CN112685653A

CN112685653A - Question bank pushing configuration method and system of talent employment model

Info

Publication number: CN112685653A
Application number: CN202110278795.2A
Authority: CN
Inventors: 颜文德; 吴洋洋; 叶祖锋; 钟金华
Original assignee: Guangzhou Ocs Information Technology Co ltd
Current assignee: Guangzhou Ocs Information Technology Co ltd
Priority date: 2021-03-16
Filing date: 2021-03-16
Publication date: 2021-04-20
Anticipated expiration: 2041-03-16
Also published as: CN112685653B

Abstract

The invention relates to the technical field of information pushing, in particular to a question bank pushing configuration method and system of a talent employment model. The invention obtains the first question bank label characteristic information of the question bank input configuration data list and the second question bank label characteristic information of the question bank output configuration data in the target question bank configuration service according to employment information distribution, and further, the link between the question bank label characteristic information of the question bank configuration input and the question bank configuration output can be considered in the process of assigning the question bank, therefore, the label mapping correlation characteristic information is obtained after the label mapping correlation is carried out on the question bank and the question bank, the input characteristic when the question bank allocation is carried out on the target question bank allocation service can be enriched, the accuracy of the question bank allocation is convenient to improve, in addition, the classification of the question bank object allocated by combining the question bank allocation networks of two different question bank allocation types is carried out on the label mapping correlation characteristic information, the question bank distribution can be carried out from the distribution dimensionality of the compound question bank, and the accuracy of the question bank distribution is further improved.

Description

Question bank pushing configuration method and system of talent employment model

Technical Field

The invention relates to the technical field of information pushing, in particular to a question bank pushing configuration method and system of a talent employment model.

Background

In the related art, usually, only the question bank input configuration data is subjected to question bank distribution identification, and the relation between the question bank input configuration data and the question bank output configuration data is not considered, and the inventor finds that in some cases, if the question bank distribution identification is only carried out on the question bank input configuration data alone, employment information features generated on the basis of the relation between the question bank input configuration data and the question bank output configuration data may be omitted, so that the accuracy of input features during question bank distribution of a target question bank configuration service is not high, and the precision of question bank distribution is influenced.

Disclosure of Invention

In order to overcome at least the above-mentioned deficiencies in the prior art, the present invention provides a question bank pushing configuration method and system for talent employment model, which obtains the first question bank label characteristic information of the question bank input configuration data list and the second question bank label characteristic information of the question bank output configuration data in the target question bank configuration service according to the employment information distribution, and further can combine the relation between the question bank label characteristic information between the question bank configuration input and the question bank configuration output in the question bank allocation process, thereby obtaining the label mapping correlation characteristic information after performing the label mapping correlation between the two, can enrich the input characteristics when performing question bank allocation to the target question bank configuration service, and is convenient to improve the accuracy of question bank allocation, and further combines the question bank allocation networks of two different question bank allocation categories to allocate the classification of question bank objects to the label mapping correlation characteristic information, the question bank distribution can be carried out from the distribution dimensionality of the compound question bank, and the accuracy of the question bank distribution is further improved.

In a first aspect, the present invention provides a question bank pushing configuration method for a talent employment model, which is applied to the server, wherein the server is in communication connection with the plurality of question bank service terminals, and the method includes:

acquiring employment information distribution associated with a talent employment model corresponding to an employment category partition acquired by current talent employment statistics, acquiring first question bank label characteristic information of a question bank input configuration data list in a target question bank configuration service according to the employment information distribution, and acquiring second question bank label characteristic information of question bank output configuration data in the target question bank configuration service;

performing label mapping association on first question bank label characteristic information of the question bank input configuration data list and second question bank label characteristic information of the question bank output configuration data to obtain label mapping association characteristic information;

according to an item bank calling node in a first item bank distribution network, identifying the label mapping associated characteristic information and distribution reference degrees of a plurality of distribution item bank indexes in the first item bank distribution network, and labeling and binding the distribution reference degrees obtained by the first item bank distribution network and distribution item bank objects corresponding to the plurality of distribution item bank indexes in the first item bank distribution network to obtain a first distribution item bank object list;

according to an item bank calling node in a second item bank distribution network, identifying the label mapping associated characteristic information and the distribution reference degrees of a plurality of distribution item bank indexes in the second item bank distribution network, and labeling and binding the distribution reference degrees obtained by the second item bank distribution network and distribution item bank objects corresponding to the plurality of distribution item bank indexes in the second item bank distribution network to obtain a second distribution item bank object list, wherein the first item bank distribution network and the second item bank distribution network are used for carrying out item bank distribution on the label mapping associated characteristic information from different item bank distribution categories;

and performing label mapping association on the first distributed question bank object list and the second distributed question bank object list to obtain a distributed question bank object corresponding to the target question bank configuration service, and performing corresponding question bank pushing configuration on the target question bank configuration service according to the distributed question bank object.

In a possible implementation manner of the first aspect, the obtaining, according to the employment information distribution, first question bank tag feature information of a question bank input configuration data list in a target question bank configuration service, and obtaining second question bank tag feature information of question bank output configuration data in the target question bank configuration service includes:

acquiring a target question bank configuration service containing a target employment plan, extracting question bank output configuration data from the target question bank configuration service, generating a plurality of question bank input configuration data according to demand source information and a plurality of question bank label demands in the target question bank configuration service, and combining the plurality of question bank input configuration data into a question bank input configuration data list;

acquiring a first employment attribute distribution and a second employment attribute distribution corresponding to the employment information distribution, wherein the first employment attribute distribution comprises question bank label characteristics matched with a plurality of characteristics, and the second employment attribute distribution comprises question bank label characteristics matched with the characteristics of a plurality of question bank output configuration data;

and extracting first question bank label characteristic information of the question bank input configuration data list through the first employment attribute distribution, and extracting second question bank label characteristic information of the question bank output configuration data through the second employment attribute distribution.

In a possible implementation manner of the first aspect, the step of extracting the first question bank tag feature information of the question bank input configuration data list through the first employment attribute distribution includes:

extracting key source labels from each item library input configuration data in the item library input configuration data list, and combining the same key source labels in all item library input configuration data into a unit item library input configuration data list;

inputting the input configuration data lists of the unit item banks into first employment attribute distribution respectively, and matching the first item bank label characteristic information of the characteristics of the input configuration data lists of the unit item banks in the first employment attribute distribution;

according to the label incidence relation between key source labels corresponding to the input configuration data lists of each unit question bank, connecting the first question bank label characteristic information of the input configuration data lists of each unit question bank to obtain the first question bank label characteristic information of the input configuration data lists of the question bank.

In a possible implementation manner of the first aspect, the extracting, by the second employment attribute distribution, second question bank tag feature information of the question bank output configuration data includes:

and respectively inputting the request target subdata in the question bank output configuration data into second employment attribute distribution, and extracting second question bank label characteristic information matched with the characteristics of each request target subdata through the first employment attribute distribution.

In a possible implementation manner of the first aspect, the performing label mapping association on the first distribution question bank object list and the second distribution question bank object list to obtain a distribution question bank object corresponding to the target question bank configuration service includes:

in the first distribution question bank object list and the second distribution question bank object list, carrying out weighted average on distribution reference degrees associated with the same distribution question bank object, and carrying out label binding on the distribution reference degrees after weighted average and the distribution question bank object to obtain a target distribution question bank object list;

and extracting the distribution question bank object associated with the maximum distribution reference degree from the target distribution question bank object list, and taking the extracted distribution question bank object as the distribution question bank object corresponding to the target question bank configuration service.

In a possible implementation manner of the first aspect, the second question bank distribution network is obtained by:

acquiring first calibration label mapping associated characteristic information and second calibration label mapping associated characteristic information;

extracting second question bank label characteristic information of the first calibration label mapping associated characteristic information, identifying second question bank label characteristic information of the first calibration label mapping associated characteristic information and distribution reference degrees of a plurality of distribution question bank indexes in a second question bank distribution network according to question bank calling nodes in the second question bank distribution network, and labeling and binding the distribution reference degrees obtained by the second question bank label characteristic information of the first calibration label mapping associated characteristic information and distribution question bank objects corresponding to the plurality of distribution question bank indexes in the second question bank distribution network to obtain a third distribution question bank object list;

extracting second question bank label characteristic information of the second calibration label mapping associated characteristic information, identifying second question bank label characteristic information of the second calibration label mapping associated characteristic information and distribution reference degrees of a plurality of distribution question bank indexes according to question bank calling nodes in a second question bank distribution network, and labeling and binding the distribution reference degrees obtained by the second question bank label characteristic information of the second calibration label mapping associated characteristic information and distribution question bank objects corresponding to the plurality of distribution question bank indexes in the second question bank distribution network to obtain a fourth question bank object list;

determining a loss function value according to second question bank label characteristic information and the third distribution question bank object list of the first calibration label mapping correlation characteristic information, and second question bank label characteristic information and the fourth distribution question bank object list of the second calibration label mapping correlation characteristic information, and adjusting model parameters in a second question bank distribution network according to the loss function value;

the second question bank distribution network is used for outputting a second distribution question bank object list matched with second question bank label characteristic information of question bank output configuration data in the target question bank configuration service;

the second distribution question bank object list is used for performing label mapping association with the first distribution question bank object list to obtain a distribution question bank object corresponding to the target question bank configuration service;

the first distribution question bank object list is a label set which is output by a first question bank distribution network and matched with the first question bank label characteristic information of the question bank input configuration data list in the target question bank configuration service.

In one possible implementation of the first aspect, the loss function value comprises an identification loss parameter value and a verification loss parameter value;

determining a loss function value according to the second question bank label characteristic information and the third distribution question bank object list of the first calibration label mapping correlation characteristic information, the second question bank label characteristic information and the fourth distribution question bank object list of the second calibration label mapping correlation characteristic information, and the method comprises the following steps:

generating an identification loss parameter value of the first calibration label mapping association characteristic information according to the third distribution question bank object list and a label distribution question bank index corresponding to the first calibration label mapping association characteristic information;

generating an identification loss parameter value of the second calibration label mapping association characteristic information according to the fourth calibration label mapping association characteristic information and the label distribution item base index corresponding to the second calibration label mapping association characteristic information;

generating the verification loss parameter value according to second question bank label characteristic information of the first calibration label mapping correlation characteristic information, a label distribution question bank index corresponding to the first calibration label mapping correlation characteristic information, second question bank label characteristic information of the second calibration label mapping correlation characteristic information, and a label distribution question bank index corresponding to the second calibration label mapping correlation characteristic information;

and generating the loss function value according to the identification loss parameter value of the first calibration label mapping correlation characteristic information, the identification loss parameter value of the second calibration label mapping correlation characteristic information and the verification loss parameter value.

In a possible implementation manner of the first aspect, the step of obtaining employment information distribution associated with the talent employment model corresponding to the employment category partition obtained by the current talent employment statistics includes:

acquiring a talent employment model corresponding to an employment category partition acquired by current talent employment statistics, acquiring current employment form-filling statistical information from a corresponding talent employment interface based on the talent employment module, and analyzing employment distribution nodes of the current employment form-filling statistical information so as to analyze the current employment form-filling statistical information into current employment distribution node configuration information to acquire processed aggregated employment distribution node identification information;

generating a plurality of groups of employment distribution node configuration information sets of different employment categories based on the aggregated employment distribution node identification information, and respectively detecting employment behavior characteristics in the employment distribution node configuration information sets of the plurality of groups of different employment categories to obtain employment behavior characteristic information in the employment distribution node configuration information sets of the plurality of groups of different employment categories;

determining employment distribution weights based on employment behavior characteristic information of the employment distribution node configuration information sets of the multiple groups of different employment categories and employment distribution node change information of the aggregated employment distribution node identification information, and mapping the employment behavior characteristic information in the employment distribution node configuration information sets of the multiple groups of different employment categories to the aggregated employment distribution node identification information to obtain multiple groups of employment distribution filling information;

and distributing the plurality of groups of employment distribution filling information according to employment sharing behavior information among the employment behavior characteristic information to obtain employment information distribution associated with the talent employment model.

In a possible implementation manner of the first aspect, the analyzing the employment distribution node for the current employment form filling statistical information to analyze the current employment form filling statistical information into current employment distribution node configuration information, so as to obtain the processed aggregated employment distribution node identification information includes:

detecting employment requirement items in the current employment form filling statistical information;

selecting target employment requirement items which accord with the distribution statistical range of the employment filling statistical information from the detected employment requirement items;

determining employment distribution node distribution corresponding to the target employment demand project, and constructing a recruitment demand distribution list according to a recruitment demand plan corresponding to the employment distribution node distribution;

and analyzing employment distribution nodes of the current employment form filling statistical information according to the recruitment requirement distribution list so as to analyze the current employment form filling statistical information into current employment distribution node configuration information and obtain the processed aggregated employment distribution node identification information.

In a second aspect, an embodiment of the present invention further provides an question bank pushing and configuring device for a talent employment model, which is applied to a server, where the server is in communication connection with multiple question bank service terminals, and the device includes:

the acquisition module is used for acquiring employment information distribution associated with a talent employment model corresponding to an employment category partition acquired by current talent employment statistics, acquiring first question bank label characteristic information of a question bank input configuration data list in a target question bank configuration service according to the employment information distribution, and acquiring second question bank label characteristic information of question bank output configuration data in the target question bank configuration service;

the correlation module is used for performing label mapping correlation on first question bank label characteristic information of the question bank input configuration data list and second question bank label characteristic information of the question bank output configuration data to obtain label mapping correlation characteristic information;

the first identification module is used for identifying the label mapping associated characteristic information and the distribution reference degrees of a plurality of distribution question bank indexes in the first question bank distribution network according to question bank calling nodes in the first question bank distribution network, and labeling and binding the distribution reference degrees obtained by the first question bank distribution network and distribution question bank objects corresponding to the plurality of distribution question bank indexes in the first question bank distribution network to obtain a first distribution question bank object list;

a second identification module, configured to identify, according to an item library retrieval node in a second item library distribution network, the tag mapping association feature information and an allocation reference degree of multiple allocated item library indexes in the second item library distribution network, and label and bind an allocation reference degree obtained by the second item library distribution network and an allocated item library object corresponding to the multiple allocated item library indexes in the second item library distribution network to obtain a second allocated item library object list, where the first item library distribution network and the second item library distribution network are configured to perform item library allocation on the tag mapping association feature information from different item library allocation categories;

and the configuration module is used for performing label mapping association on the first distribution question bank object list and the second distribution question bank object list to obtain a distribution question bank object corresponding to the target question bank configuration service, and performing corresponding question bank pushing configuration on the target question bank configuration service according to the distribution question bank object.

In a third aspect, an embodiment of the present invention further provides an item bank pushing configuration system for a talent employment model, where the item bank pushing configuration system for a talent employment model includes a server and multiple item bank service terminals in communication connection with the server;

the server is configured to:

In a fourth aspect, an embodiment of the present invention further provides a server, where the server includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be communicatively connected to at least one question bank service terminal, the machine-readable storage medium is configured to store a program, an instruction, or a code, and the processor is configured to execute the program, the instruction, or the code in the machine-readable storage medium to perform the question bank push configuration method of the talent employment model in the first aspect or any one of possible implementation manners in the first aspect.

In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed, the computer executes the question bank pushing configuration method for the talent employment model in the first aspect or any one of the possible implementation manners of the first aspect.

Based on any one of the above aspects, the invention obtains the first question bank label characteristic information of the question bank input configuration data list and the second question bank label characteristic information of the question bank output configuration data in the target question bank configuration service according to the employment information distribution, and further, the link between the question bank label characteristic information of the question bank configuration input and the question bank configuration output can be considered in the process of assigning the question bank, therefore, the label mapping correlation characteristic information is obtained after the label mapping correlation is carried out on the question bank and the question bank, the input characteristic when the question bank allocation is carried out on the target question bank allocation service can be enriched, the accuracy of the question bank allocation is convenient to improve, in addition, the classification of the question bank object allocated by combining the question bank allocation networks of two different question bank allocation types is carried out on the label mapping correlation characteristic information, the question bank distribution can be carried out from the distribution dimensionality of the compound question bank, and the accuracy of the question bank distribution is further improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that need to be called in the embodiments are briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic view of an application scenario of a question bank pushing configuration system of a talent employment model according to an embodiment of the present invention;

fig. 2 is a schematic flow chart illustrating a question bank pushing configuration method of a talent employment model according to an embodiment of the present invention;

fig. 3 is a schematic diagram of a functional module of the question bank pushing configuration device of the talent employment model according to the embodiment of the present invention;

fig. 4 is a schematic block diagram of a structural object of a server for implementing the question bank pushing configuration method of the talent employment model according to the embodiment of the present invention.

Detailed Description

The present invention is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the apparatus embodiments or the system embodiments.

Fig. 1 is an interaction diagram of a question bank pushing configuration system 10 of a talent employment model according to an embodiment of the present invention. The question bank push configuration system 10 of the talent employment model can comprise a server 100 and an information device 200 which is in communication connection with the server 100. The question bank pushing configuration system 10 of the talent employment model shown in fig. 1 is only one possible example, and in other possible embodiments, the question bank pushing configuration system 10 of the talent employment model may also include only a part of the components shown in fig. 1 or may also include other components.

In this embodiment, the server 100 and the information device 200 in the question bank pushing configuration system 10 of the talent employment model may cooperatively execute the question bank pushing configuration method of the talent employment model described in the following method embodiment, and the specific steps executed by the server 100 and the information device 200 may refer to the detailed description of the following method embodiment.

To solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of the question bank pushing configuration method of the talent employment model according to the embodiment of the present invention, and the question bank pushing configuration method of the talent employment model according to the embodiment may be executed by the server 100 shown in fig. 1, and the following describes the question bank pushing configuration method of the talent employment model in detail.

Step S110, acquiring employment information distribution associated with the talent employment model corresponding to the employment category partition acquired by the current talent employment statistics, acquiring first question bank label characteristic information of a question bank input configuration data list in the target question bank configuration service according to the employment information distribution, and acquiring second question bank label characteristic information of question bank output configuration data in the target question bank configuration service.

In this embodiment, the talent employment model corresponding to the employment category partition may be run in the form of a certain program script, and may have one or more employment information distributions available for running.

In this embodiment, the question bank tag feature information may refer to an information component in which the question bank input configuration data list in the target question bank configuration service or the question bank output configuration data in the target question bank configuration service matches each question bank configuration rule in the employment information distribution, and may be represented in the form of an information component set, for example, may be represented as (matching information component 1, matching information component 2, matching information component 3, ·.

In this embodiment, the question bank input configuration data may be used to represent source data information of a source object initiating the target question bank configuration service, for example, a request source initiates the target question bank configuration service, the target question bank configuration service generally includes many fields, such as requirement source information, requirement information of multiple question banks labels, and the like, and then specifically obtains specific field contents and past field contents in the information to obtain the question bank input configuration data. The question bank output configuration data can be used for representing the request instruction information of the target data field configured by the target question bank configuration service, and can comprise question bank configuration behavior, question bank configuration protocol, question bank configuration content, question bank configuration authority and other data.

Step S120, performing label mapping association on the first question bank label characteristic information of the question bank input configuration data list and the second question bank label characteristic information of the question bank output configuration data to obtain label mapping association characteristic information.

In some alternative embodiments, the first question bank label characteristic information and the second question bank label characteristic information are subjected to label mapping association to obtain request complete characteristic information of the target question bank configuration service, and the request complete characteristic information is referred to as label mapping association characteristic information. The label mapping association process can be that firstly, the first question bank label characteristic information and the second question bank label characteristic information are normalized to be in the same component mapping interval, and the two question bank label characteristic information are directly connected in a one-to-one characteristic mapping mode to serve as label mapping association characteristic information; or mapping and associating the features with the same dimension in the two question bank label feature information by using a support vector machine, and then performing unified modeling processing on the two mapping and associating feature information to obtain the feature information, namely the label mapping and associating feature information. In other possible implementation manners, other label mapping association manners may also be adopted, and only the mapping relationship characteristics between the first question bank label characteristic information and the second question bank label characteristic information need to be considered.

Step S130, according to the question bank calling node in the first question bank distribution network, identifying the tag mapping association feature information and the distribution reference degrees of the multiple distribution question bank indexes in the first question bank distribution network, and labeling and binding the distribution reference degrees obtained by the first question bank distribution network and the distribution question bank objects corresponding to the multiple distribution question bank indexes in the first question bank distribution network to obtain a first distribution question bank object list.

In this embodiment, the question bank invoking node in the first question bank distributing network may be trained in advance, the input of the question bank invoking node is the label mapping associated feature information, and the output of the question bank invoking node is the distribution reference degree of the label mapping associated feature information and the plurality of distributed question bank indexes in the first question bank distributing network, and the higher the distribution reference degree is, the greater the matching probability of the label mapping associated feature information and the distributed question bank object label corresponding to the distributed question bank index is; the number and types of the assigned question bank indexes included in the first question bank assignment network are determined by the number and types of the assigned question bank object labels included in the training data set when the recurrent neural network model is trained.

In this embodiment, the allocated question bank index may represent a feature for reflecting the allocated question bank object, and the allocated question bank object may refer to a question bank allocation result of the target question bank configuration service.

Step S140, according to the question bank calling node in the second question bank distribution network, identifying the tag mapping association feature information and the distribution reference degrees of the multiple distribution question bank indexes in the second question bank distribution network, and performing label binding on the distribution reference degree obtained by the second question bank distribution network and the distribution question bank objects corresponding to the multiple distribution question bank indexes in the second question bank distribution network to obtain a second distribution question bank object list.

In this embodiment, the first question bank distribution network and the second question bank distribution network are used to distribute question banks to the tag mapping associated feature information from different question bank distribution categories. The question bank allocation category may refer to feature extraction dimensions for the tag mapping associated feature information, so that feature information of the tag mapping associated feature information is extracted from different feature extraction dimensions for subsequent question bank allocation. The types of the distribution item library indexes in the first item library distribution network and the second item library distribution network may be the same or partially the same, and are not limited specifically.

And step S150, performing label mapping association on the first distribution question bank object list and the second distribution question bank object list to obtain a distribution question bank object corresponding to the target question bank configuration service, and processing the target question bank configuration service according to the distribution question bank object.

Based on the above design, the present embodiment obtains the first question bank label characteristic information of the question bank input configuration data list and the second question bank label characteristic information of the question bank output configuration data in the target question bank configuration service according to the employment information distribution, and further, the link between the question bank label characteristic information of the question bank configuration input and the question bank configuration output can be considered in the process of assigning the question bank, therefore, the label mapping correlation characteristic information is obtained after the label mapping correlation is carried out on the question bank and the question bank, the input characteristic when the question bank allocation is carried out on the target question bank allocation service can be enriched, the accuracy of the question bank allocation is convenient to improve, in addition, the classification of the question bank object allocated by combining the question bank allocation networks of two different question bank allocation types is carried out on the label mapping correlation characteristic information, the question bank distribution can be carried out from the distribution dimensionality of the compound question bank, and the accuracy of the question bank distribution is further improved.

In one possible implementation manner, for step S110, in the process of obtaining the first question bank tag feature information of the question bank input configuration data list in the target question bank configuration service and obtaining the second question bank tag feature information of the question bank output configuration data in the target question bank configuration service according to the employment information distribution, the following exemplary sub-steps can be implemented, which are described in detail below.

And the substep S111, acquiring a target question bank configuration service containing the target employment plan, extracting question bank output configuration data from the target question bank configuration service, generating a plurality of question bank input configuration data according to the requirement source information and a plurality of question bank label requirements in the target question bank configuration service, and combining the plurality of question bank input configuration data into a question bank input configuration data list.

And a substep S112, obtaining a first employment attribute distribution and a second employment attribute distribution corresponding to the employment information distribution.

The first employment attribute distribution comprises the question bank label characteristics matched with the characteristics, and the second employment attribute distribution comprises the question bank label characteristics matched with the characteristics of the question bank output configuration data.

And a substep S113, extracting the first question bank label characteristic information of the question bank input configuration data list through the first employment attribute distribution, and extracting the second question bank label characteristic information of the question bank output configuration data through the second employment attribute distribution.

For example, in the process of extracting the first question bank tag feature information of the question bank input configuration data list through the first employment attribute distribution, the key source tag may be extracted from each question bank input configuration data in the question bank input configuration data list, and the key source tags having the same key source tag in all the question bank input configuration data may be combined into the unit question bank input configuration data list. Then, the input configuration data lists of the unit item banks are respectively input into the first employment attribute distribution, and the first item bank label characteristic information which is matched with the characteristics of the input configuration data lists of the unit item banks in the first employment attribute distribution is used. And then, according to the label incidence relation among the key source labels corresponding to the input configuration data lists of each unit question bank, connecting the first question bank label characteristic information of the input configuration data lists of each unit question bank to obtain the first question bank label characteristic information of the input configuration data lists of the question bank.

For example, the key source tag is a tag capable of representing key object features in the question bank input configuration data list, combining the same key source labels in all question bank input configuration data into a unit question bank input configuration data list according to the time sequence of the question bank input configuration data list, therefore, the label relevance among the plurality of unit question bank input configuration data lists can be converted into a structured cyclic dependency relationship according to the label relevance among the plurality of unit question bank input configuration data lists in the unit question bank input configuration data lists and the dependency among the plurality of unit question bank input configuration data lists, further, the first question bank label characteristic information matching the characteristic of each unit question bank input configuration data list in the first employment attribute distribution, wherein, each unit question bank input configuration data list corresponds to a first question bank label characteristic information.

Correspondingly, in the process of extracting the second question bank label characteristic information of the question bank output configuration data through the second employment attribute distribution, each request target subdata in the question bank output configuration data can be respectively input into the second employment attribute distribution, and the second question bank label characteristic information matched with the characteristic of each request target subdata is extracted through the first employment attribute distribution.

In a possible implementation manner, for step S150, in the process of performing label mapping association on the first distribution question bank object list and the second distribution question bank object list to obtain the distribution question bank object corresponding to the target question bank configuration service, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S151, performing weighted average on the distribution reference degrees associated with the objects belonging to the same distribution question bank in the first distribution question bank object list and the second distribution question bank object list, and performing label binding on the distribution reference degrees and the distribution question bank objects after weighted average to obtain a target distribution question bank object list.

And a substep S152 of extracting the distribution question bank object associated with the maximum distribution reference degree from the target distribution question bank object list, and using the extracted distribution question bank object as the distribution question bank object corresponding to the target question bank configuration service.

Further, the following briefly describes the training process of the second question bank distribution network with reference to a specific alternative example, and the training process of the first question bank distribution network may also be performed with reference to the following embodiments. The second question bank distribution network may be obtained by:

(1) and acquiring the first calibration label mapping correlation characteristic information and the second calibration label mapping correlation characteristic information.

(2) And extracting second question bank label characteristic information of the first calibration label mapping associated characteristic information, identifying the second question bank label characteristic information of the first calibration label mapping associated characteristic information and distribution reference degrees of a plurality of distribution question bank indexes in a second question bank distribution network according to question bank calling nodes in the second question bank distribution network, and labeling and binding the distribution reference degrees obtained by the second question bank label characteristic information of the first calibration label mapping associated characteristic information and distribution question bank objects corresponding to the plurality of distribution question bank indexes in the second question bank distribution network to obtain a third distribution question bank object list.

(3) And extracting second question bank label characteristic information of the second calibration label mapping associated characteristic information, identifying the second question bank label characteristic information of the second calibration label mapping associated characteristic information and the distribution reference degrees of a plurality of distribution question bank indexes according to question bank calling nodes in a second question bank distribution network, and labeling and binding the distribution reference degrees obtained by the second question bank label characteristic information of the second calibration label mapping associated characteristic information and distribution question bank objects corresponding to the plurality of distribution question bank indexes in the second question bank distribution network to obtain a fourth distribution question bank object list.

(4) And determining a loss function value according to the second question bank label characteristic information and the third distribution question bank object list of the first calibration label mapping correlation characteristic information, and the second question bank label characteristic information and the fourth distribution question bank object list of the second calibration label mapping correlation characteristic information, and adjusting model parameters in the second question bank distribution network according to the loss function value.

In one possible implementation, the above-mentioned loss function value may specifically include identifying a loss parameter value and verifying the loss parameter value.

Therefore, the identification loss parameter value of the first calibration label mapping associated feature information can be generated according to the third distribution question bank object list and the label distribution question bank index corresponding to the first calibration label mapping associated feature information.

And generating an identification loss parameter value of the second calibration label mapping associated characteristic information according to the fourth calibration label mapping associated characteristic information and the label distribution item base index corresponding to the fourth calibration label mapping associated characteristic information.

In addition, verification loss parameter values (e.g., loss parameter values between the second question bank label characteristic information of the first calibration label mapping associated characteristic information and the second question bank label characteristic information of the second calibration label mapping associated characteristic information, and loss parameter values between the label distribution question bank index corresponding to the first calibration label mapping associated characteristic information and the label distribution question bank index corresponding to the second calibration label mapping associated characteristic information) are generated according to the second question bank label characteristic information of the first calibration label mapping associated characteristic information, the label distribution question bank index corresponding to the second calibration label mapping associated characteristic information, and the label distribution question bank index corresponding to the second calibration label mapping associated characteristic information.

Thus, a loss function value can be generated based on the identification loss parameter value of the first calibration label mapping-related feature information, the identification loss parameter value of the second calibration label mapping-related feature information, and the verification loss parameter value (for example, the sum or weighted value of the identification loss parameter value of the first calibration label mapping-related feature information, the identification loss parameter value of the second calibration label mapping-related feature information, and the verification loss parameter value can be used as the loss function value).

In this embodiment, the second question bank distributing network is configured to output a second distributed question bank object list matching with second question bank tag feature information of the question bank output configuration data in the target question bank configuration service.

In this embodiment, the second distribution question bank object list is used to perform tag mapping association with the first distribution question bank object list to obtain a distribution question bank object corresponding to the target question bank configuration service.

In this embodiment, the first question bank object list is a label set output by the first question bank distribution network and matching with the first question bank label feature information of the question bank input configuration data list in the target question bank configuration service.

In a further possible implementation manner, for the foregoing step S110, in the process of obtaining employment information distribution associated with the talent employment model corresponding to the employment category partition obtained by the current talent employment statistics, the following exemplary sub-steps may be implemented, which are described in detail below.

Step S111, acquiring a talent employment model corresponding to the employment category partition acquired by the current talent employment statistics, acquiring current employment form-filling statistical information from a corresponding talent employment interface based on the talent employment module, and performing employment distribution node analysis on the current employment form-filling statistical information so as to analyze the current employment form-filling statistical information into current employment distribution node configuration information to acquire processed aggregated employment distribution node identification information.

Step S112, based on the aggregated employment distribution node identification information, generating a plurality of groups of employment distribution node configuration information sets of different employment categories, and respectively detecting employment behavior characteristics in the plurality of groups of employment distribution node configuration information sets of different employment categories to obtain employment behavior characteristic information in the plurality of groups of employment distribution node configuration information sets of different employment categories.

Step S113, determining employment distribution weight based on employment behavior characteristic information of a plurality of groups of employment distribution node configuration information sets of different employment categories and employment distribution node change information of aggregated employment distribution node identification information, mapping the employment behavior characteristic information of the plurality of groups of employment distribution node configuration information sets of different employment categories into the aggregated employment distribution node identification information, and obtaining a plurality of groups of employment distribution filling information.

And step S114, distributing a plurality of groups of employment distribution filling information according to the employment sharing behavior information among the employment behavior characteristic information to obtain the employment information distribution associated with the talent employment model.

For example, in step S111, employment requirement items in the current employment form-filling statistical information may be detected, target employment requirement items meeting the distribution statistical range of the employment form-filling statistical information are selected from the detected employment requirement items, employment distribution node distribution corresponding to the target employment requirement items is determined, and a recruitment requirement distribution list is constructed according to a recruitment requirement plan corresponding to the employment distribution node distribution, so that employment distribution node analysis may be performed on the current employment form-filling statistical information according to the recruitment requirement distribution list, so as to analyze the current employment form-filling statistical information into the current employment distribution node configuration information, and obtain processed aggregated employment distribution node identification information.

Fig. 3 is a schematic diagram of functional modules of the question bank pushing configuration device 300 of the talent employment model according to the embodiment of the present disclosure, and in this embodiment, the question bank pushing configuration device 300 of the talent employment model may be divided into functional modules according to the method embodiment executed by the server 100, that is, the following functional modules corresponding to the question bank pushing configuration device 300 of the talent employment model may be used to execute the method embodiments executed by the server 100. The question bank pushing configuration device 300 of the talent employment model may include an obtaining module 310, an associating module 320, a first identifying module 330, a second identifying module 340, and a configuration module 350, and the functions of the function modules of the question bank pushing configuration device 300 of the talent employment model are described in detail below.

The obtaining module 310 is configured to obtain employment information distribution associated with the talent employment model corresponding to the employment category partition obtained by the current talent employment statistics, obtain first question bank tag feature information of a question bank input configuration data list in the target question bank configuration service according to the employment information distribution, and obtain second question bank tag feature information of question bank output configuration data in the target question bank configuration service.

The association module 320 is configured to perform tag mapping association on the first question bank tag feature information of the question bank input configuration data list and the second question bank tag feature information of the question bank output configuration data to obtain tag mapping association feature information.

The first identification module 330 is configured to identify, according to the question bank calling node in the first question bank distribution network, the tag mapping association feature information and the distribution reference degrees of the multiple distribution question bank indexes in the first question bank distribution network, and perform label binding on the distribution reference degree obtained by the first question bank distribution network and the distribution question bank objects corresponding to the multiple distribution question bank indexes in the first question bank distribution network to obtain a first distribution question bank object list.

The second identification module 340 is configured to identify, according to the question bank calling node in the second question bank distribution network, the label mapping association feature information and the distribution reference degrees of the multiple distribution question bank indexes in the second question bank distribution network, and label-bind the distribution reference degree obtained by the second question bank distribution network and the distribution question bank objects corresponding to the multiple distribution question bank indexes in the second question bank distribution network to obtain a second distribution question bank object list, where the first question bank distribution network and the second question bank distribution network are configured to perform question bank distribution on the label mapping association feature information according to different question bank distribution categories.

The configuration module 350 is configured to perform tag mapping association on the first allocated question bank object list and the second allocated question bank object list to obtain an allocated question bank object corresponding to the target question bank configuration service, and process the target question bank configuration service according to the allocated question bank object.

Fig. 4 is a schematic diagram illustrating a hardware structure of a server 100 for implementing the question bank push configuration method of the talent employment model according to the embodiment of the present disclosure, and as shown in fig. 4, the server 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.

In a specific implementation process, the at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120, so that the processor 110 may perform the question bank pushing configuration method of the talent employment model according to the above method embodiment, where the processor 110, the machine-readable storage medium 120, and the transceiver 140 are connected through the bus 130, and the processor 110 may be configured to control the transceiving action of the transceiver 140, so as to perform data transceiving with the information device 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the server 100, which implement similar principles and technical effects, and this embodiment is not described herein again.

The machine-readable storage medium 120 may comprise high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

In addition, an embodiment of the present invention further provides a readable storage medium, where a computer execution instruction is stored in the readable storage medium, and when the processor executes the computer execution instruction, the question bank push configuration method of the talent employment model is implemented.

Finally, it should be understood that the examples in this specification are only intended to illustrate the principles of the examples in this specification. Other variations are also possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. The question bank pushing configuration method of the talent employment model is applied to a server, the server is in communication connection with a plurality of question bank service terminals, and the method comprises the following steps:

2. The talent employment model question bank pushing configuration method according to claim 1, wherein said obtaining a first question bank tag feature information of a question bank input configuration data list in a target question bank configuration service and obtaining a second question bank tag feature information of a question bank output configuration data in the target question bank configuration service according to the employment information distribution comprises:

3. The talent employment model question bank pushing configuration method according to claim 2, wherein said step of extracting a first question bank tag feature information of said question bank input configuration data list through said first employment attribute distribution comprises:

4. The talent employment model question bank pushing configuration method according to claim 2, wherein said extracting second question bank tag feature information of said question bank output configuration data through said second employment attribute distribution comprises:

5. The question bank pushing configuration method of the talent employment model according to claim 1, wherein the obtaining of the assignment question bank object corresponding to the target question bank configuration service by performing tag mapping association on the first assignment question bank object list and the second assignment question bank object list comprises:

6. The question bank pushing configuration method of the talent employment model according to any one of claims 1 to 5, wherein the second question bank distribution network is obtained by:

7. The question bank push configuration method of the talent employment model according to claim 6, wherein the loss function value comprises an identification loss parameter value and a verification loss parameter value;

8. The question bank pushing configuration method of the talent employment model according to any one of claims 1 to 5, wherein the step of obtaining employment information distribution associated with the talent employment model corresponding to the employment category partition obtained by the current talent employment statistics comprises:

9. The question bank pushing and configuring method of the talent employment model according to claim 8, wherein the step of performing employment distribution node parsing on the current employment fill-up statistical information to parse the current employment fill-up statistical information into current employment distribution node configuration information to obtain processed aggregated employment distribution node identification information comprises:

10. The question bank pushing configuration system of the talent employment model is characterized by comprising a server and a plurality of question bank service terminals in communication connection with the server;

the server is configured to: