CN113269535B - Human resource management method and system based on big data analysis - Google Patents
Human resource management method and system based on big data analysis Download PDFInfo
- Publication number
- CN113269535B CN113269535B CN202110643747.9A CN202110643747A CN113269535B CN 113269535 B CN113269535 B CN 113269535B CN 202110643747 A CN202110643747 A CN 202110643747A CN 113269535 B CN113269535 B CN 113269535B
- Authority
- CN
- China
- Prior art keywords
- cooperative
- operation data
- line
- cooperative operation
- collaborative
- 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
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
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Embodiments of the present invention provide a human resource management method and system based on big data analysis, which can sort a group of online cooperative operation data based on a cooperative transformation parameter value between each online cooperative operation data and a human resource online cooperative service and a cooperative operation flow characteristic of each online cooperative operation data, and further automatically generate an ordered group of cooperative optimization labels for the human resource online cooperative service based on an ordered online cooperative operation data cluster. Therefore, a more reasonable and accurate collaborative optimization tag sequence can be automatically generated, the updating optimization cost of the collaborative service of the online collaborative service of the human resources can be reduced, and the precision and the generation efficiency of the collaborative optimization tag are effectively improved; in addition, the generated collaborative optimization label has priority, and the reference degree of the final collaborative optimization label can be further improved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a human resource management method and system based on big data analysis.
Background
In the related art, for some key-focused online collaborative services of human resources, a user is required to perform data analysis on online collaborative operation big data of the online collaborative services of the human resources, to know a collaborative optimization label of the online collaborative services of the human resources, and further to know a frequency situation of a collaborative service of the online collaborative services of the human resources so as to perform targeted service optimization. However, in the related art solution, the precision and the generation efficiency of the collaborative optimization tag are very limited in a manner that a user performs individual analysis and sorting based on a data analysis tool.
Disclosure of Invention
In order to overcome at least the above disadvantages in the prior art, the present invention provides a human resource management method and system based on big data analysis.
In a first aspect, the present invention provides a human resource management method based on big data analysis, which is applied to a human resource management service platform, where the human resource management service platform is in communication connection with a plurality of human resource service terminals, and the method includes:
acquiring online cooperative operation big data aiming at online cooperative service of human resources, wherein the online cooperative operation big data comprises at least two online cooperative operation data;
obtaining a cooperative conversion parameter value between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources;
sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to the on-line cooperative operation data and the cooperative operation flow characteristic of the on-line cooperative operation data to obtain a corresponding on-line cooperative operation data cluster;
generating a collaborative optimization tag sequence for the online collaborative service of the human resources based on the online collaborative operation data cluster, wherein the collaborative optimization tag sequence comprises at least two reference collaborative optimization tags.
Secondly, the invention provides a human resource management classification network configuration method based on big data analysis, which is applied to a human resource management service platform, wherein the human resource management service platform is in communication connection with a plurality of human resource service terminals, and the method comprises the following steps:
the collaborative optimization label decision model is obtained by training through the following process:
obtaining a sequence of co-operating data on a reference line for at least one reference on-line co-service of human resources;
according to the cooperative operation data on the reference line in the cooperative operation data sequence on the reference line, executing random walk execution configuration on the unconfigured cooperative optimization label decision model to obtain the cooperative optimization label decision model meeting the model convergence requirement; wherein, each round of random walk execution configuration process comprises the following steps:
selecting a group of cooperative operation data on reference lines aiming at the same reference human resource online cooperative service from the cooperative operation data sequence on the reference lines, respectively inputting the cooperative operation data on the reference lines included in the cooperative operation data on the selected reference lines into a cooperative transformation parameter value prediction unit in the unconfigured cooperative optimization label decision model, and obtaining the cooperative transformation parameter value corresponding to the cooperative operation data on the reference lines output by the cooperative transformation parameter value prediction unit;
constructing a first model evaluation index based on the loss between the cooperative transformation parameter value corresponding to the cooperative operation data on each reference line and the corresponding reference information;
inputting the selected cooperative operation data on the reference line in the cooperative operation data on the reference line and the cooperative conversion parameter value corresponding to the cooperative operation data on the reference line into a grouping and sorting unit in the unconfigured cooperative optimization label decision model, and grouping the cooperative operation data on the reference lines based on the grouping and sorting unit to obtain at least two cooperative operation data groups on the line;
sorting each online cooperative operation data group based on the grouping and sorting unit to obtain a second cooperative label coding characteristic of the cooperative label output by the grouping and sorting unit;
inputting the second collaborative label coding feature into a collaborative optimization label prediction unit in the unconfigured collaborative optimization label decision model, and performing collaborative optimization label feature extraction based on the collaborative optimization label prediction unit to obtain a group of prediction collaborative optimization label lists output by the collaborative optimization label prediction unit, wherein the prediction collaborative optimization label lists comprise at least two prediction collaborative optimization labels;
for any one predicted collaborative optimization label, determining collaborative optimization probability loss of the predicted collaborative optimization label in the predicted collaborative optimization label list and an actual collaborative optimization label in the real collaborative optimization label sequence based on the collaborative optimization probability of the predicted collaborative optimization label in a preset collaborative optimization label sequence and the collaborative optimization probability of the predicted collaborative optimization label in the online collaborative operation big data;
constructing the second model evaluation index based on the determined collaborative optimization probability loss;
constructing a third model evaluation index based on the attention values of the on-line cooperative operation data elements in each on-line cooperative operation data group;
and updating model configuration data of the unconfigured collaborative optimization label decision model according to the first model evaluation index, the second model evaluation index and the third model evaluation index.
In a second aspect, an embodiment of the present invention further provides a human resource management system based on big data analysis, where the human resource management system based on big data analysis includes a human resource management service platform and a plurality of human resource service terminals communicatively connected to the human resource management service platform;
the human resource management service platform is used for:
acquiring online cooperative operation big data aiming at online cooperative service of human resources, wherein the online cooperative operation big data comprises at least two online cooperative operation data;
obtaining a cooperative conversion parameter value between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources;
sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to the on-line cooperative operation data and the cooperative operation flow characteristic of the on-line cooperative operation data to obtain a corresponding on-line cooperative operation data cluster;
generating a collaborative optimization tag sequence for the online collaborative service of the human resources based on the online collaborative operation data cluster, wherein the collaborative optimization tag sequence comprises at least two reference collaborative optimization tags.
