuracy of the initial Gaussian model is obtained based on the verification data set, and the method comprises the steps of processing the index observation data of at least one user based on the initial Gaussian model to obtain at least one prediction index chain corresponding to the user; and comparing the prediction index chain with the actual index chain to obtain the classification accuracy.
In one embodiment, the second preset algorithm is an EM (Expectation-maximization) algorithm. Specifically, assuming that M gaussian distributions exist in the hidden space of the index chain, the probability distribution obeyed by the index chain is:
Where P (x) is the probability that the observed data x belongs to the current class, P (x|m) =p (x; μ m, Σm) is the probability density function of the mth gaussian model, P (k) =pi m is the weight of the mth gaussian model, Σm is the covariance of the mth gaussian model, μ m is the mean of the mth gaussian model.
The iteration solution is carried out through an EM algorithm, and the method is divided into an E step and an M step, and is as follows:
E, step E:
Wherein z i =j denotes that the ith index is from the jth model, Probability from the jth model for the ith index.
The M step is as follows:
Wherein, For the ith index is the probability from z (i), z (i) is the class to which the ith index corresponds.
Solving by the Laplace method to obtain:
Order the Then there are:
Wherein,
At the completion of the iteration, target parameter data pi, μ, Σ relating to the gaussian mixture model are obtained.
In one embodiment, an initial gaussian model is obtained according to target parameter data, and index observation data in the verification data set is correspondingly clustered through the initial gaussian model, so that a prediction index chain of each type of user can be obtained. And comparing the prediction index chain with an actual index chain in the verification data set to obtain the classification accuracy of the initial Gaussian model.
In one embodiment, when the classification accuracy is greater than or equal to a preset accuracy threshold, the initial gaussian model at that time is taken as a gaussian mixture model. When the classification accuracy is smaller than a preset accuracy threshold, adjusting relevant parameters of the model, such as increasing or decreasing the number of Gaussian distributions (namely the number of components), and obtaining a new Gaussian model until the classification accuracy is larger than or equal to the preset accuracy threshold. The accuracy threshold can be freely set by a user according to the needs.
S204, generating the mapping relation table based on at least one user category and the index chain recommendation template corresponding to each user category.
In one embodiment, the corresponding relationship between each user category and the index chain recommendation template is used as the mapping relationship between the user category and the index chain recommendation template.
In one embodiment, each user category and the corresponding index chain recommendation template are stored in a table in a one-to-one correspondence mode, and a mapping relation table is generated.
Referring to fig. 3, fig. 3 is a flowchart illustrating a third embodiment of a content recommendation method based on a gaussian mixture model according to an embodiment of the present application. The content recommendation method based on the Gaussian mixture model can be applied to a server, and is used for acquiring current observation data of a user when the user is a new type user, acquiring an index chain recommendation template of the new type user through the Gaussian mixture model, recommending content of an operation index to the user, and improving the observation efficiency of the new type user in a business APP, and further improving the enterprise management efficiency and decision accuracy of the user.
As shown in fig. 3, after the step S101 of the content recommendation method based on the gaussian mixture model, steps S301 to S303 are specifically further included.
S301, monitoring current observation data of the user when the user category is a new category;
s302, analyzing the current observation data based on a Gaussian mixture model to obtain an index chain recommendation template corresponding to the new category;
S303, recommending the content of the operation index to the user based on the index chain recommendation template.
In one embodiment, when the user category is a new category, the index chain recommendation template corresponding to the new category cannot be determined according to the preset mapping relation table. The operation of the user needs to be monitored, and the current observation data of the user is obtained.
In one embodiment, the current observation data is index data that is currently being observed by a new class of users.
In one embodiment, the current observed data is analyzed using a Gaussian mixture model to obtain an index chain recommendation template corresponding to the new category. Specifically, abnormality detection is performed on the current observation data, and the abnormality data is deleted. And processing the current observed data after deleting the abnormal data based on the session dimension and the day dimension to generate an initial index chain. And eliminating repeated indexes and abnormal indexes at adjacent positions in the initial index chain to obtain a target index chain. And converting the target index chain into feature vectors conforming to the word semantic relation through Embedding to serve as input parameters of the Gaussian mixture model. And inputting the feature vector into a Gaussian mixture model to obtain an index recommendation template of the new class of users.
In one embodiment, content recommendation may be made during the current observation of the user based on the obtained index recommendation template. Illustratively, current observation data of the user is obtained according to the current observation process of the user, and subsequent observation content is recommended to the user after an index chain recommendation template is obtained according to the current observation data. The method can improve the observation efficiency of the new class of users in the business APP, and further improve the enterprise management efficiency and the decision accuracy of the users.
In another embodiment, content recommendation may also be performed during the next observation of the user based on the obtained index recommendation template.
In one embodiment, after the index chain recommendation template of the new class of users is obtained, the user class and the index recommendation template are stored in the mapping relation table for the next use.
In the above embodiment, when the user is a new class user, the current observation data of the user may be obtained, and the index chain recommendation template of the new class user is obtained through the gaussian mixture model, so as to recommend the content of the operation index to the user, thereby improving the observation efficiency of the new class user in the commercial APP, and further improving the enterprise management efficiency and the decision accuracy of the user.
Referring to fig. 4, fig. 4 is a schematic block diagram of a content recommendation device based on a gaussian mixture model according to an embodiment of the present application, where the content recommendation device based on the gaussian mixture model is used to execute the content recommendation method based on the gaussian mixture model. Wherein, the content recommendation device based on the Gaussian mixture model can be configured on a server.
As shown in fig. 4, the content recommendation device 400 based on the gaussian mixture model includes:
the user category determining module 401 is configured to obtain user information when a user login is detected, process the user information based on a first preset algorithm, and determine a user category;
A recommendation template determining module 402, configured to determine an index chain recommendation template corresponding to the user category based on a preset mapping relation table, where the mapping relation table includes a mapping relation between the user category and the index chain recommendation template;
The content recommendation module 403 is configured to perform content recommendation of the operation index based on the index chain recommendation template, so as to be viewed by a user.
Further, the content recommendation device 400 based on the gaussian mixture model further includes a mapping relation table generating module, where the mapping relation table generating module includes:
The historical data acquisition sub-module is used for acquiring user information and historical observation indexes of at least one historical user;
the characteristic vector obtaining submodule is used for converting the historical observation index into a characteristic vector;
the recommendation template obtaining sub-module is used for processing the user information and the feature vector based on a Gaussian mixture model and determining at least one user category and an index chain recommendation template corresponding to each user category;
and the mapping relation table generation sub-module is used for generating the mapping relation table based on at least one user category and the index chain recommendation template corresponding to each user category.
Further, the feature vector obtaining sub-module includes:
The index set obtaining unit is used for carrying out abnormal index screening on the historical observation indexes to obtain an observation index set;
the target index chain obtaining unit is used for processing the observation index set based on a preset dimension to obtain a target index chain;
And the characteristic vector obtaining unit is used for carrying out word vector conversion on the target index chain to obtain the characteristic vector.
Further, the target index chain obtaining unit includes:
the initial index chain generation subunit is used for analyzing the observation index set based on a preset dimension to generate an initial index chain;
And the target index chain obtaining subunit is used for deleting each operation index in the initial index chain based on a preset rule to obtain a target index chain.
Further, the recommendation template determining module 402 further includes a gaussian mixture model obtaining sub-module, where the gaussian mixture model obtaining sub-module includes:
the target parameter data obtaining unit is used for obtaining target parameter data related to the Gaussian mixture model based on a second preset algorithm and the historical observation index;
an initial Gaussian model generation unit, which is used for generating an initial Gaussian model based on the target parameter data;
The classification accuracy obtaining unit is used for obtaining a verification data set and obtaining the classification accuracy of the initial Gaussian model based on the verification data set;
and the Gaussian mixture model determining unit is used for taking the initial Gaussian mixture model as the Gaussian mixture model when the classification accuracy is greater than or equal to a preset accuracy threshold.
Further, the verification data set includes index observation data of at least one user and an actual observation index chain, and the classification accuracy obtaining unit includes:
an observation index chain obtaining subunit, configured to process index observation data of at least one user based on the initial gaussian model, to obtain at least one prediction index chain corresponding to the user;
And the classification accuracy obtaining subunit is used for comparing the prediction index chain with the actual index chain to obtain the classification accuracy.
Further, the content recommendation device 400 based on the gaussian mixture model further includes:
the data monitoring module is used for monitoring the current observation data of the user when the user category is a new category;
the template obtaining module is used for analyzing the current observation data based on a Gaussian mixture model to obtain an index chain recommendation template corresponding to the new category;
And the content recommendation module is used for recommending the content of the operation index to the user based on the index chain recommendation template.
It should be noted that, for convenience and brevity of description, the specific working process of the apparatus and each module described above may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The apparatus described above may be implemented in the form of a computer program which is executable on a computer device as shown in fig. 5.
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device may be a server.
With reference to FIG. 5, the computer device includes a processor, memory, and a network interface connected by a system bus, where the memory may include a non-volatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program comprises program instructions that, when executed, cause the processor to perform any of a variety of content recommendation methods based on a gaussian mixture model.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium that, when executed by a processor, causes the processor to perform any of a variety of content recommendation methods based on a gaussian mixture model.
The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the Processor may be a central processing unit (Central Processing Unit, CPU), it may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein in one embodiment the processor is configured to run a computer program stored in the memory to implement the steps of:
When the user login is detected, user information is acquired, the user information is processed based on a first preset algorithm, and the user category is determined;
determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises the mapping relation between the user category and the index chain recommendation template;
And recommending the content of the operation index based on the index chain recommendation template for the user to check.
In one embodiment, before implementing determining the index chain recommendation template corresponding to the user category based on the preset mapping relation table, the processor is further configured to implement:
acquiring user information and historical observation indexes of at least one historical user;
Converting the historical observation index into a feature vector;
Processing the user information and the feature vector based on a Gaussian mixture model, and determining at least one user category and an index chain recommendation template corresponding to each user category;
And generating the mapping relation table based on at least one user category and the index chain recommendation template corresponding to each user category.
In one embodiment, the processor, when implementing converting the historical observation index into a feature vector, is configured to implement:
Screening the historical observation indexes to obtain an observation index set;
processing the observation index set based on a preset dimension to obtain a target index chain;
And carrying out word vector conversion on the target index chain to obtain the feature vector.
In one embodiment, the processor is configured to, when implementing processing the set of observation indexes based on a preset dimension to obtain a target index chain, implement:
Analyzing the observation index set based on a preset dimension to generate an initial index chain;
and deleting each operation index in the initial index chain based on a preset rule to obtain a target index chain.
In one embodiment, before implementing the gaussian mixture model, the processor is further configured to, before implementing processing the user information and the feature vector to determine at least one user category and an index chain recommendation template corresponding to each user category, implement:
Acquiring target parameter data related to the Gaussian mixture model based on a second preset algorithm and the historical observation index;
Generating an initial Gaussian model based on the target parameter data;
Acquiring a verification data set, and acquiring the classification accuracy of the initial Gaussian model based on the verification data set;
and when the classification accuracy is greater than or equal to a preset accuracy threshold, taking the initial Gaussian mixture model as the Gaussian mixture model.
In one embodiment, the verification data set includes index observation data of at least one user and an actual observation index chain, and the processor is configured, when implementing obtaining the classification accuracy of the initial gaussian model based on the verification data set, to implement:
Processing index observation data of at least one user based on the initial Gaussian model to obtain at least one prediction index chain corresponding to the user;
And comparing the prediction index chain with the actual index chain to obtain the classification accuracy.
In one embodiment, the processor is further configured to, when implementing that the user login is detected, obtain user information, process the user information based on a first preset algorithm, and determine a user category, after that, implement:
When the user category is a new category, monitoring current observation data of the user;
analyzing the current observation data based on a Gaussian mixture model to obtain an index chain recommendation template corresponding to the new category;
and recommending the content of the operation index to the user based on the index chain recommendation template.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, the computer program comprises program instructions, and the processor executes the program instructions to realize any content recommendation method based on the Gaussian mixture model.
The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are provided on the computer device.
While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. A content recommendation method based on a gaussian mixture model, comprising:
When the user login is detected, user information is acquired, the user information is processed based on a first preset algorithm, and the user category is determined;
determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises the mapping relation between the user category and the index chain recommendation template;
And recommending the content of the operation index based on the index chain recommendation template for the user to check.
2. The content recommendation method based on the gaussian mixture model according to claim 1, wherein before determining the index chain recommendation template corresponding to the user category based on the preset mapping relation table, the method further comprises:
acquiring user information and historical observation indexes of at least one historical user;
Converting the historical observation index into a feature vector;
Processing the user information and the feature vector based on a Gaussian mixture model, and determining at least one user category and an index chain recommendation template corresponding to each user category;
And generating the mapping relation table based on at least one user category and the index chain recommendation template corresponding to each user category.
3. The gaussian mixture model based content recommendation method according to claim 2, wherein said converting said historical observation index into a feature vector comprises:
Screening the historical observation indexes to obtain an observation index set;
processing the observation index set based on a preset dimension to obtain a target index chain;
And carrying out word vector conversion on the target index chain to obtain the feature vector.
4. The content recommendation method based on the gaussian mixture model according to claim 3, wherein the processing the set of observation indexes based on a preset dimension to obtain a target index chain comprises:
Analyzing the observation index set based on a preset dimension to generate an initial index chain;
and deleting each operation index in the initial index chain based on a preset rule to obtain a target index chain.
5. The content recommendation method based on a gaussian mixture model according to claim 2, wherein before processing the user information and the feature vector based on the gaussian mixture model to determine at least one user category and an index chain recommendation template corresponding to each user category, the method further comprises:
Acquiring target parameter data related to the Gaussian mixture model based on a second preset algorithm and the historical observation index;
Generating an initial Gaussian model based on the target parameter data;
Acquiring a verification data set, and acquiring the classification accuracy of the initial Gaussian model based on the verification data set;
and when the classification accuracy is greater than or equal to a preset accuracy threshold, taking the initial Gaussian mixture model as the Gaussian mixture model.
6. The gaussian mixture model based content recommendation method according to claim 5, wherein said verification data set comprises at least one user's index observation data and an actual observation index chain, said obtaining a classification accuracy of said initial gaussian model based on said verification data set comprises:
Processing index observation data of at least one user based on the initial Gaussian model to obtain at least one prediction index chain corresponding to the user;
And comparing the prediction index chain with the actual index chain to obtain the classification accuracy.
7. The content recommendation method based on a gaussian mixture model according to claims 1 to 6, wherein when a user login is detected, user information is acquired, the user information is processed based on a first preset algorithm, and after determining a user category, the method further comprises:
When the user category is a new category, monitoring current observation data of the user;
analyzing the current observation data based on a Gaussian mixture model to obtain an index chain recommendation template corresponding to the new category;
and recommending the content of the operation index to the user based on the index chain recommendation template.
8. A content recommendation device based on a gaussian mixture model, comprising:
the user category determining module is used for acquiring user information when the user login is detected, processing the user information based on a first preset algorithm and determining the user category;
the recommendation template determining module is used for determining an index chain recommendation template corresponding to the user category based on a preset mapping relation table, wherein the mapping relation table comprises the mapping relation between the user category and the index chain recommendation template;
And the content recommendation module is used for recommending the content of the operation index based on the index chain recommendation template so as to be checked by a user.
9. A computer device, the computer device comprising a memory and a processor;
the memory is used for storing a computer program;
The processor for executing the computer program and for implementing the content recommendation method based on a gaussian mixture model according to any of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, causes the processor to implement the content recommendation method based on a gaussian mixture model according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411171655.5A CN119128260A (en) | 2024-08-23 | 2024-08-23 | Content recommendation method, device, equipment and medium based on Gaussian mixture model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411171655.5A CN119128260A (en) | 2024-08-23 | 2024-08-23 | Content recommendation method, device, equipment and medium based on Gaussian mixture model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119128260A true CN119128260A (en) | 2024-12-13 |
Family
ID=93769155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411171655.5A Pending CN119128260A (en) | 2024-08-23 | 2024-08-23 | Content recommendation method, device, equipment and medium based on Gaussian mixture model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119128260A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119938900A (en) * | 2025-04-03 | 2025-05-06 | 中国水利水电第五工程局有限公司 | Implementation method and system for displaying recommended content on the dashboard of a science and technology management system |
-
2024
- 2024-08-23 CN CN202411171655.5A patent/CN119128260A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119938900A (en) * | 2025-04-03 | 2025-05-06 | 中国水利水电第五工程局有限公司 | Implementation method and system for displaying recommended content on the dashboard of a science and technology management system |
| CN119938900B (en) * | 2025-04-03 | 2025-06-24 | 中国水利水电第五工程局有限公司 | Method and system for realizing recommended content display of bulletin board of science and technology management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11818136B2 (en) | System and method for intelligent agents for decision support in network identity graph based identity management artificial intelligence systems | |
| US10977293B2 (en) | Technology incident management platform | |
| CN111401777B (en) | Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium | |
| US20210357835A1 (en) | Resource Deployment Predictions Using Machine Learning | |
| US11853337B2 (en) | System to determine a credibility weighting for electronic records | |
| US9798788B1 (en) | Holistic methodology for big data analytics | |
| CN107862425B (en) | Wind control data acquisition method, device and system and readable storage medium | |
| CN112348321A (en) | Risk user identification method and device and electronic equipment | |
| CN118606559A (en) | Product recommendation method, device, equipment and storage medium | |
| CN115204886A (en) | Account identification method and device, electronic equipment and storage medium | |
| US11922352B1 (en) | System and method for risk tracking | |
| CN114493853A (en) | Credit rating evaluation method, device, electronic device and storage medium | |
| CN119128260A (en) | Content recommendation method, device, equipment and medium based on Gaussian mixture model | |
| CN117011080A (en) | Financial risk prediction method, apparatus, device, medium and program product | |
| Thöni et al. | An information system for assessing the likelihood of child labor in supplier locations leveraging Bayesian networks and text mining | |
| CN116757851A (en) | Data configuration method, device, equipment and storage medium based on artificial intelligence | |
| CN118504752A (en) | Determination method of transaction risk prediction model, transaction risk prediction method, device, equipment, storage medium and program product | |
| CN112712270A (en) | Information processing method, device, equipment and storage medium | |
| Ang et al. | Investment and risk management with online news and heterogeneous networks | |
| CN117709710A (en) | Risk identification method, apparatus, device and storage medium | |
| CN115795345A (en) | Information processing method, device, equipment and storage medium | |
| CN120088007B (en) | Commodity market dynamic forecasting method, system, medium and equipment | |
| Bohlscheid | Social security data mining: An Australian case study | |
| Tripathy et al. | A Comparison of Interdependent Deep Learning Models and Exponential Smoothing Method for Predicting Bitcoin Price | |
| Kenyon | An intelligent method of predicting insurance claims fraud |
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 |