CN117172978A

CN117172978A - Learning path information generation method, device, electronic equipment and medium

Info

Publication number: CN117172978A
Application number: CN202311444149.4A
Authority: CN
Inventors: 马岩; 王雨萱; 刘少静
Original assignee: State Grid Information and Telecommunication Co Ltd; Beijing Guodiantong Network Technology Co Ltd
Current assignee: State Grid Information and Telecommunication Co Ltd; Beijing Guodiantong Network Technology Co Ltd
Priority date: 2023-11-02
Filing date: 2023-11-02
Publication date: 2023-12-05
Anticipated expiration: 2043-11-02
Also published as: CN117172978B

Abstract

The embodiment of the invention discloses a learning path information generation method, a learning path information generation device, electronic equipment and a learning path information generation medium. One embodiment of the method comprises the following steps: acquiring personnel requirement information, personnel post skill information and personnel identity information; carrying out semantic recognition on the personnel requirement information, the personnel post skill information and the personnel identity information to obtain a requirement skill dimension information set and a personnel post skill dimension information set; matching the skill dimension information of each personnel post with the corresponding skill dimension information of the requirement to obtain a difference degree value set; recommending skill knowledge points to the personnel to obtain a skill knowledge point information set; generating learning path information; carrying out knowledge tracking processing on the learning path information to obtain learning progress information; and controlling shooting of the learning state image set, and sending the alarm information, the learning path information and the skill knowledge point information set to a user side. The method and the device can improve accuracy of skill knowledge point recommendation and reduce waste of communication resources.

Description

Learning path information generation method, device, electronic equipment and medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a learning path information generation method, a learning path information generation device, electronic equipment and a learning path information generation medium.

Background

Skill knowledge point recommendation is an important process for improving post skills and post cognition of personnel, and working skills of the personnel and competitive power of enterprises can be improved by carrying out skill knowledge point recommendation on the personnel. For the generation of the learned route information, the following means are generally adopted: and recommending the skill knowledge points of the target user based on the user similarity or a recommendation algorithm based on the historical skill knowledge point similarity to obtain a knowledge point information set, and sending the knowledge point information set to a user side for the user to check.

However, when the learning path information is generated in the above manner, there are often the following technical problems:

firstly, because the recommendation algorithm based on the user similarity or the historical knowledge point similarity only considers the preference information of the personnel, and does not consider the gap between the existing working skills of the personnel and the working skills required by the posts, the accuracy of skill knowledge point recommendation is low, a large amount of time and resources are wasted, the experience of the personnel is low, and the communication resources and the storage resources of the user side are wasted.

Secondly, because the recommendation algorithm based on the user similarity or the historical knowledge point similarity only recommends a large number of skill knowledge points to the user, and does not mine the association relation among the skill knowledge points, the user does not have planning in the skill knowledge point learning process, the learning time is prolonged, and the user experience is low and the learning effect is poor.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a learning path information generation method, apparatus, electronic device, and medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a learning path information generating method, including: acquiring personnel requirement information, personnel post skill information and personnel identity information; carrying out semantic recognition on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set; carrying out semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set; matching each person post skill dimension information in the person post skill dimension information set with the required skill dimension information corresponding to the person post skill dimension information in the required skill dimension information set to generate a difference value, so as to obtain a difference value set; in response to determining that the personnel information corresponding to the personnel post skill information is target personnel information, carrying out skill knowledge point recommendation on personnel corresponding to the personnel post skill information according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold value from the difference degree value set; generating learning path information aiming at the personnel post skill information according to the skill knowledge point information set; carrying out knowledge tracking processing on the learning path information to obtain learning progress information; and controlling a related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set according to the learning progress information, and sending alarm information, the learning path information and the skill knowledge point information set to the user side according to the learning state image set.

In a second aspect, some embodiments of the present disclosure provide a learning path information generating apparatus including: the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to acquire personnel requirement information, personnel post skill information and personnel identity information; the first semantic identification unit is configured to carry out semantic identification on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set; the second semantic recognition unit is configured to perform semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set; the matching unit is configured to match each piece of personnel post skill dimension information in the personnel post skill dimension information set with the required skill dimension information corresponding to the personnel post skill dimension information in the required skill dimension information set so as to generate a difference value and obtain a difference value set; a skill knowledge point recommending unit configured to respond to the fact that the personnel information corresponding to the personnel post skill information is target personnel information, and according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set, conduct skill knowledge point recommendation on the personnel corresponding to the personnel post skill information to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold value from the difference degree value set; a generating unit configured to generate learning path information for the person post skill information based on the skill knowledge point information set; the knowledge tracking processing unit is configured to perform knowledge tracking processing on the learning path information to obtain learning progress information; and the control unit is configured to control the related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set according to the learning progress information, and send alarm information, the learning path information and the skill knowledge point information set to the user side according to the learning state image set.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method as described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantages: according to the learning path information generation method, through the gap between the requirement skill dimension information and the personnel post skill dimension information, the history knowledge point information and the requirement planning information, accurate skill knowledge point recommendation is performed on personnel from multiple aspects, and the learning path is generated, the learning efficiency of a user can be improved, the learning time is reduced, the experience of the personnel is further improved, and the waste of communication resources and storage resources of a user side is reduced. Specifically, the related human experience is low, and the waste of communication resources and storage resources at the user side is caused by: because the recommendation algorithm based on the user similarity or the historical knowledge point similarity only considers the preference information of the personnel, the gap between the existing working skills of the personnel and the working skills required by the posts is not considered, the accuracy of skill knowledge point recommendation is low, a large amount of time and resources are wasted, the experience of the personnel is low, and the communication resources and the storage resources of the user side are wasted. Based on this, the learning path information generation method of some embodiments of the present disclosure may first acquire the person demand information, the person post skill information, and the person identity information. Here, the person demand information, person post skill information, and person identity information are used to subsequently determine the demand skill dimension information and person post skill dimension information. Secondly, carrying out semantic recognition on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set. The personal identification information and the personal demand information can be used for obtaining a more personalized demand skill dimension information set, so that the personalized skill knowledge point recommendation can be conveniently carried out later. And performing semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set. Here, the individual difference of the personnel can be considered through the personnel identity information and the personnel post skill information, so that the obtained personnel post skill dimension information is more personalized. And then, matching each person post skill dimension information in the person post skill dimension information set with the required skill dimension information corresponding to the person post skill dimension information in the required skill dimension information set to generate a difference value, so as to obtain a difference value set. The difference between the post skills possessed by the personnel and the skills required by the post can be determined in a targeted manner through the personnel post skill dimension information set and the requirement skill dimension information set. And then, in response to determining that the personnel information corresponding to the personnel post skill information is target personnel information, carrying out skill knowledge point recommendation on the personnel corresponding to the personnel post skill information according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold from the difference degree value set. In this case, the skill and the skill required by the post, the historical knowledge point information and the requirement planning information of the personnel are used for recommending the skill knowledge points in multiple aspects, so that the accuracy and the comprehensiveness of recommending the skill knowledge points can be improved, and the problem of cold start recommended to new post personnel can be solved. And then, according to the skill knowledge point information set, learning path information aiming at the personnel post skill information is generated. Here, learning path information can improve the learning efficiency of personnel and shorten learning time, improve personnel's experience. And then, carrying out knowledge tracking processing on the learning path information to obtain learning progress information. The knowledge tracking processing can track the learning condition of the personnel in real time, so that the learning path can be adjusted in time later, and the user experience and the learning efficiency can be improved conveniently. Finally, according to the learning progress information, controlling a related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set, and according to the learning state image set, sending alarm information, the learning path information and the skill knowledge point information set to the user side. Here, the related shooting device is controlled to shoot, so that the learning condition of the personnel can be monitored in real time, and the warning information, the learning path information and the skill knowledge point information are sent to the user side, so that the waste of communication resources can be reduced, and the learning efficiency of the personnel can be improved. Therefore, the learning path information generation method can accurately recommend skill knowledge points of the personnel from multiple aspects through the difference between the requirement skill dimension information and the personnel post skill dimension information, the history knowledge point information and the requirement planning information, and generate a learning path, so that the learning efficiency of the user can be improved, the learning time can be reduced, the experience of the personnel can be further improved, and the waste of communication resources and storage resources of a user side can be reduced.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of a learned path information generation method according to the present disclosure;

fig. 2 is a schematic structural diagram of some embodiments of a learned path information generating apparatus according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates a flow 100 of some embodiments of a learned path information generation method according to the present disclosure. The learning path information generation method comprises the following steps:

Step 101, acquiring personnel requirement information, personnel post skill information and personnel identity information.

In some embodiments, the executing body (e.g., electronic device) of the learning path information generating method may acquire the person requirement information, the person post skill information and the person identity information through a wired connection manner or a wireless connection manner. The personnel requirement information may be post skill information that a post needs personnel to possess. For example, the person demand information may be post information. The person post skill information may be existing post skill information possessed by an incumbent post person. For example, the above-mentioned personnel post skill information may be personnel resume information and personnel task completion information (performance information). The personnel identity information may be information representing the identities of various personnel owned by the incumbent personnel. In practice, the person identity information may include, but is not limited to, at least one of the following: post category identity information, expert grade identity information, job grade identity information, and political face identity information. The post category identity information may be category information of a post to which the person belongs. For example, the post class identity information may be technical post information. In practice, the aforementioned personnel demand information may be information crawled from a recruitment site or obtained in the form of a questionnaire. The personnel position skill information may be information obtained through interviews, questionnaires, or a local database. The person identity information may be information obtained from a local database.

And 102, carrying out semantic recognition on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set.

In some embodiments, the executing body may perform semantic recognition on the person requirement information and the person identity information to obtain a requirement skill dimension information set. The required skill dimension information in the required skill dimension information set may be post quality skill information that needs to be possessed by a characterization competence. The skills required dimension information in the skill required dimension information set may be, but is not limited to, at least one of the following: leadership information, professional skill information, and mental quality information.

As an example, the executing body may perform knowledge-graph construction on the personnel requirement information by using a top-down knowledge-graph construction algorithm to obtain a target requirement dimension information set. And then, determining the weight value of each piece of target requirement dimension information in the target requirement dimension information set corresponding to the personnel identity information through a preset identity weight table, and obtaining a requirement weight value set. The preset identity weight table may be a data table for storing weights of the requirement dimension information corresponding to different identities. And finally, carrying out weighting processing on each demand weight value in the demand weight value set and the target demand dimension information of the demand weight value corresponding to the target demand dimension information set so as to generate weight demand dimension information, and obtaining a weight demand dimension information set as a demand skill dimension information set.

In some optional implementations of some embodiments, the executing body may perform semantic recognition on the person requirement information and the person identity information to obtain a requirement skill dimension information set, and may include the following steps:

firstly, preprocessing the personnel requirement information to obtain preprocessed personnel requirement information. Wherein the pretreatment may include at least one of: words and text fills are deactivated.

And secondly, extracting the word vector from the preprocessed personnel requirement information to obtain a word vector sequence. Wherein the word vectors in the sequence of word vectors may be vectorized representations of words.

As an example, the execution body may first perform chinese sentence segmentation processing on the pre-processed personnel requirement information by using a WordPiece algorithm in a dynamic byte encoding model, to obtain a word sequence. The dynamic byte encoding model may be a model that encodes logical relationships between clauses. Then, each word in the word sequence is converted into a one-dimensional vector by querying a word vector table, and a word vector sequence is obtained. The word vectors in the word vector sequence are composed of word vectors, segment vectors and position vectors. The segment vectors may be vectors that are automatically learned during model training, used to divide clauses, and fused with semantic information of word vectors. The position vector is used for representing that semantic information carried by words at different positions of the text is different.

And thirdly, performing head entity identification processing on the word vector sequence to obtain a head entity vector sequence. The head entity vector in the head entity vector sequence may be a vector corresponding to an entity located at an initial position in the triplet. The triples described above may characterize a set of entity relationships that are relationships between two entities. The header entity vector may characterize the entity type and location information of the header entity. The entity types may be, but are not limited to, at least one of: name of person, place, organization, institution, time, date, currency, and percentage. It should be noted that, if multiple head entities appear in a sentence, the intersection problem is solved by adopting the proximity rule, that is, the range of the initial position and the final position marks of the two head entities nearest to each other is taken as one head entity. The header entity recognition processing may be a process of inputting a word vector sequence to a header entity decoder for recognition. The above-mentioned header entity decoder may be a decoder in which the start tag and the end tag of the header entity are represented in a matrix form by using a pointer marking method, and different rows represent positions of possible existence entities on different entity types. In the start tag of the head entity, "1" represents the start position of the head entity in the sentence, and "1" represents the end position of the head entity in the sentence in the end tag.

As an example, the execution body may perform two classification on a start position or an end position of each word vector in the word vector sequence by using two classifiers to generate a classification probability value, so as to obtain a classification probability value sequence. And then, determining word vectors corresponding to the classification probability values with the classification probability values larger than or equal to a preset probability threshold value in the classification probability value sequence as a head entity vector set.

And step four, inputting the head entity vector sequence into a self-attention model to obtain a weight head entity vector sequence. The weighted head entity vectors in the weighted head entity vector sequence may be head entity vectors with different weights of different feature vectors.

And fifthly, determining vector sums of each weight head entity vector and the corresponding word vector in the weight head entity vector sequence as fusion vectors to obtain a fusion vector sequence.

And sixthly, carrying out tail entity identification processing on the fusion vector sequence to obtain an initial triplet set. Wherein, the initial triplet in the initial triplet set may be an entity relation set for representing the relation between the head entity and the tail entity. For example, the initial triplet may be (skill dimension, inclusion relationship, tail entity). The inclusion relationship may be a specific skill name that may be included in different skill dimensions. The tail entities may be specific skill names corresponding to different skill dimensions. For example, the tail entity may be the skill of the data analysis. The tail entity may be an entity located at the termination location of the triplet. The tail entity recognition processing may be recognition processing performed by inputting the fusion vector sequence into a tail entity decoder. The tail entity decoder may be a decoder for resolving the scope and entity type of the existence of a tail entity after a given head entity. The tail entity decoder may be a decoder including a two-layer bi-directional LSTM (Long Short-Term Memory) model and a full-concatenated layer.

And seventhly, screening the initial triplet set through a preset likelihood function to obtain a target triplet set. The preset likelihood function can be a function for representing the matching degree of the head entity, the inclusion relation and the tail entity. The target triples in the target triples set may be initial triples with skill dimension and tail entity matching degree values greater than or equal to preset matching degree values. For example, the preset matching degree value may be 0.8.

And eighth, carrying out weighting processing on the initial requirement skill dimension information set corresponding to the target triplet set according to the personnel identity information to obtain a requirement skill dimension information set. The initial requirement skill dimension information in the initial requirement skill dimension information set corresponding to the target triplet set may be specific post skill information corresponding to the tail entity.

As an example, the executing body may determine a weight value of each initial requirement skill dimension information in the initial requirement skill dimension information set corresponding to the personnel identity information through a preset identity weight table, so as to obtain an initial weight value set. And then, carrying out weighting processing on each piece of initial requirement skill dimension information in the initial requirement skill dimension information set and the initial weight value of the corresponding initial requirement skill dimension information to obtain a requirement skill dimension information set.

In some optional implementations of some embodiments, the executing body may perform, according to the person identity information, weighting processing on an initial requirement skill dimension information set corresponding to the target triplet set to obtain a requirement skill dimension information set, and may include the following steps:

the first step is to classify the initial requirement skill dimension information set according to the personnel identity information to obtain a classified requirement dimension information set. The classification requirement dimension information set in the classification requirement dimension information set may be an initial requirement skill dimension information set corresponding to one type of identity information in the personnel identity information. For example, the one type of identity information may be expert-level identity information.

As an example, the executing body may perform classification processing on the initial requirement skill dimension information set through identity information of different dimensions of the personnel identity information, to obtain a classification requirement dimension information set.

And a second step of determining the weight value of each classification requirement dimension information group in the classification requirement dimension information group set to obtain a weight value set. In practice, the executing body may determine the weight value of each classification requirement dimension information set in the classification requirement dimension information set through a preset identity weight table, so as to obtain a weight value set. The preset identity weight table may be a preset data table with different weights given to the classification requirement dimension information sets corresponding to different identity information. The specific weight value of the preset identity weight table needs to be determined according to specific practical situations, which is not limited herein.

And thirdly, weighting each weight value in the weight value set and the classification requirement dimension information set corresponding to the weight value in the classification requirement dimension information set to generate a weight classification requirement dimension information set, and obtaining a weight classification requirement dimension information set as a requirement skill dimension information set.

And step 103, carrying out semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set.

In some embodiments, the executive body may perform semantic recognition on the personnel position skill information and the personnel identity information to obtain a personnel position skill dimension information set. The staff position skill dimension information in the staff position skill dimension information set may be position skill information of a staff on an incumbent position. The personnel position skill dimension information may be, but is not limited to, at least one of: leadership capability information, post skill information, and psychometric capability information.

As an example, the executing body may perform knowledge-graph construction on the personnel post skill information by using a top-down knowledge-graph construction algorithm to obtain a target personnel dimension information set. And then, determining the weight value of each piece of target personnel dimension information in the target personnel dimension information set corresponding to the personnel identity information through a preset identity weight table, and obtaining a personnel weight value set. And finally, carrying out weighting processing on each personnel weight value in the personnel weight value set and the target personnel dimension information of the corresponding personnel weight value in the target personnel dimension information set so as to generate weight personnel dimension information, and obtaining a weight personnel dimension information set as a personnel post skill dimension information set.

Step 104, matching each person post skill dimension information in the person post skill dimension information set with the requirement skill dimension information corresponding to the person post skill dimension information in the requirement skill dimension information set to generate a difference value, and obtaining a difference value set.

In some embodiments, the executing body may match each of the person post skill dimension information in the person post skill dimension information set with the required skill dimension information in the required skill dimension information set corresponding to the person post skill dimension information to generate a difference value, so as to obtain a difference value set. The difference degree value can represent the difference degree of personnel post skill dimension information and demand skill information.

As an example, the executing body may utilize a person demand matching model to match each person post skill dimension information in the person post skill dimension information set with the demand skill dimension information corresponding to the person post skill dimension information in the demand skill dimension information set, so as to generate a difference value, and obtain a difference value set. The person demand matching model may be a neural network model for matching a gap between existing post skill information possessed by a person and post skills required by a post. The person demand matching model may be a neural network model based on a pre-trained BERT (Bidirectional Encoder Representation from Transformers) model and an attention mechanism.

In some optional implementations of some embodiments, the executing entity may match each of the person post skill dimension information in the person post skill dimension information set with the requirement skill dimension information in the requirement skill dimension information set corresponding to the person post skill dimension information to generate a difference value, to obtain a difference value set, and may include the following steps:

the first step, carrying out feature coding processing on each person post skill dimension information in the person post skill dimension information set to generate person post skill feature vectors, and obtaining a person post skill feature vector set. The person post skill feature vector may represent a feature vector of the person post skill dimension information. The feature encoding process described above may be a feature encoding process performed using a BERT model.

And secondly, performing feature coding processing on each piece of requirement skill dimension information in the requirement skill dimension information set to generate a requirement skill feature vector, and obtaining a requirement skill feature vector set. The demand skill feature vector may represent a feature vector of demand skill dimension information. The feature encoding process described above may be a feature encoding process performed using a BERT model.

And thirdly, determining similarity values of the required skill feature vectors corresponding to the personnel post skill feature vectors in the personnel post skill feature vector set and the required skill feature vectors in the required skill feature vector set, and obtaining a similarity value set serving as a difference value set. Wherein, the similarity value may be a hamming distance value.

Step 105, in response to determining that the personnel information corresponding to the personnel post skill information is target personnel information, carrying out skill knowledge point recommendation on the personnel corresponding to the personnel post skill information according to the requirement skill dimension information set, the history knowledge point information set and the personnel requirement planning information corresponding to the target difference degree value set to obtain a skill knowledge point information set.

In some embodiments, the executing body may respond to determining that the personnel information corresponding to the personnel post skill information is target personnel information, and perform skill knowledge point recommendation on the personnel corresponding to the personnel post skill information according to the requirement skill dimension information set, the history knowledge point information set and the personnel requirement planning information corresponding to the target difference value set to obtain a skill knowledge point information set. The target personnel information is personnel information with a historical knowledge point information set. The historical knowledge point information in the historical knowledge point information set may be knowledge point information about post skills selected by the target person information before the current time. The target difference value set is a set formed by selecting at least one difference value greater than or equal to a preset difference threshold from the difference value set. The preset difference threshold may be a threshold for determining whether the target user needs knowledge point learning. For example, the preset difference threshold may be 0.2. The personnel requirement planning information may be occupation planning information of the target personnel on own post. The skill point information in the skill point information set may be skill course information about post skill information. For example, the skill knowledge point information may be communication skill information.

As an example, the executing body may respond to determining the personnel characterization target personnel information corresponding to the personnel post skill information, and perform skill knowledge point recommendation on the personnel corresponding to the personnel post skill information according to the requirement skill dimension information set, the historical knowledge point information set and the personnel requirement planning information corresponding to the target difference degree value set by using a recommendation algorithm based on collaborative filtering, so as to obtain a skill knowledge point information set.

Optionally, after the executing body performs skill knowledge point recommendation on the person corresponding to the person post skill information according to the requirement skill dimension information set, the history knowledge point information set and the person requirement planning information corresponding to the target difference value set in response to determining that the person information corresponding to the person post skill information is target person information, the step of obtaining the skill knowledge point information set may include:

and in response to determining that the personnel information corresponding to the personnel position skill information is not target personnel information, carrying out skill knowledge point recommendation on the personnel corresponding to the personnel position skill information according to the requirement skill dimension information set corresponding to the target difference degree numerical value set and the personnel requirement planning information to obtain a skill knowledge point information set.

As an example, the executing body may perform, in response to determining that the person corresponding to the person post skill information is not the target person information, skill knowledge point recommendation on the person corresponding to the person post skill information according to the requirement skill dimension information set corresponding to the target difference value set and the person requirement planning information by using a recommendation algorithm based on collaborative filtering, to obtain a skill knowledge point information set.

In some optional implementations of some embodiments, in response to determining that the person information corresponding to the person post skill information is target person information, the executing entity may recommend skill knowledge points for the person corresponding to the person post skill information according to a requirement skill dimension information set, a history knowledge point information set, and person requirement planning information corresponding to a target difference value set, to obtain a skill knowledge point information set, and may include the following steps:

the first step, knowledge point description information of each skill knowledge point in a preset skill knowledge point database is obtained, and a knowledge point description information set is obtained. The preset skill knowledge point database may be a pre-designed database storing skill knowledge point information. The knowledge point description information in the knowledge point description information set may represent information of contents of skill knowledge points. The knowledge point description information in the knowledge point description information set may be outline summary information of the knowledge points.

And secondly, extracting the knowledge point entity from each knowledge point description information in the knowledge point description information set to generate a knowledge point entity information set, and obtaining a knowledge point entity information set. The knowledge point entity information set may be name information for characterizing a knowledge point.

As an example, the execution body may perform word segmentation processing on each knowledge point description information in the knowledge point description information set to generate a phrase, so as to obtain a vocabulary set. Then, using clustering algorithm to perform entity disambiguation processing on each phrase in the phrase set to generate disambiguated phrases, and obtaining disambiguated phrase set as knowledge point entity information set

And thirdly, generating a personnel portrait aiming at the personnel post skill information according to the requirement skill dimension information set, the historical knowledge point information set and the personnel requirement planning information corresponding to the target difference degree value set. The person image can represent the preference of the selected skill knowledge point information and the existing post skill information.

As an example, the execution subject may first perform keyword extraction on the requirement skill dimension information set corresponding to the target variability value set and the personnel requirement planning information to obtain a keyword set. And then, constructing the label of the keyword set to obtain a characteristic label set. And then, inputting the historical knowledge point information set into the long-short-period memory neural network by utilizing the long-short-period memory neural network so as to generate characteristic weight values aiming at the characteristic labels in the characteristic label set, thereby obtaining a characteristic weight value set. And finally, weighting each characteristic weight value in the characteristic weight value set and the corresponding characteristic label in the characteristic label set to obtain a weight characteristic label set serving as a personnel portrait.

And step four, recommending skill knowledge points for the personnel corresponding to the personnel post skill information according to the personnel portrait and the knowledge point entity information set to obtain a skill knowledge point information set.

As an example, the executing body may use a collaborative filtering recommendation algorithm based on the object to recommend skill knowledge points to the person corresponding to the person post skill information, so as to obtain a skill knowledge point information set.

In some optional implementations of some embodiments, the executing entity may generate a personnel portrait for the personnel post skill information according to the requirement skill dimension information set, the historical knowledge point information set, and the personnel requirement planning information corresponding to the target difference value set, and may include the following steps:

and firstly, extracting features of a demand skill dimension information set corresponding to the target difference degree value set to obtain a difference demand skill feature vector set. The difference demand skill feature vector in the difference demand skill feature vector set may be a feature vector representing demand skill dimension information corresponding to a difference value greater than or equal to a preset difference threshold. The feature extraction may be feature extraction using a topic model based on a variation-from-encoder. The above described theme model based on the variant-auto-encoder may be a dirichlet distribution that changes the latent variable distribution in the variant-auto-encoder to be consistent with the LDA (Latent Dirichlet Allocation, implicit dirichlet distribution) model.

And secondly, preprocessing the personnel requirement planning information to obtain preprocessed requirement planning information. Wherein the pretreatment may include at least one of: and stopping word and word segmentation processing.

And thirdly, extracting features of the preprocessing requirement planning information to obtain a planning feature vector. The planning feature vector may be a feature vector representing the job occupation planning of the target user. The feature extraction may be feature extraction using a topic model based on a variation-from-encoder.

And step four, carrying out knowledge forgetting behavior feature extraction on the historical knowledge point information set to obtain a time interval feature vector set, a time span feature vector set and a time delay feature vector set. The time interval feature vector in the time interval feature vector set may be a feature vector representing a learning time interval of any two learning history knowledge point information sets. The time span feature vector in the time span feature vector set may characterize a feature vector that learns a time sequence distance of any two pieces of history knowledge point information having a learning order. The time delay feature vector in the time delay feature vector set may be a feature vector representing a time sequence distance of the learned history knowledge point information. The feature extraction of the knowledge forgetting behavior can be performed by adding three forgetting gates in a long-term and short-term memory neural network.

And fifthly, performing feature stitching on the time interval feature vector set, the time span feature vector set and the time delay feature vector set to obtain a stitched feature vector set.

And sixthly, inputting the difference demand skill feature vector set, the planning feature vector and the spliced feature vector set into a self-attention mechanism model to obtain a personnel portrait corresponding to the personnel post skill information.

And 106, generating learning path information aiming at the personnel post skill information according to the skill knowledge point information set.

In some embodiments, the executive body may generate learning path information for the person post skill information according to the skill knowledge point information set. The learning path information may be shortest learning path information obtained by planning a skill knowledge point information set of the target person information.

As an example, the execution subject may first determine a learning order relation between skill knowledge point information included in the skill knowledge point information set, to obtain a learning order relation set. Then, by using a simulated annealing method, learning path information for the person post skill information is generated according to the skill knowledge point information set and the learning sequence relation set.

In some optional implementations of some embodiments, the executing entity may generate learning path information for the person post skill information according to the skill knowledge point information set, and may include the following steps:

the first step, carrying out entity identification on each skill knowledge point information in the skill knowledge point information set to generate a skill knowledge point entity information set, and obtaining a skill knowledge point entity information set. The skill point entity information in the skill point entity information set may be information characterizing a content outline of the skill point information. The entity identification may be an entity identification using a conditional random field algorithm. The skill point of knowledge entity information set may include: skill knowledge point entity information and skill knowledge point attribute information. The skill point attribute information may include at least one of: teaching teacher information, subject information and school information.

And secondly, extracting the relationship of the skill knowledge point entity information set to obtain a first association relationship information set among the skill knowledge point information included in the skill knowledge point information set. The first association relationship information in the first association relationship information set may represent information of attribute relationships between skill knowledge point information. The first association information may be, but is not limited to, at least one of: the subordinate association relationship between the skill knowledge points and the disciplines, the source association relationship between the skill knowledge points and the schools, the tenure association relationship between the skill knowledge points and the teaching teacher, and the containing association relationship between the skill knowledge points and the skill knowledge point entities. The relationship extraction may be a relationship extraction using a convolutional neural network model.

And thirdly, extracting associated keywords from each skill knowledge point information in the skill knowledge point information set to generate associated keyword groups and keyword value groups, and obtaining associated keyword group sets and keyword value group sets. Wherein, the related key word groups and the key value groups have a one-to-one correspondence in quantity. The related keywords in the related keyword groups can be keywords for representing skill knowledge point information. The key values in the key value group may be key values corresponding to the associated key words. The key value may be a weighted sum of a TF-IDF (Term Frequency-Inverse Document Frequency) value and an association degree value of the associated keyword. The association degree of the association key words may be mutual information PMI (Pointwise Mutual Information). The above-mentioned related keyword extraction may be a keyword extraction based on TF-IDF and related keyword association degree.

Fourth, for any two target associated keyword groups in the target associated keyword group, determining the same target associated keyword in the any two target associated keyword groups as a common keyword group. The target associated keywords in the target associated keyword group set may be a set formed by a preset number of associated keywords, wherein the preset number of associated keywords are selected from the associated keyword groups, and the key values of the preset number of associated keywords are ordered from big to small. For example, the preset number may be 20.

And fifthly, determining the sum of key values of each skill knowledge point information of the key phrase in the corresponding skill knowledge point information group for each common key phrase in the obtained common key phrase set so as to generate a first common key value and a second common key value.

And a sixth step of determining whether a second association relation information set exists between the skill knowledge point information included in the skill knowledge point information set according to the obtained first common key value set and the obtained second common key value set. The second association information in the second association information set may be association relations before and after learning between the skill knowledge points.

As an example, the execution body may first determine that the first skill knowledge point information corresponding to the first common key value and the second skill knowledge point information corresponding to the second common key value have an association relationship in response to determining that the first common key value and the second common key value are both greater than a common key value threshold, and compare the first key value and the second key value to obtain a comparison result. Wherein the common key value threshold may be 0.7. And secondly, determining that the first skill knowledge point information is the preamble skill knowledge point information of the second skill knowledge point information in response to determining that the first key value on the comparison result representation is larger than or equal to the second key value. The pre-skill knowledge points may be skill knowledge points that require learning of the first skill knowledge point before learning of the second skill knowledge point. Then, in response to determining that the first key value is less than the second key value, determining that the second skill point information is a prior skill point of the first skill point information. And finally, in response to determining that the first common key value and the second common key value are not greater than a common key value threshold, determining that the first skill knowledge point information and the second skill knowledge point information have no association relationship.

Seventh, in response to determining that a second association information set exists among the skill knowledge point information included in the skill knowledge point information set, a knowledge point knowledge graph aiming at the skill knowledge point information set is generated according to the first association information set, the second association information set and the skill knowledge point information set. The knowledge point knowledge graph may be a graph database that characterizes association relations between skill knowledge point information included in a skill knowledge point information set.

As an example, in response to determining that a second association information set exists between the skill knowledge point information included in the skill knowledge point information set, the executing body may input the first association information set, the second association information set, and the skill knowledge point information set into a graph database to obtain a knowledge point knowledge graph.

And eighth step, carrying out weighted summation processing on the recommended value and the key value corresponding to each skill knowledge point information in the skill knowledge point information set to generate a path value, and obtaining a path value set. The recommended value may be a value of a person image similarity between each skill knowledge point obtained in performing skill knowledge point recommendation and the target person. The path values may characterize distances between skill knowledge points.

And a ninth step of generating learning path information for the personnel post skill information according to the knowledge point knowledge graph and the path value set.

As an example, the execution body may generate learning path information for the person post skill information from the knowledge point knowledge graph and the path value set using Dijkstra (Dijkstra's algorism, disco tesla).

The first to ninth steps and related content thereof are taken as an invention point of the embodiments of the present disclosure, which solves the second technical problem mentioned in the background art, because the recommendation algorithm based on the user similarity or the historical knowledge point similarity only recommends a large number of skill knowledge points to the user, and does not mine the association relationship between a large number of skill knowledge points, the user does not have planning in the skill knowledge point learning process, the learning time is prolonged, and the user experience is lower and the learning effect is poor. Factors that cause the user experience to be low and the learning effect to be poor are often as follows: because the recommendation algorithm based on the user similarity or the historical knowledge point similarity only recommends a large number of skill knowledge points to the user, and does not mine the association relation among the skill knowledge points, the user does not have planning in the skill knowledge point learning process, and the learning time is prolonged. If the above factors are solved, the effects of improving the user experience and learning effect can be achieved. In order to achieve the effect, the method and the device firstly determine the first association relation of the skill knowledge points through entity and relation extraction, initially construct the relation between the skill knowledge points, and facilitate the follow-up generation of an accurate learning path. And secondly, determining a second association relation between skill knowledge points, namely a front-back learning sequence between the skill knowledge points through a knowledge point group set included in the skill knowledge point information set, so that the association relation between the skill knowledge points can be further perfected, and a more accurate knowledge point knowledge map can be conveniently built later. And then, constructing a knowledge point knowledge graph through the first association relationship and the second association relationship, so that the skill knowledge point learning sequence can be conveniently planned through a path planning algorithm. And finally, carrying out weighted summation on the recommended value and the key value to serve as a path distance, and generating a learning path through the path distance, so that the learning time of the user can be reduced, and the experience and learning efficiency of the user can be improved.

And 107, carrying out knowledge tracking processing on the learning path information to obtain learning progress information.

In some embodiments, the executing body may perform knowledge tracking processing on the learning path information to obtain learning progress information. The learning progress information may be information indicating learning conditions of the person. For example, the learning progress information may include at least one of: learning duration information and skill knowledge point mastering condition information.

As an example, the execution subject may perform knowledge tracking processing on the learning path information by using DKT (Deep Knowledge Tracing, deep knowledge tracking model) to obtain learning progress information.

And step 108, according to the learning progress information, controlling a related shooting device of the user side corresponding to the post skill information of the personnel to shoot a learning state image set, and according to the learning state image set, sending alarm information, learning path information and skill knowledge point information set to the user side.

In some embodiments, the executing body may control the related photographing device of the user terminal corresponding to the person post skill information to photograph the learning state image set according to the learning progress information, and send the alarm information, the learning path information and the skill knowledge point information set to the user terminal according to the learning state image set. The related shooting device may be a device for shooting face information of a person learning skill knowledge point. The learning state images in the learning state image set may be facial expression images of persons. The user terminal may be at least one of the following: cell phones, computers, and tablets.

As an example, the executing body may control the related photographing device of the user terminal corresponding to the person post skill information to photograph the learning state image set in response to determining that the learning progress information is less than the preset learning progress information. The preset learning progress information may be average learning progress information of all people. And in response to determining that the learning progress information is greater than or equal to the preset learning progress information, closing a related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set. And carrying out facial expression detection on the learning state images in the learning state image set to obtain facial expression information of the personnel. And matching the facial expression of the person with a preset expression information set to obtain a matching result. The preset expression information in the preset expression information set may be prestored expression information representing not carefully learned. For example, the preset expression information may be a dozing facial expression. And responding to the matching result to represent successful matching, and sending the alarm information, the learning path information and the skill knowledge point information set to the user side.

With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a learning path information generating apparatus, which correspond to those method embodiments shown in fig. 1, and which are particularly applicable to various electronic devices.

As shown in fig. 2, a learned route information generation apparatus 200 includes: an acquisition unit 201, a first semantic recognition unit 202, a second semantic recognition unit 203, a matching unit 204, a skill knowledge point recommendation unit 205, a generation unit 206, a knowledge tracking processing unit 207, and a control unit 208. Wherein the acquisition unit 201 is configured to: and acquiring personnel requirement information, personnel post skill information and personnel identity information. The first semantic recognition unit 202 is configured to: and carrying out semantic recognition on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set. The second semantic recognition unit 203 is configured to: and carrying out semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set. The matching unit 204 is configured to: matching each person post skill dimension information in the person post skill dimension information set with the required skill dimension information corresponding to the person post skill dimension information in the required skill dimension information set to generate a difference value, and obtaining a difference value set. The skill knowledge point recommendation unit 205 is configured to: and in response to determining that the personnel information corresponding to the personnel position skill information is target personnel information, carrying out skill knowledge point recommendation on personnel corresponding to the personnel position skill information according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold value from the difference degree value set. The generation unit 206 is configured to: and generating learning path information aiming at the personnel post skill information according to the skill knowledge point information set. The knowledge tracking processing unit 207 is configured to: and carrying out knowledge tracking processing on the learning path information to obtain learning progress information. The control unit 208 is configured to: and controlling a related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set according to the learning progress information, and sending alarm information, the learning path information and the skill knowledge point information set to the user side according to the learning state image set.

It will be appreciated that the elements described in the learned path information generation apparatus 200 correspond to the respective steps in the method described with reference to fig. 1. Thus, the operations, features, and advantages described above for the method are equally applicable to the learning path information generating device 200 and the units contained therein, and are not described herein.

Referring now to fig. 3, a schematic diagram of an electronic device (e.g., electronic device) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, in some embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring personnel requirement information, personnel post skill information and personnel identity information; carrying out semantic recognition on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set; carrying out semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set; matching each person post skill dimension information in the person post skill dimension information set with the required skill dimension information corresponding to the person post skill dimension information in the required skill dimension information set to generate a difference value, so as to obtain a difference value set; in response to determining that the personnel information corresponding to the personnel post skill information is target personnel information, carrying out skill knowledge point recommendation on personnel corresponding to the personnel post skill information according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold value from the difference degree value set; generating learning path information aiming at the personnel post skill information according to the skill knowledge point information set; carrying out knowledge tracking processing on the learning path information to obtain learning progress information; and controlling a related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set according to the learning progress information, and sending alarm information, the learning path information and the skill knowledge point information set to the user side according to the learning state image set.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: the processor comprises an acquisition unit, a first semantic recognition unit, a second semantic recognition unit, a matching unit, a skill knowledge point recommendation unit, a generation unit, a knowledge tracking processing unit and a control unit. The names of these units do not constitute a limitation of the unit itself in some cases, and for example, the acquisition unit may also be described as "a unit that acquires personnel requirement information, personnel post skill information, and personnel identity information".

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A learning path information generation method, comprising:

acquiring personnel requirement information, personnel post skill information and personnel identity information;

carrying out semantic recognition on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set;

carrying out semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set;

matching each person post skill dimension information in the person post skill dimension information set with the required skill dimension information corresponding to the person post skill dimension information in the required skill dimension information set to generate a difference value, and obtaining a difference value set;

in response to determining that the personnel information corresponding to the personnel post skill information is target personnel information, carrying out skill knowledge point recommendation on personnel corresponding to the personnel post skill information according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold value from the difference degree value set;

Generating learning path information aiming at the personnel post skill information according to the skill knowledge point information set;

carrying out knowledge tracking processing on the learning path information to obtain learning progress information;

and controlling a related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set according to the learning progress information, and sending alarm information, learning path information and skill knowledge point information set to the user side according to the learning state image set.

2. The method of claim 1, wherein after the step of performing skill point recommendation on the person corresponding to the person post skill information according to the required skill dimension information set, the historical knowledge point information set, and the person requirement planning information corresponding to the target variability value set in response to determining that the person information corresponding to the person post skill information is target person information, obtaining a skill point information set comprises:

and in response to determining that the personnel information corresponding to the personnel post skill information is not target personnel information, carrying out skill knowledge point recommendation on the personnel corresponding to the personnel post skill information according to the requirement skill dimension information set corresponding to the target difference degree numerical value set and the personnel requirement planning information to obtain a skill knowledge point information set.

3. The method of claim 1, wherein the performing semantic recognition on the person demand information and the person identity information to obtain a demand skills dimension information set includes:

preprocessing the personnel requirement information to obtain preprocessed personnel requirement information;

extracting a word vector from the preprocessed personnel requirement information to obtain a word vector sequence;

performing head entity identification processing on the word vector sequence to obtain a head entity vector sequence;

inputting the head entity vector sequence into a self-attention model to obtain a weight head entity vector sequence;

determining the vector sum of each weight head entity vector and the corresponding word vector in the weight head entity vector sequence as a fusion vector to obtain a fusion vector sequence;

performing tail entity identification processing on the fusion vector sequence to obtain an initial triplet set;

screening the initial triplet set through a preset likelihood function to obtain a target triplet set;

and carrying out weighting processing on the initial requirement skill dimension information set corresponding to the target triplet set according to the personnel identity information to obtain a requirement skill dimension information set.

4. The method of claim 3, wherein the weighting the initial requirement skill dimension information set corresponding to the target triplet set according to the personnel identity information to obtain a requirement skill dimension information set includes:

classifying the initial requirement skill dimension information set according to the personnel identity information to obtain a classification requirement dimension information set;

determining a weight value of each classification requirement dimension information group in the classification requirement dimension information group set to obtain a weight value set;

and carrying out weighting processing on each weight value in the weight value set and the classification requirement dimension information set corresponding to the weight value in the classification requirement dimension information set to generate a weight classification requirement dimension information set, so as to obtain a weight classification requirement dimension information set as a requirement skill dimension information set.

5. The method of claim 1, wherein said matching each person post skill dimension information in the person post skill dimension information set with a required skill dimension information in the required skill dimension information set corresponding to the person post skill dimension information to generate a difference value, resulting in a difference value set, comprises:

Performing feature coding processing on each person post skill dimension information in the person post skill dimension information set to generate person post skill feature vectors, and obtaining a person post skill feature vector set;

performing feature coding processing on each piece of requirement skill dimension information in the requirement skill dimension information set to generate a requirement skill feature vector, and obtaining a requirement skill feature vector set;

and determining similarity values of each person post skill feature vector in the person post skill feature vector set and the required skill feature vector corresponding to the person post skill feature vector in the required skill feature vector set, and obtaining a similarity value set serving as a difference value set.

6. The method of claim 1, wherein the performing, in response to determining that the person information corresponding to the person post skill information is target person information, skill knowledge point recommendation on the person corresponding to the person post skill information according to the requirement skill dimension information set, the historical knowledge point information set, and the person requirement planning information corresponding to the target difference value set, to obtain a skill knowledge point information set includes:

acquiring knowledge point description information of each skill knowledge point in a preset skill knowledge point database to obtain a knowledge point description information set;

Extracting knowledge point entity from each knowledge point description information in the knowledge point description information set to generate a knowledge point entity information set, and obtaining a knowledge point entity information set;

generating a personnel portrait aiming at the personnel post skill information according to the requirement skill dimension information set, the historical knowledge point information set and the personnel requirement planning information corresponding to the target difference degree value set;

and recommending skill knowledge points for the personnel corresponding to the personnel post skill information according to the personnel portrait and the knowledge point entity information set to obtain a skill knowledge point information set.

7. The method of claim 6, wherein the generating a personnel representation for the personnel post skill information from the set of demand skill dimension information, the set of historical knowledge point information, and the personnel demand planning information corresponding to the set of target variability values comprises:

carrying out feature extraction on a demand skill dimension information set corresponding to the target difference degree value set to obtain a difference demand skill feature vector set;

preprocessing the personnel requirement planning information to obtain preprocessing requirement planning information;

Extracting features of the preprocessing requirement planning information to obtain a planning feature vector;

carrying out knowledge forgetting behavior feature extraction on the historical knowledge point information set to obtain a time interval feature vector set, a time span feature vector set and a time delay feature vector set;

performing feature stitching on the time interval feature vector set, the time span feature vector set and the time delay feature vector set to obtain a stitched feature vector set;

and inputting the difference demand skill feature vector set, the planning feature vector and the spliced feature vector set into a self-attention mechanism model to obtain a personnel portrait corresponding to the personnel post skill information.

8. A learned path information generation apparatus, comprising:

the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to acquire personnel requirement information, personnel post skill information and personnel identity information;

the first semantic identification unit is configured to carry out semantic identification on the personnel requirement information and the personnel identity information to obtain a requirement skill dimension information set;

the second semantic recognition unit is configured to perform semantic recognition on the personnel post skill information and the personnel identity information to obtain a personnel post skill dimension information set;

The matching unit is configured to match each piece of personnel post skill dimension information in the personnel post skill dimension information set with the required skill dimension information corresponding to the personnel post skill dimension information in the required skill dimension information set so as to generate a difference value and obtain a difference value set;

a skill knowledge point recommending unit, configured to respond to the fact that personnel information corresponding to the personnel post skill information is target personnel information, and according to a required skill dimension information set, a historical knowledge point information set and personnel requirement planning information corresponding to a target difference degree value set, conduct skill knowledge point recommendation on personnel corresponding to the personnel post skill information to obtain a skill knowledge point information set, wherein the target personnel information is personnel information with the historical knowledge point information set, and the target difference degree value set is a set formed by selecting at least one difference degree value greater than or equal to a preset difference degree threshold value from the difference degree value set;

a generating unit configured to generate learning path information for the person post skill information according to the skill knowledge point information set;

The knowledge tracking processing unit is configured to perform knowledge tracking processing on the learning path information to obtain learning progress information;

the control unit is configured to control the related shooting device of the user side corresponding to the personnel post skill information to shoot a learning state image set according to the learning progress information, and send alarm information, the learning path information and the skill knowledge point information set to the user side according to the learning state image set.

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.

10. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-7.