An intelligent task matching method and system

Abstract

The application discloses an intelligent task matching algorithm and system, loads a task for each flying insect, executes a flying insect walking algorithm, searches for position control, executes flying insect task loading and personnel matching, and the application can perform large batch multi-task calculation matching by loading different flying insects with tasks, performing collision monitoring on the flying insects, utilizing enemy-avoiding characteristics of the flying insect algorithm, intelligently and dynamically monitoring, improving calculation efficiency, and realizing multi-task intelligent calculation matching of task distribution to people in human resource management enterprises.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data application, and particularly relates to an intelligent task matching method and system. BACKGROUND

[0002] Public service is an important part of urban public service, and has a profound impact on the quality of life of citizens, so ensuring the quality of public service has become the focus of people's concern. After the completion of home decoration, new problems of installation or maintenance appear, and the public service platform needs to inquire the operation and maintenance personnel one by one to determine the target operation and maintenance personnel, which takes a lot of time, which may lead to the task cannot be processed in time, thereby reducing the efficiency of operation and maintenance work.

[0003] In the prior art, new task matching methods have also emerged, such as grid computing based on resource sharing and cloud computing for on-demand service. Traditional resource scheduling algorithms include first-come-first-served algorithm and polling algorithm. The first-come-first-served algorithm matches resources according to the order of network task arrival, and the task that arrives first is matched with suitable resources first. This kind of non-depriving scheduling algorithm is easy to implement but low in efficiency. The polling algorithm also causes problems such as task starvation and resource imbalance. SUMMARY

[0004] Based on the above problems, the present application is an intelligent task matching algorithm based on fly algorithm, which loads different flies for tasks, monitors the collision of flies, uses the nature of fly enemy avoidance, and performs intelligent dynamic monitoring. A large number of multi-task computing matching can be executed, the computing efficiency is improved, and the multi-task intelligent computing matching of human resource management enterprises to task allocation to people is realized.

[0005] The present application provides an intelligent task matching method, which comprises:

[0006] Step 101, initializing a fly population;

[0007] Step 102, loading a task for each fly;

[0008] Step 103, executing a fly walking algorithm to search for position control;

[0009] Step 104, executing the fly loading task and personnel matching;

[0010] Step 105, outputting and displaying the matching result.

[0011] Further, the fly walking algorithm is executed to search for position control, which specifically comprises:

[0012] A two-dimensional plane model is established with the historical satisfaction of personnel as the horizontal coordinate and the historical average salary as the vertical coordinate, and all personnel are loaded into the two-dimensional plane coordinate system with the historical satisfaction and historical average salary data, and an initial position C(Xi, Yi) is randomly assigned to each fly,

[0013] Wherein, the next position C(Xj+1, Yj+1) of the jth fly is calculated as follows: the X coordinate calculation method is Wherein is a fixed step direction vector

[0014] The LSSVM algorithm is used to calculate the y coordinate value of the jth fly, and the algorithm is as follows:

[0015]

[0016] Wherein, b is a budget parameter, is a fixed step direction vector, and the calculation method of P(Xi, Xi+1) is as follows:

[0017] P(Xi, Xi-1) = exp-((Xi-Xi-1) 2 / 2ε 2 ), wherein ε is a budget parameter.

[0018] After the calculation of the next position C(Xj+1, Yj+1) of the jth fly is completed, the position table of natural enemies is traversed to determine whether the position is a natural enemy position. If it is not a natural enemy position, the position is assigned to the fly, and the matching algorithm is executed. If the position is a natural enemy position, the position is abandoned, and a random function is executed to assign a new position to the fly;

[0019] When the fly realizes the matching of the loading task and the person in the position C(XL, YL), the position is marked as a simulated natural enemy position, and the detection T function is used to prevent the fly from colliding with the natural enemy position, thereby realizing the enemy-avoiding nature of the fly, which is specifically represented as:

[0020] Wherein X' is the natural enemy position C(XL, YL), is a fixed step direction vector.

