Part-time worker matching degree prediction system and method
By designing a part-time staff matching prediction system, using hierarchical analysis method and fuzzy evaluation matrix to calculate the matching degree, the problem that the existing system cannot predict the matching degree between part-time staff and tasks is solved, and the efficiency and success rate of part-time work are improved.
Patent Information
- Application Number
- CN202410980825.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
AI Technical Summary
The existing part-time job matching system cannot effectively predict the matching degree between part-time staff and tasks, resulting in poor fit between the two parties.
A part-time staff matching degree prediction system was designed. By collecting part-time task information and existing information of part-time staff, they obtained hidden information, and used hierarchical analysis method and fuzzy evaluation matrix to calculate the matching degree, perform the first and second screening, and generate Sort the list to display matching results.
It improves the matching degree between part-time personnel and tasks, increases the fit between the two parties, and improves the efficiency and success rate of part-time work.
Smart Images

Figure CN118941144A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing, and in particular to a part-time employee matching prediction system and method based on part-time employee information data and part-time task data. Background Art
[0002] With the development of society, part-time jobs are becoming more and more common in social life. Ordinary workers or students usually choose one or more part-time jobs after work and study to make full use of their spare time, increase their income, increase their work experience and enrich their life experience.
[0003] The existing part-time job search solution usually inputs the needs of the part-time workers to find related part-time jobs on a website or APP, and then compares the needs of the part-time workers with the tasks that have been published to obtain a related task list; although the above-mentioned character list can be arranged according to time, location, salary, etc.; however, the existing method of comparing the needs of the part-time workers with the tasks that have been published cannot predict the matching degree between the part-time workers and the tasks, resulting in a poor fit between the two parties.
[0004] Based on this, a part-time staff matching prediction system based on part-time staff information data and part-time task data needs to be developed urgently. Summary of the invention
[0005] The present application provides a part-time employee matching prediction system and method, which can solve at least one technical problem in the prior art.
[0006] Specifically, the technical solution is as follows:
[0007] A part-time staff matching prediction system, comprising:
[0008] The collection module is used to collect part-time task information and existing information of personnel to be part-time employees;
[0009] An information module, used for obtaining hidden information of the personnel to be employed as part-time employees by using the existing information of the personnel to be employed as part-time employees;
[0010] A processing module, which performs data interaction with the acquisition module and the information module, and is used to obtain the status information of the person to be employed as a part-time employee according to the existing information of the person to be employed as a part-time employee and the part-time task information;
[0011] A prediction module, which interacts with the processing module for data, is used to perform a primary screening of part-time employees according to the status information and hidden information to obtain a candidate set, and to perform a secondary screening according to the historical positive ratings of any candidate in the candidate set to obtain a matching degree prediction value of the candidate;
[0012] An output module, which interacts with the prediction module for data, and is used to sort any candidate in the candidate set according to the matching degree prediction value to form a sorted list;
[0013] The display module performs data interaction with the output module and is used to display the prediction results matching the part-time task information according to the sorted list.
[0014] The prediction module comprises:
[0015] A first prediction unit, connected to the processing module, is used to obtain the status information of the personnel to be employed part-time, and to perform a preliminary screening of the personnel to be employed part-time according to the rigid requirements in the part-time task information to obtain a preliminary candidate set;
[0016] A second prediction unit, connected to the first prediction unit, is used to screen the preliminary candidate set again according to the hidden information to obtain a candidate list;
[0017] The third prediction unit is connected to the second prediction unit and is used to perform a second screening using the historical favorable comment scores of any candidate in the candidate set according to the following method:
[0018] Obtaining a preset indicator in the information of the part-time employees to be recruited, and ensuring that the number of part-time employees in the candidate set is less than a preset value;
[0019] Determine the weight of any preset indicator by using the hierarchical analysis method to obtain the judgment matrix corresponding to the part-time employee;
[0020] The historical scoring data of the personnel to be employed as part-time employees are obtained, and a fuzzy evaluation matrix is constructed according to the historical scoring data to obtain the matching degree between the personnel to be employed as part-time employees and the part-time task information.
[0021] The acquisition of the hidden information includes:
[0022] Set comparison threshold;
[0023] Compare the historical scores in the existing information of the personnel to be employed part-time with the comparison threshold to obtain a low score set and a high score set for the personnel to be employed part-time;
[0024] Obtaining part-time job information corresponding to the low-score set, including one or more of part-time job, working hours, working location, and income;
[0025] Counting the number of any information element in the part-time job information to obtain at least one subjective hidden preference element of the staff to be employed;
[0026] The subjective hidden preference element is used as the hidden information.
[0027] The re-screening of the preliminary candidate set according to the hidden information comprises:
[0028] Obtaining the subjective hidden preference factor;
[0029] The subjective hidden preference factors of any part-time employee in the preliminary candidate set are compared with the hard requirements in the part-time task information, and the preliminary candidate set is screened again.
[0030] The step of ensuring that the number of part-time employees in the candidate set is less than a preset value includes:
[0031] Obtaining the current number of elements in the candidate set, and comparing the current number with a preset value;
[0032] Classifying the candidate set according to the number of part-time jobs and average historical scores of the candidates to be processed, to obtain a set to be processed;
[0033] The to-be-processed set is subjected to the second screening to obtain the matching degree between the to-be-part-time personnel and the part-time task information.
[0034] The acquiring, according to the information of the person to be employed as a part-time employee and the information of the part-time task, the status information of the person to be employed as a part-time employee comprises:
[0035] Obtaining login information of any part-time employee in the information of the part-time employees to be employed;
[0036] Acquire the identity information and position information of the person to be a part-time employee according to the login information;
[0037] According to the rigid requirements in the part-time task information, any of the personnel to be part-time employees are compared to obtain status information of the personnel to be part-time employees matching the part-time task information;
[0038] The identity information of the person to be employed part-time includes: one or more of age, gender, skills, and work location;
[0039] The hard requirements in the part-time task information include: one or more of age requirements, gender requirements, skill requirements, and work location requirements.
[0040] The step of comparing any of the personnel to be employed as part-time employees according to the rigid requirements in the part-time task information to obtain status information of the personnel to be employed as part-time employees matching the part-time task information includes:
[0041] Extracting the information of the logged-in part-time personnel to obtain login information, setting a label for any of the part-time personnel to distinguish the working status, the label including: a signed working status label or an unsigned working status label;
[0042] Extract the working time of any one of the part-time employees in the signed work status tag to obtain the first working time;
[0043] Extracting the time requirement in the part-time task information, removing the part-time employees whose working time conflicts with the time requirement, and obtaining a first preparation list;
[0044] Acquire the identity information of any one of the part-time employees in the first preparation list according to the login information;
[0045] Extracting the rigid requirements in the part-time task information, removing the part-time personnel whose identity information does not meet the rigid requirements, and obtaining a second preparation list;
[0046] Setting the corresponding part-time employee in the second preparation list to a prepared state, so that the part-time employee matches the part-time task information; and / or,
[0047] The part-time worker with the unsigned work status label is set to a ready state, so that the part-time worker is matched with the part-time task information; and,
[0048] For the part-time personnel who have not logged in, the preset information is set as the identity, and the unsigned work status label is set.
[0049] Grouping the part-time employees who have signed work status tags to obtain a group to be processed;
[0050] Extracting task publisher information from the part-time task information;
[0051] The task publisher information is compared with any of the part-time employees in the to-be-processed group, and the part-time employee whose work location is consistent with the task publisher information is set to a prepared state, so that the part-time employee is matched with the part-time task information.
[0052] The part-time employee matching prediction system further includes: an input module;
[0053] The input module is connected to the acquisition module and is used to input search instructions;
[0054] The processing module is connected to the acquisition module, and is used to obtain the status information of the person to be a part-time employee according to the search instruction, obtain the tasks matching the person to be a part-time employee through the prediction module, and display the tasks matching the person to be a part-time employee in sequence through the display module according to the degree of matching;
[0055] The search instructions include: a name search instruction for a person who is to take a part-time job or a task search instruction that matches any person who is to take a part-time job.
[0056] A part-time employee matching degree prediction method based on the part-time employee matching degree prediction system as described above comprises:
[0057] Collect part-time task information and existing information of personnel to be part-time employees;
[0058] Using the existing information of the part-time employees to obtain the hidden information of the part-time employees;
[0059] Acquiring status information of the person to be employed as a part-time employee according to the existing information of the person to be employed as a part-time employee and the part-time task information;
[0060] Performing a primary screening of the part-time employees according to the status information and the hidden information to obtain a candidate set, and performing a secondary screening according to the historical positive rating score of any candidate in the candidate set to obtain a matching degree prediction value of the candidate;
[0061] Any candidate in the candidate set is sorted according to the predicted matching value to form a sorted list; and the predicted result matching the part-time task information is displayed according to the sorted list.
[0062] This application has at least the following beneficial effects:
[0063] The part-time employee matching prediction system described in the present application collects part-time task information and existing information of the part-time employee through the collection module; obtains the hidden information of the part-time employee through the information module using the existing information of the part-time employee; and obtains the status information of the part-time employee according to the existing information of the part-time employee and the part-time task information through the processing module; performs an initial screening of the part-time employee according to the status information and hidden information through the prediction module, and performs a second screening according to the historical positive score of any candidate in the candidate set to obtain the matching prediction value of the candidate; uses the output module to sort any candidate in the candidate set according to the matching prediction value to form a sorted list; and finally, displays the prediction result matching the part-time task information through the display module according to the sorted list. After obtaining the data of the part-time employee information and the part-time task information, the present application finally obtains the matching prediction value of the candidate and the task after two screenings, which is convenient for the mutual selection of the part-time employee and the task issuing enterprise, increases the fit between the two parties, and improves the efficiency and success rate of part-time work. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0065] Figure 1 This is a structural diagram of the part-time employee matching prediction system described in this application;
[0066] Figure 2 A flowchart for ensuring that the number of part-time employees in the candidate set is less than a preset value in the part-time employee matching prediction system of the present application;
[0067] Figure 3 A flowchart of obtaining the status information of the candidate part-time employee in the part-time employee matching prediction system of the present application;
[0068] Figure 4 A flowchart of obtaining the status information of the matching between the waiting part-time employee and the part-time task information in the part-time employee matching prediction system of the present application;
[0069] Figure 5 A flowchart of the method for predicting the matching degree of part-time employees described in this application;
[0070] exist Figure 1-5 middle:
[0071] 100. Acquisition module; 200. Processing module; 300. Prediction module; 400. Output module; 500. Display module; 600. Input module; 700. Information module; 301. First prediction unit; 302. Second prediction unit; 303. Third prediction unit. DETAILED DESCRIPTION
[0072] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.
[0073] In order to explain the present application in detail, the following embodiments are provided, and the technical solution of the present application will be explained in detail in conjunction with the accompanying drawings. Specific embodiment 1:
[0075] This application provides an embodiment:
[0076] like Figure 1A part-time employee matching prediction system includes: a collection module 100, a processing module 200, a prediction module 300, an output module 400, a display module 500, an input module 600 and an information module 700; wherein the collection module 100 is used to collect part-time task information and existing information of the part-time employee; the information module 700 is used to obtain the hidden information of the part-time employee by using the existing information of the part-time employee; the processing module 200 interacts with the collection module 100 and the information module 700 for data acquisition, and is used to obtain the status information of the part-time employee according to the existing information of the part-time employee and the part-time task information; the prediction module 300 interacts with the processing module 200 for primary screening of the part-time employee according to the status information and the hidden information, and obtains a candidate set, and performs a second screening according to the historical praise score of any candidate in the candidate set, and obtains the matching prediction value of the candidate; the output module 400 interacts with the prediction module 300 for data acquisition, and is used to obtain the matching prediction value of the candidate according to the matching prediction The display module 500 interacts with the output module 400 for data display of the prediction results matching the part-time task information according to the sorted list; the input module 600 is connected to the acquisition module 100 for inputting search instructions; the processing module 200 is connected to the acquisition module 100 for obtaining the status information of the part-time employee according to the search instructions, obtaining the tasks matching the part-time employee through the prediction module 300, and displaying the tasks matching the part-time employee in sequence through the display module 500 according to the degree of matching; the search instructions include: a search instruction for the name of the part-time employee or a search instruction for tasks matching any part-time employee; specifically, if the name of the part-time employee has obtained a job from the task publisher after being queried, at this time, all tasks subsequently issued by the task publisher are added to the sorted list, sorted by time, and no matching prediction is made, and are displayed first, so that the part-time employee can obtain the tasks issued by the task publisher first. The input module 600 can be any existing information input tool such as voice input, keyboard, mouse, etc.; the display module 500 can be any display, including but not limited to a mobile phone display or a PC display.
[0077] Specifically, the prediction module 300 includes: a first prediction unit 301, a second prediction unit 302, and a third prediction unit 303; wherein the first prediction unit 301 is connected to the processing module 200, and is used to obtain the status information of the part-time personnel to be employed, and to perform a preliminary screening of the part-time personnel to be employed according to the hard requirements in the part-time task information to obtain a preliminary candidate set; the second prediction unit 302 is connected to the first prediction unit 301, and is used to screen the preliminary candidate set again according to the hidden information to obtain a candidate list; the third prediction unit 303 is connected to the first prediction unit 301, and is used to perform a second screening using the historical positive score of any candidate in the candidate set according to the following method: obtaining the preset indicators in the information of the part-time personnel to be employed, and ensuring that the number of part-time personnel in the candidate set is less than the preset value; using the hierarchical analysis method to determine the weight of any preset indicator, and obtain the judgment matrix corresponding to the part-time personnel to be employed; obtaining the historical scoring data of the part-time personnel to be employed, and constructing a fuzzy judgment matrix based on the historical scoring data to obtain the matching degree between the part-time personnel to be employed and the part-time task information.
[0078] The acquisition of the hidden information includes: setting a comparison threshold, which is a score threshold, set to 3.5 or other empirical values; using the historical score in the existing information of the part-time personnel to be compared with the comparison threshold to obtain a low score set and a high score set for the part-time personnel to be part-time; because the high score set represents that the work of the part-time personnel to be part-time has achieved good results, it is not considered; obtaining the part-time information corresponding to the low score set, including: one or several information elements of part-time work, working hours, work location, and income, preferably one information element; counting the number corresponding to any information element in the part-time information to obtain a subjective hidden preference element of the staff to be part-time; using the subjective hidden preference element as the hidden information; and then comparing the subjective hidden preference element of any part-time personnel to be part-time in the preliminary candidate set with the hard requirements in the part-time task information, and re-screening the preliminary candidate set. The existing information of the part-time personnel to be part-time in this article includes historical scores and the name, gender, address and other filled-in content information filled in by the part-time personnel to be part-time.
[0079] If part-time employee A has 10 historical evaluations with scores below 3.5, the situation is as shown in Table 1.
[0080] Table 1: Information elements of part-time employee A:
[0081]
[0082] According to the analysis of Table 1, part-time employee A is competent for both the night driving and food delivery jobs, but according to the number statistics, the part-time employee A is in a very bad state at night, resulting in a very low score; therefore, the information element is matched to the part-time job with working time at night. For the night work in the part-time task, although part-time employee A is competent, its hidden information can show that part-time employee A is not suitable for night work, so it is screened out, and the candidate list is obtained by analogy.
[0083] In the specific work, due to the gradual increase of the system, the number of users is also gradually increasing; among the above users, there are a large number of task publishers and part-time workers; and by ensuring that the number of part-time workers in the candidate set is less than the preset value, the specific steps include: Figure 2 , obtain the current number of elements in the candidate set, and compare the current number with a preset value; classify the candidate set according to the number of part-time jobs and the average historical score of the person to be part-time, to obtain a set to be processed; perform the second screening on the set to be processed, to obtain the matching degree between the person to be part-time and the part-time task information.
[0084] For example, the existing number of elements in the candidate set is greater than the preset value of 2000; the product of the historical average score of the person to be part-time and the number of part-time jobs is divided by the sum of the historical average score of the person to be part-time and the number of part-time jobs, and the result is used as the classification standard; moreover, by using the above-mentioned technical means, the score of the person to be part-time with more part-time jobs can be made greater than the person to be part-time with fewer part-time jobs. Under the same conditions, the person to be part-time with more part-time jobs and higher scores is more protected; for example, the historical average score of a person to be part-time is 4.2, and the number of times he has worked is 1000, and his score is: (1000×4.2) / 1000+4.2=4.18; the historical average score of another person to be part-time is 4.2, but the number of times he has worked is 100, and his score is: (100×4.2) / 100+4.2=4.03; at the same time, according to the preset value of 2000, the candidate set is reduced so that the elements in the candidate set are less than the preset value, thereby reducing the amount of calculation and improving the speed.
[0085] like Figure 3, the status information of the personnel to be part-time is obtained according to the information of the personnel to be part-time and the part-time task information, including: obtaining the login information of any part-time personnel to be part-time in the information of the personnel to be part-time; obtaining the identity information and position information of the personnel to be part-time according to the login information; comparing any of the personnel to be part-time according to the hard requirements in the part-time task information, and obtaining the status information of the personnel to be part-time that matches the part-time task information; the identity information of the personnel to be part-time includes: age, gender, skills, and work location; the hard requirements in the part-time task information include: age requirements, gender requirements, skill requirements, and work location requirements.
[0086] like Figure 4 , the step of comparing any of the waiting part-time employees according to the hard requirements in the part-time task information to obtain status information of the waiting part-time employees matching the part-time task information includes: extracting information of the logged-in waiting part-time employees to obtain login information, setting a label for any of the waiting part-time employees to distinguish the working status, wherein the label includes: a signed working status label or an unsigned working status label; extracting the working time of any of the waiting part-time employees in the signed working status label to obtain the first working time; extracting the time requirements in the part-time task information, removing the waiting part-time employees whose working time conflicts with the time requirements, and obtaining the first preparation list; obtaining the identity information of any of the waiting part-time employees in the first preparation list according to the login information; extracting the hard requirements in the part-time task information, removing the waiting part-time employees whose identity information does not meet the hard requirements, and obtaining the second preparation list; setting the corresponding waiting part-time employees in the second preparation list to the prepared state, so that the waiting part-time employees match the part-time task information; setting the waiting part-time employees with the unsigned working status label to the prepared state, so that the waiting part-time employees match the part-time task information. However, for the part-time employees who have not logged in, the system described in this embodiment will assign preset information as identity information, such as the location is a certain city, the gender is male, the age is 30 years old, and set the unsigned work status label.
[0087] The part-time workers to be processed who are set with signed work status tags are grouped to obtain a group to be processed; the task publisher information in the part-time task information is extracted; the task publisher information is compared with any of the part-time workers to be processed in the group to be processed, and the part-time workers to be processed whose work location is consistent with the task publisher information are set to a prepared state, so that the part-time workers to be processed are matched with the part-time task information.
[0088] The matching degree calculation method described in this embodiment is as follows: obtaining the preset indicators in the information of the part-time personnel to be employed, and ensuring that the number of part-time personnel in the candidate set is less than the preset value; using the hierarchical analysis method to determine the weight of any preset indicator, and obtaining the judgment matrix corresponding to the part-time personnel to be employed; obtaining the historical scoring data of the part-time personnel to be employed, and constructing a fuzzy judgment matrix based on the historical scoring data to obtain the matching degree between the part-time personnel to be employed and the part-time task information. The specific steps are as follows:
[0089] Step 1: Construct preset indicators;
[0090] Table 2: Constructing a preset indicator table based on task information:
[0091]
[0092]
[0093] Step 2: Use the analytic hierarchy process to determine the weights of all preset indicators and obtain the judgment matrix corresponding to the part-time employees; scale each factor in Table 2 from 1 to 9 according to the degree of reuse, and construct the judgment matrix based on experience;
[0094] 1. According to the contents of Table 2, combined with historical scores, the following judgment matrix is constructed:
[0095]
[0096] The above judgment matrix is checked for consistency. The weight of any preset indicator is obtained by calculating the eigenvector of the judgment matrix. Then the eigenvector method is used to solve it and perform a consistency check:
[0097] CI=λ max -n / (n-1); where λ max is the maximum eigenvalue; n represents the dimension of the judgment matrix; then, by finding the value of the corresponding average random consistency index RI, the random consistency ratio is obtained:
[0098] CR = CI / RI;
[0099] Table 3: Random consistency indicators:
[0100] Matrix order 1 2 3 4 RI 0 0 0.55 0.87
[0101] According to the calculation method described above, the weights of each indicator are obtained, as shown in Table 4:
[0102] Table 4: Weight table:
[0103]
[0104]
[0105] Step 3: Obtain the historical scoring data of the person to be employed as a part-time employee, construct a fuzzy evaluation matrix based on the historical scoring data, and obtain the matching degree between the person to be employed as a part-time employee and the part-time task information:
[0106] Read the historical ratings of the part-time employee and set 5 levels, divided into {excellent, good, average, poor, very poor}, and the corresponding quantitative set after assignment is M = (0.9, 0.7, 0.5, 0.3, 0.1), then the corresponding evaluation distribution of the part-time employee in Table 2 is:
[0107] Table 5: Evaluation table after assignment;
[0108]
[0109]
[0110] According to the historical scores after the assignment, the historical average score of the part-time employee is obtained as: 0.61; according to the content of Table 5, normalization is performed to obtain the fuzzy judgment matrix of the brother indicator comment level;
[0111]
[0112] Using fuzzy matrix synthesis operation: S = W·R; vector S represents the evaluation result; W is the membership matrix; the matching degree T between the part-time personnel and the part-time task information is obtained by weighted average method;
[0113] Among them, x k is the historical score of the kth indicator; f k is the weight of the kth indicator; k is 10; i=1…k; through the above formula, the matching degree T between the part-time employee and the part-time task information is 0.75.
[0114] By analogy, the matching degree between the part-time employees and the part-time task information is obtained through the process described in this embodiment, and the results are arranged from high to low to form a sorted list; the predicted results matching the part-time task information are output according to the sorted list, so as to facilitate the mutual selection between the part-time employees and the task issuing enterprises, increase the compatibility between the two parties, and improve the efficiency and success rate of part-time work. Specific embodiment 2:
[0116] This application also provides an embodiment:
[0117] like Figure 5A part-time employee matching prediction method based on the part-time employee matching prediction system as described in specific embodiment 1, comprising: collecting part-time task information and existing information of employees to be assigned to the part-time job; using the existing information of employees to be assigned to the part-time job to obtain hidden information of the employees to be assigned to the part-time job; obtaining status information of the employees to be assigned to the part-time job based on the existing information of the employees to be assigned to the part-time job and the part-time task information; performing an initial screening of the employees to be assigned to the part-time job based on the status information and the hidden information to obtain a candidate set, and performing a second screening based on the historical praise scores of any candidate in the candidate set to obtain a matching prediction value of the candidate; sorting any candidate in the candidate set based on the matching prediction value to form a sorted list; and displaying a prediction result matching the part-time task information based on the sorted list. Specific embodiment 3:
[0119] This application also provides an embodiment:
[0120] An electronic device for predicting the matching degree of a part-time employee, comprising: a storage medium and a processing unit; wherein the storage medium is used to store a computer program; the processing unit exchanges data with the storage medium, and is used to execute the computer program through the processing unit when predicting the matching degree of a part-time employee, and perform the steps of the part-time employee matching degree prediction method as described in specific embodiment 2.
[0121] This application also provides an embodiment:
[0122] A computer-readable storage medium having a computer program stored therein; when the computer program is run, the steps of the part-time employee matching degree prediction method as described in specific embodiment 2 are executed.
[0123] In the present invention, a readable storage medium may be any tangible medium that contains or stores a program, as long as it can be recognized by an Android platform or a computer; the program may be used by or in combination with an instruction execution system, device, or device. In the present invention, a readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or device. The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0124] The present invention provides an embodiment, including a program product, which includes a program carried on an Android platform readable medium, the program including a program for executing Figure 5 The program code of the method shown in any of the flowcharts described in the present invention. The program can be downloaded and installed from the network. When the program is executed by the CPU, the functions defined in the system of the present invention are executed.
[0125] The above serial numbers of the present invention are only for description and do not represent the advantages or disadvantages of the implementation scenarios.
[0126] The above disclosures are only several specific implementation scenarios of the present invention, but the present invention is not limited thereto, and any changes that can be thought of by a person skilled in the art should fall within the protection scope of the present invention. The above serial numbers of the present invention are only for description and do not represent the advantages and disadvantages of the implementation scenarios.
Claims
1. A part-time employee matching prediction system, characterized in that: include: The collection module is used to collect part-time task information and existing information of personnel to be part-time employees; An information module, used for obtaining hidden information of the personnel to be employed as part-time employees by using the existing information of the personnel to be employed as part-time employees; A processing module, which performs data interaction with the acquisition module and the information module, and is used to obtain the status information of the person to be employed as a part-time employee according to the existing information of the person to be employed as a part-time employee and the part-time task information; A prediction module, which interacts with the processing module for data, is used to perform a primary screening of part-time employees according to the status information and hidden information to obtain a candidate set, and to perform a secondary screening according to the historical positive ratings of any candidate in the candidate set to obtain a matching degree prediction value of the candidate; An output module, which interacts with the prediction module for data, and is used to sort any candidate in the candidate set according to the matching degree prediction value to form a sorted list; A display module performs data interaction with the output module and is used to display prediction results matching the part-time task information according to the sorted list.
2. A part-time employee matching prediction system according to claim 1, characterized in that: The prediction module comprises: A first prediction unit, connected to the processing module, is used to obtain the status information of the personnel to be employed part-time, and to perform a preliminary screening of the personnel to be employed part-time according to the rigid requirements in the part-time task information to obtain a preliminary candidate set; A second prediction unit, connected to the first prediction unit, is used to screen the preliminary candidate set again according to the hidden information to obtain a candidate list; The third prediction unit is connected to the second prediction unit and is used to perform a second screening using the historical favorable comment scores of any candidate in the candidate set according to the following method: Obtaining a preset indicator in the information of the part-time employees to be recruited, and ensuring that the number of part-time employees in the candidate set is less than a preset value; Determine the weight of any preset indicator by using the hierarchical analysis method to obtain the judgment matrix corresponding to the part-time employee; The historical scoring data of the personnel to be employed as part-time employees are obtained, and a fuzzy evaluation matrix is constructed according to the historical scoring data to obtain the matching degree between the personnel to be employed as part-time employees and the part-time task information.
3. A part-time employee matching prediction system according to claim 1 or 2, characterized in that: The acquisition of the hidden information includes: Set comparison threshold; Compare the historical scores in the existing information of the personnel to be employed part-time with the comparison threshold to obtain a low score set and a high score set for the personnel to be employed part-time; Obtaining part-time job information corresponding to the low-score set, including one or more of part-time job, working hours, working location, and income; Counting the number of any information element in the part-time job information to obtain at least one subjective hidden preference element of the staff to be employed; The subjective hidden preference element is used as the hidden information.
4. A part-time employee matching prediction system according to claim 1 or 2, characterized in that: The re-screening of the preliminary candidate set according to the hidden information comprises: Obtaining the subjective hidden preference factor; The subjective hidden preference factors of any part-time employee in the preliminary candidate set are compared with the hard requirements in the part-time task information, and the preliminary candidate set is screened again.
5. A part-time employee matching prediction system according to claim 2, characterized in that: The step of ensuring that the number of part-time employees in the candidate set is less than a preset value includes: Obtaining the current number of elements in the candidate set, and comparing the current number with a preset value; Classifying the candidate set according to the number of part-time jobs and average historical scores of the personnel to be processed, to obtain a set to be processed; The to-be-processed set is subjected to the second screening to obtain the matching degree between the to-be-part-time personnel and the part-time task information.
6. A part-time employee matching prediction system according to claim 1, characterized in that: The acquiring, according to the information of the person to be employed as a part-time employee and the information of the part-time task, the status information of the person to be employed as a part-time employee comprises: Obtaining login information of any part-time employee in the information of the part-time employees to be hired; Acquire the identity information and position information of the person to be a part-time employee according to the login information; According to the rigid requirements in the part-time task information, any of the personnel to be part-time employees are compared to obtain status information of the personnel to be part-time employees matching the part-time task information; The identity information of the person to be employed part-time includes: one or more of age, gender, skills, and work location; The hard requirements in the part-time task information include: one or more of age requirements, gender requirements, skill requirements, and work location requirements.
7. A part-time employee matching prediction system according to claim 6, characterized in that: The step of comparing any of the personnel to be employed as part-time employees according to the rigid requirements in the part-time task information to obtain status information of the personnel to be employed as part-time employees matching the part-time task information includes: Extracting the information of the logged-in part-time personnel to obtain login information, setting a label for any of the part-time personnel to distinguish the working status, the label including: a signed working status label or an unsigned working status label; Extract the working time of any one of the part-time employees in the signed work status tag to obtain the first working time; Extracting the time requirement in the part-time task information, removing the part-time employees whose working time conflicts with the time requirement, and obtaining a first preparation list; Acquire the identity information of any one of the part-time employees in the first preparation list according to the login information; Extracting the rigid requirements in the part-time task information, removing the part-time personnel whose identity information does not meet the rigid requirements, and obtaining a second preparation list; Setting the corresponding part-time employee in the second preparation list to a prepared state, so that the part-time employee matches the part-time task information; and / or, The part-time worker with the unsigned work status label is set to a ready state, so that the part-time worker is matched with the part-time task information; and, For the part-time personnel who have not logged in, the preset information is set as the identity, and the unsigned work status label is set.
8. A part-time employee matching prediction system according to claim 7, characterized in that: Grouping the part-time employees who have signed work status tags to obtain a group to be processed; Extracting task publisher information from the part-time task information; The task publisher information is compared with any of the part-time employees in the to-be-processed group, and the part-time employee whose work location is consistent with the task publisher information is set to a prepared state, so that the part-time employee is matched with the part-time task information.
9. A part-time employee matching prediction system according to claim 1, characterized in that: Also includes: Input module; The input module is connected to the acquisition module and is used to input search instructions; The processing module is connected to the acquisition module, and is used to obtain the status information of the person to be a part-time employee according to the search instruction, obtain the tasks matching the person to be a part-time employee through the prediction module, and display the tasks matching the person to be a part-time employee in sequence through the display module according to the degree of matching; The search instructions include: a name search instruction for a person who is to take a part-time job or a task search instruction that matches any person who is to take a part-time job.
10. A part-time employee matching degree prediction method based on the part-time employee matching degree prediction system according to any one of claims 1 to 9, characterized in that: include: Collect part-time task information and existing information of personnel to be part-time employees; Using the existing information of the part-time employees to obtain the hidden information of the part-time employees; Acquiring status information of the person to be employed as a part-time employee according to the existing information of the person to be employed as a part-time employee and the part-time task information; Performing a primary screening of the part-time employees according to the status information and the hidden information to obtain a candidate set, and performing a secondary screening according to the historical positive rating score of any candidate in the candidate set to obtain a matching degree prediction value of the candidate; Sorting any candidate in the candidate set according to the predicted matching value to form a sorted list; Prediction results matching the part-time task information are displayed according to the sorted list.
Citation Information
Patent Citations
Mobile terminal-based part-time job recommendation method and system
CN106649390A
Mobile terminal-based job seeker and part time job matching method and system
CN106651281A
Intelligent job recommendation system and system thereof
CN110196943A
Personalized post recommendation method based on preference of user to post popularity
CN116610857A
