CN114202309A - Method for determining matching parameters of user and enterprise, electronic device and program product - Google Patents
Method for determining matching parameters of user and enterprise, electronic device and program product Download PDFInfo
- Publication number
- CN114202309A CN114202309A CN202111506930.0A CN202111506930A CN114202309A CN 114202309 A CN114202309 A CN 114202309A CN 202111506930 A CN202111506930 A CN 202111506930A CN 114202309 A CN114202309 A CN 114202309A
- Authority
- CN
- China
- Prior art keywords
- user
- enterprise
- characteristic
- weight
- determining
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 230000007115 recruitment Effects 0.000 claims abstract description 106
- 238000011156 evaluation Methods 0.000 claims abstract description 69
- 230000006870 function Effects 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 17
- 239000000203 mixture Substances 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000002457 bidirectional effect Effects 0.000 abstract description 11
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000012512 characterization method Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model provides a method, electronic equipment and program product for determining matching parameters of users and enterprises, which relate to deep learning technology and comprise the following steps: acquiring resume data of a user and recruitment information of an enterprise; determining a first characteristic and a second characteristic according to the resume data and the recruitment information; determining a first parameter value according to a preset first weight and a first characteristic of a user to the enterprise; determining a second parameter value according to a preset second weight and a second characteristic of the enterprise to the user; the first parameter value and the second parameter value are used to determine a match between the user and the enterprise. According to the scheme provided by the disclosure, the characteristics can be extracted according to the resume data and the recruitment information, and the characteristics are processed by utilizing the preset first weight and the preset second weight, so that a bidirectional evaluation result between an enterprise and a user is obtained, and the enterprise is assisted in making a recruitment decision.
Description
Technical Field
The present disclosure relates to deep learning techniques in artificial intelligence technologies, and in particular, to a method for determining matching parameters between a user and an enterprise, an electronic device, and a program product.
Background
With the development of network technology, many services can be carried out on the network, for example, a recruitment enterprise can publish recruitment information in the network, and an application user can deliver resumes in the network. Therefore, a great amount of data of the recruitment enterprise and data of the application user are accumulated in the recruitment platform.
In order to improve recruitment efficiency, the data can be analyzed to assist recruitment enterprises in making decisions. At present, resumes of users who apply for and recruitment information of enterprises can be analyzed, so that a result of whether the users are matched with the enterprises is obtained.
However, the recruitment decision is made based on the matching result, which is still not accurate enough.
Disclosure of Invention
The invention provides a method for determining matching parameters of a user and an enterprise, electronic equipment and a program product, so that the enterprise can be more accurately assisted to make a recruitment decision.
According to a first aspect of the present disclosure, a method for determining matching parameters of a user and an enterprise is provided, including:
acquiring resume data of a user and recruitment information of an enterprise;
determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user;
determining a first parameter value according to a preset first weight of a user to the enterprise and the first characteristic; determining a second parameter value according to a preset second weight of the enterprise to the user and the second characteristic, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user;
the first parameter value and the second parameter value are used for determining a matching result between the user and the enterprise.
According to a second aspect of the present disclosure, there is provided a method for determining a weight between a user and an enterprise, comprising:
acquiring a training data set, a first weight of a user to be trained on an enterprise, and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of a user, recruitment information of an enterprise, a real admission record of the enterprise sending admission notification to the user, and a real receiving record of the user receiving the admission notification of the enterprise;
predicting a predicted admission record of the enterprise sending an admission notification to the user and a predicted acceptance record of the user accepting the admission notification of the enterprise according to the first weight, the second weight, the resume data and the recruitment information;
optimizing the first weight and the second weight according to the real admission record, the real acceptance record, the predicted admission record, and the predicted acceptance record;
and the optimized first weight and the optimized second weight which meet preset conditions are used for determining the matching degree between the user and the enterprise.
According to a third aspect of the present disclosure, there is provided an apparatus for determining matching parameters of a user and an enterprise, including:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring resume data of a user and recruitment information of an enterprise;
the characteristic determining unit is used for determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user;
the parameter determining unit is used for determining a first parameter value according to a preset first weight of the user to the enterprise and the first characteristic; determining a second parameter value according to a preset second weight of the enterprise to the user and the second characteristic, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user;
the first parameter value and the second parameter value are used for determining a matching result between the user and the enterprise.
According to a fourth aspect of the present disclosure, there is provided a weight determination apparatus between a user and an enterprise, including:
the training device comprises an acquisition unit, a calculation unit and a control unit, wherein the acquisition unit is used for acquiring a training data set, a first weight of a user to be trained on an enterprise and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of a user, recruitment information of an enterprise, a real admission record of the enterprise sending admission notification to the user, and a real receiving record of the user receiving the admission notification of the enterprise;
the forecasting unit is used for forecasting a forecasting admission record of the enterprise sending an admission notification to the user and a forecasting receiving record of the user receiving the admission notification of the enterprise according to the first weight, the second weight, the resume data and the recruitment information;
a training unit configured to optimize the first weight and the second weight according to the real admission record, the real acceptance record, the predicted admission record, and the predicted acceptance record;
and the optimized first weight and the optimized second weight which meet preset conditions are used for determining the matching degree between the user and the enterprise.
According to a fifth aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first or second aspect.
According to a sixth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the first or second aspect.
According to a seventh aspect of the present disclosure, there is provided a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of an electronic device can read the computer program, execution of the computer program by the at least one processor causing the electronic device to perform the method according to the first aspect or the second aspect.
The method for determining the matching parameters of the user and the enterprise, the electronic device and the program product provided by the disclosure comprise the following steps: acquiring resume data of a user and recruitment information of an enterprise; determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user; determining a first parameter value according to a preset first weight and a first characteristic of a user to the enterprise; determining a second parameter value according to a preset second weight and a second characteristic of the user by the enterprise, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the user by the enterprise; the first parameter value and the second parameter value are used to determine a match between the user and the enterprise. According to the scheme provided by the disclosure, the characteristics can be extracted according to the resume data and the recruitment information, and the characteristics are processed by utilizing the preset first weight and the preset second weight, so that a bidirectional evaluation result between an enterprise and a user is obtained, and the enterprise is assisted in making a recruitment decision.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flowchart illustrating a method for determining matching parameters between a user and an enterprise according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating a method for determining matching parameters between a user and an enterprise according to another exemplary embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating a method for determining weights between users and enterprises in accordance with an exemplary embodiment of the present disclosure;
FIG. 4 is a flowchart illustrating a method for determining weights between users and enterprises in accordance with another exemplary embodiment of the present disclosure;
FIG. 5 is a diagram illustrating a process for training weights according to an exemplary embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an apparatus for determining matching parameters between a user and an enterprise according to an exemplary embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an apparatus for determining matching parameters of a user and an enterprise according to another exemplary embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a weight determination apparatus between a user and an enterprise according to an exemplary embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of a weight determination apparatus between a user and an enterprise according to another exemplary embodiment of the present disclosure;
FIG. 10 is a block diagram of an electronic device used to implement methods of embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In order to assist the enterprise in recruiting talents, the resume of the talents can be matched with the post requirements of the enterprise, so that personnel in personnel departments of the enterprise can determine talents with proper posts based on the matching results.
