CN117952585A - Post matching method, post matching device, electronic equipment and storage medium - Google Patents
Post matching method, post matching device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117952585A CN117952585A CN202311244755.1A CN202311244755A CN117952585A CN 117952585 A CN117952585 A CN 117952585A CN 202311244755 A CN202311244755 A CN 202311244755A CN 117952585 A CN117952585 A CN 117952585A
- Authority
- CN
- China
- Prior art keywords
- post
- matching
- value
- target object
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 42
- 230000006872 improvement Effects 0.000 claims abstract description 27
- 230000010365 information processing Effects 0.000 claims description 20
- 238000005516 engineering process Methods 0.000 description 22
- 238000004364 calculation method Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000013136 deep learning model Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 230000004899 motility Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a post matching method, a post matching device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a growth willingness value and a situation characteristic of a target object, and acquiring a post demand characteristic and a post capacity characteristic of a post to be processed; matching the situation characteristics and the post demand characteristics to obtain post matching values of the target object and the post to be processed; matching the situation characteristics and the post capability characteristics to obtain a capability lifting potential value of the post to be processed on the target object; processing the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters; according to the relation between the post comprehensive matching parameters of the post to be processed and the post comprehensive matching parameter threshold, prompt information for processing the post to be processed is sent to the terminal corresponding to the target object, so that whether the target object is suitable for the post to be processed or not can be accurately judged.
Description
Technical Field
The present application relates to the field of information processing, and in particular, to a post matching method, a post matching device, an electronic device, and a storage medium.
Background
In the related art, an enterprise generally needs to obtain a matching result through person post matching detection, so that whether a target object meets the skill requirement of a post is determined by using the matching result. This process typically uses a manual analysis to determine the ability of a person of a specified person type and determines the matching result for that person type to the post based on the ability of the person of the specified person type. The post matching detection is poor in accuracy, cannot adapt to the change of the individual situation characteristics of the user, cannot accurately match the situation and the post of the individual, and improves the comprehensiveness and the accuracy of the evaluation of the matching degree of the individual and the post.
Disclosure of Invention
In view of this, embodiments of the present application provide a post matching method, apparatus, electronic device, and storage medium, which can accurately determine whether a target object is suitable for a post to be processed by using a growth willingness value and a situation feature of the target object, and a post demand feature of the post to be processed and a post capability feature of the post to be processed.
The technical scheme of the embodiment of the application is realized as follows:
the embodiment of the application provides a post matching method, which comprises the following steps:
acquiring a growth willingness value and a situation characteristic of a target object, and acquiring a post demand characteristic and a post capacity characteristic of a post to be processed;
Matching the situation characteristics with the post demand characteristics to obtain post matching values of the target object and the post to be processed;
matching the situation characteristics with the post capability characteristics to obtain a capability lifting potential value of the post to be processed on the target object;
Processing the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters of the post to be processed;
and sending prompt information for processing the post to be processed to a terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold.
The embodiment of the application also provides a post matching device, which is characterized by comprising:
The information acquisition module is used for acquiring growth willingness values and situation characteristics of the target object and acquiring post demand characteristics and post capacity characteristics of the post to be processed;
the information processing module is used for matching the situation characteristics and the post demand characteristics to obtain post matching values of the target object and the post to be processed;
The information processing module is further used for matching the situation characteristics and the post capability characteristics to obtain a capability promotion potential value of the post to be processed on the target object;
The information processing module is further used for processing the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters of the post to be processed;
And the information processing module is used for sending prompt information for processing the post to be processed to the terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold.
The embodiment of the application also provides electronic equipment, which comprises:
A memory for storing executable instructions;
And the processor is used for realizing the post matching method when the executable instructions stored in the memory are operated.
The embodiment of the application also provides a computer readable storage medium which stores executable instructions, wherein the executable instructions realize the post matching method when being executed by a processor.
The embodiment of the application also provides a computer program product, which comprises a computer program or instructions, wherein the computer program or instructions realize the post matching method when being executed by a processor.
The embodiment of the application has the following beneficial effects:
According to the application, through obtaining the growth willingness value and the situation characteristics of the target object, the post demand characteristics of the post to be processed and the post capability characteristics of the post to be processed of the target object are obtained; matching the situation characteristics with the post demand characteristics to obtain post matching values of the target object and the post to be processed; the degree of adaptation of the target object and the position to be treated can thus be determined.
Further, matching the situation characteristics and the post capability characteristics to obtain a capability lifting potential value of the post to be processed on the target object; weighting the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters; and sending prompt information for processing the post to be processed to a terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold. Therefore, the improvement degree of the target object capacity of the to-be-processed post and the matching condition between the target object and the to-be-processed post can be determined by utilizing the situation characteristics of the target object, so that whether the target object is suitable for the to-be-processed post or not can be judged more accurately and rapidly by utilizing the growth wish value, the post matching value and the capacity improvement potential value, and further accurate and personalized post recommendation can be realized for different objects.
Drawings
FIG. 1 is a schematic diagram of a usage scenario of a post matching method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an implementation flow of a post matching method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of another alternative post matching method according to an embodiment of the present application;
FIG. 4 is a schematic flow chart of another alternative post matching method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device for executing the post matching method provided by the embodiment of the application.
Detailed Description
The present application will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
Before describing embodiments of the present application in further detail, the terms and terminology involved in the embodiments of the present application will be described first, and the terms and terminology involved in the embodiments of the present application are applicable to the following explanation.
1) Terminals, including but not limited to: the device comprises a common terminal and a special terminal, wherein the common terminal is in long connection or short connection with a sending channel, and the special terminal is in long connection with the sending channel.
2) The client, the carrier for realizing the specific function in the terminal, such as the mobile client (APP), is the carrier for realizing the specific function in the mobile terminal, such as the function of executing report making or the function of displaying report.
3) Cloud technology (Cloud technology) refers to a hosting technology for integrating hardware, software, network and other series resources in a wide area network or a local area network to realize calculation, storage, processing and sharing of data. The cloud computing business model application-based network technology, information technology, integration technology, management platform technology, application technology and the like can be collectively called to form a resource pool, and the resource pool is flexible and convenient as required. Cloud computing technology will become an important support. Background services of technical networking systems require a large amount of computing, storage resources, such as video websites, picture-like websites, and more portals. Along with the high development and application of the internet industry, each article possibly has an own identification mark in the future, the identification mark needs to be transmitted to a background system for logic processing, data with different levels can be processed separately, and various industry data needs strong system rear shield support and can be realized only through cloud computing.
4) A pre-trained language characterization model (Bidirectional Encoder Representations from Transformers, BERT), a language model training method that utilizes massive text. The method is widely used for various natural language processing tasks such as text classification, text matching, machine reading understanding and the like. It emphasizes that instead of pre-training as in the past using a conventional one-way language model or shallow stitching of two one-way language models, a new Masked Language Model (MLM) is used to enable deep two-way language characterization.
The inventor finds that when the matching of the target object and the post to be processed is carried out in the related technology, the application information and the past performance and behavior of the internal personnel are collected mainly through a manual method, the application information and the post demand information of the target object are matched, the matching result is combined with the past performance and behavior, and the matching degree of each internal personnel and the post is obtained according to subjective judgment.
In order to solve the defects, the application provides a post matching method which can make more accurate and rapid judgment on whether a target object is suitable for a post to be processed or not by using a growth willingness value, a post matching value and a capability lifting potential value.
Fig. 1 is a schematic diagram of an application scenario of a post matching method provided by the embodiment of the present application, referring to fig. 1, with the continuous development of computer technology, a cloud server may provide a safe and reliable elastic computing service, and may also provide different instance types to meet a target object specific post (e.g. a working post that needs to be checked for confidentiality) matching usage scenario. The terminals corresponding to the target object may include two different types of terminals or electronic devices, namely, the terminal 10-1 and the terminal 10-2, may be selected according to the use requirements of different information transmission usage scenarios, and as an example, the terminal 10-1 may upload the growth wish value and the situation characteristic of the target object to the server, and the terminal 10-2 may receive the prompt information of the replacement post sent by the server 200, where the prompt information of the replacement post is used to prompt the replacement post of the target object. The terminals (including the terminal 10-1 and the terminal 10-2) are provided with corresponding clients capable of executing the user information recording function, when the post matching method provided by the application is executed, the terminals (including the terminal 10-1 and the terminal 10-2) are required to send the growth willingness value and the situation characteristics of the target object to the server 200 at regular time, and meanwhile, the server 200 can store the post requirement characteristics of the post to be processed and the post capability characteristics of the post to be processed.
The terminal (including the terminal 10-1 and the terminal 10-2) can be connected with the server 200 through the network 300, the growth willingness value of the target object and the situation sub-characteristics of different dimensions can be transmitted by utilizing the information transmission path established by the network 300, the prompt information of changing the post and the prompt information of keeping the post unchanged can be received, the prompt information of keeping the post unchanged is used for prompting the target object to keep the post unchanged, the server 200 judges whether the post to be processed is suitable for the target object or not by utilizing the post comprehensive matching parameters and the post comprehensive matching parameter threshold value, and can also judge which post is the most suitable for the target object in a plurality of posts to be recommended and send the prompt information of the corresponding post to the target object. In this process, the terminal is connected to the server 200 through the network 300, where the network 300 may be a wide area network or a local area network, or a combination of both, and a wireless link is used to implement data transmission.
The embodiment of the application can be realized by combining Cloud technology, wherein Cloud technology (Cloud technology) refers to a hosting technology for integrating hardware, software, network and other series resources in a wide area network or a local area network to realize calculation, storage, processing and sharing of data, and can also be understood as a general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied based on a Cloud computing business mode. Background services of technical network systems require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites, so cloud technologies need to be supported by cloud computing.
It should be noted that cloud computing is a computing mode, which distributes computing tasks on a resource pool formed by a large number of computers, so that various application systems can acquire computing power, storage space and information service as required. The network that provides the resources is referred to as the "cloud". Resources in the cloud are infinitely expandable in the sense of users, and can be acquired at any time, used as needed, expanded at any time and paid for use as needed. As a basic capability provider of cloud computing, a cloud computing resource pool platform, referred to as a cloud platform for short, is generally called an infrastructure as a service (IaaS Infrastructure AS A SERVICE), and multiple types of virtual resources are deployed in the resource pool for external clients to select for use. The cloud computing resource pool mainly comprises: computing devices (which may be virtualized machines, including operating systems), storage devices, and network devices. And assigning different operation authorities to the target objects subjected to the post matching through the cloud server.
Cloud storage (cloud storage) is a new concept that extends and develops in the concept of cloud computing, and a distributed cloud storage system (hereinafter referred to as a storage system for short) refers to a storage system that integrates a large number of storage devices (storage devices are also referred to as storage nodes) of various types in a network to work cooperatively through application software or application interfaces through functions such as cluster application, grid technology, and a distributed storage file system, so as to provide data storage and service access functions for the outside. In the related art, the storage method of the storage system is as follows: when creating logical volumes, each logical volume is allocated a physical storage space, which may be a disk composition of a certain storage device or of several storage devices. The client stores data on a logical volume, that is, the data is stored on a file system, the file system divides the data into a plurality of parts, each part is an object, the object not only contains the data but also contains additional information such as a data identifier (ID IDENTITY), the file system writes each object into a physical storage space of the logical volume, and the file system records storage location information of each object, so that when the client requests to access the data, the file system can enable the client to access the data according to the storage location information of each object. The process of allocating physical storage space for the logical volume by the storage system specifically includes: physical storage space is divided into stripes in advance according to the set of capacity measures for objects stored on a logical volume (which measures tend to have a large margin with respect to the capacity of the object actually to be stored) and redundant array of independent disks (RAID Redundant Array of INDEPENDENT DISK), and a logical volume can be understood as a stripe, whereby physical storage space is allocated for the logical volume.
Referring to fig. 2, fig. 2 is a schematic flow chart of an implementation of a post matching method according to an embodiment of the present application, and it can be understood that an execution body of the steps shown in fig. 2 may be implemented by a terminal running a post matching device alone or by a server running the post matching device. The servers referred to herein may comprise individual physical servers, a server cluster consisting of a plurality of servers, or cloud servers capable of cloud computing. The following is a description of the steps shown in fig. 2.
Step 201: and acquiring a growth willingness value and a situation characteristic of the target object, and acquiring a post demand characteristic and a post capacity characteristic of the post to be processed.
The post to be treated may include the following cases: the current position of the target object (whether the target object is matched with the current position of the target object or not can be judged by the position matching method shown in fig. 2), the position to be recommended (at least one application position can be recommended to the target object by the position matching method shown in fig. 2), and in the following embodiments, different conditions of the positions to be processed are respectively described.
In some embodiments, the greater the growth willingness value of the target object is used to characterize the subjective motility of the target object, the stronger the growth willingness value is indicative of the subjective motility of the target object. The growth willingness value of the target object can be recorded in an individual growth record table, and the growth willingness value of the target object can be obtained by the following modes:
Acquiring historical growth willingness values of a target object in different historical stages; determining an average value of historical growth willingness values of the target object at different stages; and determining an average value of the historical growth willingness values of the target object at different stages as the growth willingness value of the target object. The individual growth record table can record the growth willingness values of the target object in different historical stages, and meanwhile, the growth process of the target object is different, so that the average value of the historical growth willingness values of the target object in different stages needs to be determined, and the average value of the historical growth willingness values is used for determining the growth willingness values of the target object, so that the subjective activity of the growth process of the target object can be better represented.
For example, the target object includes together at different history phases: the historical growth willingness value of the target object can be determined to be 4 (namely, the historical growth willingness average value of the stages 1-3) when the historical growth willingness value of the target object is greater, namely, the subjective activity of the growth process of the target object is stronger, wherein the historical growth willingness value of the stage 1 is 5, the historical growth willingness value of the stage 2 is 2, and the historical growth willingness value of the stage 1 is 5.
In some embodiments, the growth willingness value of the target object may be recorded in the individual growth record table, where the individual growth record table may further include the achievement of the target object in each subject of the student age, interests (the more the value ranges 1-5, the greater the number of interests), features (the more the value ranges 1-5, the greater the number of features, the greater the value), characters (the value ranges 1-5), working experiences (the value ranges 1-5), and done item information (the value ranges 1-5); the historical growth willingness value can be determined by the weighted average value of the achievement, interest, specialty, character, working experience and done project information of each subject in the student age, and the acquisition mode and the expression form of the growth willingness value of the target subject are not particularly limited.
In some embodiments, the contextual features may be used to describe the state of life of the target object, where the contextual features may include N-dimensional contextual sub-features such as: age of the target object, family condition, wedding condition, emotional condition, work ability, difficulty of the current position at present, and workload level of the current position.
In some embodiments, the post demand feature of the post to be processed is used to characterize what capabilities the target object required to execute the post to be processed has, e.g., the post demand feature of the post to be processed may include highest academic demand information, highest academic professional demand information, highest academic school type demand information, foreign language demand information, working year demand information, post sequence demand information, credit customer manager post sequence demand information, statistical loan gain demand information, bad loan rate demand information, and the like.
Specifically, the server can extract keywords of the to-be-processed post, and obtain post requirement information corresponding to the to-be-processed post in a preset post requirement information database according to the keywords of the to-be-processed post. For example, when the post to be processed is sold outwards, the post requirement information is that at least five foreign languages are understood; when the post to be processed is a research and development post, the post requirement information is a learning master and above, and the related software research and development working experience is five years.
In some embodiments, the post-processing post capability features are used to characterize what capabilities the target object may have after the post-processing post has been in operation for a period of time (optionally 3 months), for example: when the post to be processed is sold outwards, the post capability characteristics can be: communicating with the sales object through a plurality of foreign languages; when the post to be processed is a research and development post, the capability features may be: a software module with XX functionality was developed.
Step 202: and matching the situation characteristics and the post demand characteristics to obtain post matching values of the target object and the post to be processed.
In some embodiments, the situation feature may include N-dimensional situation sub-features, the post demand feature may include M-dimensional post demand sub-features, and the situation feature and the post demand feature are matched to obtain a post matching value of the target object and the post to be processed, which may be implemented by:
Performing feature matching on the situation sub-features of each dimension and the post requirement sub-features of the corresponding dimension through a working matching degree model to obtain matching values of the situation sub-features of each dimension; and processing the matching values of the situation sub-features of the N dimensions to obtain the post matching values of the target object and the post to be processed. Optionally, the average value operation can be performed on the matching values of the situation sub-features of the N dimensions, and the operation result is used as the post matching value of the processing post. The work matching degree model can be a BERT model, feature matching is performed on the situation sub-feature of each dimension in the situation sub-features of different dimensions and the requirement sub-feature of the corresponding dimension in the post requirement features by using the BERT model, and the matching value of the situation sub-feature of each dimension can be determined by performing semantic similarity of the situation sub-feature of each dimension and the requirement sub-feature of the corresponding dimension in the post requirement features in a feature matching and character ratio peer-to-peer mode. The matching value can be represented by 1 or 0, and if the situation sub-feature and the post requirement sub-feature of one dimension are matched, the matching value of the situation sub-feature of the dimension is 1; and vice versa is 0.
Wherein, because the dimension of the situation sub-feature is N, the dimension of the post capability sub-feature is M, the following situations may occur: in the first case, for each dimension of the situation sub-feature, the post capability sub-feature of the corresponding dimension can be determined, for example, the N dimensions comprise a working experience dimension and an age dimension, and the post capability sub-feature also comprises the working experience dimension and the age dimension; in a second scenario, there may be some dimensions of the situation sub-feature for which there is no post capability sub-feature of the corresponding dimension matching, such as N dimensions including a work experience dimension and an age dimension, but M dimensions of post capability sub-features including a work experience dimension but not an age dimension.
For the first case described above, the place sub-feature of each dimension has a post requirement sub-feature of the corresponding dimension, and for the second case, for the target dimension, there is a place sub-feature in the target dimension, but there is no post requirement sub-feature, a default value may be taken as the post requirement sub-feature of the target dimension, and the default value may be determined according to the matching value definition of the place sub-feature of the target dimension. For example, if the matching value of the situation sub-feature of the target dimension is defined as 1, the default value is set as follows: when the default value is matched with the situation sub-feature of the target dimension, the matching result should be 1; otherwise, the default setting rules are: when the default value matches the situation sub-feature of the target dimension, the matching result should be 0.
The BERT model, which is a deep learning model, has higher accuracy and calculation speed, and thus can be adopted as an alternative embodiment in the embodiment of the present application. The BERT model is a pre-training language model, and through a large amount of data training, the model can extract relation features at a plurality of different levels, acquire word senses according to sentence contexts, avoid ambiguity, and further reflect the semantics of sentences more comprehensively. It should be noted that, the work matching degree model not only can be a BERT model, but also can be a neural network model for realizing similarity judgment between feature vectors.
In the application, the BERT model used as the work matching degree model is obtained through pre-training, for example, a large number of user growth record document data (such as basic information, job intention, work experience, education experience, scientific research direction, academic result, self evaluation and the like) and post demand information (such as recruitment objects, school types, graduation time, professional ability, project experience and the like) are selected as training sample sets of the BERT model, a part of the user growth record document data and post demand information are randomly covered, the matching degree of the position demand information of the situation sub-features of different dimensions is predicted by the BERT model through adjusting parameters of the model, then a preset threshold is finally reached through repeated iterative training, and the BERT model reaching the preset threshold is used as a trained work matching degree model and is deployed in a corresponding server.
For example, taking a BERT model as an example, when the job matching degree model is a BERT model, the post to be processed is sold to the outside, the post demand features may be: the situation sub-features of N dimensions are as follows, communicating with sales objects through multiple foreign languages (weight 0.5), ages 25-30 (weight 0.5): working ability (mastering english, japanese), age 25; the N dimensions can comprise a working capacity dimension and an age dimension, the characteristics of each dimension are matched through a working matching degree model, the matching value of the situation sub-characteristics of each dimension is 1, weighted average calculation is carried out on the matching value of the situation characteristics of each dimension, and the position matching value of the target object and the position to be processed is determined to be 100%.
For another example, when the post to be processed is sold to the outside, the post demand feature may be: the communication with sales objects is carried out through a plurality of foreign languages, the ages are 25-30 years, and the situation sub-features with different dimensions comprise: working capacity (mastering English and Japanese), matching the characteristics of each dimension by the age 35 through a working matching degree model to obtain a matching value of the situation characteristics of the working capacity dimension as 1, a matching value of the situation characteristics of the age dimension as 0, carrying out arithmetic average calculation on the matching value of the situation sub-characteristics of each dimension, and determining that the post matching value of the target object and the post to be processed is 50%.
Step 203: and matching the situation characteristics and the post capability characteristics to obtain the capability promotion potential value of the post to be processed on the target object.
In one embodiment, the contextual features may include N-dimensional contextual sub-features and the post capability features may include P-dimensional post capability sub-features; n and P are integers greater than 1. Here, the corresponding situation between the N different-dimension situation sub-features and the P-dimension post capability sub-features may refer to the explanation of the N-dimension situation sub-features and the M post requirement sub-features in step S202, which are not described in detail herein.
For example: when the post to be processed is sold to the outside, the post capability features can comprise the following post capability sub-features in multiple dimensions: through exchanging with sales objects through a plurality of foreign languages (this is the working ability dimension), the psychological change of the sales objects (belonging to the personal feature skill dimension) is known, and at this time, the corresponding situation features are as follows: foreign language work ability, psychological information acquisition ability; when the post to be processed is a development post, the post capability features may include post capability sub-features of multiple dimensions: developing a software module with XX function, searching for XX type error information, and sequentially adopting the following corresponding situation characteristics: developing working capacity and correcting working capacity.
In one embodiment, the step S203 of matching the situation feature and the post capability feature to obtain the capability promotion potential value of the to-be-processed post to the target object may include the following steps S301-S304:
Step 301: and carrying out feature matching on the situation sub-features of each dimension and the post capability sub-features of the corresponding dimension through a working back feeding model to obtain post capability matching values of each dimension.
In some embodiments, the work-in-feed model may be a BERT model, and the feature matching of the BERT model to the position capability sub-feature of each dimension in the position capability features and the position capability sub-feature of the corresponding dimension in the position capability features is only an optional implementation manner, and the matching value of the position sub-feature of each dimension may be determined by the semantic similarity of the position sub-feature of each dimension and the requirement sub-feature of the corresponding dimension in the position requirement features in a feature matching and character ratio peer-to-peer manner, so that the BERT model is used as a deep learning model, has higher accuracy and calculation speed, and therefore may be adopted as an optional embodiment in the embodiments of the present application.
Step 302: and processing the post capability matching values of the N dimensions to obtain the post capability matching value of the target object.
Optionally, the post capability matching values of the N dimensions are processed to obtain a post capability value of the target object, which may be that the post capability matching values of the N dimensions are subjected to mean operation, and the result of the mean operation is used as the post capability matching value of the target object.
In some embodiments, taking the example of the work-backfeeding model being a BERT model, when the post to be treated is an outward sales, the post capability features may be: through exchanging with sales objects through a plurality of foreign languages, the psychological state of the user can be known, and the situation sub-features of different dimensions comprise: language working ability (mastering English and Japanese) and psychological acquisition working ability (psychological working ability), the characteristics of each dimension are matched through a working back feeding model, the language working ability matching value of a target object is 1, the psychological working ability matching value is 1, the matching value of the situation sub-characteristics of each dimension is calculated by arithmetic mean, and the position ability matching value of the target object is determined to be 100%.
In some embodiments, taking the example of the work-backfeeding model being a BERT model, when the post to be treated is an outward sales, the post capability features may be: through exchanging with sales objects through a plurality of foreign languages, the psychological state of the user can be known, and the situation sub-features of different dimensions comprise: language working ability (mastering English, having psychological acquisition working ability (psychological working ability), matching the characteristics of each dimension through a working back feeding model to obtain a language working ability matching value of 0 (weight of 0.5) of a target object, wherein the psychological working ability matching value is 1 (weight of 0.5), carrying out weighted average calculation on the matching values of the situation sub-characteristics of each dimension, and determining that the post capability matching value of the target object is 50%.
Step 303: and encoding the post capability features to obtain post capability feature values corresponding to the post capability features.
In some embodiments, taking the example that the work back feeding model is a BERT model, a coding layer may be added to the BERT model, and the coding layer is used for coding the post capability feature to obtain a post capability feature value corresponding to the post capability feature, so that the post capability feature value corresponding to the post capability feature is obtained after the post capability matching value of the target object is output in the BERT model.
Step 304: and determining the difference value between the post capability characteristic value and the post capability matching value as a capability lifting potential value.
In some embodiments, taking the example of the work-backfeeding model being a BERT model, when the post to be treated is an outward sales, the post capability features may be: through exchanging with sales objects through a plurality of foreign languages, the psychological state of the user can be known, and the situation sub-features of different dimensions comprise: language working ability (mastering English, having psychological acquisition working ability (psychological working ability), matching each dimension characteristic through a working back feeding model to obtain a language working ability matching value of 0 (weight is 0.5) of a target object, carrying out weighted average calculation on the matching value of each dimension situation sub-characteristic to determine that the position ability matching value of the target object is 50%, and coding the position ability characteristic through a coding layer added by a BERT model to obtain a position ability characteristic value corresponding to the position ability characteristic as 1, wherein the difference value between the calculated position ability characteristic value and the position ability matching value is 50%, namely, the ability improvement potential value is 50%, and when the position is treated by a bearing magnanimous, the ability improvement of the target object can be improved by 50%.
After the capability improvement potential value is obtained through the processing of steps 301-304, the post comprehensive matching parameters can be calculated through step 204.
Step 204: and processing the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters.
In some embodiments, the processing herein may be referred to as weighting processing. Because the growth willingness values of the target objects are different, the situation dimensions are different, so that judging whether the to-be-processed position is suitable for the target object cannot depend on the position matching value only, and judging whether the to-be-processed position is suitable for the target object can comprise the following various conditions:
1) The growth willingness value of the target object is low, the post matching value is low, and the capacity improvement potential value is low;
2) The growth willingness value of the target object is low, the post matching value is high, and the capacity improvement potential value is low;
3) The growth willingness value of the target object is low, the post matching value is high, and the capacity improvement potential value is high;
4) The growth willingness value of the target object is high, the post matching value is low, and the capacity improvement potential value is low;
5) The growth willingness value of the target object is high, the post matching value is low, and the capacity improvement potential value is high;
6) The growth willingness value of the target object is high, the post matching value is high, and the capacity improvement potential value is low.
In each of the above embodiments, the growth willingness value, the post matching value, and the capability promotion potential value affect whether the target object is suitable for the post to be processed, and for this purpose, a post comprehensive matching parameter needs to be obtained through weighting processing to determine whether the target object is suitable for the post to be processed.
In some embodiments, the processing of the growth willingness value, the post matching value, and the capability promotion potential value to obtain post comprehensive matching parameters may be implemented by:
Acquiring a first weight corresponding to the growth willingness value, a second weight corresponding to the post matching value and a third weight corresponding to the capacity lifting potential value; and calculating the growth willingness value, the post matching value and the capacity lifting potential value according to the first weight, the second weight and the third weight to obtain the post comprehensive matching parameters of the post to be processed. For example, a weighted average operation may be performed.
Specifically, a first weight corresponding to a growth willingness value, a second weight corresponding to a post matching value and a third weight corresponding to a capacity lifting potential value are obtained; weighting the growth willingness value according to the first weight to obtain a weighted growth willingness value; weighting the post matching value according to the second weight to obtain a weighted post matching value; weighting the capacity lifting potential value according to the third weight to obtain a weighted capacity lifting potential value; and carrying out arithmetic average on the weighted growth willingness value, the weighted post matching value and the weighted capacity lifting potential value to obtain post comprehensive matching parameters.
The growth willingness value is b, the post matching value is c, the capacity lifting potential value is d, the first weight corresponding to the growth willingness value is a1, the second weight corresponding to the post matching value is a2, and the third weight corresponding to the capacity lifting potential value is a3. Through the calculation, the weighted growth willingness value is determined to be b×a1, the weighted post matching value is determined to be c×a2, the weighted capacity boosting potential value is determined to be d×a3, and the post comprehensive matching parameter can be calculated through the following formula:
post comprehensive matching parameter= (b×a1+c×a2+d×a3)/3
In some embodiments, the relationship between the first weight corresponding to the growth willingness value, the second weight corresponding to the post matching value, and the third weight corresponding to the capacity boosting potential value includes the following:
1) When the post matching value is greater than the post matching value threshold, the post to be processed is possibly suitable for the target object, so that the first weight, the second weight and the third weight are respectively determined to be preset weights, namely, the first weight corresponding to the growth willingness value is a1, the second weight corresponding to the post matching value is a2, the third weight corresponding to the capacity lifting potential value is a3 which are the same (all are 1/3), and the influence of the growth willingness value b and the capacity lifting potential value d on the suitability of the post to be processed to the target object can be determined by respectively determining the first weight, the second weight and the third weight as preset weights.
2) When the post matching value is smaller than or equal to the post matching value threshold, it is indicated that the post to be processed may not be suitable for the target object, so that a preset weight list is queried according to the identification of the post to be processed, and the first weight, the second weight and the third weight are acquired from the weight list, wherein the first weight is larger than the second weight, and the third weight is larger than the second weight, that is, the first weight a1 corresponding to the growth willingness value, the second weight a2 corresponding to the post matching value and the third weight a3 corresponding to the capacity lifting potential value may be different, wherein the first weight a1 is larger than the second weight a2, and the third weight a3 is larger than the second weight a2 (the third weight a3 and the first weight a1 are randomly related), so that the influence of the growth willingness value b and the capacity lifting potential value d on the suitability of the post to be processed to the target object can be highlighted, and the growth potential more suitable for the target object or the capacity lifting potential can be selected.
Step 205: and sending prompt information for processing the post to be processed to a terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold.
In some embodiments, in the case that the post to be processed includes the current post where the target object is currently located, it is necessary to determine whether the target object is suitable for the current post, so when the post comprehensive matching parameter is less than or equal to the post comprehensive matching parameter threshold, a prompt message for replacing the post is sent to a terminal corresponding to the target object, and the target object can be prompted to replace the post in time by the sent prompt message for replacing the post, so that the target object is guaranteed to obtain a post suitable for the target object in time.
In some embodiments, when the post comprehensive matching parameter is greater than the post comprehensive matching parameter threshold, a prompt message for keeping the post unchanged is sent to the terminal of the target object, and the target object can be prompted to keep the post unchanged by the sent prompt message for keeping the post unchanged, so that the target object can timely learn that the current post is the post most suitable for the target object. The growth willingness value is b, the post matching value is c, the capacity lifting potential value is d, the first weight corresponding to the growth willingness value is a1, the second weight corresponding to the post matching value is a2, and the third weight corresponding to the capacity lifting potential value is a3. Through the calculation, the weighted growth willingness value is determined to be b+a1, the weighted post matching value is determined to be c+a2, the weighted capacity boosting potential value is determined to be d+a3, the post comprehensive matching parameter is determined to be b+a1+c2+da3/3, and the post comprehensive matching parameter threshold is determined to be 0.5. As shown in the foregoing embodiment, the growth willingness values of the target objects are different, and the situation dimensions are different, so that determining whether the to-be-processed post is suitable for the target object cannot depend on the post matching value alone, and when whether the to-be-processed post is suitable for the target object can include multiple situations, the comparison result with the post comprehensive matching parameter threshold value of 0.5 may include: 1) The growth willingness value of the target object is low, the post matching value is low, the capacity improvement potential value is low, and the post comprehensive matching parameter is 0.4; 2) The growth willingness value of the target object is low, the post matching value is high, the capacity improvement potential value is low, and the post comprehensive matching parameter is 0.3; 3) The growth willingness value of the target object is low, the post matching value is high, the capacity improvement potential value is high, and the post comprehensive matching parameter is 0.5; 4) The growth willingness value of the target object is high, the post matching value is low, the capacity improvement potential value is low, and the post comprehensive matching parameter is 0.4; 5) The growth willingness value of the target object is high, the post matching value is low, the capacity improvement potential value is high, and the post comprehensive matching parameter is 0.7; 6) The growth willingness value of the target object is high, the post matching value is high, the capacity lifting potential value is low, and the post comprehensive matching parameter is 1; the growth willingness value, the post matching value and the capability promotion potential value in each case in the above embodiment affect whether the target object is suitable for the post to be processed, and by comparing with the post comprehensive matching parameter threshold (0.5), the server can more accurately and rapidly judge whether the target object is suitable for the post to be processed.
Therefore, through the processing of the steps 201-205, whether the target object is suitable for the to-be-processed post is judged more accurately and rapidly by using the growth willingness value, the post matching value and the capability lifting potential value, the target object can be enabled to know own capability and situation characteristics more clearly and the necessity of whether to replace the post is known more fully.
After determining whether the target object is suitable for the post to be processed through the processing in step 201-step 205, if the post to be processed includes the post to be recommended, the target object may also be recommended with a prompt message of at least one application post for the target object to select.
Referring to fig. 3, fig. 3 is another optional flowchart of a post matching method according to an embodiment of the present application, which specifically includes the following steps:
step 401: and acquiring the post demand characteristics of each post to be processed and the post capacity characteristics of each post to be processed.
In some embodiments, the post demand characteristics for each post to be processed may be stored in the post demand characteristics database in the form of a post demand characteristics data table, wherein the post demand characteristics data table refers to table 1:
table 1 post demand feature data sheet
The post capability features for each post to be processed may be stored in the post capability feature database in the form of a post capability feature data table, wherein the post capability feature data table references table 2:
Table 2 post capability feature data sheet
Step 402: and determining the comprehensive matching parameters of the target object and the posts of each post to be processed according to the post demand characteristics of each post to be processed, the post capability characteristics of each post to be processed, the growth willingness value of the target object and the situation sub-characteristics of different dimensions.
In some embodiments, the growth willingness values of the target objects can be derived from 4 databases, namely a basic information database, an educational history database, a work history database and a skill specialty database, wherein the basic information database contains keywords corresponding to basic information parts, such as basic information, personal profile, basic information, age, gender, identity information and the like; the educational experience database contains keywords corresponding to the educational experience part, such as 'graduate universities, in school experiences, in-school experiences, community activities, student works, educational practices, scientific research papers, scientific research directions, academic achievements, winning conditions, professional ability, main maintenance courses, in-school tasks, practice researches' and the like; the work experience database contains keywords corresponding to the work experience part, such as 'work background, work experience, professional experience, project introduction, project experience', and the like; the skill feature database contains keywords corresponding to the skill feature part, such as "C language, java, c++" and the like, and the application is not limited to the source of the growth willingness value.
Step 403: and sequencing the post comprehensive matching parameters of each post to be processed, and screening the post to be recommended, the post comprehensive matching parameters of which are larger than the post comprehensive matching parameter threshold value, as the application post according to the sequencing result.
In some embodiments, taking the post to be treated as the outward sales 1 and the outward sales 2 as examples, when the post to be treated is the outward sales 1, the post demand feature may be: communicating with sales subjects through 2 foreign languages, ages 25-30 years old; the post capability is characterized in that: the sales volume exceeds 100 ten thousand yuan per month, the psychological change of a sales object can be timely known, the growth willingness value of a target object a is 5, and the situation sub-features of different dimensions comprise: age of target object a, status of mating of target object a, and work ability of target object a.
When the post to be processed is sales 2, the post demand feature may be: communicate with sales subjects through 3 foreign languages, ages 35-40, post capability features: the sales volume exceeds 500 ten thousand yuan per month, the psychological change of a sales object can be timely known, the growth willingness value of a target object a is 4, and the situation sub-features of different dimensions comprise: age of target object a, status of mating of target object a, and work ability of target object a. And determining that the comprehensive matching parameter of the target object a and the position of the outward sales 1 is 0.5, and determining that the comprehensive matching parameter of the target object a and the position of the outward sales 2 is 0.75, so that the position of the outward sales 2 can be recommended to the target object a, and more proper position recommendation to the target object is realized.
Step 404: and sending the prompting information of the application position to a terminal corresponding to the target object.
The target object can determine the most suitable target position according to the prompting information of the application position received by the terminal, so that the application position can be obtained more quickly and accurately. When the post comprehensive matching parameter is smaller than or equal to the post comprehensive matching parameter threshold, the post to be processed and the target object are not adapted at the moment, and the application post adapted to the target object can be selected for recommendation to the target object in different posts to be processed through the processing of the steps 401-404, so that the time consumption for inquiring and judging the suitability of the target object is saved.
In order to better illustrate the working process of the post matching method provided by the present application, the working process of the post matching method provided by the present application is described below by taking a target object as a and a post to be processed as a programmer as an example, and referring to fig. 4, fig. 4 is another optional flow diagram of the post matching method provided by the embodiment of the present application, which specifically includes the following steps:
Step 501: an individual growth record table is dynamically maintained.
The individual growth record table can comprise the score, interest and special length of each subject in the student age of the target object a, character, work experience and number of done projects, and meanwhile, the growth willingness value of the target object can be recorded in the individual growth record table. For example, the target object includes together at different history phases: the historical growth willingness value of the target object can be determined to be 4 (namely, the historical growth willingness average value of the stages 1-3) when the historical growth willingness value of the target object is greater, namely, the subjective activity of the growth process of the target object is stronger, wherein the historical growth willingness value of the stage 1 is 5, the historical growth willingness value of the stage 2 is 2, and the historical growth willingness value of the stage 1 is 5.
Step 502: the current situational characteristics of the individual of the target object a are acquired.
The current situation of the target object a comprises: individual age, family condition, child-bearing condition, emotional condition, work capacity, difficulty of current work, and workload level.
Step 503: and inputting the current situation characteristics of the individuals into a work matching degree model.
The work matching degree model may be a BERT model, and feature matching is performed on the situation sub-feature of each dimension in the situation sub-features of different dimensions and the requirement sub-feature of the corresponding dimension in the post requirement features by using the BERT model, which is only an optional implementation manner, and the matching value of the situation sub-feature of each dimension may be determined by the semantic similarity of the situation sub-feature of each dimension and the requirement sub-feature of the corresponding dimension in the post requirement features in a feature matching and character ratio peer-to-peer manner, so that the BERT model is used as a deep learning model, and has higher accuracy and calculation speed, and therefore, the method and the device can be adopted as an optional embodiment, and the work matching degree model may be trained by the human situation features of different target objects before executing step 503.
Step 504: and obtaining a matching value of the individual and the post to be processed, and judging whether the target object a is suitable for the current work according to the matching value and a set threshold value.
In some embodiments, since the growth willingness values of the target objects are different, the situation dimensions are different, so that determining whether the to-be-processed post is suitable for the target object cannot depend on the post matching value alone, and determining whether the to-be-processed post is suitable for the target object may include determining the corresponding weights for the growth willingness values, the post matching value, and the capability-improvement potential value through the processing of step 504.
Step 505: the current situational characteristics of the target object a are entered into the work backfeeding model.
In some embodiments, the work-in-feed model may be a BERT model, and performing feature matching on the situation sub-feature of each dimension in the situation sub-features of different dimensions and the requirement sub-feature of the corresponding dimension in the post requirement feature by using the BERT model is only an optional implementation manner, and the matching value of the situation sub-feature of each dimension and the semantic similarity of the situation sub-feature of each dimension and the requirement sub-feature of the corresponding dimension in the post requirement feature may also be determined by performing feature matching and character comparison in a peer-to-peer manner, where the BERT model is used as a deep learning model, and has higher accuracy and calculation speed, so that the method of the application may be adopted as an optional embodiment.
Step 506: and acquiring the potential value of the current work for improving the individual capacity.
In some embodiments, the capacity boost potential value is 50%, indicating that the capacity boost of the target object may be 50% when the carrier magnanimous treatment post is sold to the outside.
Step 507: and determining whether the target object a needs to change the working position or not by weighting the matching degree of the individual and the position to be processed, the capacity improvement potential value and the individual growth wish.
When the post comprehensive matching parameter is smaller than or equal to the post comprehensive matching parameter threshold, determining a target object replacement post; when the post comprehensive matching parameter is greater than the post comprehensive matching parameter threshold, determining that the target object does not need to replace the post, the comprehensive matching parameter threshold may be stored in the server, and the comprehensive matching parameter threshold corresponds to each post, for example: the comprehensive matching parameter threshold of the programmer's post is 0.5, and the comprehensive matching parameter threshold of the sales post is 0.2. When the target object is determined to need to change the post or keep the post, corresponding voice prompt information or text prompt information can be sent to the terminal corresponding to the target object, and the target object is prompted to need to change the post or keep the post through the voice prompt information or the text prompt information. Therefore, through the processing from step 501 to step 507, a better-adaptability post can be recommended to the target object, so that the basis for adjusting the post by the target object is more sufficient, and the post adapted by the target object can be known more quickly.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device for executing the post matching method provided by the embodiment of the present application, and the electronic device 100 shown in fig. 5 includes: at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. The various components in the electronic device 100 are coupled together by a bus system 440. It is understood that the bus system 440 is used to enable connected communication between these components. The bus system 440 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration the various buses are labeled in fig. 5 as bus system 440.
The Processor 410 may be an integrated circuit chip having signal processing capabilities such as a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., where the general purpose Processor may be a microprocessor or any conventional Processor, etc.
The user interface 430 includes one or more output devices 431, including one or more speakers and/or one or more visual displays, that enable presentation of the media content. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.
Memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard drives, optical drives, and the like. Memory 450 optionally includes one or more storage devices physically remote from processor 410.
Memory 450 includes volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory. The non-volatile Memory may be a Read Only Memory (ROM) and the volatile Memory may be a random access Memory (Random Access Memory, RAM). The memory 450 described in embodiments of the present application is intended to comprise any suitable type of memory.
In some embodiments, memory 450 is capable of storing data to support various operations, examples of which include programs, modules and data structures, or subsets or supersets thereof, as exemplified below.
An operating system 451 including system programs, e.g., framework layer, core library layer, driver layer, etc., for handling various basic system services and performing hardware-related tasks, for implementing various basic services and handling hardware-based tasks;
A network communication module 452 for accessing other electronic devices via one or more (wired or wireless) network interfaces 420, the exemplary network interface 420 comprising: bluetooth, wireless compatibility authentication (WiFi), universal Serial Bus (USB), etc.;
a presentation module 453 for enabling presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 431 (e.g., a display screen, speakers, etc.) associated with the user interface 430;
An input processing module 454 for detecting one or more user inputs or interactions from one of the one or more input devices 432 and translating the detected inputs or interactions.
In some embodiments, the apparatus provided in the embodiments of the present application may be implemented in software, and fig. 5 shows a post matching device 455 stored in a memory 450, which may be software in the form of a program, a plug-in, or the like, including the following software modules: the information acquisition module 4551 and the information processing module 4552 are logical, and thus may be arbitrarily combined or further split according to the functions to be implemented. The functions of the respective modules will be described hereinafter.
The information acquisition module 4551 is configured to acquire a growth willingness value and a situation characteristic of a target object, and acquire a post demand characteristic and a post capability characteristic of a post to be processed;
the information processing module 4552 is configured to match the situation feature and the post demand feature to obtain a post matching value of the target object and the post to be processed;
The information processing module 4552 is further configured to match the situation feature and the post capability feature to obtain a capability promotion potential value of the post to be processed on the target object;
the information processing module 4552 is further configured to process the growth willingness value, the post matching value, and the capability improvement potential value to obtain post comprehensive matching parameters;
The information processing module 4552 is further configured to send, to a terminal corresponding to the target object, a prompt message for processing the post to be processed according to a relationship between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold.
In some embodiments, the contextual features include N-dimensional contextual sub-features, and the post demand features include M-dimensional demand sub-features; n and M are integers greater than 1; the information processing module 4552 performs the following steps when matching the situation feature and the post demand feature to obtain a post matching value of the target object and the post to be processed:
performing feature matching on the situation sub-features of each dimension and the requirement sub-features of the corresponding dimension through a working matching degree model to obtain matching values of the situation sub-features of each dimension;
And processing the matching values of the situation sub-features of the N dimensions to obtain the post matching values of the target object and the post to be processed.
In some embodiments, the situational features include N-dimensional situational sub-features, and the post capability features include P-dimensional post capability sub-features; n and P are integers greater than 1; the information processing module 4552 performs the following steps when the situation feature and the post capability feature are matched to obtain a capability promotion potential value of the to-be-processed post on the target object:
performing feature matching on the situation sub-features of each dimension and the post capability sub-features of the corresponding dimension through a working back feeding model to obtain post capability matching values of each dimension;
processing and calculating the post capability matching values of the N dimensions to obtain the post capability matching value of the target object;
Coding the post capability features to obtain post capability feature values corresponding to the post capability features;
And determining the difference value of the post capability characteristic value and the post capability matching value as the capability lifting potential value.
In some embodiments, the information processing module 4552 performs the following steps when processing the growth willingness value, the post matching value, and the capability promotion potential value to obtain post comprehensive matching parameters of the post to be processed:
Acquiring a first weight corresponding to the growth willingness value, a second weight corresponding to the post matching value and a third weight corresponding to the capacity lifting potential value;
and calculating the growth willingness value, the post matching value and the capacity lifting potential value according to the first weight, the second weight and the third weight to obtain the post comprehensive matching parameters of the post to be processed.
In some embodiments, the information acquisition module 4551, when acquiring the growth willingness value of the target object, performs the following steps:
Acquiring historical growth willingness values of the target object in different historical stages;
and determining an average value of the historical growth willingness values of the target object at different stages as the growth willingness value of the target object.
In some embodiments, the information processing module 4552, when acquiring the first weight corresponding to the growth willingness value, the second weight corresponding to the post matching value, and the third weight corresponding to the capacity boosting potential value, performs the following steps:
when the post matching value is larger than the post matching value threshold, determining preset weights as the first weight, the second weight and the third weight;
And when the post matching value is smaller than or equal to the post matching value threshold, inquiring a preset weight list according to the identification of the post to be processed, and acquiring the first weight, the second weight and the third weight from the weight list, wherein the first weight is larger than the second weight, and the third weight is larger than the second weight.
In some embodiments, the post to be processed includes a current post at which the target object is currently located; the information processing module 4552 executes the following steps when sending prompt information for processing the post to be processed to the terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold value:
When the post comprehensive matching parameter is smaller than or equal to a post comprehensive matching parameter threshold, sending prompt information for replacing posts to a terminal corresponding to the target object;
And when the post comprehensive matching parameter is larger than the post comprehensive matching parameter threshold, sending prompt information for keeping the post unchanged to the terminal of the target object.
In one embodiment, the post to be processed includes a post to be recommended, and the information processing module 4552 executes the following steps when sending, to a terminal corresponding to the target object, a prompt message for processing the post to be processed according to a relationship between a post comprehensive matching parameter of the post to be processed and a post comprehensive matching parameter threshold value:
and when the post comprehensive matching parameter is larger than the post comprehensive matching parameter threshold, sending prompt information of the applied post to a terminal corresponding to the target object.
The embodiment of the application also provides electronic equipment, which comprises:
A memory for storing executable instructions;
and the processor is used for realizing the post matching method when the executable instructions stored in the memory are run.
The embodiment of the application also provides a computer readable storage medium which stores executable instructions, and the executable instructions realize the post matching method when being executed by a processor.
The embodiment of the application also provides a computer program product, which comprises a computer program or instructions, and the position matching method is realized when the computer program or instructions are executed by a processor.
According to the electronic device shown in fig. 5, in one aspect of the application, the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read from the computer-readable storage medium by a processor of a computer device, which executes the computer instructions, causing the computer device to perform the different embodiments and combinations of embodiments provided in various alternative implementations of the post matching method provided by the application.
The above embodiments are merely examples of the present application, and are not intended to limit the scope of the present application, so any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application should be included in the scope of the present application.
Claims (11)
1. A post matching method, the method comprising:
acquiring a growth willingness value and a situation characteristic of a target object, and acquiring a post demand characteristic and a post capacity characteristic of a post to be processed;
Matching the situation characteristics with the post demand characteristics to obtain post matching values of the target object and the post to be processed;
matching the situation characteristics with the post capability characteristics to obtain a capability lifting potential value of the post to be processed on the target object;
Processing the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters of the post to be processed;
and sending prompt information for processing the post to be processed to a terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold.
2. The method of claim 1, wherein the contextual features comprise N-dimensional contextual sub-features and the post demand features comprise M-dimensional demand sub-features; n and M are integers greater than 1; the step of matching the situation feature and the post demand feature to obtain a post matching value of the target object and the post to be processed comprises the following steps:
performing feature matching on the situation sub-features of each dimension and the requirement sub-features of the corresponding dimension through a working matching degree model to obtain matching values of the situation sub-features of each dimension;
And processing the matching values of the situation sub-features of the N dimensions to obtain the post matching values of the target object and the post to be processed.
3. The method of claim 1, wherein the contextual features comprise N-dimensional contextual sub-features and the post capability features comprise P-dimensional post capability sub-features; n and P are integers greater than 1; the matching of the situation feature and the post capability feature to obtain a capability lifting potential value of the post to be processed on the target object comprises the following steps:
performing feature matching on the situation sub-features of each dimension and the post capability sub-features of the corresponding dimension through a working back feeding model to obtain post capability matching values of each dimension;
Processing the post capability matching values of the N dimensions to obtain the post capability matching value of the target object;
Coding the post capability features to obtain post capability feature values corresponding to the post capability features;
And determining the difference value of the post capability characteristic value and the post capability matching value as the capability lifting potential value.
4. The method of claim 1, wherein the processing the growth willingness value, the post matching value, and the capacity improvement potential value to obtain post comprehensive matching parameters of the post to be processed comprises:
Acquiring a first weight corresponding to the growth willingness value, a second weight corresponding to the post matching value and a third weight corresponding to the capacity lifting potential value;
and calculating the growth willingness value, the post matching value and the capacity lifting potential value according to the first weight, the second weight and the third weight to obtain the post comprehensive matching parameters of the post to be processed.
5. The method of claim 1, wherein the obtaining the growth willingness value of the target object comprises:
Acquiring historical growth willingness values of the target object in different historical stages;
and determining an average value of the historical growth willingness values of the target object at different stages as the growth willingness value of the target object.
6. The method of claim 4, wherein the obtaining the first weight corresponding to the growth intent value, the second weight corresponding to the post match value, and the third weight corresponding to the capacity boost potential value comprises:
when the post matching value is larger than the post matching value threshold, determining preset weights as the first weight, the second weight and the third weight;
And when the post matching value is smaller than or equal to the post matching value threshold, inquiring a preset weight list according to the identification of the post to be processed, and acquiring the first weight, the second weight and the third weight from the weight list, wherein the first weight is larger than the second weight, and the third weight is larger than the second weight.
7. The method according to claim 1, wherein the post to be processed includes a current post where the target object is currently located, and the sending, to a terminal corresponding to the target object, a prompt message for processing the post to be processed according to a relationship between a post comprehensive matching parameter of the post to be processed and a post comprehensive matching parameter threshold includes:
When the post comprehensive matching parameter is smaller than or equal to a post comprehensive matching parameter threshold, sending prompt information for replacing posts to a terminal corresponding to the target object;
And when the post comprehensive matching parameter is larger than the post comprehensive matching parameter threshold, sending prompt information for keeping the post unchanged to the terminal of the target object.
8. The method according to claim 1, wherein the post to be processed includes a post to be recommended, and the sending, to the terminal corresponding to the target object, a prompt message for processing the post to be processed according to a relationship between a post comprehensive matching parameter of the post to be processed and a post comprehensive matching parameter threshold includes:
and when the post comprehensive matching parameter is larger than the post comprehensive matching parameter threshold, sending prompt information of the applied post to a terminal corresponding to the target object.
9. A post matching device, the device comprising:
The information acquisition module is used for acquiring growth willingness values and situation characteristics of the target object and acquiring post demand characteristics and post capacity characteristics of the post to be processed;
the information processing module is used for matching the situation characteristics and the post demand characteristics to obtain post matching values of the target object and the post to be processed;
The information processing module is further used for matching the situation characteristics and the post capability characteristics to obtain a capability promotion potential value of the post to be processed on the target object;
The information processing module is further used for processing the growth willingness value, the post matching value and the capacity improvement potential value to obtain post comprehensive matching parameters of the post to be processed;
The information processing module is further used for sending prompt information for processing the post to be processed to the terminal corresponding to the target object according to the relation between the post comprehensive matching parameter of the post to be processed and the post comprehensive matching parameter threshold.
10. An electronic device, the electronic device comprising:
A memory for storing executable instructions;
A processor for implementing the post matching method of any one of claims 1 to 8 when executing executable instructions stored in said memory.
11. A computer readable storage medium storing executable instructions which when executed by a processor implement the post matching method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311244755.1A CN117952585A (en) | 2023-09-25 | 2023-09-25 | Post matching method, post matching device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311244755.1A CN117952585A (en) | 2023-09-25 | 2023-09-25 | Post matching method, post matching device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117952585A true CN117952585A (en) | 2024-04-30 |
Family
ID=90804355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311244755.1A Pending CN117952585A (en) | 2023-09-25 | 2023-09-25 | Post matching method, post matching device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952585A (en) |
-
2023
- 2023-09-25 CN CN202311244755.1A patent/CN117952585A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Srinivasan et al. | Biases in AI systems | |
| US11164105B2 (en) | Intelligent recommendations implemented by modelling user profile through deep learning of multimodal user data | |
| Kosinski et al. | Mining big data to extract patterns and predict real-life outcomes. | |
| Noei et al. | Too many user-reviews! what should app developers look at first? | |
| KR20190142286A (en) | Method for filtering similar problem based on weight | |
| US8856229B2 (en) | System and method for social networking | |
| CN112292674A (en) | Processing multimodal user input for an assistant system | |
| US9704171B2 (en) | Methods and systems for quantifying and tracking software application quality | |
| US11102276B2 (en) | System and method for providing more appropriate question/answer responses based upon profiles | |
| US20150278350A1 (en) | Recommendation System With Dual Collaborative Filter Usage Matrix | |
| CN107193974B (en) | Regional information determination method and device based on artificial intelligence | |
| US20180068028A1 (en) | Methods and systems for identifying same users across multiple social networks | |
| US11928985B2 (en) | Content pre-personalization using biometric data | |
| US11615485B2 (en) | System and method for predicting engagement on social media | |
| Stapleton et al. | Design effects of multilevel estimates from national probability samples | |
| US10762438B1 (en) | Extracting questions and answers | |
| Khorramdel et al. | GDM software mdltm including parallel EM algorithm | |
| CN116204714A (en) | Recommendation method, recommendation device, electronic equipment and storage medium | |
| US20210160221A1 (en) | Privacy Preserving Document Analysis | |
| Buskirk et al. | Why machines matter for survey and social science researchers: Exploring applications of machine learning methods for design, data collection, and analysis | |
| US20190205702A1 (en) | System and method for recommending features for content presentations | |
| Jones | A dataset for the study of identity at scale: Annual Prevalence of American Twitter Users with specified Token in their Profile Bio 2015–2020 | |
| CN108550019B (en) | Resume screening method and device | |
| Kaufman | Implementing novel, flexible, and powerful survey designs in R Shiny | |
| JP6710907B2 (en) | Preference learning method, preference learning program, and preference learning device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |