CN113392291B - Service recommendation method and system based on data center - Google Patents
Service recommendation method and system based on data center Download PDFInfo
- Publication number
- CN113392291B CN113392291B CN202110763565.5A CN202110763565A CN113392291B CN 113392291 B CN113392291 B CN 113392291B CN 202110763565 A CN202110763565 A CN 202110763565A CN 113392291 B CN113392291 B CN 113392291B
- Authority
- CN
- China
- Prior art keywords
- task
- data
- recommendation
- application
- planning
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000007637 random forest analysis Methods 0.000 claims abstract description 13
- 230000006399 behavior Effects 0.000 claims description 38
- 238000007726 management method Methods 0.000 claims description 37
- 230000006870 function Effects 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 21
- 238000012163 sequencing technique Methods 0.000 claims description 15
- 238000012423 maintenance Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 3
- 230000014509 gene expression Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 238000013441 quality evaluation Methods 0.000 claims description 3
- 230000037213 diet Effects 0.000 claims description 2
- 235000005911 diet Nutrition 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims 2
- 238000004590 computer program Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
- 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
- G06Q10/06316—Sequencing of tasks or work
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure provides a service recommendation method and system based on a data center, which acquire employee behavior data in a project center; obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences; obtaining a service recommendation result according to the clustering result and a preset random forest regression model; the method and the system realize staff life service recommendation based on staff behavior data, simultaneously realize work task recommendation based on staff planning tasks and project parameter data, and greatly improve work efficiency on the premise of improving staff site life quality.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to a service recommendation method and system based on a data center.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the global vigorous development of the data center industry, the development and construction of the data center are in a high-speed period along with the rapid growth of socioeconomic, and the government departments in various places give great support to the emerging industry, so that great advantages are brought to the development of the data center industry. With the great development of the data center industry, a great development space is available in many cities in the future, and a large-scale data center is also required to be constructed in the construction and operation process of the domestic conventional thermal power generation project.
However, the inventor finds that in the management process of engineering projects, the application of the data center still stays on the simple data query, and the data is not effectively processed and integrated so as to improve the working efficiency; with the continuous development of intelligent chemical industry, the working environment and working condition of staff are improved more and more, but better life service of staff cannot be realized by directly processing data of a data center at present; most of the existing task allocation modes are field arrangement, lack of effective planning management, and cannot be completed efficiently for some non-urgent work tasks related to a flow program, such as financial reimbursement tasks for site financial staff, supervision tasks for site construction supervision staff and examination and approval tasks for various boring applications, and often the task execution efficiency is low due to parallel implementation of the tasks or the lack of task execution staff.
Disclosure of Invention
In order to solve the defects of the prior art, the present disclosure provides a service recommendation method and a system based on a data center, which realize staff life service recommendation based on staff behavior data, and simultaneously realize work task recommendation based on staff planning tasks and project parameter data, and greatly improve work efficiency on the premise of improving the life quality of staff sites.
In order to achieve the above purpose, the present disclosure adopts the following technical scheme:
the first aspect of the present disclosure provides a service recommendation method based on a data center.
A data center-based service recommendation method, comprising the following steps:
acquiring employee behavior data in a project center;
obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences;
and obtaining a service recommendation result according to the clustering result and a preset random forest regression model.
Further, the construction of the employee behavior map comprises the following steps:
and extracting attributes, relations and entities of the collected structured service data, carrying out knowledge fusion on scattered data through reference resolution, entity disambiguation and entity linking to obtain knowledge expression, and obtaining a user interest map through quality evaluation.
Further, training of the random forest regression model includes:
assuming that the divided training set data samples are N, extracting samples with the same capacity from the N training set data samples by adopting a Bootstrap sampling method to form a training subset;
assuming M features in the training subset, randomly extracting M features from the training subset to serve as a split feature subset, and splitting without pruning by adopting a CART regression algorithm;
repeating the previous two steps for n times, generating n sub-regression trees, and predicting results to form an RF regression prediction recommendation model;
and obtaining a final recommendation result by using an output average value of the n sub regression trees.
Further, acquiring project parameter data;
obtaining scores of all the planning tasks according to planning task data of staff to be recommended and project parameter data related to the planning tasks;
and sequencing the planning tasks according to the sequence from the large score to the small score, and recommending the planning tasks according to the sequencing result.
Further, the project parameter data at least includes: planning task data of each employee in a preset time period, current on-duty data of each employee, current task data of each employee and physical data required by task execution.
Further, the physical data required for task execution at least includes: the number of people, the number of materials, the status of the equipment and environmental parameters.
Furthermore, when a task needing to be executed urgently is received, executing the urgent task, and after the urgent task is executed, re-performing score calculation of the scheduled task on the rest scheduled tasks, and re-performing task recommendation according to the ranking result of the scores.
Further, according to the planning task data of the staff to be recommended and the project parameter data related to the staff to be recommended, the scoring of each planning task is obtained, including:
acquiring historical completion condition data of a planning task;
obtaining flow data required by task completion according to the acquired historical completion condition data;
matching the obtained flow data with the obtained project parameter data, calculating the time required for completing the task, and comparing the time required for completing the planned task with the historical completion time of the planned task to obtain the score of the planned task;
wherein the larger the difference, the larger the score is when the time required for completion of the scheduled task is smaller than the historical completion time, and the smaller the difference, the larger the time required for completion of the scheduled task is.
A second aspect of the present disclosure provides a data center-based service recommendation system.
A data center based service recommendation system, comprising:
a data acquisition module configured to: acquiring employee behavior data in a project center;
a preference clustering module configured to: obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences;
a service recommendation module configured to: and obtaining a service recommendation result according to the clustering result and a preset random forest regression model.
A third aspect of the present disclosure provides a computer readable storage medium having stored thereon a program which when executed by a processor implements steps in a data center based service recommendation method according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps in the data center based service recommendation method according to the first aspect of the present disclosure when the program is executed.
Compared with the prior art, the beneficial effects of the present disclosure are:
1. according to the method, the system, the medium or the electronic equipment, staff behavior patterns are obtained according to the behavior data, the established structured behavior patterns are connected with each service item, and user preference clustering is conducted; according to the clustering result and the preset random forest regression model, a service recommendation result is obtained, and through analysis of employee behavior data, employee life and work preference is achieved, and employee service recommendation can be better conducted.
2. The method, the system, the medium or the electronic equipment disclosed by the disclosure combine project parameter data and the plan task data of staff to perform task sequencing, so that the completion efficiency of the plan task is greatly improved, and the execution interruption of the plan task can be avoided to the greatest extent.
3. According to the method, the system, the medium or the electronic equipment, when the temporary important task is received, the temporary important task is preferentially executed, after the important task is executed, the rest planning tasks are reordered, and task recommendation is carried out according to the reordered result.
Additional aspects of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain the disclosure, and do not constitute an undue limitation on the disclosure.
Fig. 1 is a flow chart of a service recommendation method based on a data center according to embodiment 1 of the present disclosure.
Detailed Description
The disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
Example 1:
as shown in fig. 1, embodiment 1 of the present disclosure provides a service recommendation method based on a data center, including the following procedures:
acquiring employee behavior data in a project center;
obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences;
and obtaining a service recommendation result according to the clustering result and a preset random forest regression model.
Specifically, the method comprises the following steps:
acquiring behavior data of all staff and user attributes, wherein the behavior data at least comprise site diet data, site sleep data, site entertainment data and the like, and the user attributes at least comprise common workers, proctoring staff, project management staff and the like;
and extracting attributes, relations and entities of the collected structured user information, carrying out knowledge fusion on scattered information through key technologies such as reference resolution, entity disambiguation and entity linking to obtain a series of knowledge expressions, and carrying out quality evaluation to obtain a user behavior map.
And establishing a connection between the constructed structured user interest map and the energy service products, carrying out user preference clustering, associating employee attributes with service types, and clustering according to scores of the employees on various services.
The random forest regression model is composed of a plurality of CART (Classification andRegression Tree) regression trees, which correspond to one division of the input space (feature space) and the output values on the division units, and can be represented by a set, namely: { h (X, ψk) |k=1, 2, …, N }, X represents the input vector matrix, ψk represents the generation of k sub-regression trees, the sub-regression trees grown in the set are all independent samples extracted based on the Bootstrap method and have the same distribution, and final recommendation results are obtained through statistics, and specific training comprises:
(1) Assuming that the divided training set data samples are N, sampling samples with the same capacity from the N training set data samples by adopting a Bootstrap sampling method to form a training subset.
(2) Assuming that the training subset has M features, M are randomly extracted from the training subset as a split feature subset (M is less than or equal to M), and the training subset is split without pruning by adopting a CART regression algorithm.
(3) Repeating the steps (1) - (2) n times, thereby generating a corresponding number of sub-regression trees and predicting the result to form the RF regression prediction recommendation model.
(4) And verifying the reliability of the model by using the divided test set, and obtaining a final recommended result by using the output average value of the n sub regression trees.
Adopting a Forest-RI form, randomly selecting F (F is less than or equal to M) feature vectors to train if the training set has M dimensions, and acquiring enough small F among subtrees
Tend to diminish in correlation; meanwhile, the effect of subtree integration is improved along with the increase of F. Considering comprehensively, it is generally necessary to determine the F value according to the empirical formula (1):
F＝1+log 2 M (1)
and constructing a personalized recommendation system based on the spectral clustering and the real scoring data of staff on the construction site service by the random forest algorithm model content. 80% of user original data are selected for processing, a user behavior map is constructed, and the map is imported into a spectral clustering model for segmentation, and is clustered into N c (N c =6) cluster, N c After cluster data normalization processing, a random forest regression model is imported, a model hyper-parameter is obtained by using an empirical formula, after FR model training is finished, predicted values of all subsequence components are obtained, inverse normalization processing is carried out, and a final recommended result is obtained by superposing the predicted values of all subsequences.
The following service recommendations are also included:
s1: application function recommendation
The application function management can manage and maintain an application function list recommended by the intelligent portal, maintain modules commonly used by users in enterprises, function links, add icons to the modules and the function links, and mark the icons, so that the application functions can be recommended to the users through employee behavior logs and preference information, and simultaneously support the users to search, and an administrator promotes a certain application.
S1.1: application management
S1.1.1: and (3) application maintenance: manually adding, modifying, deleting and maintaining recommended applications, adding and modifying a recommended application list, setting icons, text descriptions and entry links of the PC and the mobile terminal of the applications, marking corresponding labels for the applications, and recommending original data for application functions.
S1.1.2: application interface import: the data dictionary interface provided by the EKP is supported and the list of applications for which to find is imported EKP as a recommended application to reduce maintenance work for management maintenance personnel.
S1.1.3: application log importation: through the user access log, the module entry with high frequency access is automatically imported into a recommendable application list by a newly built functional link, and the imported application list can be recommended to the user after editing, processing, improving information such as pictures and the like.
S1.2: application recommendation
S1.2.1: application recommendation interface: and providing an interface capable of acquiring the application recommendation list of the current user, and returning the recommendation list data of the recommendation calculated by the system to the current user.
S1.2.2: application recommendation presentation: the user provides a portal presentation component that can present application recommendation list information, presenting a presentable list.
S1.2.3: personal application collection: the user can collect the own required application list, and the collected application list is preferentially returned in the recommendation interface return list
S2: related work recommendation
The work recommendation pushes the relevant recent work tasks in the respective fields to users of different departments, posts and labels, so that the users can reasonably process the work tasks according to priority and deadlines, and the task progress and state of the users can be followed anytime and anywhere, so that the task can be completed on time.
S2.1: event management
Newly-built and maintenance event configuration, including event name, event type, detection interface address, message keyword, enabling and disabling, etc., the event sends request to detection interface address, and according to returned data, it is determined whether to generate or update correspondent task, and the event execution log is recorded.
S2.2: task management
The new and maintenance task related configuration includes task name, task type, task link, task description, priority, expiration date, generation and update event, update event execution frequency, etc. Upon execution of the rule, the generation task is thus configured.
Viewing and searching all generated task related information, and performing task names, executives, states, priorities, creation time, deadlines and the like.
S2.3: rule management
Creating and updating rules for creating and maintaining tasks, configuring related tasks for labels or departments, posts, groups and personnel, and executing related events to generate or update work tasks for configured crowds under the configured frequency. Rules can be started and stopped at regular or immediate time, providing flexible control.
S2.4: user side push
Work pushing: the user can check and process the current task to be processed at the portal, reasonably arrange work according to priority and deadline, and follow up the task progress and state.
Specifically, for related non-urgent plan tasks which need to be matched by multiple persons or are performed in parallel or are processed in a flow mode by multiple subtasks, the following task pushing is performed:
acquiring project parameter data;
obtaining scores of all the planning tasks according to planning task data of staff to be recommended and project parameter data related to the planning tasks;
and sequencing the planning tasks according to the sequence from the large score to the small score, and recommending the planning tasks according to the sequencing result.
The project parameter data at least comprises: planning task data of each employee in a preset time period, current on-duty data of each employee, current task data of each employee and physical data required by task execution.
The physical data required for task execution includes at least: the number of people, the number of materials, the status of the equipment and environmental parameters.
When a task needing to be executed urgently is received, executing the urgent task, and after the urgent task is executed, re-performing score calculation of the planning tasks on the rest planning tasks, and re-performing task recommendation according to the ranking result of the scores.
Obtaining the score of each planning task according to the planning task data of the staff to be recommended and the project parameter data related to the staff to be recommended, wherein the scoring comprises the following steps:
acquiring historical completion condition data of a planning task;
obtaining flow data required by task completion according to the acquired historical completion condition data;
matching the obtained flow data with the obtained project parameter data, calculating the time required for completing the task, and comparing the time required for completing the planned task with the historical completion time of the planned task to obtain the score of the planned task;
wherein the larger the difference, the larger the score is when the time required for completion of the scheduled task is smaller than the historical completion time, and the smaller the difference, the larger the time required for completion of the scheduled task is.
S3: content tag management
The content label management provides favorites recommendation support for knowledge content recommendation, provides uniform labeling service for knowledge to be recommended, supports processing of user picture like favorites labels by defining and labeling uniform labels, and carries out knowledge recommendation associated with favorites labels for users.
S3.1.: content tag modification
And (3) intelligent label: the system uses the text recommendation related labels according to the knowledge content, helps users to carry out quick classification mark management on the knowledge content, and reduces the document classification management burden of a plurality of knowledge content creators
Common label: the intelligent labels recommended by the system are less accurate in reflecting knowledge content information, and users can add common labels to classify knowledge
S3.2: content tag query: content tag management may filter, view and manage tag information tagged by content through a content source system and corresponding content tags
Example 2:
embodiment 2 of the present disclosure provides a service recommendation system based on a data center, including:
a data acquisition module configured to: acquiring employee behavior data in a project center;
a preference clustering module configured to: obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences;
a service recommendation module configured to: and obtaining a service recommendation result according to the clustering result and a preset random forest regression model.
The working method of the system is the same as the service recommendation method based on the data center provided in embodiment 1, and will not be described here again.
Example 3:
embodiment 3 of the present disclosure provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements steps in a data center-based service recommendation method as described in embodiment 1 of the present disclosure.
Example 4:
embodiment 4 of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor implements steps in the data center-based service recommendation method according to embodiment 1 of the present disclosure when the program is executed.
It will be apparent to those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The foregoing description of the preferred embodiments of the present disclosure is provided only and not intended to limit the disclosure so that various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (5)
1. A service recommendation method based on a data center is characterized in that: the method comprises the following steps:
staff behavior data and user attributes in the project center are obtained, wherein the behavior data at least comprise site diet data, site sleep data and site entertainment data, and the user attributes at least comprise common workers, supervisors and project management personnel;
extracting attributes, relations and entities of the collected structured service data, carrying out knowledge fusion on scattered data through reference resolution, entity disambiguation and entity linking to obtain knowledge expression, and obtaining a user interest map through quality evaluation;
obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences;
obtaining a service recommendation result according to the clustering result and a preset random forest regression model;
the user checks and processes the current task to be processed, and reasonably arranges the work, and comprises the following specific steps: acquiring project parameter data;
obtaining scores of all the planning tasks according to planning task data of staff to be recommended and project parameter data related to the planning tasks;
sequencing the planning tasks according to the sequence from the large score to the small score, and recommending the planning tasks according to the sequencing result;
when a task needing to be executed urgently is received, executing the urgent task, and after the urgent task is executed, re-performing score calculation of the planning task on the rest planning tasks, and re-performing task recommendation according to a scoring sequencing result;
also included are the following service recommendations, including:
s1: application function recommendation;
the application function management maintains an application function list recommended by the intelligent portal, maintains modules and function links commonly used by users in enterprises, adds icons to the modules and the function links, marks the icons, enables the application functions to be recommended to the users through employee behavior logs and preference information, supports the users to search, and enables an administrator to popularize for a certain application;
s1.1: application management;
s1.1.1: and (3) application maintenance: manually adding, modifying, deleting and maintaining recommended applications, adding and modifying recommended application lists, setting icons, text descriptions and entrance links of the PC and the mobile terminal of the applications, marking corresponding labels for the applications, and recommending original data for application functions;
s1.1.2: application interface import: supporting a data dictionary interface provided by an EKP, importing EKP an application list as a recommended application to reduce maintenance work of management maintenance personnel;
s1.1.3: application log importation: automatically importing a module entry accessed by a high frequency and a newly built function link into a recommended application list through a user access log, editing the imported application list, perfecting picture information and recommending to a user;
s1.2: application recommendation;
s1.2.1: application recommendation interface: providing an interface capable of acquiring a recommendation list of the application of the current user, and returning recommendation list data of the recommendation calculated by the system to the current user;
s1.2.2: application recommendation presentation: the user provides a portal showing component for showing application recommendation list information and shows a showing list;
s1.2.3: personal application collection: the user stores the own required application list, and the stored application list is preferentially returned in the recommendation interface return list;
s2: related work recommendation;
the work recommendation pushes the relevant recent work tasks in the respective fields to users of different departments, posts and labels, so that the users can reasonably process the work tasks according to priority and deadlines, and the task progress and state of the users can be followed anytime and anywhere to ensure that the tasks are completed on time;
s2.1: event management;
newly-built and maintained event configuration, including event name, event type, detection interface address, message keyword, enabling and disabling, the event sends request to detection interface address, according to returned data to determine whether to generate or update corresponding task, recording event execution log;
s2.2: task management;
newly-built and maintenance task related configuration including task name, task type, task link, task description, priority, expiration date, generation and update event, update event execution frequency, when rule is executed, thereby configuring generation task;
viewing and searching all the generated task related information, and checking task names, executives, states, priorities, creation time and deadlines;
s2.3: rule management;
creating and updating rules for creating and updating the rules for configuring related tasks for labels or departments, posts, groups and personnel, executing related events to generate or update work tasks for configured people under the configured frequency, and starting and stopping the rules regularly or immediately to provide flexible control;
s2.4: pushing the user end;
work pushing: the user can check and process the current task to be processed at the portal, reasonably arrange work according to priority and deadline, and follow up the task progress and state;
for related non-urgent planning tasks which need to be matched by multiple persons or are performed in parallel or are processed in a flow mode by multiple subtasks, the following task pushing is performed:
acquiring project parameter data;
obtaining scores of all the planning tasks according to planning task data of staff to be recommended and project parameter data related to the planning tasks;
sequencing the planning tasks according to the sequence from the large score to the small score, and recommending the planning tasks according to the sequencing result;
the project parameter data at least comprises: planning task data of each employee in a preset time period, current on-duty data of each employee, current task data of each employee and physical data required by task execution;
the physical data required for task execution includes at least: the personnel number, the material number, the equipment state and the environmental parameters;
obtaining the score of each planning task according to the planning task data of the staff to be recommended and the project parameter data related to the staff to be recommended, wherein the scoring comprises the following steps:
acquiring historical completion condition data of a planning task;
obtaining flow data required by task completion according to the acquired historical completion condition data;
matching the obtained flow data with the obtained project parameter data, calculating the time required for completing the task, and comparing the time required for completing the planned task with the historical completion time of the planned task to obtain the score of the planned task;
wherein, when the time required for completing the planning task is smaller than the historical completion time and the score is larger as the difference is larger, the time required for completing the planning task is larger than the historical completion time and the score is smaller as the difference is larger;
s3: content tag management;
content tag management provides a preference recommendation support for knowledge content recommendation, provides uniform tagging service for knowledge to be recommended, supports processing of user image preference tags by defining and tagging uniform tags, and carries out knowledge recommendation associated with preference tags for users;
s3.1.: modifying the content label;
and (3) intelligent label: the system uses relevant labels according to the text recommendation of the knowledge content, so that a user is helped to carry out quick classification mark management on the knowledge content, and the burden of knowledge content creator on document classification management is reduced;
common label: the intelligent labels recommended by the system are less accurate in reflecting knowledge content information, and a user can newly add common labels to classify knowledge;
s3.2: content tag query: content tag management enables screening through a content source system and corresponding content tags, viewing and managing tag information tagged by content.
2. The data center-based service recommendation method according to claim 1, wherein:
training of a random forest regression model, comprising:
assuming that the divided training set data samples are N, extracting samples with the same capacity from the N training set data samples by adopting a Bootstrap sampling method to form a training subset;
assuming M features in the training subset, randomly extracting M features from the training subset to serve as a split feature subset, and splitting without pruning by adopting a CART regression algorithm;
repeating the previous two steps for n times, generating n sub-regression trees, and predicting results to form an RF regression prediction recommendation model;
and obtaining a final recommendation result by using an output average value of the n sub regression trees.
3. A data center-based service recommendation system, characterized by: comprising the following steps:
a data acquisition module configured to: acquiring employee behavior data in a project center;
a preference clustering module configured to: obtaining employee behavior patterns according to the behavior data, establishing a connection between the constructed structured behavior patterns and each service item, and clustering user preferences;
a service recommendation module configured to: obtaining a service recommendation result according to the clustering result and a preset random forest regression model; the user checks and processes the current task to be processed, and reasonably arranges the work, and comprises the following specific steps: acquiring project parameter data;
obtaining scores of all the planning tasks according to planning task data of staff to be recommended and project parameter data related to the planning tasks;
sequencing the planning tasks according to the sequence from the large score to the small score, and recommending the planning tasks according to the sequencing result;
when a task needing to be executed urgently is received, executing the urgent task, and after the urgent task is executed, re-performing score calculation of the planning task on the rest planning tasks, and re-performing task recommendation according to a scoring sequencing result;
also included are the following service recommendations, including:
s1: application function recommendation;
the application function management maintains an application function list recommended by the intelligent portal, maintains modules and function links commonly used by users in enterprises, adds icons to the modules and the function links, marks the icons, enables the application functions to be recommended to the users through employee behavior logs and preference information, supports the users to search, and enables an administrator to popularize for a certain application;
s1.1: application management;
s1.1.1: and (3) application maintenance: manually adding, modifying, deleting and maintaining recommended applications, adding and modifying recommended application lists, setting icons, text descriptions and entrance links of the PC and the mobile terminal of the applications, marking corresponding labels for the applications, and recommending original data for application functions;
s1.1.2: application interface import: supporting a data dictionary interface provided by an EKP, importing EKP an application list as a recommended application to reduce maintenance work of management maintenance personnel;
s1.1.3: application log importation: automatically importing a module entry accessed by a high frequency and a newly built function link into a recommended application list through a user access log, editing the imported application list, perfecting picture information and recommending to a user;
s1.2: application recommendation;
s1.2.1: application recommendation interface: providing an interface capable of acquiring a recommendation list of the application of the current user, and returning recommendation list data of the recommendation calculated by the system to the current user;
s1.2.2: application recommendation presentation: the user provides a portal showing component for showing application recommendation list information and shows a showing list;
s1.2.3: personal application collection: the user stores the own required application list, and the stored application list is preferentially returned in the recommendation interface return list;
s2: related work recommendation;
the work recommendation pushes the relevant recent work tasks in the respective fields to users of different departments, posts and labels, so that the users can reasonably process the work tasks according to priority and deadlines, and the task progress and state of the users can be followed anytime and anywhere to ensure that the tasks are completed on time;
s2.1: event management;
newly-built and maintained event configuration, including event name, event type, detection interface address, message keyword, enabling and disabling, the event sends request to detection interface address, according to returned data to determine whether to generate or update corresponding task, recording event execution log;
s2.2: task management;
newly-built and maintenance task related configuration including task name, task type, task link, task description, priority, expiration date, generation and update event, update event execution frequency, when rule is executed, thereby configuring generation task;
viewing and searching all the generated task related information, and checking task names, executives, states, priorities, creation time and deadlines;
s2.3: rule management;
creating and updating rules for creating and updating the rules for configuring related tasks for labels or departments, posts, groups and personnel, executing related events to generate or update work tasks for configured people under the configured frequency, and starting and stopping the rules regularly or immediately to provide flexible control;
s2.4: pushing the user end;
work pushing: the user can check and process the current task to be processed at the portal, reasonably arrange work according to priority and deadline, and follow up the task progress and state;
for related non-urgent planning tasks which need to be matched by multiple persons or are performed in parallel or are processed in a flow mode by multiple subtasks, the following task pushing is performed:
acquiring project parameter data;
obtaining scores of all the planning tasks according to planning task data of staff to be recommended and project parameter data related to the planning tasks;
sequencing the planning tasks according to the sequence from the large score to the small score, and recommending the planning tasks according to the sequencing result;
the project parameter data at least comprises: planning task data of each employee in a preset time period, current on-duty data of each employee, current task data of each employee and physical data required by task execution;
the physical data required for task execution includes at least: the personnel number, the material number, the equipment state and the environmental parameters;
obtaining the score of each planning task according to the planning task data of the staff to be recommended and the project parameter data related to the staff to be recommended, wherein the scoring comprises the following steps:
acquiring historical completion condition data of a planning task;
obtaining flow data required by task completion according to the acquired historical completion condition data;
matching the obtained flow data with the obtained project parameter data, calculating the time required for completing the task, and comparing the time required for completing the planned task with the historical completion time of the planned task to obtain the score of the planned task;
wherein, when the time required for completing the planning task is smaller than the historical completion time and the score is larger as the difference is larger, the time required for completing the planning task is larger than the historical completion time and the score is smaller as the difference is larger;
s3: content tag management;
content tag management provides a preference recommendation support for knowledge content recommendation, provides uniform tagging service for knowledge to be recommended, supports processing of user image preference tags by defining and tagging uniform tags, and carries out knowledge recommendation associated with preference tags for users;
s3.1.: modifying the content label;
and (3) intelligent label: the system uses relevant labels according to the text recommendation of the knowledge content, so that a user is helped to carry out quick classification mark management on the knowledge content, and the burden of knowledge content creator on document classification management is reduced;
common label: the intelligent labels recommended by the system are less accurate in reflecting knowledge content information, and a user can newly add common labels to classify knowledge;
s3.2: content tag query: content tag management enables screening through a content source system and corresponding content tags, viewing and managing tag information tagged by content.
4. A computer readable storage medium, having stored thereon a program, which when executed by a processor, implements the steps of the data center based service recommendation method according to any of claims 1-2.
5. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the data center based service recommendation method of any one of claims 1-2 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763565.5A CN113392291B (en) | 2021-07-06 | 2021-07-06 | Service recommendation method and system based on data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763565.5A CN113392291B (en) | 2021-07-06 | 2021-07-06 | Service recommendation method and system based on data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392291A CN113392291A (en) | 2021-09-14 |
| CN113392291B true CN113392291B (en) | 2024-01-23 |
Family
ID=77625291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110763565.5A Active CN113392291B (en) | 2021-07-06 | 2021-07-06 | Service recommendation method and system based on data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392291B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109831531A (en) * | 2019-03-15 | 2019-05-31 | 河北冀联人力资源服务集团有限公司 | Job seeker resume method for pushing and device and task method for pushing and device |
| CN110070291A (en) * | 2019-04-22 | 2019-07-30 | 北京冠群信息技术股份有限公司 | Audit task distribution method and system |
| CN110991834A (en) * | 2019-11-20 | 2020-04-10 | 黑龙江电力调度实业有限公司 | Scheduling system of electric power overhaul task |
| CN111242370A (en) * | 2020-01-10 | 2020-06-05 | 西南交通大学 | Railway station node resource scheduling method based on availability |
| CN112669096A (en) * | 2021-03-16 | 2021-04-16 | 蚂蚁智信(杭州)信息技术有限公司 | Object recommendation model training method and device |
| CN112734112A (en) * | 2021-01-08 | 2021-04-30 | 深圳市昂捷信息技术股份有限公司 | Task-driven digital store management method |
-
2021
- 2021-07-06 CN CN202110763565.5A patent/CN113392291B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109831531A (en) * | 2019-03-15 | 2019-05-31 | 河北冀联人力资源服务集团有限公司 | Job seeker resume method for pushing and device and task method for pushing and device |
| CN110070291A (en) * | 2019-04-22 | 2019-07-30 | 北京冠群信息技术股份有限公司 | Audit task distribution method and system |
| CN110991834A (en) * | 2019-11-20 | 2020-04-10 | 黑龙江电力调度实业有限公司 | Scheduling system of electric power overhaul task |
| CN111242370A (en) * | 2020-01-10 | 2020-06-05 | 西南交通大学 | Railway station node resource scheduling method based on availability |
| CN112734112A (en) * | 2021-01-08 | 2021-04-30 | 深圳市昂捷信息技术股份有限公司 | Task-driven digital store management method |
| CN112669096A (en) * | 2021-03-16 | 2021-04-16 | 蚂蚁智信(杭州)信息技术有限公司 | Object recommendation model training method and device |
Non-Patent Citations (2)
| Title |
|---|
| "基于用户画像的兴趣预测与推荐算法研究";孙静;《万方》;20201230;论文正文第4章 * |
| "面向众包设计平台的任务推荐算法研究";邱丹逸;《中国优秀硕士学位论文全文数据库 信息科技辑》;20180615;论文正文第2,3章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392291A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shvaiko et al. | Ontology matching: state of the art and future challenges | |
| CN107291902B (en) | Automatic marking method for public contribution review based on mixed classification technology | |
| US20100318492A1 (en) | Data analysis system and method | |
| CN110378206B (en) | Intelligent image examination system and method | |
| CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
| CN111444348A (en) | Method, system and medium for constructing and applying knowledge graph architecture | |
| CN110109908B (en) | Analysis system and method for mining potential relationship of person based on social basic information | |
| US20040237041A1 (en) | Apparatus, method and program for supporting a review | |
| CN111553751A (en) | Sales information data processing method, device and equipment | |
| Karras et al. | Researcher or crowd member? Why not both! The open research knowledge graph for applying and communicating CrowdRE research | |
| CN113220951B (en) | Medical clinic support method and system based on intelligent content | |
| CN112860899B (en) | Label generation method and device, computer equipment and computer readable storage medium | |
| CN112348348A (en) | Task data processing method and system | |
| CN109242431A (en) | A kind of enterprise management method and its system based on data system | |
| CN113392291B (en) | Service recommendation method and system based on data center | |
| US20210142233A1 (en) | Systems and methods for process mining using unsupervised learning | |
| Singh | Impact of technology in library services | |
| US20180150543A1 (en) | Unified multiversioned processing of derived data | |
| Shayakhmetova et al. | Descriptive big data analytics in the field of education | |
| CN116756373A (en) | Project review expert screening method, system and medium based on knowledge graph update | |
| CN110062112A (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN114090777A (en) | Text data processing method and device | |
| CN115269862A (en) | Electric power question-answering and visualization system based on knowledge graph | |
| CN110399337A (en) | File automating method of servicing and system based on data-driven | |
| CN111815125A (en) | Innovative entity science and technology evaluation system optimization method and device based on technical atlas |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |