A talent assessment and recommendation method and system based on artificial intelligence

Abstract

The present invention discloses a talent assessment and recommendation method and system based on artificial intelligence. The system includes a database module, a demand input module, a data analysis module, a data processing module, and a data display module; the demand input module is used to receive talent demand information, generate talent demand data, and send it to the data analysis module; the data analysis module obtains related talent information from the database according to the talent demand data, generates talent information vectors and demand feature data, and sends them to the data processing module; the data processing module is used to obtain recommended data according to the talent information vectors and demand feature data, and sends them to the data display module; the data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander. The present invention has high computing efficiency, can accurately perform personalized talent recommendations based on the behavior of the demander, and has strong timeliness.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and specifically relates to a talent assessment and recommendation method and system based on artificial intelligence. Background Art

[0002] The talent recommendation system is the main means to alleviate the problem of talent information overload. Its main task is to use specific algorithms to model and analyze the historical browsing records of existing demanders, so as to predict the talent needs of demanders and make personalized recommendations. However, the existing talent recommendation system has low computational efficiency, insufficient personalization, and insufficient timeliness. Summary of the invention

[0003] The present invention provides a talent assessment and recommendation method and system based on artificial intelligence, which specifically adopts the following technical solutions:

[0004] A talent assessment and recommendation system based on artificial intelligence, the system comprising a database module, a demand input module, a data analysis module, a data processing module, and a data display module;

[0005] The database module is used to store talent information;

[0006] The demand input module is used to receive talent demand information, clean and integrate the talent demand information, obtain talent demand data, and send it to the data analysis module;

[0007] The data analysis module includes an information extraction unit and a demand calculation unit;

[0008] The information extraction unit is used to receive the talent demand data, and obtain the related talent information from the database according to the talent demand data, generate a talent information vector, and send it to the data processing module;

[0009] The demand calculation unit is used to calculate demand feature data based on the talent demand data including multiple data items and send the data to the data processing module;

[0010] The data processing module is used to obtain recommendation data based on the talent information vector and demand feature data, and send it to the data display module;

[0011] The data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander.

[0012] The present invention also relates to a talent evaluation and recommendation method based on artificial intelligence, which is applied to the talent evaluation and recommendation system based on artificial intelligence as described above, and specifically comprises the following steps:

[0013] S1. The demand input module receives talent demand information, cleans and integrates the talent demand information, obtains talent demand data, and sends it to the data analysis module;

[0014] S2. The information extraction unit of the data analysis module receives the talent demand data, obtains the associated talent information from the database according to the talent demand data, generates a talent information vector, and sends it to the data processing module;

[0015] S3. The demand calculation unit of the data analysis module calculates the demand feature data based on the talent demand data including multiple data items and sends it to the data processing module;

[0016] S4. The data processing module is used to obtain recommended data based on the talent information vector and demand feature data and send it to the data display module;

[0017] S5. The data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander.

[0018] The present invention also relates to a computer program product, characterized in that the computer program product comprises a computer program, and the computer program is executed by a processor to execute the talent assessment and recommendation method based on artificial intelligence as described above.

[0019] The present invention also relates to a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program, and the computer program is executed by a processor to execute the talent assessment and recommendation method based on artificial intelligence as described above.

[0020] The technical solution of the present invention has high computing efficiency, can accurately perform personalized talent recommendations based on the behavior of the demander, and has strong timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The present invention is a structural block diagram of an artificial intelligence-based talent assessment and recommendation system. DETAILED DESCRIPTION

[0022] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the scope of protection of the present invention. It should be pointed out that the following detailed description is exemplary and is intended to provide further explanation of the present invention.

[0023] Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those generally understood by those of ordinary skill in the art to which the present invention belongs. It should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0024] As attached Figure 1 As shown, Embodiment 1 of the present invention relates to a talent assessment and recommendation system based on artificial intelligence, and the system includes a database module, a demand input module, a data analysis module, a data processing module, and a data display module.

[0025] The database module is used to store talent information.

[0026] The demand input module is used to receive talent demand information, clean and integrate the talent demand information, obtain talent demand data, and send it to the data analysis module. The talent demand information includes demander behavior information, weight information, and setting parameter information.

[0027] The demander behavior information includes the selection browsing action information when the demander browses the talent information stored in the database module through the demand input module.

[0028] The weight information includes browsing time length information when the demander browses the talent information stored in the database module through the demand input module.

[0029] The setting parameter information includes the preference parameters set by the demander through the demand input module.

[0030] The data cleaning and integration includes merging the demand party's behavior information, weight information, and setting parameter information corresponding to the same browsing action of the demand party into one data item, in which the demand party's behavior information, weight information, and setting parameter information are respectively set to one field, and in each data item, the same type of fields use the same length and format, and for multiple data items with repeated content, only one of the data items is retained, and data items including blank field information are deleted, and each data item is encoded and normalized, and each field data in each data item is normalized separately, and processed into data with the same maximum value and the same minimum value, thereby obtaining talent demand data including multiple data items.

[0031] The data analysis module includes an information extraction unit and a demand calculation unit.

[0032] The information extraction unit is used to receive the talent demand data, and obtain the related talent information from the database according to the talent demand data, generate a talent information vector, and send it to the data processing module. Specifically, the information extraction unit obtains n pieces of talent information associated with the talent demand data from the database, and performs segmentation, punctuation removal, paragraph format removal, preposition removal, and conjunction removal operations respectively to obtain n pieces of standardized talent information; each piece of standardized talent information is segmented to obtain m feature segmentations, which are input into the Word2vec model for processing to obtain a standardized talent information vector matrix W,

[0033]

[0034] Among them, w 11 …w 1m Respectively represent the first to m word vectors of the first standardized talent information, w n1 …w nm They respectively represent the 1st to mth word vectors of the nth piece of standardized talent information.

[0035] The demand calculation unit is used to calculate demand feature data based on talent demand data including multiple data items and send the data to the data processing module.

[0036] Specifically, the demand calculation unit receives talent demand data including m data items, extracts data from the demand side behavior information field, obtains m feature segmentations, inputs them into the Word2vec model for processing, and obtains the demand side behavior vector matrix Q.

[0037] Q=[q1…q m ]

[0038] Among them, q1…q m Represent the 1st to mth demand-side behavior vectors respectively.

[0039] The demand calculation unit further extracts data from the weight information field to obtain m pieces of weight information, normalizes them, and obtains a weight information vector matrix Z.

[0040] Z=[z1…z m ]

[0041] Among them, z1…z m Represent the 1st to mth weight information vectors respectively.

[0042] The demand calculation unit further extracts data from the setting parameter information field to obtain m pieces of setting parameter information, normalizes them, and obtains a setting parameter information vector matrix B.

[0043] B=[b1…b m ]

[0044] Among them, b1…b m Represent the 1st to mth setting parameter information vectors respectively.

[0045] The demand calculation unit calculates the demand characteristic data U according to the demand side behavior vector matrix Q, the weight information vector matrix Z, and the setting parameter information vector matrix B, specifically:

[0046]

[0047] c i =q i tanh(q i z i +b i )

[0048] Among them, q i is the behavior vector of the i-th demand side, z i is the i-th weight information vector, b i Set the parameter information vector for the i-th parameter, c i is the preference value corresponding to the ith demand side behavior vector, and tanh() represents the hyperbolic tangent function.

[0049] The data processing module is used to obtain recommendation data according to the talent information vector and demand feature data, and send the recommendation data to the data display module.

[0050] Specifically, the data processing module calculates the demand probability matrix G of the demand side for talent information,

[0051] G=UW

[0052] The element g of the demand probability matrix G i Represents the recommendation probability of the i-th talent information.

[0053] The data processing module processes the element g of the demand probability matrix G i Sort in descending order and obtain the first j pieces of talent information as recommended data.

[0054] The data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander.

[0055] Embodiment 2 of the present invention relates to a talent assessment and recommendation method based on artificial intelligence, which is applied to the system of Embodiment 1 and specifically includes the following steps:

[0056] S1. The demand input module receives talent demand information, cleans and integrates the talent demand information, obtains talent demand data, and sends it to the data analysis module.

[0057] The talent demand information includes demander behavior information, weight information, and setting parameter information.

[0058] The demander behavior information includes the selection browsing action information when the demander browses the talent information stored in the database module through the demand input module.

[0059] The weight information includes browsing time length information when the demander browses the talent information stored in the database module through the demand input module.

[0060] The setting parameter information includes the preference parameters set by the demander through the demand input module.

[0061] The data cleaning and integration includes merging the demand party's behavior information, weight information, and setting parameter information corresponding to the same browsing action of the demand party into one data item, in which the demand party's behavior information, weight information, and setting parameter information are respectively set to one field, and in each data item, the same type of fields use the same length and format, and for multiple data items with repeated content, only one of the data items is retained, and data items including blank field information are deleted, and each data item is encoded and normalized, and each field data in each data item is normalized separately, and processed into data with the same maximum value and the same minimum value, thereby obtaining talent demand data including multiple data items.

[0062] S2. The information extraction unit of the data analysis module receives the talent demand data, obtains related talent information from the database according to the talent demand data, generates a talent information vector, and sends it to the data processing module.

[0063] Specifically, the information extraction unit obtains n pieces of talent information associated with the talent demand data from the database, and performs segmentation, punctuation removal, paragraph format removal, preposition removal, and conjunction removal operations to obtain n pieces of standardized talent information; performs word segmentation on each piece of standardized talent information to obtain m feature word segmentations, which are input into the Word2vec model for processing to obtain a standardized talent information vector matrix W.

[0064]

[0065] Among them, w 11 …w 1m Respectively represent the first to m word vectors of the first standardized talent information, w n1…w nm They respectively represent the 1st to mth word vectors of the nth piece of standardized talent information.

[0066] S3. The demand calculation unit of the data analysis module calculates demand feature data based on the talent demand data including multiple data items and sends it to the data processing module.

[0067] Specifically, the demand calculation unit receives talent demand data including m data items, extracts data from the demand side behavior information field, obtains m feature segmentations, inputs them into the Word2vec model for processing, and obtains the demand side behavior vector matrix Q.

[0068] Q=[q1…q m ]

[0069] Among them, q1…q m Represent the 1st to mth demand-side behavior vectors respectively.

[0070] The demand calculation unit further extracts data from the weight information field to obtain m pieces of weight information, normalizes them, and obtains a weight information vector matrix Z.

[0071] Z=[z1…z m ]

[0072] Among them, z1…z m Represent the 1st to mth weight information vectors respectively.

[0073] The demand calculation unit further extracts data from the setting parameter information field to obtain m pieces of setting parameter information, normalizes them, and obtains a setting parameter information vector matrix B.

[0074] B=[b1…b m ]

[0075] Among them, b1…b m Represent the 1st to mth setting parameter information vectors respectively.

[0076] The demand calculation unit calculates the demand characteristic data U according to the demand side behavior vector matrix Q, the weight information vector matrix Z, and the setting parameter information vector matrix B, specifically:

[0077]

[0078] c i =q i tanh(q i z i +b i )

[0079] Among them, q iis the behavior vector of the i-th demand side, z i is the i-th weight information vector, b i Set the parameter information vector for the i-th parameter, c i is the preference value corresponding to the ith demand side behavior vector, and tanh() represents the hyperbolic tangent function.

[0080] S4. The data processing module is used to obtain recommended data based on the talent information vector and demand feature data, and send it to the data display module.

[0081] Specifically, the data processing module calculates the demand probability matrix G of the demand side for talent information,

[0082] G=UW

[0083] The element g of the demand probability matrix G i Represents the recommendation probability of the i-th talent information.

[0084] The data processing module processes the element g of the demand probability matrix G i Sort in descending order and obtain the first j pieces of talent information as recommended data.

[0085] S5. The data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander.

[0086] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A talent assessment and recommendation system based on artificial intelligence, characterized in that: The system includes a database module, a demand input module, a data analysis module, a data processing module, and a data display module; The database module is used to store talent information; The demand input module is used to receive talent demand information, clean and integrate the talent demand information, obtain talent demand data, and send it to the data analysis module; The talent demand information includes demander behavior information, weight information, and setting parameter information; The demander behavior information includes the selection and browsing action information when the demander browses the talent information stored in the database module through the demand input module; The weight information includes browsing time length information when the demander browses the talent information stored in the database module through the demand input module; The setting parameter information includes the preference parameters set by the demander through the demand input module; The data analysis module includes an information extraction unit and a demand calculation unit; The information extraction unit is used to receive the talent demand data, and obtain the related talent information from the database according to the talent demand data, generate a talent information vector, and send it to the data processing module; The information extraction unit is used to receive the talent demand data, and obtain related talent information from the database according to the talent demand data to generate a talent information vector, specifically including: The information extraction unit obtains n pieces of talent information associated with the talent demand data from the database according to the talent demand data, and performs segmentation, punctuation removal, paragraph format removal, preposition removal, and conjunction removal operations respectively to obtain n pieces of standardized talent information; Each piece of standardized talent information is segmented to obtain m feature segmentations, which are input into the Word2vec model for processing to obtain the standardized talent information vector matrix W. Among them, w 11 …w 1m Respectively represent the first to m word vectors of the first standardized talent information, w n1 …w nm Respectively represent the 1st to mth word vectors of the nth standardized talent information; The demand calculation unit is used to calculate demand feature data based on the talent demand data including multiple data items and send the data to the data processing module; The demand calculation unit is used to calculate demand feature data according to the talent demand data including multiple data items, specifically including: The demand calculation unit receives talent demand data including m data items, extracts data in the demander behavior information field, obtains m feature segmentations, inputs them into the Word2vec model for processing, and obtains the demander behavior vector matrix Q. Q=[q1…q m ] Among them, q1…q m Represent the 1st to mth demand-side behavior vectors respectively; The demand calculation unit further extracts data from the weight information field to obtain m pieces of weight information, normalizes them, and obtains a weight information vector matrix Z. Z=[z1…z m ] Among them, z1…z m Respectively represent the 1st to mth weight information vectors; The demand calculation unit further extracts data from the setting parameter information field to obtain m pieces of setting parameter information, normalizes them, and obtains a setting parameter information vector matrix B. B=[b1…b m ] Among them, b1…b m Respectively represent the 1st to mth setting parameter information vectors; The demand calculation unit calculates the demand characteristic data U according to the demand side behavior vector matrix Q, the weight information vector matrix Z, and the setting parameter information vector matrix B, specifically: c i =q i tanh(q i z i +b i ) Among them, q i is the behavior vector of the i-th demand side, z i is the i-th weight information vector, b i Set the parameter information vector for the i-th parameter, c i is the preference value corresponding to the behavior vector of the i-th demand side, tanh() represents the hyperbolic tangent function; The data processing module is used to obtain recommendation data based on the talent information vector and demand feature data, and send it to the data display module; The data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander.

2. According to claim 1, a talent assessment and recommendation system based on artificial intelligence is characterized in that: The data cleaning and integration includes merging the demand party's behavior information, weight information, and setting parameter information corresponding to the same browsing action of the demand party into one data item, in which the demand party's behavior information, weight information, and setting parameter information are respectively set to one field, and in each data item, the same type of fields use the same length and format, and for multiple data items with repeated content, only one of the data items is retained, and data items including missing field information are deleted, and each data item is encoded and normalized, and each field data in each data item is normalized separately, and processed into data with the same maximum value and the same minimum value.

3. The talent assessment and recommendation system based on artificial intelligence according to claim 1, characterized in that: The data processing module is used to obtain recommendation data according to the talent information vector and the demand characteristic data, specifically including: The data processing module calculates the demand probability matrix G of the demand side for talent information. G=UW The element g of the demand probability matrix G i represents the recommendation probability of the i-th talent information; The data processing module processes the element g of the demand probability matrix G i Sort in descending order and obtain the first j pieces of talent information as recommended data.

4. A talent evaluation and recommendation method based on artificial intelligence, which is applied to the talent evaluation and recommendation system based on artificial intelligence according to any one of claims 1 to 3, and specifically comprises the following steps: S1. The demand input module receives talent demand information, cleans and integrates the talent demand information, obtains talent demand data, and sends it to the data analysis module; S2. The information extraction unit of the data analysis module receives the talent demand data, obtains the associated talent information from the database according to the talent demand data, generates a talent information vector, and sends it to the data processing module; S3. The demand calculation unit of the data analysis module calculates the demand feature data based on the talent demand data including multiple data items and sends it to the data processing module; S4. The data processing module is used to obtain recommended data based on the talent information vector and demand feature data and send it to the data display module; S5. The data display module obtains the recommended data, reads the corresponding talent information from the database module, and displays it to the demander.

5. The talent assessment and recommendation method based on artificial intelligence according to claim 4, characterized in that: The step S3 specifically includes: The demand calculation unit receives talent demand data including m data items, extracts data in the demander behavior information field, obtains m feature segmentations, inputs them into the Word2vec model for processing, and obtains the demander behavior vector matrix Q. Q=[q1…q m ] Among them, q1…q m Represent the 1st to mth demand-side behavior vectors respectively; The demand calculation unit further extracts data from the weight information field to obtain m pieces of weight information, normalizes them, and obtains a weight information vector matrix Z. Z=[z1…z m ] Among them, z1…z m Respectively represent the 1st to mth weight information vectors; The demand calculation unit further extracts data from the setting parameter information field to obtain m pieces of setting parameter information, normalizes them, and obtains a setting parameter information vector matrix B. B=[b1…b m ] Among them, b1…b m Respectively represent the 1st to mth setting parameter information vectors; The demand calculation unit calculates the demand characteristic data U according to the demand side behavior vector matrix Q, the weight information vector matrix Z, and the setting parameter information vector matrix B, specifically: c i =q i tanh(q i z i +b i ) Among them, q i is the behavior vector of the i-th demand side, z i is the i-th weight information vector, b i Set the parameter information vector for the i-th parameter, c i is the preference value corresponding to the ith demand side behavior vector, and tanh() represents the hyperbolic tangent function.

6. A computer program product, characterized in that The computer program product includes a computer program, which is executed by a processor and is used to execute the talent assessment and recommendation method based on artificial intelligence as described in claim 4 or 5.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and the computer program is executed by a processor to execute the talent assessment and recommendation method based on artificial intelligence as described in claim 4 or 5.

Images