[0021] Further, before executing the search position control, the budget parameter b and the budget parameter ε are obtained, which specifically includes:

[0022] Constructing fly state parameters (b, ε);

[0023] Establish a system test dataset, train the insect state (b, ε), initialize the insect state parameters, execute the insect walking algorithm, record the first time consumed by the algorithm, assign values ​​to the budget parameters b and ε using a random function, re-execute the insect walking algorithm, record the time consumed by the algorithm on the nth time, and select the algorithm with the smallest time consumed as the budget parameter of the insect state (b, ε).

[0024] Furthermore, the process of matching personnel with the insect loading task includes:

[0025] The task loaded by the flying insect is matched with the work of the personnel. If the matching is greater than the threshold, the flying insect task is assigned to the relative individual, the key-value pair of the person and the task organization is stored in the database, the flying insect resources are released, and the location is marked as the location of the natural enemy.

[0026] In addition, the present invention also provides an intelligent task matching system, the system comprising:

[0027] Initialization module 201 is used to initialize the flying insect population;

[0028] Task loading module 202 is used to load tasks for each flying insect;

[0029] The flying insect search module 203 is used to execute the flying insect walking algorithm and control the search position;

[0030] Task matching module 204 is used to match the flying insect loading task with personnel;

[0031] Display module 205 is used to output and display the matching results.

[0032] Furthermore, the insect search module 203 specifically performs the following:

[0033] A two-dimensional plane model is constructed using historical employee satisfaction data as the x-axis and historical average salary data as the y-axis. All employees are loaded into the two-dimensional coordinate system using their historical satisfaction and average salary data. An initial position C(Xi, Yi) is randomly assigned to each flying insect.

[0034] The next position C(Xj+1, Yj+1) of the j-th flying insect is calculated as follows: The X-coordinate is calculated as follows: in Fixed step size direction vector

[0035] The LSSVM algorithm is used to calculate the y-coordinate of the j-th flying insect. The algorithm is as follows:

[0036]

[0037] Where b is the budget parameter, For a fixed step-size direction vector, P(Xi,Xi+1) is calculated as follows:

[0038] P(Xi,Xi-1)=exp-((Xi-Xi-1) 2 / 2ε 2 ), where ε is the budget parameter.

[0039] After calculating the next position C(Xj+1, Yj+1) of the j-th flying insect, traverse the predator position table and determine whether the position is a predator position. If it is not a predator position, assign the position to the flying insect and execute the matching algorithm. If the position is a predator position, discard the position, execute the random function, and assign a new random position to the flying insect.

[0040] When a flying insect completes its loading task and matches itself with a human at position C(XL,YL), this position is marked as a simulated predator position. The T-function is then used to prevent the flying insect from colliding with the predator's position, thus realizing the insect's natural instinct to avoid predators. Specifically:

[0041] Where X′ represents the position of the natural enemy C(XL,YL), It is a direction vector with a fixed step size.

[0042] Furthermore, before executing search location control, the budget parameter b and budget parameter ε are obtained, specifically including:

[0043] Construct the state parameters (b, ε) of the flying insect;

[0044] Establish a system test dataset, train the insect state (b, ε), initialize the insect state parameters, execute the insect walking algorithm, record the first time consumed by the algorithm, assign values ​​to the budget parameters b and ε using a random function, re-execute the insect walking algorithm, record the time consumed by the algorithm on the nth time, and select the algorithm with the smallest time consumed as the budget parameter of the insect state (b, ε).

[0045] Furthermore, the task matching module 204 performs the following:

[0046] The task loaded by the flying insect is matched with the work of the personnel. If the matching is greater than the threshold, the flying insect task is assigned to the relative individual, the key-value pair of the person and the task organization is stored in the database, the flying insect resources are released, and the location is marked as the location of the natural enemy.

[0047] In addition, the present invention provides a computer-readable storage medium on which a computer program is stored, the computer program being executed by a processor, such as an intelligent task matching method.

[0048] Furthermore, the present invention also provides an electronic device, comprising: a processor, a memory, and a display screen; wherein the memory is used to store a computer program; and the processor is used to load and execute the computer program to enable the electronic device to perform a method such as intelligent task matching.

[0049] This invention proposes an intelligent task matching algorithm and system based on the flying insect algorithm. Each flying insect is loaded with a task, and the flying insect roaming algorithm is executed to search for and control the location. The system then matches the loaded task with the assigned person. By loading tasks onto different flying insects and performing collision monitoring, this invention utilizes the insect algorithm's enemy avoidance characteristics for intelligent dynamic monitoring. It can perform multi-task calculation and matching on a large scale, improving computational efficiency and enabling human resource management companies to intelligently calculate and match tasks to individuals. Attached Figure Description

[0050] Figure 1 This is a flowchart of the intelligent task matching method of the present invention;

[0051] Figure 2 This is a block diagram of the intelligent task matching system of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] This invention proposes a job matching algorithm and system based on the flying insect algorithm, which performs intelligent dynamic monitoring, can perform multi-task calculation and matching in large batches, improves calculation efficiency, and realizes intelligent multi-task calculation and matching for human resource management enterprises to assign tasks to people.

[0054] As attached Figure 1 As shown, this invention proposes an intelligent task matching method.

[0055] Step 101: Initialize the flying insect population;

[0056] The present invention includes an initialization module for initializing a flying insect population F(F1,F2....Fn), the flying insect population consists of n flying insects, where n is a natural number, and each flying insect is allocated independent computing resources and data storage resources.

[0057] Step 102: Load tasks for each flying insect;

[0058] The insect task loading module is used to load database tasks into each specific insect. These tasks are structured data stored in the database, using a primary key as a unique identifier.

[0059] Step 103: Execute the flying insect walking algorithm to search for position control;

[0060] The insect-walking algorithm module controls the insect's search position. A two-dimensional plane model is constructed using historical employee satisfaction data as the x-axis and historical average salary data as the y-axis. All employees are loaded into this two-dimensional coordinate system using their historical satisfaction and average salary data. Position control refers to searching within this coordinate system. An initial position C(Xi, Yi) is randomly assigned to each insect. Before the search, the insect's state parameters are initialized (X=1, Y=1), or initial values ​​are generated using a random algorithm.

[0061] The next position C(Xj+1, Yj+1) of the j-th flying insect is calculated as follows: The X coordinate is calculated as follows: in Fixed step size direction vector

[0062] The LSSVM algorithm is used to calculate the y-coordinate of the j-th flying insect. The algorithm is as follows:

[0063]

[0064] Where b is the budget parameter, For a fixed step-size direction vector, P(Xi,Xi+1) is calculated as follows:

[0065] P(Xi,Xi-1)=exp-((Xi-Xi-1) 2 / 2ε 2 ), where ε is the budget parameter.

[0066] Construct the state parameters (b, ε) of the flying insect using budget parameters b and ε.

[0067] Establish a system test dataset for training the insect state (b, ε). Initialize the insect state parameters to (1, 1), execute the insect walking algorithm, and record the algorithm's time T1. Use a random function to assign values ​​to the budget parameters b and ε, re-execute the insect walking algorithm, and record the algorithm's time Tn. Select the algorithm with the shortest time as the budget parameter for the insect state (b, ε).

[0068] After calculating the next position C(Xj+1, Yj+1) of the j-th flying insect, traverse the predator position table and determine whether the position is a predator position. If it is not a predator position, assign the position to the flying insect and execute the matching algorithm. If the position is a predator position, discard the position, execute the random function, and assign a new random position to the flying insect.

[0069] When a flying insect completes its loading task and matches with a human at position C(XL,YL) (matching method as in step 104), this position is marked as a simulated predator position. By detecting the T function, collisions between the flying insect and the predator position are prevented, thus realizing the insect's natural instinct to avoid predators. Specifically:

[0070] Where X′ represents the position of the natural enemy C(XL,YL), It is a direction vector with a fixed step size.

[0071] Step 104: Perform the insect loading task and match personnel;

[0072] The task matching module matches the tasks loaded by the flying insects with the work of personnel. It extracts the keyword string A of the task description loaded by the flying insects and the keyword string B of the personnel's work ability description. It compares strings A and B using string edit distance or cosine similarity algorithms. When the similarity is greater than a threshold, such as 60%, the flying insect task is assigned to the corresponding individual, the key-value pair of the person and task organization is stored in the database, the flying insect resources are released, and the location is marked as the predator location.

[0073] Step 105: Output the matching results.

[0074] The matching result output module outputs and displays the matching results, which include the tasks and the people who performed them.

[0075] Additionally, as attached Figure 2 As shown, this invention also proposes an intelligent task matching system:

[0076] Initialization module 201 is used to initialize the flying insect population;

[0077] The present invention includes an initialization module for initializing a flying insect population F(F1,F2....Fn), the flying insect population consists of n flying insects, where n is a natural number, and each flying insect is allocated independent computing resources and data storage resources.

[0078] Task loading module 202 is used to load tasks for each flying insect;

[0079] The insect task loading module is used to load database tasks into each specific insect. These tasks are structured data stored in the database, using a primary key as a unique identifier.

[0080] The flying insect search module 203 is used to execute the flying insect walking algorithm and control the search position;

[0081] The insect search module 203 specifically performs the following tasks:

[0082] A two-dimensional plane model is constructed using historical employee satisfaction data as the x-axis and historical average salary data as the y-axis. All employees are loaded into the two-dimensional coordinate system using their historical satisfaction and average salary data. An initial position C(Xi, Yi) is randomly assigned to each flying insect.

[0083] The next position C(Xj+1, Yj+1) of the j-th flying insect is calculated as follows: The X-coordinate is calculated as follows: in Fixed step size direction vector

[0084] The LSSVM algorithm is used to calculate the y-coordinate of the j-th flying insect. The algorithm is as follows:

[0085]

[0086] Where b is the budget parameter, For a fixed step-size direction vector, P(Xi,Xi+1) is calculated as follows:

[0087] P(Xi,Xi-1)=exp-((Xi-Xi-1) 2 / 2ε 2 ), where ε is the budget parameter.

[0088] Before executing search location control, the budget parameter b and budget parameter ε are also obtained, specifically including:

[0089] Construct the state parameters (b, ε) of the flying insect;

[0090] Establish a system test dataset, train the insect state (b, ε), initialize the insect state parameters, execute the insect walking algorithm, record the first time consumed by the algorithm, assign values ​​to the budget parameters b and ε using a random function, re-execute the insect walking algorithm, record the time consumed by the algorithm on the nth time, and select the algorithm with the smallest time consumed as the budget parameter of the insect state (b, ε).

[0091] After calculating the next position C(Xj+1, Yj+1) of the j-th flying insect, traverse the predator position table and determine whether the position is a predator position. If it is not a predator position, assign the position to the flying insect and execute the matching algorithm. If the position is a predator position, discard the position, execute the random function, and assign a new random position to the flying insect.

[0092] When a flying insect completes its loading task and matches itself with a human at position C(XL,YL), this position is marked as a simulated predator position. The T-function is then used to prevent the flying insect from colliding with the predator's position, thus realizing the insect's natural instinct to avoid predators. Specifically:

[0093] Where X′ represents the position of the natural enemy C(XL,YL), It is a direction vector with a fixed step size.

[0094] Task matching module 204 is used to match the flying insect loading task with personnel;

[0095] Task matching module 204 execution includes:

[0096] The task matching module matches the tasks loaded by the flying insects with the work of personnel. It extracts the keyword string A of the task description loaded by the flying insects and the keyword string B of the personnel's work ability description. It compares strings A and B using string edit distance or cosine similarity algorithms. When the similarity is greater than a threshold, such as 60%, the flying insect task is assigned to the corresponding individual, the key-value pair of the person and task organization is stored in the database, the flying insect resources are released, and the location is marked as the predator location.

[0097] Display module 205 is used to output and display the matching results.

[0098] The matching result output module outputs and displays the matching results, which include the tasks and the people who performed them.

[0099] In addition, the present invention provides a computer-readable storage medium on which a computer program is stored, the computer program being executed by a processor, such as an intelligent task matching method.

[0100] Furthermore, the present invention also provides an electronic device, comprising: a processor, a memory, and a display screen; wherein the memory is used to store a computer program; and the processor is used to load and execute the computer program to enable the electronic device to perform a method such as intelligent task matching.

[0101] This invention proposes an intelligent task matching algorithm and system based on the flying insect algorithm. Each flying insect is loaded with a task, and the flying insect roaming algorithm is executed to search for and control the location. The system then matches the loaded task with the assigned person. By loading tasks onto different flying insects and performing collision monitoring, this invention utilizes the insect algorithm's enemy avoidance characteristics for intelligent dynamic monitoring. It can perform multi-task calculation and matching on a large scale, improving computational efficiency and enabling human resource management companies to intelligently calculate and match tasks to individuals.

[0102] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. It should be noted that those skilled in the art can make several improvements and modifications to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. An intelligent task matching method, characterized in that, Step 101: Initialize the flying insect population; Step 102: Load tasks for each flying insect; Step 103: Execute the flying insect walking algorithm to search for position control; perform two-dimensional plane modeling with historical satisfaction as the horizontal axis and historical average salary as the vertical axis, and load all personnel with historical satisfaction and historical average salary data into the two-dimensional plane coordinate system. The position control is the search of the two-dimensional plane coordinate system. Each flying insect is randomly assigned an initial position C(Xi, Yi), where the next position C(Xj+1, Yj+1) of the j-th flying insect is calculated as follows: the X-coordinate is calculated as follows... ,in Fixed step size direction vector ; The LSSVM algorithm is used to calculate the y-coordinate of the j-th flying insect. The algorithm is as follows: Where b is the budget parameter, For a fixed step size direction vector, The calculation method is as follows: ,in For budget parameters; After calculating the next position C(Xj+1, Yj+1) of the j-th flying insect, traverse the predator position table and determine whether the position is a predator position. If it is not a predator position, assign the position to the flying insect. Step 104: Execute the insect-loaded task and personnel matching; the task loaded by the insect is matched with the personnel's work, extract the keyword string A of the task description loaded by the insect, extract the keyword string B of the personnel's work ability description, and compare strings A and B using string edit distance or cosine similarity algorithm. If the similarity is greater than the threshold, it is marked as a predator position; specifically, if the task loaded by the insect matches the personnel's work and the matching is greater than the threshold, the insect task is assigned to the relative individual, the key-value pair of the person and the task organization is stored in the database, the insect resources are released, and the position is marked as a predator position; Step 105: Output and display the matching results.

2. The method according to claim 1, characterized in that, The insect traversal algorithm is executed to search for and control the location. If the location is not a predator's location, the process of assigning that location to the insect includes: The matching algorithm is executed. If the position is the position of a natural enemy, the position is abandoned, and a random function is executed to assign a new random position to the flying insect. When a flying insect completes its loading task and matches itself with a human at position C(XL,YL), this position is marked as a simulated predator location. A detection function T is used to prevent the flying insect from colliding with the predator's location, thus realizing the insect's natural tendency to avoid predators. Specifically: ,in The position of the natural enemy is C (XL, YL). It is a direction vector with a fixed step size.

3. The method according to claim 2, characterized in that, Before executing search location control, budget parameter b and budget parameter are also performed. The acquisition of, specifically includes: Construct the state parameters of the flying insect (b, ); Establish a system test dataset and train the flying insect state (b, Initialize and assign values ​​to the insect state parameters, execute the insect walking algorithm, record the first time consumed by the algorithm, and use a random function to adjust the budget parameter b and the budget parameter. Assign values, re-execute the insect walking algorithm, record the time taken by the algorithm on the nth time, and select the state with the shortest time as the insect state (b, Budget parameters.

4. An intelligent task matching system, characterized in that, The system includes: Initialization module 201 is used to initialize the flying insect population; Task loading module 202 is used to load tasks for each flying insect; The flying insect search module 203 is used to execute the flying insect walking algorithm and search position control; it performs two-dimensional plane modeling with the historical satisfaction of personnel as the horizontal axis and the historical average wage as the vertical axis, and loads all personnel with historical satisfaction and historical average wage data into the two-dimensional plane coordinate system. The position control is the search of the two-dimensional plane coordinate system. Each flying insect is randomly assigned an initial position C(Xi, Yi), where the next position C(Xj+1, Yj+1) of the j-th flying insect is calculated as follows: the X-coordinate is calculated as follows... ,in Fixed step size direction vector ; The LSSVM algorithm is used to calculate the y-coordinate of the j-th flying insect. The algorithm is as follows: Where b is the budget parameter, For a fixed step size direction vector, The calculation method is as follows: ,in For budget parameters; After calculating the next position C(Xj+1, Yj+1) of the j-th flying insect, traverse the predator position table and determine whether the position is a predator position. If it is not a predator position, assign the position to the flying insect. The task matching module 204 is used to perform the matching of the task loaded by the flying insect with personnel; the task loaded by the flying insect is matched with the work of the personnel, the keyword string A of the task description loaded by the flying insect is extracted, and the keyword string B of the work ability description of the personnel is extracted. The string edit distance or cosine similarity algorithm is used to compare the strings A and B. If the similarity is greater than the threshold, it is marked as the position of the natural enemy; specifically, if the task loaded by the flying insect is matched with the work of the personnel and the matching is greater than the threshold, the flying insect task is assigned to the relative individual, the key-value pair of the person and the task organization is stored in the database, the flying insect resources are released, and the position is marked as the position of the natural enemy. Display module 205 is used to output and display the matching results.

5. The system according to claim 4, characterized in that, The flying insect search module 203, if not the location of a natural enemy, after assigning the location to the flying insect, also includes: The matching algorithm is executed. If the position is the position of a natural enemy, the position is abandoned, and a random function is executed to assign a new random position to the flying insect. When a flying insect completes its loading task and matches itself with a human at position C(XL,YL), this position is marked as a simulated predator location. A detection function T is used to prevent the flying insect from colliding with the predator's location, thus realizing the insect's natural tendency to avoid predators. Specifically: ,in The position of the natural enemy is C (XL, YL). It is a direction vector with a fixed step size.

6. The system according to claim 5, characterized in that, Before executing search location control, budget parameter b and budget parameter are also performed. The acquisition of, specifically includes: Construct the state parameters of the flying insect (b, ); Establish a system test dataset and train the flying insect state (b, Initialize and assign values ​​to the insect state parameters, execute the insect walking algorithm, record the first time consumed by the algorithm, and use a random function to adjust the budget parameter b and the budget parameter. Assign values, re-execute the insect walking algorithm, record the time taken by the algorithm on the nth time, and select the state with the shortest time as the insect state (b, Budget parameters.

7. The system according to claim 4, characterized in that, Task matching module 204 execution includes: The task loaded by the flying insect is matched with the work of the personnel. If the matching is greater than the threshold, the flying insect task is assigned to the relative individual, the key-value pair of the person and the task organization is stored in the database, the flying insect resources are released, and the location is marked as the location of the natural enemy.

8. A computer-readable storage medium storing a computer program that, when executed by a processor, performs the intelligent task matching method as claimed in any one of claims 1-3.

9. An electronic device, comprising: A processor, a memory, and a display screen; wherein the memory is used to store a computer program; and the processor is used to load and execute the computer program to cause the electronic device to perform the intelligent task matching method as described in any one of claims 1-3.

Images