According to any one of the above aspects, in the embodiment provided by the present invention, a group of online cooperative operation data can be sorted based on the cooperative transformation parameter value between each online cooperative operation data and the online cooperative service of the human resource and the cooperative operation flow characteristic of each online cooperative operation data, and then a group of ordered cooperative optimization tags for the online cooperative service of the human resource is automatically generated based on the ordered online cooperative operation data cluster. Therefore, a more reasonable and accurate collaborative optimization tag sequence can be automatically generated, the updating optimization cost of the collaborative service of the online collaborative service of the human resources can be reduced, and the precision and the generation efficiency of the collaborative optimization tag are effectively improved; in addition, the generated collaborative optimization label has priority, and the reference degree of the final collaborative optimization label can be further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that need to be called in the embodiments are briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic view of an application scenario of a human resource management system based on big data analysis according to an embodiment of the present invention;
FIG. 2 is a schematic flowchart of a human resource management method based on big data analysis according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a human resource management service platform for implementing the human resource management method based on big data analysis according to an embodiment of the present invention.
Detailed Description
The scheme of the embodiment of the invention is explained in detail in the following with the attached drawings of the specification.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the particular embodiments of the invention.
FIG. 1 is a schematic diagram illustrating a human resources management system 10 based on big data analysis according to an embodiment of the present invention. The human resource management system 10 based on big data analysis can include a human resource management service platform 100 and a human resource service terminal 200 communicatively connected to the human resource management service platform 100. The big data analysis based human resource management system 10 shown in FIG. 1 is only one possible example, and in other possible embodiments, the big data analysis based human resource management system 10 may also include only at least some of the components shown in FIG. 1 or may also include other components.
In this embodiment, the human resource management service platform 100 and the human resource service terminal 200 in the human resource management system 10 based on big data analysis may cooperatively perform the human resource management method based on big data analysis described in the following method embodiments, and the detailed description of the following method embodiments may be referred to for the specific steps performed by the human resource management service platform 100 and the human resource service terminal 200.
To solve the technical problem in the foregoing background, fig. 2 is a flowchart illustrating a human resource management method based on big data analysis according to an embodiment of the present invention, where the human resource management method based on big data analysis according to the present embodiment may be executed by the human resource management service platform 100 shown in fig. 1, and the human resource management method based on big data analysis is described in detail below.
Step S110, obtaining on-line cooperative operation big data for the human resource on-line cooperative service, where the on-line cooperative operation big data includes at least two on-line cooperative operation data.
The on-line cooperative operation big data comprises a plurality of on-line cooperative operation data, and the on-line cooperative operation data can be from different on-line cooperative objects but are all on-line cooperative operation data for the same human resource on-line cooperative service.
The human resource online collaboration service in the embodiment of the invention mainly refers to a collaboration application which is already developed, such as an intelligent office collaboration application.
Step S120, obtaining a cooperative transformation parameter value between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources.
Step S130, sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to each on-line cooperative operation data and the cooperative operation flow characteristic of each on-line cooperative operation data, to obtain a corresponding on-line cooperative operation data cluster.
Step S140, a group of collaborative optimization label sequences aiming at the online collaborative service of the human resources is generated based on the online collaborative operation data cluster, and the collaborative optimization label sequences comprise at least two reference collaborative optimization labels.
The online cooperative operation data generated in general may further include a large amount of useless redundant data, and the more useless redundant data, the smaller the value of the cooperative conversion parameter between the online cooperative operation data and the online cooperative service of the human resource.
In a design idea, the online collaborative operation data group may be divided into a plurality of online collaborative operation data groups according to a collaborative transformation parameter value between each online collaborative operation data and the online collaborative service of the human resource and a collaborative operation flow characteristic of each online collaborative operation data, so that operation timing portions of each online collaborative operation data in the online collaborative operation data group are relatively similar, and the collaborative transformation parameter values between the online collaborative operation data and the online collaborative service of the human resource are also relatively similar. Therefore, after grouping to obtain the on-line cooperative operation data groups, the on-line cooperative operation data groups are sorted, the on-line cooperative operation data in the on-line cooperative operation data groups are sorted respectively to obtain on-line cooperative operation data clusters, and the ordered target cooperative optimization tag is generated based on the ordered on-line cooperative operation data clusters.
In the embodiment of the present invention, if the online cooperative operation big data is grouped into the plurality of online cooperative operation data sets, when the reference cooperative optimization tag is generated based on the online cooperative operation data cluster, one target cooperative optimization tag may be correspondingly generated for one online cooperative operation data set, one target cooperative optimization tag may also be correspondingly generated for a plurality of online cooperative operation data sets, or a plurality of target cooperative optimization tags may be correspondingly generated for one online cooperative operation data set. In practical applications, if there may be many on-line cooperative operation data in the on-line cooperative operation big data, in practice, the generated cooperative optimization tag sequence generally includes several target cooperative optimization tags, so generally, a target cooperative optimization tag is generated by corresponding multiple on-line cooperative operation data sets.
In a design idea, when grouping the on-line cooperative operation data, a grouping method is mainly adopted, and the specific process is as follows: respectively performing feature fusion on the cooperative operation flow characteristics of the on-line cooperative operation data according to the cooperative conversion parameter values corresponding to the on-line cooperative operation data to obtain fusion cooperative operation flow characteristics of the on-line cooperative operation data; and grouping the on-line cooperative operation data according to the fusion cooperative operation flow characteristics of the on-line cooperative operation data to obtain at least two on-line cooperative operation data groups.
Because the cooperative transformation parameter value is also called the degree of association with the requirement of cooperative application in the cooperative process, the characteristic fusion is carried out on the cooperative operation flow characteristic of the cooperative operation data on the line based on the cooperative transformation parameter value, and the significance information of the cooperative operation data on the line and the cooperative service on the human resource line can be calculated, so that the goal of reducing the noise of a large amount of cooperative operation data on the line is achieved, the selection of the cooperative operation data on the significance line is facilitated, and irrelevant cooperative operation data on the line is weakened.
In the embodiment of the present invention, after the on-line cooperative operation big data is grouped into the plurality of on-line cooperative operation data groups based on the grouping algorithm, the on-line cooperative operation data groups and the on-line cooperative operation data in the on-line cooperative operation data groups may be sorted to form the on-line cooperative operation data cluster.
In a design idea, the step of sorting among the on-line cooperative operation data groups, and sorting the on-line cooperative operation data in each on-line cooperative operation data group respectively to obtain a group of on-line cooperative operation data clusters includes:
arranging the on-line cooperative operation data groups according to the quantity of on-line cooperative operation data contained in each on-line cooperative operation data group; and, for each on-line cooperative operation data group, respectively executing the following steps: and sorting the on-line cooperative operation data in the on-line cooperative operation data group according to the cooperative operation flow characteristics of the on-line cooperative operation data in the on-line cooperative operation data group and the characteristic matching information of the on-line cooperative operation data in the center line of the on-line cooperative operation data group. Finally, after the arrangement is performed between the on-line cooperative operation data groups and the arrangement is also performed between the on-line cooperative operation data in the on-line cooperative operation data groups, the on-line cooperative operation data cluster is generated based on the arrangement data according to the arrangement between the on-line cooperative operation data groups and the arrangement data of the on-line cooperative operation data in the on-line cooperative operation data groups.
In the embodiment of the present invention, after the on-line cooperative operation data groups are sorted, the on-line cooperative operation data in the on-line cooperative operation data groups may be further sorted, or before the on-line cooperative operation data groups are sorted, the on-line cooperative operation data in the on-line cooperative operation data groups may be sorted, or sorted at the same time, and the like, which is not specifically limited herein. For example, for each on-line cooperative operation data group, when sorting the on-line cooperative operation data in the on-line cooperative operation data group, the feature matching information is mainly based on the cooperative operation flow feature of each on-line cooperative operation data in the on-line cooperative operation data group and the feature matching information of the on-line cooperative operation data group, for example, the higher the feature matching information is, the earlier the order is, the lower the feature matching information is, and the later the order is.
The generation method of the collaborative optimization label in the embodiment of the invention can also be realized by combining an artificial intelligence technology, for example, the steps are as follows: and respectively inputting the on-line cooperative operation data into a cooperative optimization label decision model meeting the model convergence requirement, and performing feature extraction on the on-line cooperative operation data based on a cooperative transformation parameter value prediction unit in the cooperative optimization label decision model meeting the model convergence requirement to obtain a cooperative transformation parameter value corresponding to the on-line cooperative operation data output by the cooperative transformation parameter value prediction unit. Then, respectively inputting the on-line cooperative operation data and the cooperative conversion parameter value corresponding to the on-line cooperative operation data into a grouping and sorting unit in a cooperative optimization label decision model meeting the model convergence requirement, grouping and sorting the on-line cooperative operation data based on the grouping and sorting unit to obtain a first cooperative label coding feature of the cooperative label output by the grouping and sorting unit, wherein each on-line cooperative operation data element in the first cooperative label coding feature is combined to form an on-line cooperative operation data cluster; and finally, inputting the coding characteristics of the first collaborative label into a collaborative optimization label prediction unit in a collaborative optimization label decision model meeting the model convergence requirement, and extracting the collaborative optimization label characteristics based on the collaborative optimization label prediction unit to obtain a collaborative optimization label sequence output by the collaborative optimization label prediction unit.
The collaborative optimization label decision model provided by the embodiment of the invention mainly comprises a collaborative transformation parameter value prediction unit, a grouping and sorting unit and a collaborative optimization label prediction unit. The cooperative conversion parameter value prediction unit is mainly used for distinguishing from a subsequent cooperative label, cooperative operation track representation of on-line cooperative operation data is obtained in the cooperative conversion parameter value prediction unit, a first cooperative label coding feature finally obtained in the grouping and sorting unit is of a cooperative label, and the first cooperative label coding feature mainly refers to vector representation of on-line cooperative operation data in a cooperative operation data cluster on a line which is spliced in sequence and then converted into vector representation obtained by the cooperative label.
The collaborative optimization label model is obtained by training according to a collaborative operation data sequence on a reference line, the collaborative operation data on the reference line in the collaborative operation data sequence on the reference line comprises collaborative operation data on the reference line added with reference information, wherein the reference information represents whether the collaborative operation data on the reference line and collaborative service on a reference human resource line have a resource collaborative transformation correlation, and can be a binary label. It should be noted that, in the above-mentioned co-operation data sequence, the above-mentioned co-operation data in the above-mentioned co-operation data sequence may be for the same reference human resource online co-service, or may be for a plurality of reference human resource online co-services, and generally, the same reference human resource online co-service corresponds to a plurality of above-mentioned co-operation data. Further, the collaborative optimization label decision model in the embodiment of the present invention is obtained by using machine learning configuration by using multiple sets of collaborative operation data on the reference line.
For example, the following exemplary description is made for a collaborative optimization tag decision model, which may include three parts: the system comprises a collaborative transformation parameter value prediction unit, a grouping and sorting unit and a collaborative optimization label prediction unit for collaborative optimization label classification.
First, a group of on-line co-operation data (X1, X2, …, XM) of the on-line co-operation service of the human resource is inputted, M represents the total amount of the on-line co-operation data, and the co-operation data prediction unit can predict the association degree of the requirement of the co-operation application in a co-operation process for each on-line co-operation data to evaluate the characteristics of the on-line co-operation data and the on-line co-operation service of the human resource, that is, the co-operation parameter value corresponding to the on-line co-operation data.
In the embodiment of the present invention, the purpose of the cooperative conversion parameter value prediction unit is to calculate, for each on-line cooperative operation data Xi, a degree of association between the requirement of a cooperative application and one cooperative process. The co-transformation parameter value prediction unit emphasizes on-line co-operation data associated with a characteristic of a co-service on a human resource line and weakens useless redundant data. The method comprises the steps of firstly mapping the cooperative operation data on each line to preset feature partitions by using a bidirectional recurrent neural network to obtain cooperative operation feature vectors of the cooperative operation data on each line, and converting the cooperative operation feature vectors into the cooperative vector sequences on the lines by depth vector extraction. For example, a self-attention mechanism at the cooperative operation track level is adopted to respectively extract cooperative optimization tag characteristics between the on-line cooperative vector sequence of the cooperative operation data on each line and the on-line cooperative vector sequences of the cooperative operation data on other lines except the self-attention mechanism, a cooperative transformation parameter value between the cooperative operation data on each line and the cooperative service on the human resource line is obtained based on the cooperative optimization tag characteristics corresponding to the cooperative operation data on each line, and a correlation degree zi between the cooperative operation data on each line and the requirement of cooperative application in a cooperative process is obtained through calculation.
It should be noted that the bidirectional recurrent neural network is used as the feature vector extraction unit, and may be replaced by other models represented by a cooperating trajectory, which is not specifically limited herein.
After zi corresponding to the on-line cooperative operation data is obtained through calculation based on the cooperative conversion parameter value prediction unit, the on-line cooperative operation data can be grouped and sequenced based on a grouping and sorting unit in the cooperative optimization label decision model meeting the model convergence requirement. The specific process is as follows:
firstly, mapping each on-line cooperative operation data to a preset feature partition to obtain a cooperative operation object vector set corresponding to each on-line cooperative operation data, and extracting time domain information of the cooperative operation object vector set corresponding to each on-line cooperative operation data through time domain feature extraction operation to obtain a time domain cooperative operation feature vector of each on-line cooperative operation data; and then respectively performing feature fusion on the time domain cooperative operation feature vectors of the cooperative operation data on each line according to the cooperative transformation parameter values corresponding to the cooperative operation data on each line to obtain fusion time domain cooperative operation feature vectors Xi' of the cooperative operation data on each line.
Further, the fused time domain cooperative operation feature vectors of the cooperative operation data on all the lines can be grouped by applying a K-Means grouping algorithm, and the cooperative operation data on all the lines are grouped into K groups; and sequencing all the groups from large to small according to the quantity of the contained on-line cooperative operation data, and sequencing each group from small to large according to the distance from the on-line cooperative operation data to the center of the group area, thereby finally obtaining the ordered on-line cooperative operation data cluster. After the on-line cooperative operation data are spliced in sequence to obtain vector representation, the embodiment of the invention carries out cooperative label conversion and tiles the cooperative label into the first cooperative label coding characteristics of the cooperative labels. Finally, in the collaborative optimization label prediction unit, two reference benchmark limits, namely a reference operation vector and a reference benchmark loss, are adopted, so that the collaborative optimization label decision model can generate an ordered collaborative optimization label according to the time domain collaborative operation feature vector of the online collaborative operation data. The specific process is as follows:
and sequentially generating each cooperative optimization tag in the cooperative optimization tag sequence by adopting a random walk strategy, wherein one cooperative optimization tag in the cooperative optimization tag sequence at least comprises one cooperative optimization tag.
Wherein, each generation of a cooperative optimization label is regarded as a round of random walk execution, which can also be referred to as a time step. For example, in a round of random walk execution, the following steps are performed:
step S210, inputting the reference collaborative optimization label output in the previous round into a collaborative optimization label prediction unit, where the first round of the input collaborative optimization label prediction unit is a preset initial collaborative optimization label object.
In the embodiment of the present invention, a reference operation vector is introduced into the online collaborative vector sequence representation of the collaborative optimization label and the grouping, for example, the following steps are referred to for a specific reference benchmark process:
step S220, the target packet selected this time and the associated data group of the target packet are used as focused packets, and other packets are used as external packets, wherein the target packet selected each time is determined based on the order among the packets.
Step S230, adding a first reference operation vector to the on-line cooperative operation data elements in the focused group in the on-line cooperative operation data cluster, and adding a second reference operation vector to the on-line cooperative operation data elements in the external group in the on-line cooperative operation data cluster, to obtain a first reference on-line cooperative vector sequence corresponding to each on-line cooperative operation data element in the on-line cooperative operation data; and adding a first reference operation vector for the reference collaborative optimization label output in the previous round to obtain a corresponding collaborative vector sequence on a second reference datum line.
Assuming that the reference cooperative optimization label output in the previous round is yj, q-1, for yj, q-1, the on-line cooperative vector sequence of the cooperative optimization label of the first reference operation vector is integrated, that is, the on-line cooperative vector sequence of the second reference base line.
In order to capture the operation timing sequence part and the reference datum information from the ordered grouping, the attention value between the online cooperative operation data element and the cooperative optimization tag output in the previous round in the embodiment of the present invention is specifically implemented as follows:
step S240, analyzing, based on an attention mechanism, a related binding probability between the reference cooperative optimization tag output in the previous round and the cooperative operation data elements on each line in the cooperative operation data on the line, in combination with a first reference base vector corresponding to each cooperative operation data element on the line in the cooperative operation data on the line and a second reference base vector sequence corresponding to the reference cooperative optimization tag output in the previous round, where the related binding probability represents an attention value between the cooperative operation data element on the line and the cooperative optimization tag output in the previous round.
And step S250, performing feature fusion on the related binding probability and an online cooperative vector sequence of online cooperative operation data elements in the online cooperative operation data cluster, and inputting the feature fusion into a forward neural network to obtain a target time domain cooperative operation feature vector of the output online cooperative operation data cluster.
And step S260, generating the reference cooperative optimization label output this time based on the reference cooperative optimization label output in the previous round and the target time domain cooperative operation characteristic vector.
Further, the collaborative optimization label decision model in the embodiment of the present invention is obtained by using machine learning configuration by using multiple sets of collaborative operation data on the reference line. The specific configuration process is as follows:
acquiring a cooperative operation data sequence on a reference line aiming at least one reference human resource online cooperative service, and executing random walk execution configuration on an unconfigured cooperative optimization label decision model according to cooperative operation data on the reference line in the cooperative operation data sequence on the reference line to obtain a cooperative optimization label decision model meeting the model convergence requirement;
wherein, each round of random walk execution configuration process comprises the following steps:
(1) firstly, selecting a group of cooperative operation data on a reference line aiming at the same reference human resource online cooperative service from a cooperative operation data sequence on the reference line, taking the group of cooperative operation data on the reference line as large data of online cooperative operation, and inputting the cooperative operation data on the reference line contained in the selected cooperative operation data on the reference line into a cooperative transformation parameter value prediction unit in an unconfigured cooperative optimization label decision model to obtain a cooperative transformation parameter value corresponding to the cooperative operation data on the reference line output by the cooperative transformation parameter value prediction unit, wherein the cooperative operation data on the reference line is similar to the enumerated application process; and then, constructing a first model evaluation index based on the loss between the cooperative conversion parameter value corresponding to the cooperative operation data on each reference line and the corresponding reference information.
For example, the cooperative conversion parameter value prediction unit may determine the correlation between the cooperative operation data on each line and the cooperative operation data on other lines by using the correlation between the cooperative vector sequences on the cooperative operation data lines on the line, and calculate the significance information of the cooperative operation data on each line, which is related to the cooperative service on the human resource line, so as to achieve the goal of reducing noise of a large amount of cooperative operation data on the line, select the cooperative operation data on the significance line, and weaken the cooperative operation data on the irrelevant line.
(2) And respectively inputting the selected cooperative operation data on the reference lines in the cooperative operation data on the reference lines and the cooperative conversion parameter values corresponding to the cooperative operation data on the reference lines into a grouping and arranging unit in an unconfigured cooperative optimization label decision model, grouping the cooperative operation data on the reference lines based on the grouping and arranging unit, arranging the groups after obtaining at least two groups, and obtaining a second cooperative label coding characteristic of the cooperative label output by the grouping and arranging unit. Then, the second collaborative label coding feature is input into a collaborative optimization label prediction unit in an unconfigured collaborative optimization label decision model, and collaborative optimization label feature extraction is performed based on the collaborative optimization label prediction unit to obtain a group of prediction collaborative optimization label lists output by the collaborative optimization label prediction unit, wherein the prediction collaborative optimization label lists comprise at least two prediction collaborative optimization labels.
(3) For the grouping sorting unit and the order-enhanced collaborative optimization label prediction unit, constructing a second model evaluation index based on the collaborative optimization probability loss of a predicted collaborative optimization label in a predicted collaborative optimization label list and an actual collaborative optimization label in a real collaborative optimization label sequence; and constructing a third model evaluation index based on the attention values of the cooperative operation data elements on the lines in each group.
(4) For any one predicted collaborative optimization label, determining collaborative optimization probability loss of the predicted collaborative optimization label in the predicted collaborative optimization label list and an actual collaborative optimization label in the real collaborative optimization label sequence based on the collaborative optimization probability of the predicted collaborative optimization label in a preset collaborative optimization label sequence and the collaborative optimization probability of the predicted collaborative optimization label in the online collaborative operation big data; and constructing a second model evaluation index based on the determined collaborative optimization probability loss.
And continuously updating model configuration data of the collaborative optimization label decision model based on the enumerated model evaluation indexes, and finally stopping iteration until the model meets the model convergence requirement or the iteration frequency reaches the upper limit to obtain the collaborative optimization label decision model meeting the model convergence requirement.
(5) After the collaborative optimization tag decision model is configured, a collaborative optimization tag sequence can be generated based on the configured collaborative optimization tag decision model. For example, a group of online cooperative operation data for online cooperative services of human resources is input into a configured cooperative optimization tag decision model, a group of cooperative optimization tag sequences is generated based on the cooperative optimization tag decision model, and finally the generated cooperative optimization tag sequences are returned.
In a design idea, a flow of a configuration method of a human resource management classification network based on big data analysis in an embodiment of the present invention is described below, where the specific implementation flow of the method is as follows:
step S300, acquiring a cooperative operation data sequence on a reference line aiming at least one reference human resource online cooperative service.
Step S301, a group of cooperative operation data on the reference line aiming at the same reference human resource online cooperative service is selected from the cooperative operation data sequence on the reference line.
Step S302, respectively inputting the cooperative operation data on the reference line included in the selected cooperative operation data on each reference line into a cooperative transformation parameter value prediction unit in the unconfigured cooperative optimization label decision model, and obtaining a cooperative transformation parameter value corresponding to the cooperative operation data on each reference line output by the cooperative transformation parameter value prediction unit.
Step S303, constructing a first model evaluation index based on the cooperative transformation parameter values corresponding to the cooperative operation data on each reference line and the loss before the corresponding reference information.
Step S304, respectively inputting the selected cooperative operation data on the reference line in the cooperative operation data on each reference line and the cooperative conversion parameter value corresponding to the cooperative operation data on each reference line into a grouping and sorting unit in the unconfigured cooperative optimization label decision model, and grouping the cooperative operation data on each reference line based on the grouping and sorting unit to obtain at least two groups.
Step S305, the groups are sorted based on the group sorting unit, and second cooperative label coding characteristics of the cooperative labels output by the group sorting unit are obtained.
Step S306, inputting the second collaborative label coding characteristics into a collaborative optimization label prediction unit with enhanced order in an unconfigured collaborative optimization label decision model, and extracting the collaborative optimization label characteristics based on the collaborative optimization label prediction unit to obtain a group of prediction collaborative optimization label lists output by the collaborative optimization label prediction unit.
Step S307, constructing a second model evaluation index based on the cooperative optimization probability loss of the predicted cooperative optimization tag in the predicted cooperative optimization tag list and the actual cooperative optimization tag in the real cooperative optimization tag sequence.
Step S308, constructing a third model evaluation index based on the attention values of the cooperative operation data elements on the lines in each group.
Step S309, updating model configuration data of the unconfigured collaborative optimization label decision model according to the first model evaluation index, the second model evaluation index and the third model evaluation index.
And S310, judging whether the collaborative optimization label decision model meets the model convergence requirement, if so, ending the process, otherwise, returning to the step S301.
FIG. 3 is a schematic diagram of a hardware structure of the human resource management service platform 100 for implementing the human resource management method based on big data analysis according to an embodiment of the present invention, and as shown in FIG. 3, the human resource management service platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.
In a specific implementation process, at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120, so that the processor 110 may execute the human resource management method based on big data analysis according to the above method embodiment, the processor 110, the machine-readable storage medium 120, and the communication unit 140 are connected through the bus 130, and the processor 110 may be configured to control transceiving actions of the communication unit 140, so as to perform data transceiving with the human resource service terminal 200.
For a specific implementation process of the processor 110, reference may be made to the above-mentioned various method embodiments executed by the human resource management service platform 100, which implement principles and technical effects are similar, and this embodiment is not described herein again.
In addition, an embodiment of the present invention further provides a readable storage medium, where a computer execution instruction is preset in the readable storage medium, and when a processor executes the computer execution instruction, the human resource management method based on big data analysis is implemented.
Finally, it should be understood that the examples in this specification are only intended to illustrate the principles of the examples in this specification. Other variations are also possible within the scope of this description. Accordingly, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be seen as matching the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.
Claims (9)
1. A human resource management method based on big data analysis is applied to a human resource management service platform, the human resource management service platform is in communication connection with a plurality of human resource service terminals, and the method comprises the following steps:
acquiring online cooperative operation big data aiming at online cooperative service of human resources, wherein the online cooperative operation big data comprises at least two online cooperative operation data;
obtaining a cooperative conversion parameter value between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources;
sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to the on-line cooperative operation data and the cooperative operation flow characteristic of the on-line cooperative operation data to obtain a corresponding on-line cooperative operation data cluster;
generating a collaborative optimization tag sequence for the online collaborative service of the human resources based on the online collaborative operation data cluster, wherein the collaborative optimization tag sequence comprises at least two reference collaborative optimization tags;
wherein the step of obtaining the value of the cooperative conversion parameter between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources comprises:
respectively inputting the on-line cooperative operation data into a cooperative optimization label decision model meeting the model convergence requirement, and performing feature extraction on the on-line cooperative operation data based on a cooperative transformation parameter value prediction unit in the cooperative optimization label decision model meeting the model convergence requirement to obtain a cooperative transformation parameter value corresponding to the on-line cooperative operation data output by the cooperative transformation parameter value prediction unit;
the step of sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to each on-line cooperative operation data and the cooperative operation flow characteristic of each on-line cooperative operation data to obtain a corresponding on-line cooperative operation data cluster includes:
respectively inputting the on-line cooperative operation data and the cooperative conversion parameter value corresponding to the on-line cooperative operation data into a grouping and sorting unit in the cooperative optimization label decision model meeting the model convergence requirement, grouping and sorting the on-line cooperative operation data based on the grouping and sorting unit to obtain a first cooperative label coding feature of the cooperative label output by the grouping and sorting unit, wherein the on-line cooperative operation data elements in the first cooperative label coding feature are combined to form the on-line cooperative operation data cluster;
the step of generating a collaborative optimization tag sequence for the online collaborative service of the human resource based on the online collaborative operation data cluster includes:
inputting the cooperative label coding characteristics into a cooperative optimization label prediction unit in the cooperative optimization label decision model meeting the model convergence requirement, and extracting the cooperative optimization label characteristics based on the cooperative optimization label prediction unit to obtain the cooperative optimization label sequence output by the cooperative optimization label prediction unit; the collaborative optimization label decision model meeting the model convergence requirement is obtained by training according to a collaborative operation data sequence on a reference line, the collaborative operation data on the reference line in the collaborative operation data sequence on the reference line comprises collaborative operation data on the reference line added with reference information, and the reference information represents whether the collaborative operation data on the reference line and collaborative service on a reference human resource line have the association of resource collaborative transformation.
2. The human resource management method based on big data analysis according to claim 1, wherein the step of sorting the on-line cooperative operation data according to the cooperative transformation parameter value corresponding to the on-line cooperative operation data and the cooperative operation flow characteristic of the on-line cooperative operation data to obtain the corresponding on-line cooperative operation data cluster comprises:
grouping the on-line cooperative operation data according to the cooperative conversion parameter values corresponding to the on-line cooperative operation data and the cooperative operation flow characteristics of the on-line cooperative operation data to obtain at least two on-line cooperative operation data groups;
and arranging all the on-line cooperative operation data groups, and arranging all the on-line cooperative operation data in all the on-line cooperative operation data groups respectively to obtain the on-line cooperative operation data cluster.
3. The human resource management method based on big data analysis according to claim 2, wherein the step of grouping the online collaborative operation data according to the collaborative transformation parameter values corresponding to the online collaborative operation data and the collaborative operation process characteristics of the online collaborative operation data to obtain at least two online collaborative operation data groups comprises:
respectively performing feature fusion on the cooperative operation flow characteristics of the on-line cooperative operation data according to the cooperative transformation parameter values corresponding to the on-line cooperative operation data to obtain fusion cooperative operation flow characteristics of the on-line cooperative operation data;
and grouping the on-line cooperative operation data according to the fusion cooperative operation flow characteristics of the on-line cooperative operation data to obtain at least two on-line cooperative operation data groups.
4. The human resource management method based on big data analysis according to claim 2, wherein the step of sorting the on-line cooperative operation data groups and sorting the on-line cooperative operation data in the on-line cooperative operation data groups to obtain the on-line cooperative operation data cluster comprises:
arranging each on-line cooperative operation data group according to the quantity of on-line cooperative operation data contained in each on-line cooperative operation data group;
and, for each said online co-operation data set, respectively performing the steps of:
sorting the on-line cooperative operation data in the on-line cooperative operation data group according to the cooperative operation flow characteristics of the on-line cooperative operation data in the on-line cooperative operation data group and the characteristic matching information of the on-line cooperative operation data group;
and generating the on-line cooperative operation data cluster based on the sorting and sorting data among the on-line cooperative operation data groups and the sorting and sorting data of the on-line cooperative operation data in the on-line cooperative operation data groups.
5. The human resource management method based on big data analysis according to claim 1, wherein the step of respectively inputting the online collaborative operation data into the collaborative optimization label decision model satisfying the model convergence requirement, and obtaining the collaborative transformation parameter value corresponding to the online collaborative operation data outputted by the collaborative transformation parameter value prediction unit based on the collaborative transformation parameter value prediction unit in the collaborative optimization label decision model satisfying the model convergence requirement comprises:
respectively inputting the on-line cooperative operation data into the cooperative transformation parameter value prediction unit, and mapping the on-line cooperative operation data to a preset feature partition based on a feature vector extraction unit in the cooperative transformation parameter value prediction unit to obtain a cooperative operation feature vector of the on-line cooperative operation data;
converting the cooperative operation characteristic vectors of the cooperative operation data on each line into corresponding cooperative vector sequences on the lines respectively through depth vector extraction;
respectively extracting the cooperative optimization label features between the on-line cooperative vector sequence of the on-line cooperative operation data and the on-line cooperative vector sequences of the on-line cooperative operation data except the cooperative optimization label features on the basis of the cooperative transformation parameter value prediction unit;
and acquiring a cooperative conversion parameter value between each online cooperative operation data and the human resource online cooperative service based on the cooperative optimization label characteristic corresponding to each online cooperative operation data.
6. The human resource management method based on big data analysis according to claim 1, wherein the step of grouping and sorting the on-line cooperative operation data based on the grouping and sorting unit to obtain the first cooperative tag encoding characteristic of the cooperative tag output by the grouping and sorting unit comprises:
based on the grouping and sorting unit in the collaborative optimization label decision model meeting the model convergence requirement, mapping each online collaborative operation data to a preset feature partition to obtain a collaborative operation object vector set corresponding to each online collaborative operation data;
extracting time domain information of the cooperative operation object vector set corresponding to the cooperative operation data on each line through time domain feature extraction operation to obtain time domain cooperative operation feature vectors of the cooperative operation data on each line;
respectively performing feature fusion on the time domain cooperative operation feature vector of each on-line cooperative operation data according to the cooperative transformation parameter value corresponding to each on-line cooperative operation data to obtain a fusion time domain cooperative operation feature vector of each on-line cooperative operation data;
grouping based on the fusion time domain cooperative operation feature vectors of the cooperative operation data on each line to obtain at least two cooperative operation data groups on the line;
and arranging all the on-line cooperative operation data groups, arranging all the on-line cooperative operation data in each on-line cooperative operation data group, splicing the fusion time domain cooperative operation feature vectors of all the on-line cooperative operation data, and performing cooperative label conversion to obtain the first cooperative label coding feature.
7. The human resource management method based on big data analysis according to claim 1, wherein the step of inputting the cooperative label coding features into a cooperative optimization label prediction unit in the cooperative optimization label decision model satisfying the model convergence requirement, and performing cooperative optimization label feature extraction based on the cooperative optimization label prediction unit to obtain the cooperative optimization label sequence output by the cooperative optimization label prediction unit comprises:
sequentially generating each cooperative optimization tag in the cooperative optimization tag sequence by adopting a random walk strategy, wherein one cooperative optimization tag in the cooperative optimization tag sequence at least comprises one cooperative optimization tag; wherein, in a round of random walk execution process, the following steps are executed:
inputting a reference collaborative optimization label output in the previous round into the collaborative optimization label prediction unit, wherein the reference collaborative optimization label input in the first round is a preset initial collaborative optimization label object;
analyzing, by an attention mechanism, a related binding probability of each online cooperative operation data element in the reference cooperative optimization tag output in the previous round and the online cooperative operation data, wherein the related binding probability represents an attention value between the online cooperative operation data element and the cooperative optimization tag output in the previous round;
performing feature fusion on the related binding probability and an online cooperative vector sequence of online cooperative operation data elements in the online cooperative operation data cluster, and inputting the feature fusion into a forward neural network to obtain a target time domain cooperative operation feature vector of the output online cooperative operation data cluster;
and generating the reference cooperative optimization label output this time based on the reference cooperative optimization label output in the previous round and the target time domain cooperative operation characteristic vector.
8. The method for human resource management based on big data analysis as claimed in claim 7, wherein before analyzing the related binding probabilities of the reference co-optimization label outputted from the previous round of the analysis by attention mechanism and the respective on-line co-operation data elements in the on-line co-operation data, further comprising:
taking the currently selected cooperative operation data group on the target line and the associated data group of the cooperative operation data group on the target line as a focused cooperative operation data group on the line, and taking other cooperative operation data groups on the line as external cooperative operation data groups on the line, wherein the cooperative operation data group on the target line selected each time is determined based on the sequence among the cooperative operation data groups on the line;
adding a first reference operation vector to the on-line cooperative operation data elements in the focused on-line cooperative operation data group in the on-line cooperative operation data cluster, and adding a second reference operation vector to the on-line cooperative operation data elements in the external on-line cooperative operation data group in the on-line cooperative operation data cluster to obtain a first reference on-line cooperative vector sequence corresponding to each on-line cooperative operation data element in the on-line cooperative operation data;
adding the first reference operation vector to the reference collaborative optimization label output in the previous round to obtain a corresponding collaborative vector sequence on a second reference datum line;
the step of analyzing, by an attention mechanism, the related binding probabilities of the reference collaborative optimization label output in the previous round and the respective on-line collaborative operation data elements in the on-line collaborative operation data includes:
and analyzing the related binding probability of the reference cooperative optimization tag output in the previous round and each on-line cooperative operation data element in the on-line cooperative operation data based on an attention mechanism by combining a first reference base vector corresponding to each on-line cooperative operation data element in the on-line cooperative operation data with a second reference base line cooperative vector sequence corresponding to the reference cooperative optimization tag output in the previous round.
9. The human resource management system based on big data analysis is characterized by comprising a human resource management service platform and a plurality of human resource service terminals in communication connection with the human resource management service platform;
the human resource management service platform is used for:
acquiring online cooperative operation big data aiming at online cooperative service of human resources, wherein the online cooperative operation big data comprises at least two online cooperative operation data;
obtaining a cooperative conversion parameter value between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources;
sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to the on-line cooperative operation data and the cooperative operation flow characteristic of the on-line cooperative operation data to obtain a corresponding on-line cooperative operation data cluster;
generating a collaborative optimization tag sequence for the online collaborative service of the human resources based on the online collaborative operation data cluster, wherein the collaborative optimization tag sequence comprises at least two reference collaborative optimization tags;
the method for obtaining the value of the cooperative conversion parameter between each online cooperative operation data in the online cooperative operation big data and the online cooperative service of the human resources comprises:
respectively inputting the on-line cooperative operation data into a cooperative optimization label decision model meeting the model convergence requirement, and performing feature extraction on the on-line cooperative operation data based on a cooperative transformation parameter value prediction unit in the cooperative optimization label decision model meeting the model convergence requirement to obtain a cooperative transformation parameter value corresponding to the on-line cooperative operation data output by the cooperative transformation parameter value prediction unit;
the step of sorting the on-line cooperative operation data according to the cooperative conversion parameter value corresponding to each on-line cooperative operation data and the cooperative operation flow characteristic of each on-line cooperative operation data to obtain a corresponding on-line cooperative operation data cluster includes:
respectively inputting the on-line cooperative operation data and the cooperative conversion parameter value corresponding to the on-line cooperative operation data into a grouping and sorting unit in the cooperative optimization label decision model meeting the model convergence requirement, grouping and sorting the on-line cooperative operation data based on the grouping and sorting unit to obtain a first cooperative label coding feature of the cooperative label output by the grouping and sorting unit, wherein the on-line cooperative operation data elements in the first cooperative label coding feature are combined to form the on-line cooperative operation data cluster;
the step of generating a collaborative optimization tag sequence for the online collaborative service of the human resource based on the online collaborative operation data cluster includes:
inputting the cooperative label coding characteristics into a cooperative optimization label prediction unit in the cooperative optimization label decision model meeting the model convergence requirement, and extracting the cooperative optimization label characteristics based on the cooperative optimization label prediction unit to obtain the cooperative optimization label sequence output by the cooperative optimization label prediction unit; the collaborative optimization label decision model meeting the model convergence requirement is obtained by training according to a collaborative operation data sequence on a reference line, the collaborative operation data on the reference line in the collaborative operation data sequence on the reference line comprises collaborative operation data on the reference line added with reference information, and the reference information represents whether the collaborative operation data on the reference line and collaborative service on a reference human resource line have the association of resource collaborative transformation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643747.9A CN113269535B (en) | 2021-06-09 | 2021-06-09 | Human resource management method and system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643747.9A CN113269535B (en) | 2021-06-09 | 2021-06-09 | Human resource management method and system based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113269535A CN113269535A (en) | 2021-08-17 |
| CN113269535B true CN113269535B (en) | 2022-02-15 |
Family
ID=77234814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110643747.9A Active CN113269535B (en) | 2021-06-09 | 2021-06-09 | Human resource management method and system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113269535B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6721941B1 (en) * | 1996-08-27 | 2004-04-13 | Compuware Corporation | Collection of timing and coverage data through a debugging interface |
| CN103679384A (en) * | 2013-12-25 | 2014-03-26 | 武汉武船信息集成有限公司 | Method for workflow cooperative office work |
| CN104700177A (en) * | 2013-12-09 | 2015-06-10 | 广州市科秀电子科技有限公司 | Collaborative work platform |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050020945A1 (en) * | 2002-07-02 | 2005-01-27 | Tosaya Carol A. | Acoustically-aided cerebrospinal-fluid manipulation for neurodegenerative disease therapy |
| CN103166934A (en) * | 2011-12-15 | 2013-06-19 | 方正国际软件(北京)有限公司 | Cooperative service system and cooperative service method |
| CN105453930A (en) * | 2015-12-06 | 2016-04-06 | 吴邦道 | Online and offline cooperative creation and production method, and needed auxiliary mechanism |
-
2021
- 2021-06-09 CN CN202110643747.9A patent/CN113269535B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6721941B1 (en) * | 1996-08-27 | 2004-04-13 | Compuware Corporation | Collection of timing and coverage data through a debugging interface |
| CN104700177A (en) * | 2013-12-09 | 2015-06-10 | 广州市科秀电子科技有限公司 | Collaborative work platform |
| CN103679384A (en) * | 2013-12-25 | 2014-03-26 | 武汉武船信息集成有限公司 | Method for workflow cooperative office work |
Non-Patent Citations (2)
| Title |
|---|
| "Organizational knowledge and collaborative human resource practices as determinants of innovation";Julia Nieves等;《Knowledge Management Research &Practice》;20171219;第14卷(第3期);第237-245页 * |
| "基于服务的模具协同设计技术研究";周盛;《中国博士学位论文全文数据库 工程科技I辑》;20111115(第11期);B022-76页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113269535A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191934B (en) | Multi-target cloud workflow scheduling method based on reinforcement learning strategy | |
| CN111461226A (en) | Countermeasure sample generation method, device, terminal and readable storage medium | |
| CN112416585B (en) | Deep learning-oriented GPU resource management and intelligent scheduling method | |
| CN107197006B (en) | Multi-constraint service selection method and device based on global QoS decomposition | |
| CN113361680A (en) | Neural network architecture searching method, device, equipment and medium | |
| CN113098714A (en) | Low-delay network slicing method based on deep reinforcement learning | |
| CN110110858A (en) | A kind of automatic machinery learning method based on intensified learning | |
| CN113299382A (en) | Intelligent medical information decision method based on artificial intelligence and cloud computing system | |
| Talbi | Hybrid metaheuristics for multi-objective optimization | |
| CN113837492B (en) | Method, apparatus, storage medium, and program product for predicting article supply amount | |
| CN117573307B (en) | Method and system for overall management of multiple tasks in cloud environment | |
| Li et al. | Symbolic expression transformer: A computer vision approach for symbolic regression | |
| CN113269535B (en) | Human resource management method and system based on big data analysis | |
| CN117236427A (en) | Decision constraint rule characterization method for task actions | |
| CN116149855A (en) | Method and system for optimizing performance resource cost under micro-service architecture | |
| CN111475496A (en) | Multi-condition constraint-based time series data generation method, device and medium | |
| CN114143059B (en) | Safety protection index optimization method based on big data information safety and artificial intelligence system | |
| CN114625967A (en) | User information mining method based on big data service optimization and artificial intelligence system | |
| CN114443970A (en) | Artificial intelligence and big data based digital content pushing method and AI system | |
| CN112488343B (en) | Smart city intelligent perception terminal address selection method based on hyper-heuristic algorithm | |
| CN115454473A (en) | Data processing method based on deep learning vulnerability decision and information security system | |
| CN112925831A (en) | Big data mining method and big data mining service system based on cloud computing service | |
| Liu et al. | Experience-based optimization: A coevolutionary approach | |
| CN115330319B (en) | Logistics information processing method based on big data and artificial intelligence server | |
| Frenkel | Ontological and probabilistic aspects of assessing predictors quality |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Human resource management method and system based on big data analysis Effective date of registration: 20220921 Granted publication date: 20220215 Pledgee: Nantong Rongquan Electronics Co.,Ltd. Pledgor: Nantong xinchuangku Information Technology Co.,Ltd. Registration number: Y2022320000564 |