CN116307489A - Visual dynamic analysis method and system based on user behavior modeling - Google Patents
Visual dynamic analysis method and system based on user behavior modeling Download PDFInfo
- Publication number
- CN116307489A CN116307489A CN202310049613.3A CN202310049613A CN116307489A CN 116307489 A CN116307489 A CN 116307489A CN 202310049613 A CN202310049613 A CN 202310049613A CN 116307489 A CN116307489 A CN 116307489A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- data
- target
- behavior analysis
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 274
- 230000000007 visual effect Effects 0.000 title claims abstract description 26
- 230000006399 behavior Effects 0.000 claims description 415
- 238000011161 development Methods 0.000 claims description 56
- 238000004891 communication Methods 0.000 claims description 27
- 230000008520 organization Effects 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 description 5
- 238000013480 data collection Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a visual dynamic analysis method and a visual dynamic analysis system based on user behavior modeling, and relates to the technical field of data intelligent processing.
Description
Technical Field
The invention relates to the technical field of data intelligent processing, in particular to a visual dynamic analysis method and system based on user behavior modeling.
Background
Along with diversification of enterprise business demands, reasonable distribution management and control of enterprise business are required to be guaranteed, optimization flow management and control of multi-business cooperation is realized so as to meet demands of clients, timeliness and completion degree of task completion are required to be guaranteed for long-term development of enterprises, at present, distribution personnel conduct adaptive distribution mainly through group distribution according to user capacities, certain subjectivity exists in the distribution process, certain deviation exists between the distribution personnel and the user suitability, certain hidden danger exists in subsequent task execution, and further improvement is required in task distribution so as to maximize personal capacity.
In the prior art, when an enterprise performs task allocation, the allocation method is insufficient in intelligence, so that an allocation result is inaccurate, the actual degree of fit with a user is insufficient, the task execution efficiency is low, and defects exist in the execution result.
Disclosure of Invention
The application provides a visual dynamic analysis method and a visual dynamic analysis system based on user behavior modeling, which are used for solving the technical problems that when an enterprise in the prior art performs task allocation, the intelligent degree of an allocation method is insufficient, so that an allocation result is inaccurate, the actual degree of fit with a user is insufficient, the task execution efficiency is low, and the execution result has flaws.
In view of the above problems, the present application provides a method and a system for visual dynamic analysis based on user behavior modeling.
In a first aspect, the present application provides a visual dynamic analysis method based on user behavior modeling, the method comprising:
acquiring a digital archive, wherein the digital archive comprises behavior data of a plurality of users;
acquiring a target behavior data set of a target user based on a plurality of behavior types according to the digital archive;
inputting the target behavior data set into a user behavior analysis model to obtain a plurality of user behavior analysis results, wherein the user behavior analysis model comprises a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types;
inputting the analysis results of the plurality of user behaviors into a user portrait analysis model to obtain a target user portrait;
acquiring a current task set;
and distributing a plurality of tasks in the task set to the target user according to the target user portrait.
In a second aspect, the present application provides a visual dynamic analysis system based on user behavior modeling, the system comprising:
the document library acquisition module is used for acquiring a digital archive, wherein the digital archive comprises behavior data of a plurality of users;
the data acquisition module is used for acquiring a target behavior data set of a target user based on a plurality of behavior types according to the digital archive;
the result acquisition module is used for inputting the target behavior data set into a user behavior analysis model to obtain a plurality of user behavior analysis results, wherein the user behavior analysis model comprises a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types;
the portrait acquisition module is used for inputting the analysis results of the plurality of user behaviors into a user portrait analysis model to obtain a target user portrait;
the task acquisition module is used for acquiring a current task set;
and the task issuing module is used for issuing a plurality of tasks in the task set to the target user according to the target user portrait.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the visual dynamic analysis method based on user behavior modeling, a digital archive is obtained, behavior data of a plurality of users are included, a target behavior data set of a target user is obtained based on a plurality of behavior types according to the digital archive, and then a user behavior analysis model is input to obtain a plurality of user behavior analysis results, wherein the user behavior analysis model comprises a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types; the method comprises the steps of inputting a plurality of user behavior analysis results into a user portrait analysis model to obtain a target user portrait, distributing a plurality of tasks in a current task set to the target user based on the target user portrait, solving the technical problems that the distribution method is insufficient in intelligence, the distribution result is accurate enough, the actual matching degree with the user is insufficient, the task execution efficiency is low, the execution result has flaws, and the comprehensive evaluation is performed based on a plurality of behavior types through modeling, so that the intelligent task distribution is realized, the matching degree of the distributed tasks and the user is improved, and the follow-up task execution effect is ensured.
Drawings
FIG. 1 is a schematic flow chart of a visual dynamic analysis method based on user behavior modeling;
FIG. 2 is a schematic diagram of a digital archive acquisition process in a visual dynamic analysis method based on user behavior modeling;
FIG. 3 is a schematic diagram of a target user portrait acquisition flow in a visual dynamic analysis method based on user behavior modeling;
fig. 4 is a schematic structural diagram of a visual dynamic analysis system based on user behavior modeling.
Reference numerals illustrate: the system comprises a document library acquisition module 11, a data acquisition module 12, a result acquisition module 13, a portrait acquisition module 14, a task acquisition module 15 and a task issuing module 16.
Detailed Description
The visual dynamic analysis method and the visual dynamic analysis system based on the user behavior modeling are used for acquiring a digital archive, acquiring a target behavior data set of a target user based on a plurality of behavior types, further inputting a user behavior analysis model to acquire a plurality of user behavior analysis results, inputting the plurality of user behavior analysis results into a user portrait analysis model to acquire a target user portrait, and issuing a plurality of tasks in a current task set to the target user based on the target user behavior analysis results.
Example 1
As shown in fig. 1, the present application provides a visual dynamic analysis method based on user behavior modeling, the method comprising:
step S100: acquiring a digital archive, wherein the digital archive comprises behavior data of a plurality of users;
specifically, along with diversification of business demands of enterprises, in order to facilitate comprehensive management and realize optimization flow management and control of multi-business cooperation, the visual dynamic analysis method based on user behavior modeling provided by the application performs multi-dimensional behavior analysis on a plurality of users, performs adaptive task matching on analysis results, realizes decentralized management and control of integrated tasks, performs tasks independently to realize efficient operation, determines a plurality of task execution users in an enterprise to be managed, comprises a plurality of different occupation directions, takes development behaviors, communication behaviors and organization behaviors as data retrieval dimensions, performs the behavior data acquisition on the plurality of users respectively, performs user corresponding integration identification on data acquisition results, generates a digital archive, and provides a basic basis for subsequent user behavior analysis.
Further, as shown in fig. 2, the step S100 of obtaining the digital archive further includes:
step S110: acquiring a preset time period;
step S120: acquiring behavior data of a plurality of users in the preset time period based on the behavior types to obtain a plurality of behavior data sets, wherein the behavior types comprise development behaviors, communication behaviors and organization behaviors;
step S130: constructing a plurality of entity information based on the plurality of users;
step S140: constructing a plurality of data attributes based on the plurality of behavior types;
step S150: constructing a plurality of data element sets according to the plurality of behavior data sets;
step S160: and constructing the digital archive according to the entity information, the data attributes and the data element sets.
Specifically, a preset time period is obtained, namely, a time interval for collecting user behavior data, the development behavior, the communication behavior and the organization behavior are used as multiple behavior types, task execution capacity of a user can be comprehensively reflected to perform the analysis of the adequacy field, the multiple users are subjected to behavior data collection based on the multiple behavior types based on the preset time period, data collection results correspond to the users, preferably, business requirements corresponding to different stages of an enterprise have differences, and in order to ensure the accuracy of data collection, data collection of multiple time zones in multiple seasons is performed to generate multiple behavior data sets.
Specifically, specific behavior data acquisition corresponding to a plurality of behavior types, namely data entities in a knowledge graph, is respectively carried out on the plurality of users, and the acquired data are corresponding to the plurality of users and are used as the plurality of entity information; determining the plurality of data attributes based on the plurality of behavior types, wherein the plurality of data attributes are in one-to-one correspondence; determining the plurality of sets of data elements based on the plurality of sets of behavioral data; based on the multiple behavior data sets, multi-dimensional data contained in each type of behavior data is determined, and multiple data element sets are constructed, such as development times, communication times, maintenance times and the like. And carrying out association correspondence on the plurality of entity information, the plurality of data attributes and the plurality of data element sets to generate the data archive, and guaranteeing the data accuracy, completeness and standardization of the data archive by carrying out data acquisition regularity so as to facilitate the subsequent rapid identification and extraction of the required data.
Step S200: acquiring a target behavior data set of a target user based on a plurality of behavior types according to the digital archive;
step S300: inputting the target behavior data set into a user behavior analysis model to obtain a plurality of user behavior analysis results, wherein the user behavior analysis model comprises a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types;
specifically, based on the digital archive, data retrieval is performed on the target user, the target user is a user to be subjected to behavior analysis, the digital archive is traversed to identify associated data corresponding to a plurality of behavior types of the target user, data extraction and classification integration are performed, identification is performed based on the data types, so that identification and distinction can be performed quickly later, the target behavior data set is generated, and the target behavior data set is used as sample data to perform the target user behavior analysis.
Further, the user behavior analysis model, namely an auxiliary virtual tool for performing user behavior analysis, is constructed to ensure the accuracy and objectivity of behavior analysis, a plurality of user behavior analysis modules are embedded in the user behavior analysis model and are respectively in one-to-one correspondence with the development behavior, the communication behavior and the organization behavior so as to perform targeted analysis of behavior data, reduce data dimensionality and improve data analysis efficiency, the target behavior data set is input into the user behavior analysis model, data identification and matching are performed based on data identification results, corresponding user behavior analysis modules are determined, data module corresponding transmission analysis is performed, a plurality of module analysis results are output, a plurality of behavior types are corresponding, integrated identification is performed on the corresponding user behavior analysis results, the integrated identification is output as a model output result, the plurality of user behavior analysis results are obtained, and user portrait analysis is further performed based on the result.
Further, the target behavior data set is input into a user behavior analysis model to obtain a plurality of user behavior analysis results, and step S300 of the present application further includes:
step S310: constructing a first user behavior analysis module according to the behavior type of the development behavior;
step S320: constructing a second user behavior analysis module according to the behavior type of the communication behavior;
step S330: constructing a third user behavior analysis module according to the behavior type of the organization behavior;
step S340: obtaining the user behavior analysis model according to the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module;
step S350: the development behavior data, the communication behavior data and the organization behavior data in the target behavior data set are acquired, the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module are input, and a first user behavior analysis result, a second user behavior analysis result and a third user behavior analysis result are acquired and are used as the plurality of user behavior analysis results.
Specifically, sample development data in a plurality of preset time periods are called based on the digital archive, and the first user behavior analysis module, namely a module for development data analysis, is generated by performing supervision training and verification of a feedforward neural network; similarly, aiming at the behavior type of the communication behavior, sample communication data is called to carry out supervision training and verification of a feedforward neural network, and the second user behavior analysis module is generated; and aiming at the behavior type of the organization behaviors, invoking organization communication data to perform supervision training and verification of a feedforward neural network, and generating the third user behavior analysis module, wherein the modeling methods of the first user behavior analysis module, the second behavior analysis module and the third behavior analysis module are the same as a model operation mechanism.
Further, the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module are integrated to generate the user behavior analysis model, the development behavior data, the communication behavior data and the organization behavior data are respectively extracted based on the target behavior data set and input into the user behavior analysis model, data targeted analysis is performed based on the user behavior analysis module matched with the input data, the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result are obtained, and the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result are used as the multiple user behavior analysis results, namely multiple behavior type analysis results of the target user, and targeted analysis of multiple data types is performed by performing multi-module construction, so that the data analysis accuracy and the analysis efficiency can be effectively improved.
Further, according to the behavior type of the development behavior, a first user behavior analysis module is constructed, and step S310 of the present application further includes:
step S311: acquiring a plurality of sample development behavior data based on the preset time period;
step S312: carrying out development capability grading according to the plurality of sample development behavior data to obtain a first user behavior analysis result of the plurality of samples;
step S313: the first user behavior analysis module is constructed based on a feedforward neural network, wherein input data of the first user behavior analysis module is development behavior data, and output data is a first user behavior analysis result;
step S314: obtaining a construction data set, wherein the construction data set is obtained by carrying out data annotation on the plurality of sample development behavior data and the first user behavior analysis results of the plurality of samples;
step S315: and performing supervision training and verification on the first user behavior analysis module by adopting the constructed data set to obtain the first user behavior analysis module with the accuracy meeting the preset requirement.
Specifically, the preset time period is taken as a data acquisition time interval, a plurality of pieces of development behavior data are called as the plurality of pieces of sample development behavior data, the calling randomness of the sample data is required to be ensured, multi-level development capability is set, the plurality of pieces of sample development behavior data are respectively subjected to level judgment, the level judgment result is taken as the first user behavior analysis result of the plurality of samples, the development behavior execution times are in direct proportion to the level judgment result, and the plurality of pieces of sample development behavior data correspond to the first user behavior analysis result of the plurality of samples.
Further, based on a feedforward neural network, a data identification layer and a decision analysis layer are determined as module network layers, the first user behavior analysis module is constructed, the correlation connection identification is carried out on the sample development behavior data and the sample first user behavior analysis results, the sample development behavior data are taken as matching layer nodes, the sample first user behavior analysis results are taken as decision layer nodes, the construction data set is obtained, the construction data set is divided in proportion, a training set and a verification set are determined, the training set is input into the first user behavior analysis module, module supervision training is carried out, node coverage is carried out on repeated data which exist, module verification is carried out based on the verification set, verification results and corresponding sample first user behavior analysis results are checked, whether the module training is qualified or not is judged, secondary training verification can be carried out through sample repartition until the module accurately meets the preset requirements, the constructed first user behavior analysis model is obtained, development behavior data analysis is carried out based on the first user behavior analysis model, and the objectivity and the accuracy of the data analysis result can be effectively improved. The construction process of the second user behavior analysis module and the third user behavior analysis module is the same as that of the first user behavior analysis module, but the construction data are different, and the description is omitted here.
Step S400: inputting the analysis results of the plurality of user behaviors into a user portrait analysis model to obtain a target user portrait;
step S500: acquiring a current task set;
specifically, the user portrait analysis model is constructed, the user portrait analysis model comprises a space coordinate area and a plurality of clustering area labeling results, the plurality of user behavior analysis results are input into the user portrait analysis model, corresponding coordinate axial data is determined based on the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result, a target coordinate point is determined, clusters to which the target coordinate point belongs are determined through clustering area matching, and identification information corresponding to the area is used as a target user portrait to which the target coordinate point belongs. Further, the current task summarization, that is, a plurality of tasks to be executed in a preset time interval, is performed, task integration is performed to obtain a task set to which the task set belongs, and the acquisition of the target user portrait and the task set is performed to tamp the subsequent task allocation of the target user.
Further, as shown in fig. 3, the step S400 of inputting the plurality of user behavior analysis results into the user portrait analysis model to obtain a target user portrait, further includes:
step S410: constructing a user portrait coordinate space according to the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result;
step S420: acquiring a plurality of sample second user behavior analysis results and a plurality of sample third user behavior analysis results, and acquiring a plurality of sample user portrait input data by combining the plurality of sample first user behavior analysis results;
step S430: acquiring a plurality of sample user portraits, wherein each sample user portrait corresponds to at least one sample user portrayal input data;
step S440: inputting the user portrait input data of the plurality of samples into the user portrait coordinate space to obtain a plurality of sample coordinate points;
step S450: performing cluster analysis on the plurality of sample coordinate points to obtain a plurality of cluster results;
step S460: marking the clustering results by adopting the plurality of sample user portraits to obtain the user portrayal analysis model;
step S470: and taking the analysis results of the plurality of user behaviors as target user portraits input data, inputting the user portrayal analysis model, and obtaining the target user portrayal.
Further, the step S470 of inputting the user behavior analysis results as target user portrait input data, inputting the user portrait analysis model, and obtaining the target user portrait further includes:
step S471: inputting the user portrayal analysis model by taking the analysis results of the plurality of user behaviors as target user portrayal input data to obtain a target coordinate point;
step S472: and acquiring a clustering result of the target coordinate point, taking a corresponding sample user portrait as the target user portrait, or acquiring a clustering result nearest to the target coordinate point, and taking a corresponding sample user portrait as the target user portrait.
Specifically, the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result are respectively used as coordinate axes to construct the user portrait coordinate space, a plurality of sample development behavior data are obtained based on the preset time period, development capability classification is carried out on the sample development behavior data, and the first user behavior analysis result of the samples is obtained; similarly, a plurality of sample communication behavior data are obtained, communication capacity grading is carried out, and a second user behavior analysis result of the plurality of samples is obtained; and acquiring a plurality of sample organization behavior data, classifying organization capacity, acquiring third user behavior analysis results of the plurality of samples, and correspondingly integrating the samples to acquire the plurality of sample user portrait input data.
And randomly extracting a group based on the plurality of sample user portraits input data, wherein the group comprises a sample first user behavior analysis result, a sample second user behavior analysis result and a sample third user behavior analysis result, namely corresponding behavior grades, so as to form a sample user portrait, and acquiring the plurality of sample user portraits based on the plurality of sample user portraits input data. Inputting the user portrait input data of the plurality of samples into the user portrait coordinate space, determining the plurality of sample coordinate points, wherein a group of user behavior analysis results, namely three behavior grades, correspond to the coordinate data, clustering the plurality of sample coordinate points, calculating Euclidean distances between every two coordinate points, setting a distance threshold, classifying the distance into the same type when the distance is smaller than the preset threshold, setting the preset threshold according to the distribution condition of the coordinate points, determining a plurality of clusters, preferably, the more the clusters are, the more accurate the corresponding division results are, obtaining the plurality of clustering results, mapping and matching the plurality of sample user portraits with the plurality of clustering results, and marking the user portrait analysis model based on the mapping results.
Specifically, the multiple user behavior analysis results are input into the user portrait analysis model, corresponding axial data is determined based on the corresponding first user behavior analysis result, second user behavior analysis result and third user behavior analysis result, the target coordinate point is obtained, the clustering result of the target coordinate point is determined, and the corresponding labeling sample user portrait is taken as the target user portrait; when the target coordinate point does not belong to the clustering result coverage area, determining the nearest clustering result, judging the nearest clustering result as the clustering area to which the target coordinate point belongs, and taking the marked sample user portrait as the target user portrait so as to ensure the accuracy of target attribution.
Step S600: and distributing a plurality of tasks in the task set to the target user according to the target user portrait.
Further, according to the target user portrait, a plurality of tasks in the task set are issued to the target user, and step S600 of the present application further includes:
step S610: acquiring development behavior proportion information, communication behavior proportion information and organization behavior proportion information in the tasks, and acquiring a plurality of task behavior proportion information sets;
step S620: marking the tasks according to the task behavior duty ratio information sets to obtain task description information;
step S630: acquiring the task quantity of the target user;
step S640: calculating the degree of fit between the target user and the tasks according to the target user portrait and the task description information, and obtaining the information of the degree of fit;
step S650: and selecting a plurality of tasks corresponding to the maximum plurality of fitness information according to the task quantity, and issuing the tasks to the target user.
Specifically, multiple behavior type duty ratio analysis is performed on the task set, the development behavior duty ratio information, the communication behavior duty ratio information and the organization behavior duty ratio information are obtained, task information integration is performed to obtain multiple task behavior duty ratio information sets, wherein the same task comprises three duty ratio information, the multiple tasks are further marked, and multiple task description information is obtained, for example, the development duty ratio of a certain task is 40%, the communication duty ratio is 25% and the maintenance duty ratio is 35%. And evaluating the executable task amount of the target user, acquiring the task amount of the target user, respectively calculating the degree of fit of the target user with the tasks based on the target user portrait and the task description information, and determining a corresponding plurality of persons with higher degree of fit based on the task amount, for example, in the user portrait of the target user, the development level 7, the communication level 5 and the maintenance level 6, wherein the development work content of a certain task accounts for 40%, the communication work content accounts for 25%, the maintenance work content accounts for 35%, the development level 7/18=39% of the target user is calibrated with the development work content 40%, the closer the degree of fit is, the higher the degree of fit is, the plurality of degree of fit information of the target user with respect to the tasks is acquired, the corresponding plurality of persons with higher degree of fit are determined based on the task amount, and the corresponding tasks are determined through reverse matching, and are issued to the target user as the execution tasks of the target user, so that the degree of fit of the task with the target user can be effectively issued, and the task allocation can be guaranteed.
Example two
Based on the same inventive concept as the visual dynamic analysis method based on user behavior modeling in the foregoing embodiments, as shown in fig. 4, the present application provides a visual dynamic analysis system based on user behavior modeling, the system comprising:
the document library acquisition module 11 is used for acquiring a digital archive, wherein the digital archive comprises behavior data of a plurality of users;
the data acquisition module 12 is configured to acquire a target behavior data set of a target user based on a plurality of behavior types according to the digital archive;
the result acquisition module 13 is configured to input the target behavior data set into a user behavior analysis model to obtain a plurality of user behavior analysis results, where the user behavior analysis model includes a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types;
a portrayal acquisition module 14, wherein the portrayal acquisition module 14 is used for inputting the analysis results of the plurality of user behaviors into a user portrayal analysis model to obtain a target user portrayal;
the task acquisition module 15 is used for acquiring a current task set;
and the task issuing module 16 is used for issuing a plurality of tasks in the task set to the target user according to the target user portrait.
Further, the system further comprises:
the period acquisition module is used for acquiring a preset time period;
the behavior data acquisition module is used for acquiring behavior data of a plurality of users in the preset time period based on the behavior types to obtain a plurality of behavior data sets, wherein the behavior types comprise development behaviors, communication behaviors and organization behaviors;
the entity information construction module is used for constructing a plurality of entity information based on the plurality of users;
the data attribute construction module is used for constructing a plurality of data attributes based on the plurality of behavior types;
the data element construction module is used for constructing a plurality of data element sets according to the plurality of behavior data sets;
and the digital archive construction module is used for constructing the digital archive according to the plurality of entity information, the plurality of data attributes and the plurality of data element sets.
Further, the system further comprises:
the first user behavior analysis module building module is used for building the first user behavior analysis module according to the behavior type of the development behavior;
the second user behavior analysis module construction module is used for constructing a second user behavior analysis module according to the behavior type of the communication behavior;
the third user behavior analysis module building module is used for building a third user behavior analysis module according to the behavior type of the organization behaviors;
the model construction module is used for obtaining the user behavior analysis model according to the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module;
the analysis result acquisition module is used for acquiring development behavior data, communication behavior data and organization behavior data in the target behavior data set, inputting the development behavior data, the communication behavior data and the organization behavior data into the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module, and acquiring a first user behavior analysis result, a second user behavior analysis result and a third user behavior analysis result as the plurality of user behavior analysis results.
Further, the system further comprises:
the sample data acquisition module is used for acquiring a plurality of sample development behavior data based on the preset time period;
the sample dividing module is used for carrying out development capability grade division according to the plurality of sample development behavior data to obtain a plurality of sample first user behavior analysis results;
the behavior analysis module construction module is used for constructing the first user behavior analysis module based on a feedforward neural network, wherein the input data of the first user behavior analysis module is development behavior data, and the output data is a first user behavior analysis result;
the construction data set acquisition module is used for acquiring a construction data set, wherein the construction data set is obtained by carrying out data annotation on the plurality of sample development behavior data and the first user behavior analysis results of the plurality of samples;
and the supervision and training module is used for performing supervision and training and verification on the first user behavior analysis module by adopting the constructed data set to obtain the first user behavior analysis module with the accuracy meeting the preset requirement.
Further, the system further comprises:
the coordinate space construction module is used for constructing a user portrait coordinate space according to the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result;
the input data acquisition module is used for acquiring a plurality of sample second user behavior analysis results and a plurality of sample third user behavior analysis results, and acquiring a plurality of sample user portrait input data by combining the plurality of sample first user behavior analysis results;
the system comprises a sample user portrait acquisition module, a sample user portrait acquisition module and a sample user portrait processing module, wherein the sample user portrait acquisition module is used for acquiring a plurality of sample user portraits, and each sample user portrait corresponds to at least one sample user portrait input data;
the coordinate point acquisition module is used for inputting the user portrait input data of the plurality of samples into the user portrait coordinate space to obtain a plurality of sample coordinate points;
the coordinate point clustering module is used for carrying out cluster analysis on the plurality of sample coordinate points to obtain a plurality of clustering results;
the result marking module is used for marking the plurality of clustering results by adopting the plurality of sample user portraits to obtain the user portraits analysis model;
and the target user portrait acquisition module is used for inputting the plurality of user behavior analysis results serving as target user portrait input data into the user portrait analysis model to obtain the target user portrait.
Further, the system further comprises:
the target coordinate point acquisition module is used for taking the plurality of user behavior analysis results as target user portrait input data, inputting the user portrait analysis model and obtaining target coordinate points;
and the target user portrait determining module is used for acquiring a clustering result in which the target coordinate points fall, taking a corresponding sample user portrait as the target user portrait, or acquiring a clustering result nearest to the target coordinate points, and taking a corresponding sample user portrait as the target user portrait.
Further, the system further comprises:
the task behavior proportion information acquisition module is used for acquiring development behavior proportion information, communication behavior proportion information and organization behavior proportion information in the tasks to acquire a plurality of task behavior proportion information sets;
the task marking module is used for marking the tasks according to the task behavior duty ratio information sets to obtain task description information;
the task amount acquisition module is used for acquiring the task amount of the target user;
the compliance information acquisition module is used for calculating the compliance of the target user and the tasks according to the target user portrait and the task description information to acquire a plurality of pieces of compliance information;
the task selection issuing module is used for selecting a plurality of tasks corresponding to the maximum plurality of fit degree information according to the task quantity and issuing the tasks to the target user.
In the present disclosure, through the foregoing detailed description of a visual dynamic analysis method based on user behavior modeling, those skilled in the art may clearly know a visual dynamic analysis method and a visual dynamic analysis system based on user behavior modeling in this embodiment, and for the apparatus disclosed in the embodiments, the description is relatively simple because it corresponds to the method disclosed in the embodiments, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A visual dynamic analysis method based on user behavior modeling, the method comprising:
acquiring a digital archive, wherein the digital archive comprises behavior data of a plurality of users;
acquiring a target behavior data set of a target user based on a plurality of behavior types according to the digital archive;
inputting the target behavior data set into a user behavior analysis model to obtain a plurality of user behavior analysis results, wherein the user behavior analysis model comprises a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types;
inputting the analysis results of the plurality of user behaviors into a user portrait analysis model to obtain a target user portrait;
acquiring a current task set;
and distributing a plurality of tasks in the task set to the target user according to the target user portrait.
2. The method of claim 1, wherein the obtaining a digital archive comprises:
acquiring a preset time period;
acquiring behavior data of a plurality of users in the preset time period based on the behavior types to obtain a plurality of behavior data sets, wherein the behavior types comprise development behaviors, communication behaviors and organization behaviors;
constructing a plurality of entity information based on the plurality of users;
constructing a plurality of data attributes based on the plurality of behavior types;
constructing a plurality of data element sets according to the plurality of behavior data sets;
and constructing the digital archive according to the entity information, the data attributes and the data element sets.
3. The method of claim 2, wherein inputting the set of target behavior data into a user behavior analysis model to obtain a plurality of user behavior analysis results comprises:
constructing a first user behavior analysis module according to the behavior type of the development behavior;
constructing a second user behavior analysis module according to the behavior type of the communication behavior;
constructing a third user behavior analysis module according to the behavior type of the organization behavior;
obtaining the user behavior analysis model according to the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module;
the development behavior data, the communication behavior data and the organization behavior data in the target behavior data set are acquired, the first user behavior analysis module, the second user behavior analysis module and the third user behavior analysis module are input, and a first user behavior analysis result, a second user behavior analysis result and a third user behavior analysis result are acquired and are used as the plurality of user behavior analysis results.
4. A method according to claim 3, wherein constructing a first user behavior analysis module based on the behavior type of the development behavior comprises:
acquiring a plurality of sample development behavior data based on the preset time period;
carrying out development capability grading according to the plurality of sample development behavior data to obtain a first user behavior analysis result of the plurality of samples;
the first user behavior analysis module is constructed based on a feedforward neural network, wherein input data of the first user behavior analysis module is development behavior data, and output data is a first user behavior analysis result;
obtaining a construction data set, wherein the construction data set is obtained by carrying out data annotation on the plurality of sample development behavior data and the first user behavior analysis results of the plurality of samples;
and performing supervision training and verification on the first user behavior analysis module by adopting the constructed data set to obtain the first user behavior analysis module with the accuracy meeting the preset requirement.
5. The method of claim 4, wherein inputting the plurality of user behavior analysis results into a user representation analysis model to obtain a target user representation, comprising:
constructing a user portrait coordinate space according to the first user behavior analysis result, the second user behavior analysis result and the third user behavior analysis result;
acquiring a plurality of sample second user behavior analysis results and a plurality of sample third user behavior analysis results, and acquiring a plurality of sample user portrait input data by combining the plurality of sample first user behavior analysis results;
acquiring a plurality of sample user portraits, wherein each sample user portrait corresponds to at least one sample user portrayal input data;
inputting the user portrait input data of the plurality of samples into the user portrait coordinate space to obtain a plurality of sample coordinate points;
performing cluster analysis on the plurality of sample coordinate points to obtain a plurality of cluster results;
marking the clustering results by adopting the plurality of sample user portraits to obtain the user portrayal analysis model;
and taking the analysis results of the plurality of user behaviors as target user portraits input data, inputting the user portrayal analysis model, and obtaining the target user portrayal.
6. The method of claim 5, wherein inputting the plurality of user behavior analysis results as target user portrayal input data into the user portrayal analysis model to obtain the target user portrayal comprises:
inputting the user portrayal analysis model by taking the analysis results of the plurality of user behaviors as target user portrayal input data to obtain a target coordinate point;
and acquiring a clustering result of the target coordinate point, taking a corresponding sample user portrait as the target user portrait, or acquiring a clustering result nearest to the target coordinate point, and taking a corresponding sample user portrait as the target user portrait.
7. The method of claim 1, wherein issuing a plurality of tasks within the task set to the target user in accordance with the target user representation comprises:
acquiring development behavior proportion information, communication behavior proportion information and organization behavior proportion information in the tasks, and acquiring a plurality of task behavior proportion information sets;
marking the tasks according to the task behavior duty ratio information sets to obtain task description information;
acquiring the task quantity of the target user;
calculating the degree of fit between the target user and the tasks according to the target user portrait and the task description information, and obtaining the information of the degree of fit;
and selecting a plurality of tasks corresponding to the maximum plurality of fitness information according to the task quantity, and issuing the tasks to the target user.
8. A visual dynamic analysis system based on user behavior modeling, the system comprising:
the document library acquisition module is used for acquiring a digital archive, wherein the digital archive comprises behavior data of a plurality of users;
the data acquisition module is used for acquiring a target behavior data set of a target user based on a plurality of behavior types according to the digital archive;
the result acquisition module is used for inputting the target behavior data set into a user behavior analysis model to obtain a plurality of user behavior analysis results, wherein the user behavior analysis model comprises a plurality of user behavior analysis modules, and the plurality of user behavior analysis modules correspond to the plurality of behavior types;
the portrait acquisition module is used for inputting the analysis results of the plurality of user behaviors into a user portrait analysis model to obtain a target user portrait;
the task acquisition module is used for acquiring a current task set;
and the task issuing module is used for issuing a plurality of tasks in the task set to the target user according to the target user portrait.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310049613.3A CN116307489A (en) | 2023-02-01 | 2023-02-01 | Visual dynamic analysis method and system based on user behavior modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310049613.3A CN116307489A (en) | 2023-02-01 | 2023-02-01 | Visual dynamic analysis method and system based on user behavior modeling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116307489A true CN116307489A (en) | 2023-06-23 |
Family
ID=86836789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310049613.3A Pending CN116307489A (en) | 2023-02-01 | 2023-02-01 | Visual dynamic analysis method and system based on user behavior modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307489A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842238A (en) * | 2023-07-24 | 2023-10-03 | 武汉赛思云科技有限公司 | Method and system for realizing enterprise data visualization based on big data analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784625A (en) * | 2018-12-10 | 2019-05-21 | 南京南瑞信息通信科技有限公司 | A kind of work order intelligence distributing method based on personnel ability's analysis |
| CN111666351A (en) * | 2020-05-29 | 2020-09-15 | 北京睿知图远科技有限公司 | Fuzzy clustering system based on user behavior data |
| CN112232773A (en) * | 2020-10-19 | 2021-01-15 | 北京人人众包科技有限公司 | Software recommendation method and system |
| CN113313470A (en) * | 2021-06-10 | 2021-08-27 | 郑州科技学院 | Employment type evaluation method and system based on big data |
| CN113807809A (en) * | 2021-08-24 | 2021-12-17 | 姚玲 | Method for constructing audit user portrait based on machine learning technology |
| CN114780838A (en) * | 2022-04-12 | 2022-07-22 | 浪潮软件股份有限公司 | Digital archive situational information recommendation method based on user portrait |
-
2023
- 2023-02-01 CN CN202310049613.3A patent/CN116307489A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784625A (en) * | 2018-12-10 | 2019-05-21 | 南京南瑞信息通信科技有限公司 | A kind of work order intelligence distributing method based on personnel ability's analysis |
| CN111666351A (en) * | 2020-05-29 | 2020-09-15 | 北京睿知图远科技有限公司 | Fuzzy clustering system based on user behavior data |
| CN112232773A (en) * | 2020-10-19 | 2021-01-15 | 北京人人众包科技有限公司 | Software recommendation method and system |
| CN113313470A (en) * | 2021-06-10 | 2021-08-27 | 郑州科技学院 | Employment type evaluation method and system based on big data |
| CN113807809A (en) * | 2021-08-24 | 2021-12-17 | 姚玲 | Method for constructing audit user portrait based on machine learning technology |
| CN114780838A (en) * | 2022-04-12 | 2022-07-22 | 浪潮软件股份有限公司 | Digital archive situational information recommendation method based on user portrait |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842238A (en) * | 2023-07-24 | 2023-10-03 | 武汉赛思云科技有限公司 | Method and system for realizing enterprise data visualization based on big data analysis |
| CN116842238B (en) * | 2023-07-24 | 2024-03-22 | 右来了(北京)科技有限公司 | Method and system for realizing enterprise data visualization based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| CN115276006A (en) | Load prediction method and system for power integration system | |
| CN107844914B (en) | Risk management and control system based on group management and implementation method | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| CN111199493A (en) | Arrearage risk identification method based on customer payment information and credit investigation information | |
| CN116307489A (en) | Visual dynamic analysis method and system based on user behavior modeling | |
| CN115794803B (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
| Alibrandi et al. | A decision support tool for sustainable and resilient building design | |
| CN111078512A (en) | Alarm record generation method and device, alarm equipment and storage medium | |
| CN109992592B (en) | College poverty and poverty identification method based on flow data of campus consumption card | |
| CN115600856A (en) | Method, device, equipment and medium for automatically auditing and distributing events | |
| Hammad et al. | Knowledge discovery in data: A case study | |
| CN110717837A (en) | User portrait construction method for hacker forum | |
| Lu et al. | Formation and Diffusion Analysis of Agricultural Product Brand Communication Influence Based on Big Data Fuzzy K‐Means Clustering in Convergent Media Era | |
| CN117910968B (en) | Regional cultural house total museum cluster automatic management system | |
| CN112163740B (en) | Method and device for acquiring maintenance personnel assessment results based on blockchain | |
| CN116993307B (en) | Collaborative office method and system with artificial intelligence learning capability | |
| CN117172415A (en) | Analysis method and device for comprehensive carbon reduction of high-energy-consumption enterprise and computer storage medium | |
| CN113538020B (en) | Method and device for acquiring association degree of group of people features, storage medium and electronic device | |
| CN113627883B (en) | Cloud customization recruitment method and system | |
| CN113222169B (en) | Federal machine combination service method and system combining big data analysis feedback | |
| CN116126852B (en) | BIM-based intelligent management data storage method for fabricated building | |
| CN117575542B (en) | Building engineering data control system and method based on modularized assembly | |
| CN116542380B (en) | Power plant supply chain carbon footprint optimization method and device based on natural language | |
| Tripathi et al. | Analyzing Cross-impact Matrices for Managerial Decision-making Problems with the DEMATEL Approach. |
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 |