Currently, methods for assisting enterprises in making recruitment decisions include making decisions based on matching algorithms. In this scheme, a technology based on natural language processing is required to match the talent resume with the post requirements, and a decision is made based on the matching situation.
However, the matching result determined in this scheme is only to measure the "matching degree" between the talents and the post, and the will of the talents is largely ignored, so that the decision made based on the matching result is not accurate enough, resulting in low recruitment efficiency.
In order to solve the technical problem, according to the scheme provided by the disclosure, the matching degree of the user to the enterprise and the matching degree of the enterprise to the user are determined according to the resume data of the user and the recruitment information of the enterprise, so that the matching degree between the enterprise and the user is measured in a two-way manner.
Fig. 1 is a flowchart illustrating a method for determining matching parameters between a user and an enterprise according to an exemplary embodiment of the present disclosure.
As shown in fig. 1, the method for determining matching parameters between a user and an enterprise provided by the present disclosure includes:
The method provided by the present disclosure may be executed by an electronic device with computing capability, and the electronic device may be a server or a user terminal.
If the server executes the scheme provided by the disclosure, the user can operate the user terminal and send resume data of the user and recruitment information of the enterprise to the server, so that the server acquires the resume data and the recruitment information.
If the scheme provided by the disclosure is executed by the user terminal, the user can operate the user terminal, so that the user terminal acquires the resume data and the recruitment information. For example, the user may operate in an interface of the terminal device to select resume data of the user and recruitment information of an enterprise, so that the user terminal may process the resume data and the recruitment information based on a scheme provided by the present disclosure.
Specifically, after acquiring resume data of the user and recruitment information of the enterprise, the electronic device can process the resume data and the recruitment information by using the scheme provided by the disclosure. For example, the solution provided by the present disclosure can be packaged as a piece of software, and resume data of the user and recruitment information of the enterprise are processed through the piece of software.
And step 102, determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user.
Further, the electronic device can extract features according to the resume data and the recruitment information, and then determine the first feature and the second feature.
In practical application, the electronic equipment can directly extract features from resume data, can also extract features from recruitment information, and can also determine similar information of the resume data and the recruitment information as a class of features, so that the electronic equipment can acquire various features.
Some features may belong to both the first and second features.
The electronic equipment can determine a first feature from the extracted multiple features, wherein the first feature is used for representing evaluation information of the user on the enterprise; the electronic device may determine a second feature from the extracted plurality of features, the second feature being used to characterize the business' assessment information for the user.
For example, the first feature includes, for example, a post resume text matching degree, a department employee composition, and the like; the second characteristics include, for example, the degree of matching between the position resume and the pen, talent learning, interview evaluation, and the like.
By determining the evaluation information for representing the enterprise by the user and the evaluation information for representing the user by the enterprise, the evaluation result of the user to the enterprise and the evaluation result of the enterprise to the user can be determined according to the information, and further the matching degree between the enterprise and the user can be determined from two directions.
103, determining a first parameter value according to a preset first weight and a first characteristic of the user to the enterprise; determining a second parameter value according to a preset second weight and a second characteristic of the enterprise to the user; the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user.
Specifically, a first weight of the user to the enterprise and a second weight of the enterprise to the user may be preset in the electronic device.
Further, the first weight and the second weight can be obtained through machine learning technology training.
Training data can be prepared in advance, and the training data can comprise resume data of the user, recruitment information of the enterprise, information of the enterprise sending out the admission notification and information of the user receiving the admission notification. The first characteristic and the second characteristic can be extracted according to resume data and recruitment information, the matching degree between the enterprise and the user is determined according to the characteristics and the preset first weight and second weight, the information that the enterprise sends out the admission notice is predicted according to the matching degree, the information that the user receives the admission notice is predicted, and then the first weight and the second weight can be optimized by combining the real information that the enterprise sends out the admission notice in the training data and the information that the user receives the admission notice. The values of the first and second weights can be obtained through a number of iterations.
In practical application, the electronic device may use a product of the first weight and the first characteristic as a first parameter value; and taking the product of the second weight and the second characteristic as a second parameter value.
The matching degree of the characterization user to the enterprise can be determined through the first parameter value obtained through the first weight and the first characteristic, and therefore the evaluation result of the user to the enterprise is obtained. And determining the matching degree of the characterization enterprise to the user according to the second weight and the second parameter value obtained by the second characteristic, so as to obtain the evaluation result of the enterprise to the user. Thereby obtaining the two-way evaluation result between the enterprise and the user.
For example, if the first parameter value is larger, it indicates that the user has a higher rating for the enterprise, and the user will receive the enrollment notification for the enterprise, and if the second parameter value is larger, it indicates that the enterprise has a higher rating for the user, and the enterprise will send the enrollment notification to the user. Therefore, the two parameters can be used for obtaining the two-way evaluation result between the user and the enterprise.
In an alternative embodiment, the first parameter value and the second parameter value may be displayed in the user terminal, so that the user can determine the matching result between the user and the enterprise based on the first parameter value and the second parameter value, for example, if both values are higher, it may be determined that the enterprise is better matched with the user.
In an alternative embodiment, a first threshold and a second threshold may be set, and if the first parameter value is greater than the first threshold, it may be determined that the user will accept the admission notification of the enterprise, and if the second parameter value is greater than the second threshold, it may be determined that the enterprise will send the admission notification to the user.
If it is predicted that the user will accept the admission notification of the enterprise and the enterprise will also send the admission notification to the user, it may be determined that the matching result between the enterprise and the user is a match, and if it is predicted that the user will not accept the admission notification of the enterprise or the enterprise will not send the admission notification to the user, it may be determined that the matching result between the enterprise and the user is a mismatch.
In an alternative embodiment, the matching result may also be displayed in the user terminal, for example, if the electronic device is a server, the server may send the matching result to the user terminal, so that the user terminal displays the matching result.
The method for determining the matching parameters of the user and the enterprise, provided by the disclosure, comprises the following steps: acquiring resume data of a user and recruitment information of an enterprise; determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user; determining a first parameter value according to a preset first weight and a first characteristic of a user to the enterprise; determining a second parameter value according to a preset second weight and a second characteristic of the user by the enterprise, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the user by the enterprise; the first parameter value and the second parameter value are used to determine a match between the user and the enterprise. According to the method, the characteristics can be extracted according to the resume data and the recruitment information, and the characteristics are processed by utilizing the preset first weight and the preset second weight, so that a bidirectional evaluation result between an enterprise and a user is obtained, and the enterprise is assisted in making a recruitment decision.
Fig. 2 is a flowchart illustrating a method for determining matching parameters between a user and an enterprise according to another exemplary embodiment of the present disclosure.
As shown in fig. 2, the method for determining matching parameters between a user and an enterprise provided by the present disclosure includes:
Step 201 is similar to the implementation of step 101, and is not described again.
And step 202, extracting features from the resume data and the recruitment information.
Step 203, determining a first characteristic of the user to the enterprise and a second characteristic of the enterprise to the user according to the extracted characteristics; the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user.
The resume data comprises a plurality of information, and the recruitment information also comprises a plurality of information, so that a large number of characteristics can be extracted from the resume data and the recruitment information.
For example, a user's academic character, resume character, job intention character, and the like may be extracted from the resume data. For another example, the department configuration information of the enterprise, the post requirement characteristics of the enterprise, and the like can be extracted from the recruitment information.
Specifically, the first characteristic of the user to the enterprise and the second characteristic of the enterprise to the user can be determined according to the extracted large number of characteristics. The first characteristics are used for representing the evaluation information of the user on the enterprise, and the second characteristics are used for representing the evaluation information of the enterprise on the user.
Furthermore, the electronic equipment can screen out the evaluation characteristics of the user to the enterprise from the extracted large quantity of characteristics. And determining the first characteristics according to the characteristics, screening out evaluation characteristics of the enterprise to the user, and determining the second characteristics according to the characteristics.
Through the implementation mode, the electronic equipment can determine the first characteristic of the user to the enterprise and the second characteristic of the enterprise to the user according to the resume data and the recruitment information, so that the bidirectional evaluation characteristic between the user and the enterprise is obtained, and the bidirectional evaluation result between the user and the enterprise can be determined according to the first characteristic and the second characteristic.
In an alternative embodiment, the electronic device may perform a normalization process on the extracted features to obtain normalized features.
The standardization processing procedures for different features are different, for example, the similarity between the resume data and the recruitment information can be determined, and as one feature, the feature can be directly used as a standardized feature.
For another example, for the characteristics of the user-extracted scholarly calendar, the scholarly calendar and the school of the user can be coded in a one-hot coding mode, usually, a student has at most a great deal of three experiences, and then the school category can be classified into north-clearance, C9, 985, 211 and other five grades. A 3 x 5-15 dimensional 0-1 vector is generated, such as a user master graduate, this family is 985 school, the master is in qing, then his characterization is [0,0,1,0,0,1,0,0,0,0,0,0,0,0,0] the third digit 1 represents this family 985, and the 6 th dimension 1 represents north-clearing of the master.
Specifically, the evaluation characteristics of the user on the enterprise and the evaluation characteristics of the user on the enterprise can be screened out from the standardized characteristics. The evaluation features of the enterprise by the user may be processed to obtain the first features, for example, the features may be spliced to obtain the first features. The evaluation characteristics of the enterprise to the user can be processed to obtain the second characteristics, for example, the characteristics can be spliced to obtain the second characteristics.
The extracted features are subjected to standardization processing, and then the first features and the second features are determined, so that the first features and the second features are also standardized features, the first features and the second features can be calculated, and a two-way evaluation result between an enterprise and a user is obtained.
Further, the key features after normalization include any one of the following:
cosine similarity between resume data and recruitment information;
a learning feature vector of the user; the academic calendar feature vector is used for representing the academic calendar condition of the user at each stage;
and the staff composition vector is used for representing staff composition information of the enterprise.
According to the scheme provided by the disclosure, various features can be obtained, so that the features of multiple angles can be extracted, and the first features and the second features which are mutually evaluated between users and enterprises of multiple angles are obtained.
In practice, the electronic device may use a product of the first weight and the first characteristic as the first parameter value. The first weight is used for determining the evaluation result of the user on the enterprise, and the first characteristic of the user on the enterprise can be processed through the first weight, so that which information of the enterprise is concerned by the user is determined.
The electronic device may take a product of the second weight and the second characteristic as the second parameter value. The second weight is used for determining the evaluation result of the enterprise on the user, and the second characteristic of the enterprise on the user can be processed through the second weight, so that which information of the user is concerned by the enterprise more.
By the method, bidirectional evaluation results between the enterprises and the users can be obtained, and then the enterprises can make recruitment decisions based on the evaluation results to improve recruitment efficiency.
And step 205, generating and sending recommendation information according to the first parameter and the second parameter.
After the electronic device generates the first parameter and the second parameter, recommendation information can be generated, and if the user terminal executes the method provided by the disclosure, the user terminal can directly display the generated recommendation information. If the server executes the method provided by the present disclosure, the server may send recommendation information to the user terminal.
The recommendation information may include, for example, a result of whether the user matches the enterprise, and may further include an evaluation result of the user on the enterprise, an evaluation result of the enterprise on the user, and the like.
Through the implementation mode, the staff for managing the personnel in the enterprise can timely know the bidirectional evaluation result between the user and the enterprise, and the enterprise is assisted to make a recruitment decision.
In an optional implementation, the terminal device of the enterprise may send resume information of a plurality of users and recruitment information of the enterprise to the server, and the server may determine the first parameter and the second parameter of each user and the enterprise, and then determine a bidirectional evaluation result between the enterprise and the user, so as to obtain the user matched with the enterprise.
In another optional implementation, the terminal device of the user may send resume information of the user and recruitment information of multiple enterprises to the server, and the server may determine the first parameter and the second parameter of the user and each enterprise, and then determine a bidirectional evaluation result between the enterprises and the user, so as to obtain the enterprise matched with the user.
Through the implementation mode, the server can feed back the recommendation information corresponding to the information to the terminal equipment according to the information sent by the terminal equipment, so that the user information of the user matched with the enterprise is sent to the terminal equipment of the enterprise in a targeted manner, and the enterprise information of the enterprise matched with the user can be sent to the terminal equipment of the user in a targeted manner, so that personnel managing personnel in the enterprise can directly know the information of personnel who are likely to receive admission notification, and the user can directly know the information of the enterprise which is likely to send admission notification to the user.
Fig. 3 is a flowchart illustrating a method for determining a weight between a user and an enterprise according to an exemplary embodiment of the disclosure.
As shown in fig. 3, the present disclosure provides a method for determining a weight between a user and an enterprise, including:
301, acquiring a training data set, a first weight of a user to be trained on an enterprise, and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of the user, recruitment information of the enterprise, a real admission record of the enterprise sending admission notifications to the user, and a real receiving record of the user receiving the admission notifications of the enterprise.
The method provided by the present disclosure may be performed by an electronic device with computing capability, and the electronic device may be trained by using a training data set to obtain a first weight and a second weight, which may be applied in the schemes shown in fig. 1 and 2.
Specifically, the training dataset may include resume data of the user, recruitment information of the enterprise, a real admission record of the enterprise sending admission notifications to the user, and a real acceptance record of the user accepting admission notifications of the enterprise.
Further, the training dataset may include resume data for a plurality of users and may also include recruitment information for a plurality of enterprises. The data can be data actually published in the recruitment platform.
In practical application, the training data set may further include a real admission record for an enterprise to send an admission notification to the user, for example, the training data set includes recruitment information of the enterprise A, B, C, and may further include resume data of the users a, B, and c, and the real admission record may include a record that a sends an admission notification to a, and may also include a record that B sends an admission notification to B.
The training data set may further include a record of actual acceptance, for example, the record may include that a accepts the admission notification of a, and that B accepts the admission notification of B.
Specifically, the real admission record and the real acceptance record can be used as the label data in the training process, and the first weight and the second weight are optimized by using the real admission record and the real acceptance record.
Further, the first weight and the second weight may be preset, and the first weight and the second weight may be optimized by using a training data set, and the first weight and the second weight satisfying the condition may be obtained by iterative optimization.
And step 302, predicting a predicted admission record of the enterprise sending the admission notification to the user and a predicted acceptance record of the enterprise accepting the admission notification of the user according to the first weight, the second weight, the resume data and the recruitment information.
In practical application, the electronic device can process the resume data and the recruitment information and extract the characteristics of the resume data and the recruitment information. And processing the extracted features by using the current first weight and the second weight to obtain a bidirectional evaluation result between the enterprise and the user. For example, a two-way evaluation result between enterprise a and user a, a two-way evaluation result between enterprise a and user B, a two-way evaluation result between enterprise a and user c, a two-way evaluation result between enterprise B and user a, and the like may be obtained.
The electronic device can determine the predicted admission record and the predicted acceptance record according to the determined bidirectional evaluation result between the enterprise and the user.
Specifically, the forecast admission record is used for representing information that the forecast enterprise sends admission notification to the user, and the forecast acceptance record is used for representing information that the forecast user accepts the admission notification of the enterprise. For example, it is predicted that enterprise a will send a logging notification to user a, and for example, it is predicted that enterprise a will not accept the logging notification.
In actual application, for each combination of each enterprise and each user, it can be predicted whether the enterprise will send the admission notification to the user, and it can also be predicted whether the user will accept the admission notification of the user.
Step 303, optimizing the first weight and the second weight according to the real admission record, the real acceptance record, the predicted admission record and the predicted acceptance record; and the optimized first weight and the optimized second weight which meet the preset conditions are used for determining the matching degree between the user and the enterprise.
Further, the electronic device may compare the real admission record with the predicted admission record, and may also compare the real acceptance record with the predicted acceptance record, thereby optimizing the first weight and the second weight according to the comparison result.
In practical application, the real admission record and the real acceptance record can be used as tag data, so that whether the predicted result of the electronic equipment is accurate or not can be determined by using the tag data, and if the predicted result is not accurate, the first weight and the second weight can be optimized based on the difference between the tag data and the predicted result.
A preset condition may also be set, and when the optimized first weight and the optimized second weight satisfy the preset condition, the iteration may be stopped, so as to obtain the first weight and the second weight that can be applied to the method shown in fig. 1 and 2, and specifically, to determine the matching degree between the user and the enterprise.
Fig. 4 is a flowchart illustrating a method for determining a weight between a user and an enterprise according to another exemplary embodiment of the present disclosure.
As shown in fig. 4, the present disclosure provides a method for determining a weight between a user and an enterprise, including:
step 401, acquiring a training data set, a first weight of a user to be trained on an enterprise, and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of the user, recruitment information of the enterprise, a real admission record of the enterprise sending admission notifications to the user, and a real receiving record of the user receiving the admission notifications of the enterprise.
The implementation of step 401 is similar to step 301, and is not described in detail.
The first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user.
Specifically, the electronic device can extract key features according to resume data and recruitment information; and then determining a first characteristic of the user to the enterprise and a second characteristic of the enterprise to the user from the key characteristics.
The resume data comprises a plurality of information, and the recruitment information also comprises a plurality of information, so that a large number of characteristics can be extracted from the resume data and the recruitment information.
For example, a user's academic character, resume character, job intention character, and the like may be extracted from the resume data. For another example, the department configuration information of the enterprise, the post requirement characteristics of the enterprise, and the like can be extracted from the recruitment information.
Specifically, the first characteristic of the user to the enterprise and the second characteristic of the enterprise to the user can be determined according to the extracted large number of characteristics. The first characteristics are used for representing the evaluation information of the user on the enterprise, and the second characteristics are used for representing the evaluation information of the enterprise on the user.
Furthermore, the electronic equipment can screen out the evaluation characteristics of the user to the enterprise from the extracted large quantity of characteristics. And determining the first characteristics according to the characteristics, screening out evaluation characteristics of the enterprise to the user, and determining the second characteristics according to the characteristics.
In an alternative embodiment, the electronic device may perform a normalization process on the extracted features to obtain normalized features.
The standardization processing procedures for different features are different, for example, the similarity between the resume data and the recruitment information can be determined, and as one feature, the feature can be directly used as a standardized feature.
For another example, for the characteristics of the user-extracted scholarly calendar, the scholarly calendar and the school of the user can be coded in a one-hot coding mode, usually, a student has at most a great deal of three experiences, and then the school category can be classified into north-clearance, C9, 985, 211 and other five grades. A 3 x 5-15 dimensional 0-1 vector is generated, such as a user master graduate, this family is 985 school, the master is in qing, then his characterization is [0,0,1,0,0,1,0,0,0,0,0,0,0,0,0] the third digit 1 represents this family 985, and the 6 th dimension 1 represents north-clearing of the master.
Specifically, the evaluation characteristics of the user on the enterprise and the evaluation characteristics of the user on the enterprise can be screened out from the standardized characteristics. The evaluation features of the enterprise by the user may be processed to obtain the first features, for example, the features may be spliced to obtain the first features. The evaluation characteristics of the enterprise to the user can be processed to obtain the second characteristics, for example, the characteristics can be spliced to obtain the second characteristics.
Further, the key features after normalization include any one of the following:
cosine similarity between resume data and recruitment information;
a learning feature vector of the user; the academic calendar feature vector is used for representing the academic calendar condition of the user at each stage;
and the staff composition vector is used for representing staff composition information of the enterprise.
The first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user.
Specifically, the electronic device may generate the first parameter value and the second parameter value using the current first weight and the current second weight. Specifically, the product of the first weight and the first characteristic may be determined as a first parameter value of the user to the enterprise, and the product of the second weight and the second characteristic may be determined as a second parameter value of the user to the enterprise.
The current first weight is used for predicting the evaluation result of the user on the enterprise, and the first characteristic of the user on the enterprise can be processed through the first weight, so that which information of the enterprise is concerned by the user is predicted.
The current second weight is used for predicting the evaluation result of the enterprise on the user, and the second characteristic of the enterprise on the user can be processed through the second weight, so that which information of the user is concerned by the enterprise is predicted.
And step 404, predicting the prediction admission record of the admission notice sent by the enterprise to the user and the prediction acceptance record of the admission notice of the enterprise accepted by the user according to the first parameter value and the second parameter value.
The electronic equipment can predict whether the enterprise sends the admission notice to the user according to the matching degree of the user to the enterprise and the matching degree of the enterprise to the user, so that the predicted admission record is obtained, and whether the user can accept the admission notice of the enterprise can be predicted, so that the predicted admission record is obtained.
For example, if the first parameter value is larger, it indicates that the user has a higher rating for the enterprise, and the user will receive the enrollment notification for the enterprise, and if the second parameter value is larger, it indicates that the enterprise has a higher rating for the user, and the enterprise will send the enrollment notification to the user. Based on this, a prediction result can be obtained.
Further, the matching result between the user and the enterprise can be determined according to the first parameter value of each user to each enterprise and the second parameter value of each enterprise to each user.
Specifically, the matching result between the user and the enterprise can be determined through a Gell-Shapril algorithm.
The Gale-Shapley algorithm, abbreviated as the "GS algorithm", also known as the "delayed-acceptance algorithm" (delayed-acceptance algorithm), is a market mechanism designed by Gal and Shapley to find a stable match. This algorithm is able to determine a stable matching combination based on the information of objects Ai on the market side and the information of objects Bj on the market side.
Further, the matching result between the user and the enterprise can be obtained by the Galer-Shapril algorithm, for example, which enterprises will send the admission notification to which users, and which users will receive the admission notification sent by which enterprises.
In practical application, the electronic device can predict the predicted admission record of the admission notification sent by the enterprise to the user according to the matching result, and predict the acceptance record of the admission notification received by the user. The predicted admission record may be generated based on information about which users will be sent admission notifications by the enterprise in the matching result. And generating a prediction acceptance record according to the information of which enterprises will accept the admission notice of the user in the matching result.
Step 405 determines a first loss function based on the real and predicted admission records.
The electronic equipment can determine a first loss function according to the real admission record and the predicted admission record, and the first loss function is used for representing a loss function of a link of sending admission notification to the user by the enterprise.
Further, in the above-mentioned case,means that the department d is receivedjThe user who did not actually receive the enrollment notification;for actually receiving enterprise djBy recordingNotify, but predict users that are not received.Each represents djTo pairAndof the second parameter value.
Step 406 determines a second loss function based on the true acceptance record and the predicted acceptance record.
In practical application, the electronic device may determine a second loss function according to the real acceptance record and the predicted acceptance record, where the second loss function is used to characterize a loss function of an admission notification link issued by an acceptance enterprise.
Wherein,to predict user uiReceiving a notification record, wherein the enterprise does not actually receive the notification record;for actual user uiA notification record is received but a business that is not received is predicted.Each represents uiTo pairAndthe first parameter value of (1).
Specifically, the electronic device may optimize a current first weight and a current second weight according to the first loss function and the second loss function to obtain the optimized first weight and the optimized second weight.
Further, the electronic device may perform gradient pass-back according to the first loss function and the second loss function, so as to optimize the first weight and the second weight.
In practical application, the electronic device may determine a total loss function according to the first loss function and the second loss function, and then optimize the first weight and the second weight based on the total loss function.
Wherein the total loss function loss is γ · losssending+(1-γ)·lossaccepting
Wherein gamma is a hyperparameter.
In an alternative embodiment, during each training iteration, a matching result between the user and the enterprise may be determined according to the first parameter and the second parameter. In such an embodiment, the conditions for stopping the training iteration may include: the currently determined matching result is the same as the matching result determined last time.
For example, if the matching result determined in the nth iteration is the same as the matching result determined in the (n + 1) th iteration, the electronic device may stop the iteration and not optimize the first weight and the second weight.
Fig. 5 is a schematic diagram illustrating a process of training weights according to an exemplary embodiment of the disclosure.
As shown in fig. 5, the electronic device may acquire recruitment information 51 of an enterprise and resume data 52 of a user, extract features according to the recruitment information 51 and the resume data 52, and obtain a first feature 53 and a second feature 54.
The electronic device may also determine a first parameter value 57 and a second parameter value 58 based on the features 53, 54 and the current first weight 55 and second weight 56, respectively, so as to stably match the user with the enterprise based on the first parameter value and the second parameter value.
Specifically, the electronic device may obtain a predicted result 59 according to the first parameter value 57 and the second parameter value 58, construct a loss function 61 according to the predicted result 59 and the real result 60, and further optimize the first weight 54 and the second weight 55 based on the loss function 61, where the real result 60 may include a real admission record and a real acceptance record.
Fig. 6 is a schematic structural diagram illustrating an apparatus for determining matching parameters between a user and an enterprise according to an exemplary embodiment of the present disclosure.
The device 600 for determining matching parameters of a user and an enterprise provided by the present disclosure includes:
the acquiring unit 610 is used for acquiring resume data of a user and recruitment information of an enterprise;
a feature determining unit 620, configured to determine a first feature and a second feature according to the resume data and the recruitment information, where the first feature is used to characterize evaluation information of the user on an enterprise, and the second feature is used to characterize evaluation information of the enterprise on the user;
a parameter determining unit 630, configured to determine a first parameter value according to a preset first weight of the user to the enterprise and the first characteristic; determining a second parameter value according to a preset second weight of the enterprise to the user and the second characteristic, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user;
the first parameter value and the second parameter value are used for determining a matching result between the user and the enterprise.
Fig. 7 is a schematic structural diagram of an apparatus for determining matching parameters of a user and an enterprise according to another exemplary embodiment of the present disclosure.
The present disclosure provides an apparatus 700 for determining matching parameters between a user and an enterprise, where an obtaining unit 710 in fig. 7 is similar to the obtaining unit 610 in fig. 6, a feature determining unit 720 is similar to the feature determining unit 620, and a parameter determining unit 730 is similar to the parameter determining unit 630 in fig. 6.
Wherein the feature determining unit 720 includes:
a feature extraction module 721 for extracting features from the resume data and the recruitment information;
a characteristics determination module 722 for determining a first characteristics of the user to the business and a second characteristics of the business to the user based on the characteristics.
Optionally, the feature determining module 722 is specifically configured to:
standardizing the characteristics to obtain standardized characteristics;
and determining the first characteristic and the second characteristic according to the normalized characteristics.
Optionally, the normalized key features include any one of:
cosine similarity between the resume data and the recruitment information;
a learning feature vector of the user; the academic calendar feature vector is used for representing the academic calendar condition of the user at each stage;
and the staff composition vector is used for representing staff composition information of the enterprise.
Optionally, the parameter determining unit 730 includes:
a first parameter determining module 731, configured to determine a product of the first weight and the first characteristic as a first parameter value of the user for the enterprise;
the parameter determining unit 730 includes:
a second parameter determining module 732, configured to determine a product of the second weight and the second characteristic as a second parameter value of the user for the enterprise.
Optionally, the apparatus further comprises: and the recommending unit 740 is configured to generate and send recommendation information according to the first parameter and the second parameter.
If the recommendation information represents user information of a user matched with an enterprise, the recommending unit 740 is specifically configured to: sending recommendation information to terminal equipment of an enterprise;
or, if the recommendation information represents enterprise information of an enterprise matched with the user, the recommending unit 740 is specifically configured to: and sending recommendation information to the terminal equipment of the user.
Fig. 8 is a schematic structural diagram of a weight determination apparatus between a user and an enterprise according to an exemplary embodiment of the present disclosure.
As shown in fig. 8, the present disclosure provides an apparatus 800 for determining a weight between a user and an enterprise, including:
an obtaining unit 810, configured to obtain a training data set, a first weight of a user to be trained on an enterprise, and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of a user, recruitment information of an enterprise, a real admission record of the enterprise sending admission notification to the user, and a real receiving record of the user receiving the admission notification of the enterprise;
a predicting unit 820, configured to predict, according to the first weight, the second weight, the resume data, and the recruitment information, a predicted admission record of the enterprise sending an admission notification to the user and a predicted admission record of the user accepting the admission notification of the enterprise;
a training unit 830, configured to optimize the first weight and the second weight according to the real admission record, the real acceptance record, the predicted admission record, and the predicted acceptance record;
and the optimized first weight and the optimized second weight which meet preset conditions are used for determining the matching degree between the user and the enterprise.
Fig. 9 is a schematic structural diagram of a weight determination apparatus between a user and an enterprise according to another exemplary embodiment of the present disclosure.
As shown in fig. 9, in the weight determination apparatus 900 between a user and an enterprise provided by the present disclosure, an obtaining unit 910 is similar to the obtaining unit 810 shown in fig. 8, a predicting unit 920 is similar to the predicting unit 820 shown in fig. 8, and a training unit 930 is similar to the training unit 830 shown in fig. 8.
On the basis of the embodiment shown in fig. 8, the prediction unit 920 includes:
the characteristic determining module 921, configured to determine a first characteristic of the user to the enterprise and a second characteristic of the user to the enterprise according to the resume data and the recruitment information;
a parameter determining module 922, configured to determine a first parameter value of the user for the enterprise according to the first weight and the first characteristic; determining a second parameter value of the enterprise to the user according to the second weight and the second characteristic;
a forecasting module 923, configured to forecast a forecast admission record of the enterprise sending an admission notification to the user according to the first parameter value and the second parameter value, and a forecast acceptance record of the user accepting the admission notification of the enterprise.
The feature determining module 921 is specifically configured to:
extracting features according to the resume data and the recruitment information;
a first user-to-business characteristic and a second business-to-user characteristic are determined among the characteristics.
The feature determining module 921 is specifically configured to:
standardizing the characteristics to obtain standardized characteristics;
and determining the first characteristic and the second characteristic according to the normalized characteristics.
Optionally, in the apparatus, the parameter determining module 922 is specifically configured to:
determining a product of the first weight and the first characteristic as a first parameter value of the user for the enterprise;
and determining the product of the second weight and the second characteristic as a second parameter value of the user to the enterprise.
The prediction module 923 is specifically configured to:
determining a matching result between each user and each enterprise according to each first parameter value of each user to each enterprise and each second parameter value of each enterprise to each user;
and predicting a predicted admission record of the enterprise sending an admission notice to the user according to the matching result, and predicting an acceptance record of the user accepting the admission notice of the enterprise.
Wherein the preset conditions include:
the currently determined matching result is the same as the matching result determined last time.
Wherein the training unit 930 comprises:
a first function determining module 931, configured to determine a first loss function according to the real admission record and the predicted admission record;
a second function determination module 932 for determining a second loss function based on the true acceptance record and the predicted acceptance record;
an optimizing module 933, configured to optimize the first weight and the second weight according to the first loss function and the second loss function.
The invention provides a method for determining matching parameters of a user and an enterprise, electronic equipment and a program product, which are applied to a deep learning technology in an artificial intelligence technology to more accurately assist the enterprise to make a recruitment decision.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of the electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any of the embodiments described above.
FIG. 10 illustrates a schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can also be stored. The calculation unit 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
A number of components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (33)
1. A method for determining matching parameters of a user and an enterprise comprises the following steps:
acquiring resume data of a user and recruitment information of an enterprise;
determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user;
determining a first parameter value according to a preset first weight of a user to the enterprise and the first characteristic; determining a second parameter value according to a preset second weight of the enterprise to the user and the second characteristic, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user;
the first parameter value and the second parameter value are used for determining a matching result between the user and the enterprise.
2. The method of claim 1, wherein determining a first user-to-business characteristic and a second user-to-business characteristic from the resume data and the recruitment information comprises:
extracting features from the resume data and the recruitment information;
according to the characteristics, a first characteristic of the user to the enterprise and a second characteristic of the enterprise to the user are determined.
3. The method of claim 2, wherein said determining a first user-to-business characteristic and a second business-to-user characteristic from said characteristics comprises:
standardizing the characteristics to obtain standardized characteristics;
and determining the first characteristic and the second characteristic according to the normalized characteristics.
4. The method of claim 3, wherein the normalized key features comprise any of:
cosine similarity between the resume data and the recruitment information;
a learning feature vector of the user; the academic calendar feature vector is used for representing the academic calendar condition of the user at each stage;
and the staff composition vector is used for representing staff composition information of the enterprise.
5. The method of any one of claims 1-4,
the determining a first parameter value of the user to the enterprise according to a preset first weight of the user to the enterprise and the first characteristic comprises:
determining a product of the first weight and the first characteristic as a first parameter value of the user for the enterprise;
the determining a second parameter value of the user to the enterprise according to a preset second weight of the user to the enterprise and the second characteristic comprises:
and determining the product of the second weight and the second characteristic as a second parameter value of the user to the enterprise.
6. The method of any of claims 1-5, further comprising:
and generating and sending recommendation information according to the first parameter and the second parameter.
7. The method of claim 6, wherein the recommendation information characterizes user information of users matching the business, and issuing recommendation information comprises: sending recommendation information to terminal equipment of an enterprise;
or, if the recommendation information represents enterprise information of an enterprise matched with the user, sending recommendation information includes: and sending recommendation information to the terminal equipment of the user.
8. A method for determining weight between a user and an enterprise, comprising:
acquiring a training data set, a first weight of a user to be trained on an enterprise, and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of a user, recruitment information of an enterprise, a real admission record of the enterprise sending admission notification to the user, and a real receiving record of the user receiving the admission notification of the enterprise;
predicting a predicted admission record of the enterprise sending an admission notification to the user and a predicted acceptance record of the user accepting the admission notification of the enterprise according to the first weight, the second weight, the resume data and the recruitment information;
optimizing the first weight and the second weight according to the real admission record, the real acceptance record, the predicted admission record, and the predicted acceptance record;
and the optimized first weight and the optimized second weight which meet preset conditions are used for determining the matching degree between the user and the enterprise.
9. The method of claim 8, wherein predicting a predicted admission record for the business to issue admission notifications to the user and a predicted acceptance record for the user to accept admission notifications for the business based on the first weight, the second weight, the resume data, the recruitment information comprises:
determining a first characteristic of the user to the enterprise and a second characteristic of the enterprise to the user according to the resume data and the recruitment information;
determining a first parameter value of the user for the enterprise according to the first weight and the first characteristic; determining a second parameter value of the enterprise to the user according to the second weight and the second characteristic;
and predicting a predicted admission record of the enterprise sending an admission notification to the user according to the first parameter value and the second parameter value, and predicting an acceptance record of the user accepting the admission notification of the enterprise.
10. The method of claim 9, wherein determining a first user-to-business characteristic and a second user-to-business characteristic from the resume data and the recruitment information comprises:
extracting features according to the resume data and the recruitment information;
a first user-to-business characteristic and a second business-to-user characteristic are determined among the characteristics.
11. The method of claim 10, wherein determining a first user-to-business characteristic and a second business-to-user characteristic at the characteristic comprises:
standardizing the characteristics to obtain standardized characteristics;
and determining the first characteristic and the second characteristic according to the normalized characteristics.
12. The method of any one of claims 9-11,
the determining a first parameter value of the user for the business according to the first weight and the first characteristic comprises:
determining a product of the first weight and the first characteristic as a first parameter value of the user for the enterprise;
the determining a second parameter value of the enterprise to the user according to the second weight and the second characteristic comprises:
and determining the product of the second weight and the second characteristic as a second parameter value of the user to the enterprise.
13. The method of any of claims 9-12, wherein predicting a predicted record of enrollment for the business to issue an enrollment notification to the user and predicting an acceptance record for the user to accept the enrollment notification for the business based on the first parameter value, the second parameter value comprises:
determining a matching result between each user and each enterprise according to each first parameter value of each user to each enterprise and each second parameter value of each enterprise to each user;
and predicting a predicted admission record of the enterprise sending an admission notice to the user according to the matching result, and predicting an acceptance record of the user accepting the admission notice of the enterprise.
14. The method of claim 13, wherein the preset conditions include:
the currently determined matching result is the same as the matching result determined last time.
15. The method of any of claims 8-14, wherein said optimizing said first weight and said second weight based on said real admission record, said real acceptance record, said predicted admission record, and said predicted acceptance record comprises:
determining a first loss function according to the real admission record and the predicted admission record;
determining a second loss function based on the true acceptance record and the predicted acceptance record;
optimizing the first weight and the second weight according to the first loss function and the second loss function.
16. An apparatus for determining matching parameters of a user and a business, comprising:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring resume data of a user and recruitment information of an enterprise;
the characteristic determining unit is used for determining a first characteristic and a second characteristic according to the resume data and the recruitment information, wherein the first characteristic is used for representing the evaluation information of the user on the enterprise, and the second characteristic is used for representing the evaluation information of the enterprise on the user;
the parameter determining unit is used for determining a first parameter value according to a preset first weight of the user to the enterprise and the first characteristic; determining a second parameter value according to a preset second weight of the enterprise to the user and the second characteristic, wherein the first parameter value is used for representing the matching degree of the user to the enterprise, and the second parameter value is used for representing the matching degree of the enterprise to the user;
the first parameter value and the second parameter value are used for determining a matching result between the user and the enterprise.
17. The apparatus of claim 16, wherein the feature determination unit comprises:
the characteristic extraction module is used for extracting characteristics from the resume data and the recruitment information;
and the characteristic determining module is used for determining a first characteristic of the user to the enterprise and a second characteristic of the enterprise to the user according to the characteristics.
18. The apparatus of claim 17, wherein the feature determination module is specifically configured to:
standardizing the characteristics to obtain standardized characteristics;
and determining the first characteristic and the second characteristic according to the normalized characteristics.
19. The apparatus of claim 18, wherein the normalized key features comprise any of:
cosine similarity between the resume data and the recruitment information;
a learning feature vector of the user; the academic calendar feature vector is used for representing the academic calendar condition of the user at each stage;
and the staff composition vector is used for representing staff composition information of the enterprise.
20. The apparatus of any one of claims 16-19,
the parameter determination unit includes:
a first parameter determination module, configured to determine a product of the first weight and the first characteristic as a first parameter value of the user for the enterprise;
the parameter determination unit includes:
and the second parameter determination module is used for determining the product of the second weight and the second characteristic as a second parameter value of the user to the enterprise.
21. The apparatus of any of claims 16-20, further comprising: and the recommending unit is used for generating and sending recommending information according to the first parameter and the second parameter.
22. The apparatus of claim 21, wherein the recommendation information characterizes user information of users matching an enterprise, and the recommending unit is specifically configured to: sending recommendation information to terminal equipment of an enterprise;
or, if the recommendation information represents enterprise information of an enterprise matched with the user, the recommendation unit is specifically configured to: and sending recommendation information to the terminal equipment of the user.
23. A device for determining a weight between a user and an enterprise, comprising:
the training device comprises an acquisition unit, a calculation unit and a control unit, wherein the acquisition unit is used for acquiring a training data set, a first weight of a user to be trained on an enterprise and a second weight of the enterprise to be trained on the user; the training data set comprises resume data of a user, recruitment information of an enterprise, a real admission record of the enterprise sending admission notification to the user, and a real receiving record of the user receiving the admission notification of the enterprise;
the forecasting unit is used for forecasting a forecasting admission record of the enterprise sending an admission notification to the user and a forecasting receiving record of the user receiving the admission notification of the enterprise according to the first weight, the second weight, the resume data and the recruitment information;
a training unit configured to optimize the first weight and the second weight according to the real admission record, the real acceptance record, the predicted admission record, and the predicted acceptance record;
and the optimized first weight and the optimized second weight which meet preset conditions are used for determining the matching degree between the user and the enterprise.
24. The apparatus of claim 23, wherein the prediction unit comprises:
the characteristic determining module is used for determining a first characteristic of the user to the enterprise and a second characteristic of the user to the enterprise according to the resume data and the recruitment information;
a parameter determination module, configured to determine a first parameter value of the user for the enterprise according to the first weight and the first characteristic; determining a second parameter value of the enterprise to the user according to the second weight and the second characteristic;
and the prediction module is used for predicting a prediction admission record of the enterprise sending the admission notification to the user according to the first parameter value and the second parameter value, and predicting an acceptance record of the user accepting the admission notification of the enterprise.
25. The apparatus of claim 24, wherein the feature determination module is specifically configured to:
extracting features according to the resume data and the recruitment information;
a first user-to-business characteristic and a second business-to-user characteristic are determined among the characteristics.
26. The apparatus of claim 25, wherein the feature determination module is specifically configured to:
standardizing the characteristics to obtain standardized characteristics;
and determining the first characteristic and the second characteristic according to the normalized characteristics.
27. The apparatus of any one of claims 24-26,
the parameter determination module is specifically configured to:
determining a product of the first weight and the first characteristic as a first parameter value of the user for the enterprise;
and determining the product of the second weight and the second characteristic as a second parameter value of the user to the enterprise.
28. The apparatus according to any of claims 24-27, wherein the prediction module is specifically configured to:
determining a matching result between each user and each enterprise according to each first parameter value of each user to each enterprise and each second parameter value of each enterprise to each user;
and predicting a predicted admission record of the enterprise sending an admission notice to the user according to the matching result, and predicting an acceptance record of the user accepting the admission notice of the enterprise.
29. The apparatus of claim 28, wherein the preset conditions include:
the currently determined matching result is the same as the matching result determined last time.
30. The apparatus of any one of claims 23-29, wherein the training unit comprises:
a first function determining module, configured to determine a first loss function according to the real admission record and the predicted admission record;
a second function determination module for determining a second loss function based on the true acceptance record and the predicted acceptance record;
an optimization module to optimize the first weight and the second weight according to the first loss function and the second loss function.
31. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-15.
32. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-15.
33. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method of any one of claims 1 to 15.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111506930.0A CN114202309A (en) | 2021-12-10 | 2021-12-10 | Method for determining matching parameters of user and enterprise, electronic device and program product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111506930.0A CN114202309A (en) | 2021-12-10 | 2021-12-10 | Method for determining matching parameters of user and enterprise, electronic device and program product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114202309A true CN114202309A (en) | 2022-03-18 |
Family
ID=80652245
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111506930.0A Pending CN114202309A (en) | 2021-12-10 | 2021-12-10 | Method for determining matching parameters of user and enterprise, electronic device and program product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114202309A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115330142A (en) * | 2022-07-25 | 2022-11-11 | 北京百度网讯科技有限公司 | Training method of joint capacity model, capacity requirement matching method and device |
CN117217792A (en) * | 2023-09-06 | 2023-12-12 | 五凌电力湖南能源销售有限公司 | Power value-added service product matching decision method based on data processing |
-
2021
- 2021-12-10 CN CN202111506930.0A patent/CN114202309A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115330142A (en) * | 2022-07-25 | 2022-11-11 | 北京百度网讯科技有限公司 | Training method of joint capacity model, capacity requirement matching method and device |
CN117217792A (en) * | 2023-09-06 | 2023-12-12 | 五凌电力湖南能源销售有限公司 | Power value-added service product matching decision method based on data processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114202309A (en) | Method for determining matching parameters of user and enterprise, electronic device and program product | |
CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
CN112016796A (en) | Comprehensive risk scoring request processing method and device and electronic equipment | |
CN113051911A (en) | Method, apparatus, device, medium, and program product for extracting sensitive word | |
CN114841819A (en) | Method and device for determining claim settlement scheme, electronic equipment and storage medium | |
CN114092230A (en) | Data processing method and device, electronic equipment and computer readable medium | |
CN112950359A (en) | User identification method and device | |
CN111861801A (en) | Hotel full room prediction method, system, equipment and storage medium | |
CN115545481A (en) | Risk level determination method and device, electronic equipment and storage medium | |
CN115795345A (en) | Information processing method, device, equipment and storage medium | |
CN115687031A (en) | Method, device, equipment and medium for generating alarm description text | |
CN111429257B (en) | Transaction monitoring method and device | |
CN115034511A (en) | Enterprise life cycle determining method and device, electronic equipment and medium | |
CN114187081A (en) | Estimated value table processing method and device, electronic equipment and computer readable storage medium | |
CN114416990A (en) | Object relationship network construction method and device and electronic equipment | |
CN114254028A (en) | Event attribute extraction method and device, electronic equipment and storage medium | |
CN113450208A (en) | Loan risk change early warning and model training method and device | |
CN112116253A (en) | Method, device and system for selecting central mesh point | |
CN114492409B (en) | Method and device for evaluating file content, electronic equipment and program product | |
CN114548077A (en) | Word stock construction method and device | |
CN113360346B (en) | Method and device for training model | |
CN117726426A (en) | Credit evaluation method, credit evaluation device, electronic equipment and storage medium | |
CN114428887A (en) | Click data denoising method and device, electronic equipment and storage medium | |
CN113962382A (en) | Training sample construction method and device, electronic equipment and readable storage medium | |
CN113743906A (en) | Method and device for determining service processing strategy |
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 |