CN116805202B - Method, device and application for searching for substitute staff based on artificial intelligence - Google Patents
Method, device and application for searching for substitute staff based on artificial intelligence Download PDFInfo
- Publication number
- CN116805202B CN116805202B CN202311059176.XA CN202311059176A CN116805202B CN 116805202 B CN116805202 B CN 116805202B CN 202311059176 A CN202311059176 A CN 202311059176A CN 116805202 B CN116805202 B CN 116805202B
- Authority
- CN
- China
- Prior art keywords
- employee
- working
- staff
- category
- event
- 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 34
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 239000013598 vector Substances 0.000 claims abstract description 77
- 230000002452 interceptive effect Effects 0.000 claims abstract description 24
- 230000003993 interaction Effects 0.000 claims description 78
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims 2
- 230000006870 function Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 9
- 238000011161 development Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000003245 working effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method, a device and an application for searching for a substitute employee based on artificial intelligence, which comprise the following steps: acquiring employee information and event sequences of a company, and constructing a personal relationship network according to the employee information and the event sequences; setting the length of an interactive link, traversing the personal relationship network of each employee to generate a personal relationship vector, and calculating the similarity of the personal relationship vector of the replaced employee and other employees; staff corresponding to the personal relation vector with similarity larger than the set threshold value form a replacement staff set; predicting a future event sequence, obtaining the work type, the work times and the work saturation coefficient of each employee, calculating the replacement scores of the replacement employees, and selecting the replacement employee with the highest score for replacement. According to the scheme, the staff with similar capabilities can be found by constructing the relation network of each staff, and the most suitable replacement staff can be found in an optimal mode by selecting the suitable staff for replacement by predicting the future work types.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to a method, a device and application for searching for a substitute employee based on artificial intelligence.
Background
Staff is the most important component part of an enterprise, is the foundation of enterprise development, and the absence of staff of the enterprise usually can bring negative effects to performance and profitability of the enterprise, and the absence is often regarded as related work of human resources, and is coordinated by related human resource departments to be processed by the staff departments, and appropriate substitute staff are found by relying on subjective evaluation and related knowledge of department managers.
However, finding suitable replacement employees through subjective assessment and related knowledge of the manager often ignores informal organization structures, i.e., network structures that the employees establish across functions and departments in order to accomplish the assigned tasks, that determine the actual work of the employees in the organization and represent the personal work relationships of each employee, which are inconsistent with the department network structures described by the employees themselves.
The prior art has a method for replacing a absenteeism staff with another staff performing similar tasks or establishing working relations with the absenteeism staff by extracting staff attributes from the staff log and using these attributes to define a planning model to determine a suitable alternative for the absenteeism staff, which, although can quickly find candidate replacement staff, does not reflect the change of the whole working relation, that is to say, the task needs to be redistributed according to the capabilities of the replacement staff, which can lead to the influence of the cycle time of the business process, and the change of the working property and working mode of the replacement staff can influence the working capacity of the whole team and thus the organization result, while the replacement staff can face the dilemma of not only performing the original tasks but also performing the additional tasks of the absenteeism staff, which often makes the replacement staff not burden the working strength in case of high working strength of the replacement staff itself, and the actual effect of the replacement mode is poor.
Disclosure of Invention
The embodiment of the application provides a method, a device and an application for searching for a replacement employee based on artificial intelligence.
In a first aspect, an embodiment of the present application provides a method for searching for a substitute employee based on artificial intelligence, where the method includes:
acquiring employee information and event sequences of a company, acquiring event interaction information and event interaction times among employees according to the event sequences, and constructing a personal relationship network for each employee according to the event interaction information and the event interaction times of each employee and other employees;
setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate personal relationship vectors, acquiring the personal relationship vectors of the replaced employees, calculating the similarity between the personal relationship vectors of the replaced employees and the personal relationship of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than the set threshold as the replacement employee to obtain a replacement employee set;
Predicting a future event sequence according to the event sequence by using a pre-trained event prediction model, acquiring the working type of each employee and the working times of each working type according to the future event sequence, acquiring the working saturation coefficient of each employee, calculating the replacement score of each replacement employee relative to the replaced employee according to the future working type of each employee, the working times of each working type and the working saturation coefficient, and selecting the replacement employee with the highest replacement score to replace the replaced employee.
In a second aspect, an embodiment of the present application provides an apparatus for searching for a substitute employee based on artificial intelligence, including:
the acquisition module is used for: acquiring employee information and event sequences of a company, acquiring event interaction information and event interaction times among employees according to the event sequences, and constructing a personal relationship network for each employee according to the event interaction information and the event interaction times of each employee and other employees;
and (3) selecting a module: setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate personal relationship vectors, acquiring the personal relationship vectors of the replaced employees, calculating the similarity between the personal relationship vectors of the replaced employees and the personal relationship of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than the set threshold as the replacement employee to obtain a replacement employee set;
And (3) a replacement module: predicting a future event sequence according to the event sequence by using a pre-trained event prediction model, acquiring the working type of each employee and the working times of each working type according to the future event sequence, acquiring the working saturation coefficient of each employee, calculating the replacement score of each replacement employee relative to the replaced employee according to the future working type of each employee, the working times of each working type and the working saturation coefficient, and selecting the replacement employee with the highest replacement score to replace the replaced employee.
In a third aspect, embodiments of the present application provide an electronic device comprising a memory having a computer program stored therein and a processor configured to run the computer program to perform a method of finding an alternative employee based on artificial intelligence.
In a fourth aspect, embodiments of the present application provide a readable storage medium having a computer program stored therein, the computer program comprising program code for controlling a process to execute a process, the process comprising a method of finding an alternative employee based on artificial intelligence.
The main contributions and innovation points of the application are as follows:
According to the embodiment of the application, the personal relationship network is built for each employee by acquiring employee information and event sequences of a company, the type of work participated by the employee and the interaction information with other employees are indicated through the personal relationship network, the personal relationship network is traversed by the interaction link length by setting the interaction link length, so that the personal relationship vector of each employee is obtained to compare the employees, and a proper replacement employee is found; the scheme is characterized in that the traversing of the personal relationship network is performed in a mode of combining breadth first and depth first, so that the obtained personal relationship vector can be ensured to be in a core area and a far-end relationship can be found, and an obtained result is more accurate; the scheme predicts the future event sequence by constructing a model, predicts the change of the future relation by the future event sequence, is helpful for determining proper alternative staff and centrally distributes tasks in an optimal mode so as to rapidly cope with the situation of sudden absence of staff.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a flow chart of a method for finding alternative employees based on artificial intelligence in accordance with an embodiment of the present application;
FIG. 2 is a schematic diagram of a personal relationship network in accordance with an embodiment of the application;
FIG. 3 is a block diagram of an apparatus for finding alternative employees based on artificial intelligence in accordance with an embodiment of the present application;
fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with aspects of one or more embodiments of the present description as detailed in the accompanying claims.
It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than described in this specification. Furthermore, individual steps described in this specification, in other embodiments, may be described as being split into multiple steps; while various steps described in this specification may be combined into a single step in other embodiments.
Example 1
The embodiment of the application provides a method for searching for alternative staff based on artificial intelligence, and specifically relates to a method for searching for alternative staff based on artificial intelligence, which comprises the following steps of:
acquiring employee information and event sequences of a company, acquiring event interaction information and event interaction times among employees according to the event sequences, and constructing a personal relationship network for each employee according to the event interaction information and the event interaction times of each employee and other employees;
setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate personal relationship vectors, acquiring the personal relationship vectors of the replaced employees, calculating the similarity between the personal relationship vectors of the replaced employees and the personal relationship of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than the set threshold as the replacement employee to obtain a replacement employee set;
Predicting a future event sequence according to the event sequence by using a pre-trained event prediction model, acquiring the working type of each employee and the working times of each working type according to the future event sequence, acquiring the working saturation coefficient of each employee, calculating the replacement score of each replacement employee relative to the replaced employee according to the future working type of each employee, the working times of each working type and the working saturation coefficient, and selecting the replacement employee with the highest replacement score to replace the replaced employee.
The staff information acquired in the scheme comprises staff personal information, wherein the staff personal information comprises staff current posts and staff skills, the personal information can acquire event sequences according to staff resume self-description, working capacity, regular training results of enterprises, skill detection evaluation results and the like to be all events processed by the companies within a period of time, the event sequences can be divided into a plurality of events, each event can be divided into a plurality of working categories, for example, research, development, test and operation form an event sequence, the individual research, test and operation are one event, each event can be subdivided into a plurality of working categories, and the working categories can comprise front-end development, back-end development and the like.
Furthermore, the obtained employee information and event sequences are stored as a structured data set, and data in the structured data set is subjected to data arrangement to obtain available data.
Specifically, the missing values are processed on the data in the structured dataset, the repeated data are cleaned up, and then the missing values are converted into vector representations for subsequent computation, and the data can be converted into vector representations by the following steps:
word segmentation is carried out on the text data, independent words are segmented out by using an NLP word segmentation tool, common stop words are deleted, and nonsensical word interference is reduced; performing morphological reduction, and converting the morphological reduction into a root form so as to eliminate morphological change influence; constructing a word frequency statistics dictionary, and selecting a vocabulary scale according to the word frequency; generating a bag of words representation for the text, representing the number of times of vocabulary; calculating weights based on the word bags, and reducing the weights of common words; loading a pre-training word vector to obtain word semantic vector representation; normalized vector representation, adjusted to the same numerical range; the vector representations are formed into a structured dataset and saved as a format for convenient loading; the check vector represents the accuracy and consistency of the conversion and outputs the formed text vector.
In the step of acquiring event interaction information and event interaction times between employees according to the event sequence, the event sequence is all events processed by a company within a period of time, the event sequence consists of a plurality of events, each event consists of at least one working category, the working category records the participators who complete the current work, working resources and working time, and the event interaction information and event interaction times between the employees are acquired according to the working category recorded by the event sequence.
Specifically, if two employees participate in the same working category of the same event, the two employees are considered to perform one-time event interaction and count event interaction times among the employees, the event interaction information is divided into direct interaction and indirect interaction, if the two employees participate in the same working category of the same event, the event interaction information of the two employees is recorded as direct interaction, and if the two employees do not participate in the same working category of the same event, but the two employees are indirectly associated through other employees, the event interaction information of the two employees is recorded as indirect interaction.
Specifically, event E is initiated with subdivision disassembly，f a ，f b For event E n For f a For the work category f a Denoted as->A is a resource vector describing the working resources of the current work, i.e. representing participation f a The required resource vectors, including but not limited to funds, raw materials, equipment, etc., can reflect the resource allocation situation required by a certain work category, and P is the enterprise employee combination vector of the participating employees who complete the current work, i.e. represents participation f a The personnel vector T is the time vector for recording the working time for completing the current work, namely the completion f a Time spent.
In the step of acquiring event interaction information and event interaction times between staff according to the work types recorded in an event sequence, traversing the participators of each work type, setting the participation value of each worker participating in the current work type according to the participators of the work types, acquiring the cooperative relationship of the different staff participating in the current work type by using the product of the participation values of the different staff, and summarizing all the cooperative relationships in the event sequence to obtain the event interaction information between the staff.
Specifically, for a job class f p If employee x participates then it is noted as f p (x) =1, and if not engaged, is denoted as f p (x) =0, thus for one working class f p By f p (x)*f p (y) representing that employee x and employee y are in work category f p While the co-operation of x, y throughout event E can be expressed asWhereas for the whole sequence of events L, the cooperative relationship of x, y can be expressed as +.>Thereby obtaining event interaction information in the event sequence L.
In the step of acquiring event interaction information and event interaction times between staff according to the work types recorded in the event sequence, traversing the participators of each work type, counting the participation times of the same work type in each worker participated event sequence according to the participators, taking the work types of the event sequence as columns or rows, constructing an association matrix according to the participation times of all staff in each work type as rows or columns, and acquiring the event interaction times between staff according to the association matrix.
Specifically, in the step of acquiring the event interaction times between the employees according to the incidence matrix, acquiring the participation times of each employee to participate in different work types according to the incidence matrix, acquiring the event interaction times between the employees according to the participation times, and adding 1 to the event interaction times if two employees are commonly present in the same work type.
In particular, for the same working class f present in different events p Counting the frequency of each employee participating in the same work category, and summing up the frequency of each employee participating in different work categories to obtain an association matrixThe incidence matrix is used for representing the number of times that each worker participates in different work types, in the incidence matrix, each row represents the same work type of the event sequence, each row represents the number of times that the same worker participates in different work types, and PA is obtained from the incidence matrix x,p Representative employee x participates in the same work category f p For example, can be based onThe number of times that x staff participates in back-end development in the current year is 21, and the event interaction times of x staff and y staff can be obtained according to the columns of the incidence matrix and are +.>。
In the step of constructing a personal relationship network for each employee according to event interaction information and event interaction times of each employee and other employees, an employee to be constructed is obtained, the employee to be constructed is taken as a center point, the employee with event interaction with the employee to be constructed is obtained as a node according to the event interaction information, and the personal relationship network of the employee to be constructed is obtained by taking the event interaction times between the employees represented by the two nodes as edges.
For example, as shown in fig. 2, P1 is a generation building employee, so taking P1 as a center point, P2, P3, P4, P6 are employees having direct interaction with P1, P5, P7, P8 are employees having indirect interaction with P1, P12, P13, P35, P68, etc. are event interaction times, for example, when p12=80, the event interaction times representing P1 and P2 are 80.
In the step of setting the length of an interactive link and traversing the personal relationship network of each employee according to the length of the interactive link to generate a personal relationship vector, traversing the personal relationship network according to the length of the interactive link based on a breadth-first principle to obtain a breadth relationship vector, traversing the personal relationship network according to the length of the interactive link based on a depth-first principle to obtain a depth relationship vector, and merging the breadth relationship vector and the depth relationship vector to obtain the personal relationship vector.
In some embodiments, according to breadth-first principles, the breadth link selection probability for each node in the personal relationship network is calculated, the higher the probability that an employee with a greater number of interactions with the center employee Px is selected, expressed using the following formula:
wherein n+1 represents an employee set directly interacted with Px, and the probability meaning is that the probability of selecting the next link is confirmed according to the weight of the number of activities, that is, the more employees directly interacted with Px exist, the larger the probability of selecting the next time, the breadth link probability according to the length d of the interaction link is:
Wherein, px is a central point of the personal relationship network, px+1 and px+2 are other nodes in the length of the interactive link, and the result obtained by selecting according to the breadth-first principle is a breadth relationship vector.
In some embodiments, selecting a node far from the center point and having an interaction link length d with the center point according to the depth-first principle is as follows:
the deep link probability for an interaction link length d is:
the result obtained by selecting according to the depth priority principle is a depth relation vector, and a personal relation vector is obtained by combining the breadth relation vector and the depth relation vector。
According to the scheme, firstly, the breadth-first principle is adopted, the cooperative relationship of direct interaction with key staff can be searched more comprehensively by the breadth-first principle, then the cooperative relationship of indirect interaction far away is searched by the depth-first principle, the possibility of indirect cooperation is found, the number of traversal steps can be reasonably controlled by combining the breadth-first principle with the depth-first principle, and invalid traversal is avoided.
In some embodiments, different participating employees in each job category are assigned weights based on personal information of each employee and the sequence of events.
And acquiring departments and roles of the staff according to personal information of the staff, and judging weights of different staff participating in each working class according to the historical working class in the historical data.
Specifically, all the work types participated by each employee are obtainedThe fa (x) and fp (x) respectively represent different work types, weights are distributed to the staff in each work type according to the historical data and the historical post of the staff, if the historical data and the historical post have no relevant information, the default weight value is 1, and for Px, the PAx can be converted into the motion vector:
wj (x) represents the weight value in job category j for employee x.
In the step of calculating the similarity between the personal relationship vector of the replaced employee and the personal relationship vector of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than the set threshold as the replacement employee to obtain the replacement employee set, the employee indirectly interacted with the replacement employee is put into the replacement employee set.
Obtaining personal relationship vectors for any enterprise employee x, yAnd->If->And->The similarity of (2) is greater than 80%, thenIn order to consider that the working skills of the staff x are similar to those of the staff y, the staff y can be used as a replacement staff of the staff x, and staff with direct interaction with the staff y and staff without direct interaction with the staff x are considered to have the possibility of cooperation with the staff x in the future and also used as the replacement staff.
Specifically, the related activity conditions are used for acquiring employees indirectly interacted with the replacement employees according to the activity number coefficients, the employees are updated to the replacement employee set, the activity number of each employee is acquired according to the activity vector of each employee, and the coefficients are weights of different participated employees in each activity.
In the step of predicting a future event sequence according to an event sequence by using a pre-trained event prediction model, the event prediction model constructs a prediction function to predict the future event sequence according to the event sequence, initial prediction parameters are generated for the prediction function, the prediction function uses the initial prediction parameters to obtain at least one prediction output, an objective function is constructed, the difference between each prediction output and the real output is calculated by using the objective function, the smaller the difference between the prediction output and the real output is, the higher the adaptability is, the initial prediction parameters are updated according to the prediction output with the highest adaptability, so that the search range is changed to obtain a group of new prediction outputs, and when the event prediction model meets the set condition, the final initial prediction parameters are output as final parameters of the model, so that the pre-trained event prediction model is obtained.
Specifically, for a stable company, the activities of the events show continuity, such as bidding is performed before development and operation is performed for a project, and the subsequent development, operation and maintenance work can be estimated for the bidding events which are already happened, so that for a stable company, the future event sequence can be predicted according to the known event sequence, and thus the traffic of each person can be reasonably estimated.
Specifically, for an event sequence L, which includes a plurality of events, i.e., l= { E1, E2 …, en }, the event En can be divided into a plurality of working categories, i.e., en= { fa, fb, …, fn }, each event sequence can be expressed asThe working category of L at the moment T comprisesFat represents the number of times the operation type fa occurs at time t.
Specifically, the event sequence is normalized, fmax is the largest value in the event sequence, fmin is the smallest value in the time sequence, and then:
normalizing the values of the event sequence Lt in the t period after the processingWill be in interval [ -1,1]And (3) inner part.
Specifically, since the data Lt at time t is affected by Lt-1, ht is recorded as a prediction function constructed from the predicted data of Lt:
specifically, σ is a nonlinear activation function, U represents a hidden layer-to-hidden layer weight matrix, W represents a weight matrix that was input to the hidden layer, and B represents a bias vector.
Specifically, an initial value is generated for each initial prediction parameter, that is, an initial value is randomly generated for each parameter matrix σ, W, U, B in the present scheme for training.
The scheme adopts the mean square error as an objective function and is used for calculating the difference between the predicted output and the real output:
Where MSE represents the mean square error, L represents the true output, and H represents the predicted output.
Then updating the initial prediction parameters according to the prediction output with the minimum adaptability, namely the minimum difference with the real output:
where β(s) represents the step size at the s-th iteration, hst represents the increase of the initial prediction parameter at the s-th iteration, hlt represents the decrease of the initial prediction parameter at the s-th iteration, sign () is a sign function, μ is a step size factor, generally 0.95 is taken, and if the fitness of Hst is greater than Hlt, the matrix parameter is increased by the step size β(s), otherwise, it is decreased.
Specifically, model parameters sigma and W, U, B are updated according to the prediction output, so that a search range is changed to generate new prediction output.
In the step of acquiring the work saturation coefficient of each employee, the work category with the longest time consumption, the work category with the shortest time consumption and the average work time consumption of each employee in a certain time are acquired to calculate the work saturation coefficient, wherein the average work time consumption is the average time consumption of completing one work category by the employee.
Specifically, the working saturation coefficient is calculated as follows:
wherein,for the work saturation coefficient of the staff y, t1 is the work type with the longest time consumption, t2 is the work type with the shortest time consumption, t3 is the average work time consumption, and t is a certain time, wherein the certain time refers to the past month in the scheme.
In the step of calculating the replacement score of each replacement employee relative to the replaced employee according to the future work category of each employee, the future work times of each work category and the work saturation coefficient, the replacement score of the replacement employee relative to the replaced employee is thatWherein->As the work saturation coefficient, i is the future work category of the replaced employee, ai represents the comparison of the number of works of the replaced employee with the number of works of the replaced employee in the i work category, ai is 1 if the future number of works of the replaced employee for the i work category is greater than the replaced employee, ai is the ratio of the future number of works of the replaced employee for the i work category to the future number of works of the replaced employee for the i work category if the future number of works of the replaced employee for the i work category is 0, ai is 0, bi judges the future work category of the replaced employee if the future work category of the replaced employee contains the i work category, bi is 1 if the future work category of the replaced employee does not contain the i work category, bi is 0.
Specifically, the determination mode of Ai can be expressed as:
the determination method of Bi can be expressed as:
where PAy, i is the future number of jobs by the replacement employee for job class i, pax, i is the future number of jobs by the replacement employee for job class i.
Specifically, the replacement score of each replacement employee is obtained through calculation by the method, and the replacement employee with the highest replacement score is selected to replace the replaced employee.
Example two
Based on the same conception, referring to fig. 3, the application also provides a device for searching for substitute staff based on artificial intelligence, comprising:
the acquisition module is used for: acquiring employee information and event sequences of a company, acquiring event interaction information and event interaction times among employees according to the event sequences, and constructing a personal relationship network for each employee according to the event interaction information and the event interaction times of each employee and other employees;
and (3) selecting a module: setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate personal relationship vectors, acquiring the personal relationship vectors of the replaced employees, calculating the similarity between the personal relationship vectors of the replaced employees and the personal relationship of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than the set threshold as the replacement employee to obtain a replacement employee set;
And (3) a replacement module: predicting a future event sequence according to the event sequence by using a pre-trained event prediction model, acquiring the working type of each employee and the working times of each working type according to the future event sequence, acquiring the working saturation coefficient of each employee, calculating the replacement score of each replacement employee relative to the replaced employee according to the future working type of each employee, the working times of each working type and the working saturation coefficient, and selecting the replacement employee with the highest replacement score to replace the replaced employee.
Example III
This embodiment also provides an electronic device, referring to fig. 4, comprising a memory 404 and a processor 402, the memory 404 having stored therein a computer program, the processor 402 being arranged to run the computer program to perform the steps of any of the method embodiments described above.
In particular, the processor 402 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present application.
The memory 404 may include, among other things, mass storage 404 for data or instructions. By way of example, and not limitation, memory 404 may comprise a Hard Disk Drive (HDD), floppy disk drive, solid State Drive (SSD), flash memory, optical disk, magneto-optical disk, tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Memory 404 may include removable or non-removable (or fixed) media, where appropriate. Memory 404 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 404 is a Non-Volatile (Non-Volatile) memory. In particular embodiments, memory 404 includes Read-only memory (ROM) and Random Access Memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or FLASH memory (FLASH) or a combination of two or more of these. The RAM may be Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM) where appropriate, and the DRAM may be fast page mode dynamic random access memory 404 (FPMDRAM), extended Data Output Dynamic Random Access Memory (EDODRAM), synchronous Dynamic Random Access Memory (SDRAM), or the like.
Memory 404 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions for execution by processor 402.
Processor 402 implements any of the methods of the above embodiments based on artificial intelligence to find alternative employees by reading and executing computer program instructions stored in memory 404.
Optionally, the electronic apparatus may further include a transmission device 406 and an input/output device 408, where the transmission device 406 is connected to the processor 402 and the input/output device 408 is connected to the processor 402.
The transmission device 406 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through the base station to communicate with the internet. In one example, the transmission device 406 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.
The input-output device 408 is used to input or output information. In this embodiment, the input information may be event sequences, employee information, and the like, and the output information may be replacement employees, and the like.
Alternatively, in the present embodiment, the above-mentioned processor 402 may be configured to execute the following steps by a computer program:
s101, staff information and event sequences of a company are obtained, event interaction information and event interaction times among staff are obtained according to the event sequences, and a personal relationship network is built for each staff according to the event interaction information and the event interaction times of each staff and other staff;
s102, setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate a personal relationship vector, acquiring the personal relationship vector of the replaced employee, calculating the similarity between the personal relationship vector of the replaced employee and the personal relationship vector of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than the set threshold as the replaced employee to obtain a replaced employee set;
s103, predicting a future event sequence according to the event sequence by using a pre-trained event prediction model, acquiring the working type of each employee and the working times of each working type according to the future event sequence, acquiring the working saturation coefficient of each employee, calculating the replacement score of each replacement employee relative to the replaced employee according to the future working type of each employee, the working times of each working type and the working saturation coefficient, and selecting the replacement employee with the highest replacement score to replace the replaced employee.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
In general, the various embodiments may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the invention is not limited thereto. While various aspects of the invention may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
Embodiments of the invention may be implemented by computer software executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets, and/or macros can be stored in any apparatus-readable data storage medium and they include program instructions for performing particular tasks. The computer program product may include one or more computer-executable components configured to perform embodiments when the program is run. The one or more computer-executable components may be at least one software code or a portion thereof. In this regard, it should also be noted that any block of the logic flow as in fig. 4 may represent a procedure step, or interconnected logic circuits, blocks and functions, or a combination of procedure steps and logic circuits, blocks and functions. The software may be stored on a physical medium such as a memory chip or memory block implemented within a processor, a magnetic medium such as a hard disk or floppy disk, and an optical medium such as, for example, a DVD and its data variants, a CD, etc. The physical medium is a non-transitory medium.
It should be understood by those skilled in the art that the technical features of the above embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features.
The foregoing examples illustrate only a few embodiments of the application, which are described in greater detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (4)
1. A method for searching for alternative employees based on artificial intelligence, comprising the steps of:
acquiring employee information and event sequences of a company, acquiring event interaction information and event interaction times among employees according to the event sequences, wherein the event sequences are all events processed in a period of time of the company, the event sequences are composed of a plurality of events, each event is composed of at least one working category, the working category records participation employees of the current working, working resources and working time, event interaction information and event interaction times among the employees are acquired according to the working categories recorded in the event sequences, participation employees of each working category are traversed, participation values of each employee participated in the current working category are set according to the participation employees of the working category, cooperation relations of the different employees participated in the current working category are acquired by utilizing products of participation values of different employees, event interaction information among the employees is acquired by summarizing all the cooperation relations in the event sequences, the participation employees of each working category is counted according to the participation times of the same working category in each employee, the working category of the event sequences is used as a row or a column of the working event, all the participation times among the employees are used as a column or a construction association matrix, interaction time is acquired according to the participation matrixes among the working categories, each employee is used as a node to be interacted with each employee to be interacted, and a node to be interacted with the node to be interacted, and a network node to be interacted is constructed, the interaction node is used as a node to be interacted and is constructed;
Setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate a personal relationship vector, traversing the personal relationship network according to the length of the interactive link based on a breadth-first principle to obtain a breadth relationship vector, traversing the personal relationship network according to the length of the interactive link based on a depth-first principle to obtain a depth relationship vector, merging the breadth relationship vector and the depth relationship vector to obtain a personal relationship vector, obtaining the personal relationship vector of a replaced employee, calculating the similarity between the personal relationship vector of the replaced employee and the personal relationship vector of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than a set threshold as the replaced employee to obtain a replaced employee set;
predicting a future event sequence from the event sequence using a pre-trained event prediction model, acquiring a work category of each employee, a number of works of each work category from the future event sequence, and determining a non-existence of each work category based on personal information of each employee and the event sequenceThe same participating staff is assigned with weight, the work saturation coefficient of each staff is obtained, the longest time-consuming work category, the shortest time-consuming work category and the average work time consumption of each staff in a certain time are obtained to calculate the work saturation coefficient, the average work time consumption is the average time consumption of the staff to complete one work category, the replacement score of each replacement staff relative to the replaced staff is calculated according to the future work category of each staff, the work times of each work category and the work saturation coefficient, and the replacement score of the replacement staff relative to the replaced staff is Wherein->For the work saturation coefficient, i is the future work category of the replaced staff, ai represents the comparison of the number of works of the replaced staff and the replaced staff in the i work category, ai is 1 if the future work number of the replaced staff for the i work category is larger than that of the replaced staff, ai is the ratio of the future work number of the replaced staff for the i work category to the future work number of the replaced staff for the i work category if the future work number of the replaced staff for the i work category is smaller than that of the replaced staff, ai is 0 if the future work number of the replaced staff for the i work category is 0, bi judges the future work category of the replaced staff, bi is 1 if the future work category of the replaced staff contains i work category, bi is 0 if the future work category of the replaced staff does not contain i work category, and the replaced staff with the highest replacement score is selected to replace the replaced staff.
2. An apparatus for finding a surrogate employee based on artificial intelligence, the apparatus for performing a method of finding a surrogate employee based on artificial intelligence as recited in claim 1, comprising:
the acquisition module is used for: acquiring employee information and event sequences of a company, acquiring event interaction information and event interaction times among employees according to the event sequences, wherein the event sequences are all events processed in a period of time of the company, the event sequences are composed of a plurality of events, each event is composed of at least one working category, the working category records participation employees of the current working, working resources and working time, event interaction information and event interaction times among the employees are acquired according to the working categories recorded in the event sequences, participation employees of each working category are traversed, participation values of each employee participated in the current working category are set according to the participation employees of the working category, cooperation relations of the different employees participated in the current working category are acquired by utilizing products of participation values of different employees, event interaction information among the employees is acquired by summarizing all the cooperation relations in the event sequences, the participation employees of each working category is counted according to the participation times of the same working category in each employee, the working category of the event sequences is used as a row or a column of the working event, all the participation times among the employees are used as a column or a construction association matrix, interaction time is acquired according to the participation matrixes among the working categories, each employee is used as a node to be interacted with each employee to be interacted, and a node to be interacted with the node to be interacted, and a network node to be interacted is constructed, the interaction node is used as a node to be interacted and is constructed;
And (3) selecting a module: setting the length of an interactive link, traversing the personal relationship network of each employee according to the length of the interactive link to generate a personal relationship vector, traversing the personal relationship network according to the length of the interactive link based on a breadth-first principle to obtain a breadth relationship vector, traversing the personal relationship network according to the length of the interactive link based on a depth-first principle to obtain a depth relationship vector, merging the breadth relationship vector and the depth relationship vector to obtain a personal relationship vector, obtaining the personal relationship vector of a replaced employee, calculating the similarity between the personal relationship vector of the replaced employee and the personal relationship vector of other employees, and taking the employee corresponding to the personal relationship vector with the similarity larger than a set threshold as the replaced employee to obtain a replaced employee set;
and (3) a replacement module: predicting a future event sequence according to the event sequence by using a pre-trained event prediction model, acquiring the working type of each employee, the working times of each working type according to the future event sequence, distributing weights to different participated employees in each working type based on the personal information of each employee and the event sequence, acquiring the working saturation coefficient of each employee, acquiring the longest-time working type, the shortest-time working type and the average working time consumption of each employee in a certain time to calculate the working saturation coefficient, wherein the average working time consumption is the average time consumption of the employee to complete one working type, calculating the replacement score of each replacement employee relative to the replaced employee according to the future working type of each employee, the working times of each working type and the working saturation coefficient, and the replacement score of the replacement employee relative to the replaced employee is Wherein->For the work saturation coefficient, i is the future work category of the replaced staff, ai represents the comparison of the number of works of the replaced staff and the replaced staff in the i work category, ai is 1 if the future work number of the replaced staff for the i work category is larger than that of the replaced staff, ai is the ratio of the future work number of the replaced staff for the i work category to the future work number of the replaced staff for the i work category if the future work number of the replaced staff for the i work category is smaller than that of the replaced staff, ai is 0 if the future work number of the replaced staff for the i work category is 0, bi judges the future work category of the replaced staff, bi is 1 if the future work category of the replaced staff contains i work category, bi is 0 if the future work category of the replaced staff does not contain i work category, and the replaced staff with the highest replacement score is selected to replace the replaced staff.
3. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform a method of finding alternative employees based on artificial intelligence as claimed in claim 1.
4. A readable storage medium, characterized in that the readable storage medium has stored therein a computer program comprising program code for controlling a process to execute a process comprising a method of finding an alternative employee based on artificial intelligence according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311059176.XA CN116805202B (en) | 2023-08-22 | 2023-08-22 | Method, device and application for searching for substitute staff based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311059176.XA CN116805202B (en) | 2023-08-22 | 2023-08-22 | Method, device and application for searching for substitute staff based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116805202A CN116805202A (en) | 2023-09-26 |
| CN116805202B true CN116805202B (en) | 2023-11-21 |
Family
ID=88079707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311059176.XA Active CN116805202B (en) | 2023-08-22 | 2023-08-22 | Method, device and application for searching for substitute staff based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116805202B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6334133B1 (en) * | 1998-12-21 | 2001-12-25 | Frontline Data, Inc. | System and method for performing substitute fulfillment |
| CN110555577A (en) * | 2018-05-31 | 2019-12-10 | 顺丰科技有限公司 | Scheduling method, scheduling system, device and storage medium storing computer program |
| CN110555572A (en) * | 2018-05-30 | 2019-12-10 | 顺丰科技有限公司 | Tiban recommendation system and method |
| CN112966917A (en) * | 2021-02-26 | 2021-06-15 | 重庆治略科技有限公司 | Intelligent process processing system, device and method based on relational network |
| CN113361816A (en) * | 2021-07-07 | 2021-09-07 | 北京容联七陌科技有限公司 | One set of customer service staff scheduling system |
| CN113407702A (en) * | 2021-07-09 | 2021-09-17 | 上海明略人工智能(集团)有限公司 | Method, system, computer and storage medium for quantifying employee cooperation strength |
| CN114091797A (en) * | 2021-03-05 | 2022-02-25 | 北京京东振世信息技术有限公司 | Intelligent dispatching method and device |
| CN115330217A (en) * | 2022-08-18 | 2022-11-11 | 上海墅字科技有限公司 | Workflow organization structure mining method and system based on employee interaction |
| CN116502869A (en) * | 2023-06-25 | 2023-07-28 | 海易科技(北京)有限公司 | Task allocation method, device, electronic equipment and computer readable medium |
| CN116561432A (en) * | 2023-06-27 | 2023-08-08 | 广州钛动科技股份有限公司 | Intelligent employee content data recommendation system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8639634B2 (en) * | 2010-07-28 | 2014-01-28 | Hartford Fire Insurance Company | System and method for administration of employee leave |
| US8869053B2 (en) * | 2012-07-06 | 2014-10-21 | Sap Ag | Organizer for managing employee time and attendance |
| US20140351155A1 (en) * | 2013-05-21 | 2014-11-27 | Rawlin International Inc. | Automated employee satisfaction predictor |
| US20210256626A1 (en) * | 2020-02-13 | 2021-08-19 | Vengatesan Kalimuthu | Social networking platform and method for managing the same |
-
2023
- 2023-08-22 CN CN202311059176.XA patent/CN116805202B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6334133B1 (en) * | 1998-12-21 | 2001-12-25 | Frontline Data, Inc. | System and method for performing substitute fulfillment |
| CN110555572A (en) * | 2018-05-30 | 2019-12-10 | 顺丰科技有限公司 | Tiban recommendation system and method |
| CN110555577A (en) * | 2018-05-31 | 2019-12-10 | 顺丰科技有限公司 | Scheduling method, scheduling system, device and storage medium storing computer program |
| CN112966917A (en) * | 2021-02-26 | 2021-06-15 | 重庆治略科技有限公司 | Intelligent process processing system, device and method based on relational network |
| CN114091797A (en) * | 2021-03-05 | 2022-02-25 | 北京京东振世信息技术有限公司 | Intelligent dispatching method and device |
| CN113361816A (en) * | 2021-07-07 | 2021-09-07 | 北京容联七陌科技有限公司 | One set of customer service staff scheduling system |
| CN113407702A (en) * | 2021-07-09 | 2021-09-17 | 上海明略人工智能(集团)有限公司 | Method, system, computer and storage medium for quantifying employee cooperation strength |
| CN115330217A (en) * | 2022-08-18 | 2022-11-11 | 上海墅字科技有限公司 | Workflow organization structure mining method and system based on employee interaction |
| CN116502869A (en) * | 2023-06-25 | 2023-07-28 | 海易科技(北京)有限公司 | Task allocation method, device, electronic equipment and computer readable medium |
| CN116561432A (en) * | 2023-06-27 | 2023-08-08 | 广州钛动科技股份有限公司 | Intelligent employee content data recommendation system |
Non-Patent Citations (2)
| Title |
|---|
| 金融企业员工考核系统的设计;王代潮;中国金融电脑(第06期);全文 * |
| 高速公路人力资源成本管理分析;李瑾;;中外企业家(第35期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116805202A (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11514369B2 (en) | Systems and methods for machine learning model interpretation | |
| Rahman et al. | Discretization of continuous attributes through low frequency numerical values and attribute interdependency | |
| US20210117839A1 (en) | Proactively predicting transaction dates based on sparse transaction data | |
| WO2024087512A1 (en) | Graph neural network compression method and apparatus, and electronic device and storage medium | |
| US20240177090A1 (en) | Predictive modeling method and system for dynamically quantifying employee growth opportunity | |
| CN112232833A (en) | Lost member customer group data prediction method, model training method and model training device | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| US20200050982A1 (en) | Method and System for Predictive Modeling for Dynamically Scheduling Resource Allocation | |
| Tounsi et al. | CSMAS: Improving multi-agent credit scoring system by integrating big data and the new generation of gradient boosting algorithms | |
| CN112381653A (en) | Mining and recommending method, device, equipment and storage medium for potential investment enterprises | |
| Voynarenko et al. | Applying fuzzy logic to modeling economic emergence | |
| Shannaq et al. | Management information system for predicting quantity martials | |
| CN116805202B (en) | Method, device and application for searching for substitute staff based on artificial intelligence | |
| CN115238583B (en) | Business process remaining time prediction method and system supporting incremental log | |
| US20200380446A1 (en) | Artificial Intelligence Based Job Wages Benchmarks | |
| CN116188174A (en) | Insurance fraud detection method and system based on modularity and mutual information | |
| CN114841664A (en) | Method and device for determining multitasking sequence | |
| Ivanov et al. | Fuzzy modelling of big data of HR in the conditions of industry 4.0 | |
| CN114549233A (en) | Floating population prediction method based on combination of LGB algorithm and ARIMA algorithm | |
| Liu et al. | A learning-based adjustment model with genetic algorithm of function point estimation | |
| CN114154696A (en) | Method, system, computer device and storage medium for predicting fund flow | |
| Panda et al. | Machine learning using exploratory analysis to predict taxi fare | |
| Bulusu et al. | Near future stock market forecasting based on chaos theory, sentiment analysis, and quantum computing | |
| Fair et al. | Endogenous labour flow networks | |
| Ozakca et al. | Artificial Intelligence Based Employee Attrition Analysis and Prediction |
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 |