Regional industry talent skill gap identification equipment, method and device and medium

Abstract

The invention provides a regional industry talent skill gap identification device, method and device and a medium, and the method comprises the steps: obtaining industry information corresponding to at least one industry in a target region, the industry information comprising occupational demand information and cultivation supply information; performing word segmentation processing on the occupational demand information and the cultivation supply information, and screening word segmentation results to obtain supply and demand effective vocabularies including demand effective vocabularies and supply effective vocabularies; performing clustering processing on the supply and demand effective vocabularies to obtain a supply and demand skill word library composed of skill words corresponding to each cluster; determining demand skill words and supply skill words from a supply and demand skill word bank based on the demand effective vocabularies and the supply effective vocabularies; through comparison processing between the demand skill word and the supply skill word, the target identification result for the talent skill gap of at least one industry of the target area is generated, so that the comprehensiveness and accuracy of identification are guaranteed from the two dimensions of demand and supply.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of skill recognition, in particular, to a regional industrial talent skill gap recognition device, method, apparatus and medium. BACKGROUND

[0002] In the process of urban development, industry is the main economic support for urban development. Understanding the industrial structure within the city and promoting industrial circle building and chain strengthening are effective ways to improve the economic efficiency of urban development. For industrial development, accurately identifying industrial talent skills is particularly important. Industrial talent skills are the driving force for industrial innovation and upgrading, which can help to understand the core competitiveness of industrial development and accurately locate the bottlenecks and breakthroughs of industrial development.

[0003] When identifying industrial talent skills, the dimensions considered are mostly relatively single, resulting in many limitations in the recognition results, which are difficult to meet the requirements of comprehensive accuracy, thereby being difficult to support the actual needs of industrial development. SUMMARY

[0004] The present disclosure provides at least a regional industrial talent skill gap recognition device, method, apparatus and medium.

[0005] The present disclosure provides a regional industrial talent skill gap recognition device, which includes a processor, a memory, and a display. The processor, memory, and display are connected through a bus. The processor is used to store computer instructions. The display is used to display the processing results of the processor, which includes target recognition results generated by the processor. The processor is used to read the computer instructions stored in the memory to perform the following operations: Obtain industrial information corresponding to at least one industry in a target region, which includes occupation demand information and training supply information; Perform word segmentation processing on the occupation demand information and the training supply information respectively, and filter the word segmentation results to obtain effective supply and demand words, which include effective demand words and effective supply words; Perform clustering processing on the effective supply and demand words to obtain a supply and demand skill word library composed of skill words corresponding to each cluster; Determine demand skill words and supply skill words from the supply and demand skill word library based on the effective demand words and the effective supply words; Generate target recognition results of talent skill gaps for at least one industry in the target region by comparing the demand skill words and the supply skill words.

[0006] In an alternative implementation, the professional demand information and the training supply information are respectively subjected to word segmentation processing, and the word segmentation results are filtered to obtain effective supply and demand words, comprising: The professional demand information and the training supply information are respectively subjected to word segmentation processing to obtain a plurality of professional demand word segments and a plurality of training supply word segments; Each of the professional demand word segments and each of the training supply word segments is processed by a target neural network to obtain a demand word vector corresponding to each of the professional demand word segments and a supply word vector corresponding to each of the training supply word segments; Based on a preset skill word vector, demand effective words are filtered from the plurality of professional demand word segments, and supply effective words are filtered from the plurality of training supply word segments; the preset skill word vector is obtained by processing a preset skill word by the target neural network; The demand effective words and the supply effective words are summarized and de-duplicated to obtain effective supply and demand words.

[0007] In an alternative implementation, the demand effective words are filtered from the plurality of professional demand word segments based on a preset skill word vector, and the supply effective words are filtered from the plurality of training supply word segments based on the preset skill word vector, comprising: The similarity between the preset skill word vector and each of the demand word vectors and the similarity between the preset skill word vector and each of the supply word vectors are determined; The professional demand word segments corresponding to the demand word vectors with a similarity greater than or equal to a target threshold value are determined as the demand effective words, and the training supply word segments corresponding to the supply word vectors with a similarity greater than or equal to the target threshold value are determined as the supply effective words.

[0008] In an alternative implementation, the supply and demand effective words are subjected to clustering processing to obtain a supply and demand skill word library composed of skill words corresponding to each cluster; The supply and demand effective words are subjected to clustering processing to obtain at least one cluster; For each of the clusters, a skill word matching the cluster is generated based on the supply and demand effective words included in the cluster; The supply and demand skill word library is composed of the skill words.

[0009] In an alternative implementation, the demand skill words and the supply skill words are determined from the supply and demand skill word library based on the demand effective words and the supply effective words, comprising: For each of the skill words in the supply-demand skill word library, the supply-demand effective words included in the cluster corresponding to the skill word are matched with the demand effective words and the supply effective words respectively to determine the type of the supply-demand effective words included in the cluster corresponding to the skill word; the type corresponding to the skill word is a demand skill word and / or a supply skill word.

[0010] In an optional implementation, the generating, by comparison between the demand skill words and the supply skill words, of the target recognition result of the talent skill gap of at least one industry in the target region comprises: comparing the demand skill words and the supply skill words to determine a first skill word, a second skill word and a third skill word, the first skill word being an intersection between the demand skill words and the supply skill words, the second skill word being a difference set of the demand skill words relative to the supply skill words, and the third skill word being a difference set of the supply skill words relative to the demand skill words; generating, based on the first skill word, the second skill word and the third skill word, the target recognition result of the talent skill gap of at least one industry in the target region.

[0011] In an optional implementation, the processor is further configured to perform: generating, based on the target recognition result, a development strategy of the at least one industry in the target region, the development strategy being used to indicate adjustment information of each skill belonging to the at least one industry, and the development strategy being displayed through the display; receiving an editing processing result of the displayed development strategy, and publishing the editing processing result.

[0012] The embodiments of the present disclosure further provide a method for identifying a talent skill gap of an industry in a region, the method comprising: obtaining industry information corresponding to at least one industry in a target region, the industry information comprising occupation demand information and training supply information; performing word segmentation processing on the occupation demand information and the training supply information respectively, and screening the word segmentation results to obtain supply-demand effective words, the supply-demand effective words comprising demand effective words and supply effective words; performing clustering processing on the supply-demand effective words to obtain a supply-demand skill word library composed of skill words corresponding to each cluster; determining, based on the demand effective words and the supply effective words, demand skill words and supply skill words from the supply-demand skill word library; The demand skill words and the supply skill words are compared to generate a target recognition result of a talent skill gap of at least one industry of the target region.

[0013] The disclosure also provides a device for identifying a talent skill gap of an industry in a region. The device includes a collection module configured to obtain industry information corresponding to at least one industry in a target region, the industry information including occupation demand information and training supply information. The device also includes a screening module configured to perform word segmentation on the occupation demand information and the training supply information, respectively, and to screen the word segmentation results to obtain effective supply and demand words, the effective supply and demand words including effective demand words and effective supply words. The device further includes a clustering module configured to perform clustering on the effective supply and demand words to obtain a supply and demand skill word library composed of skill words corresponding to respective clusters. The device also includes a classification module configured to determine demand skill words and supply skill words from the supply and demand skill word library based on the effective demand words and the effective supply words. The device further includes a comparison module configured to compare the demand skill words and the supply skill words to generate a target recognition result of a talent skill gap of at least one industry of the target region.

[0014] The disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the steps of the above-mentioned method for identifying a talent skill gap of an industry in a region.

[0015] The device, method, apparatus, and medium provided by the disclosure for identifying a talent skill gap of an industry in a region obtain industry information corresponding to at least one industry in a target region, the industry information including occupation demand information and training supply information. The occupation demand information and the training supply information are subjected to word segmentation, and the word segmentation results are screened to obtain effective supply and demand words, the effective supply and demand words including effective demand words and effective supply words. The effective supply and demand words are subjected to clustering to obtain a supply and demand skill word library composed of skill words corresponding to respective clusters. Demand skill words and supply skill words are determined from the supply and demand skill word library based on the effective demand words and the effective supply words. The demand skill words and the supply skill words are compared to generate a target recognition result of a talent skill gap of at least one industry of the target region.

[0016] In this way, when identifying the skill gap of regional industrial talents, the occupation demand information and the training supply information of the target regional industry are used, so that the current situation of industrial talents can be analyzed comprehensively and in detail from the two dimensions of demand and supply, considering the skills that the industry actually expects talents to have, and including the skills that the talent training system can provide, thereby avoiding the limitations caused by considering from a single dimension, ensuring the comprehensiveness and accuracy of the identification of the talent skill gap, and meeting the actual needs of industrial development. Moreover, the occupation demand information and the training supply information are segmented, screened, and clustered to obtain the supply and demand skill library, so that the scattered corpus information is converted into corresponding skills, effectively integrating the complex industrial information, and more systematically presenting the distribution of industrial skills, laying a solid foundation for positioning the gap.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the technical solutions of the present disclosure.

[0018] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments. The drawings herein are incorporated into the specification and form a part of the specification, which show the embodiments consistent with the present disclosure, and are used to explain the technical solutions of the present disclosure together with the specification. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0020] Figure 1 A schematic diagram of a device for identifying a regional industrial talent skill gap is shown. Figure 2 A process schematic diagram for determining a supply and demand skill library is shown. Figure 3 A schematic diagram for comparing and processing between demand skill words and supply skill words is shown. Figure 4 A flowchart of a method for identifying a regional industrial talent skill gap is shown. Figure 5 A schematic diagram of a device for identifying a regional industrial talent skill gap is shown. DETAILED DESCRIPTION

[0021] In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the claimed present disclosure, but only represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0022] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

[0023] The term "and / or" herein only describes an association relationship, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of multiple or any combination of at least two of multiple, for example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0024] It is found through research that when identifying industrial talent skills, the dimensions considered are mostly relatively single, for example, only analyzed and identified from the demand side or only analyzed and identified from the supply side, resulting in many limitations of the identification results, which are difficult to meet the requirements of comprehensive accuracy, and even may lead to the identification results lagging behind the actual needs of industrial development, thereby being difficult to adapt to the diversified needs of industrial development.

[0025] Based on the above research, the present disclosure provides a regional industrial talent skill gap identification device. When identifying the regional industrial talent skill gap, the professional demand information and the training supply information of the target regional industry are used, so that the industrial talent present situation can be analyzed comprehensively and in detail from the two dimensions of demand and supply, considering not only the skills that the actual expected talents in the industry should have, but also the skills that the talent training system can provide, thereby avoiding the limitations caused by considering from a single dimension, ensuring the comprehensiveness and accuracy of the identification of the talent skill gap, and meeting the actual needs of industrial development.

[0026] The regional industrial talent skill gap identification device provided by the embodiments of the present disclosure will be described below with reference to the drawings.

[0027] Referring to Figure 1 As shown in the figure, it is a schematic diagram of the device 100 for identifying regional industrial talent skill gap provided by the embodiment of the present disclosure, which comprises: The processor 110, the memory 120 and the display 130 are connected through the bus 140, the memory 120 is used for storing computer instructions, and the display is used for displaying the processing result of the processor, which includes the target identification result generated by the processor.

[0028] The memory 120 comprises the internal memory 121 and the external memory 122, the internal memory 121 is also called the internal storage, which is used for temporarily storing the operation data in the processor 110 and the data exchanged with the external memory 122 such as the hard disk, and the processor 110 exchanges data with the external memory 122 through the internal memory 121.

[0029] The memory 120 can be, but is not limited to, the random access memory (RAM), the read only memory (ROM), the programmable read only memory (PROM), the erasable programmable read only memory (EPROM), the electric erasable programmable read only memory (EEPROM) and the like.

[0030] The processor 110 can be an integrated circuit chip with signal processing capability. The above-mentioned processor can be a general processor, including the central processing unit (CPU), the network processor (NP) and the like; it can also be the digital signal processor (DSP), the application specific integrated circuit (ASIC), the field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic device, discrete hardware component. It can realize or execute the disclosed methods, steps and logic block diagrams in the embodiment of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor or the like.

[0031] It can be understood that the structure of the embodiment of the present application does not constitute a specific limitation of the regional industrial talent skill gap identification device 100. In other embodiments of the present application, the regional industrial talent skill gap identification device 100 can include more or fewer components than the illustration, or combine certain components, or split certain components, or different component arrangement. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0032] In the embodiment of the present application, the memory 120 is specifically used to store computer instructions for executing the scheme of the present application, and is controlled by the processor 110 to execute. That is, when the regional industrial talent skill gap identification device 100 is running, the processor 110 communicates with the memory 120 through the bus 140, so that the processor 110 reads the computer instructions stored in the memory 120 to perform the following operations: Obtain industry information corresponding to at least one industry of a target region, the industry information including occupation demand information and training supply information; Perform word segmentation processing on the occupation demand information and the training supply information respectively, and screen the word segmentation results to obtain supply and demand effective words, the supply and demand effective words including demand effective words and supply effective words; Perform clustering processing on the supply and demand effective words to obtain a supply and demand skill word library composed of skill words corresponding to each cluster; Determine demand skill words and supply skill words from the supply and demand skill word library based on the demand effective words and the supply effective words; Generate a target identification result of a talent skill gap of at least one industry of the target region by comparing the demand skill words and the supply skill words.

[0033] In the following, the above scheme will be described in conjunction with the specific implementation.

[0034] Here, the target region can be city-level, national-level, etc.

[0035] The occupation demand information can be obtained from a demand side associated with the at least one industry, and the training supply information can be obtained from a supply side associated with the at least one industry.

[0036] It can be understood that the demand side and the supply side have a supply and demand association. For example, the demand side is a company providing positions, and the supply side is a school training talents. For another example, the demand side is a department planning industry, and the supply side is a department promoting industrial development.

[0037] Specifically, taking a company providing a position as an example of the demand side, when obtaining professional demand information, corpus information related to the demand side can be crawled from a recruitment website, and the crawled corpus information is filtered in combination with target keywords to obtain job requirement information under various attributes of an industry as the professional demand information.

[0038] Optionally, a selection category related to a target region and related to an industry, such as a company industry and a position type, can be selected in the recruitment website, and then all professional categories under the selection category are searched for recruitment information, and multiple filtering is performed according to a level of target region-company industry and position type-position name-recruitment position-position description-job requirement to obtain corpus information.

[0039] Wherein, after obtaining the job requirement information, considering that it covers multiple industries and positions, the job requirement information can be processed to be single, and the result of the single processing is taken as the professional demand information.

[0040] Specifically, taking a school cultivating talents as an example of the supply side, when obtaining cultivation supply information, corpus information related to professional profiles and training targets in a professional talent training plan of each college related to an industry in colleges and universities in a target region can be collected as the cultivation supply information.

[0041] Here, if subsequent overall industry analysis and identification of the target region are needed, the industry information of all industries of the target region can be obtained, and if subsequent targeted analysis and identification of one or several industries of the target region are needed, the industry information of the corresponding industry of the target region can be obtained.

[0042] In some possible implementation manners, the professional demand information and the cultivation supply information are respectively processed by word segmentation, and the word segmentation results are filtered to obtain effective supply and demand words, including: The professional demand information and the cultivation supply information are respectively processed by word segmentation to obtain a plurality of professional demand words and a plurality of cultivation supply words; Each of the professional demand words and each of the cultivation supply words is processed by a target neural network to obtain a demand word vector corresponding to each of the professional demand words and a supply word vector corresponding to each of the cultivation supply words; Based on a preset skill word vector, demand effective words are filtered from the plurality of professional demand words, and supply effective words are filtered from the plurality of cultivation supply words; the preset skill word vector is obtained by processing a preset skill word by the target neural network; The demand effective words and the supply effective words are summarized and processed by de-duplication to obtain effective supply and demand words.

[0043] In the above steps, when the professional demand information and the training supply information are respectively subjected to word segmentation processing, a word segmentation algorithm can be used for word segmentation processing, for example, a jieba word segmentation algorithm is used to obtain a plurality of professional demand word segments and a plurality of training supply word segments.

[0044] The target neural network can perform embedding processing (word embedding) on the input word segments and output word vectors, which are used to represent the positions of the corresponding word segments in a semantic space. It can be understood that if two word vectors are close in distance, the semantics corresponding to the two word vectors are generally close.

[0045] Optionally, the target neural network can also filter out English and symbols in the input word segments to obtain an output result in Chinese.

[0046] Here, a plurality of preset skill words are pre-set, the preset skill words are labor skill words based on existing research, and each of the preset skill words is processed by the target neural network to obtain a preset skill word vector corresponding to each of the preset skill words.

[0047] The target neural network can be a pre-trained BERT model.

[0048] The preset skill word vector is used as a screening standard to screen demand effective words from the plurality of professional demand word segments and supply effective words from the plurality of training supply word segments.

[0049] In actual applications, there are often repeated parts between the demand effective words and the supply effective words. The demand effective words and the supply effective words are summarized and de-duplicated to obtain supply-demand effective words.

[0050] In this way, the word segmentation technology, neural network algorithm, and vector comparison method are comprehensively used to obtain supply-demand effective words, fully play the advantages of different technologies, complement the limitations of a single technology, and can process large amounts of data, making the entire skill gap identification process more reliable and effectively improving the credibility of the identification result.

[0051] In some possible implementations, the preset skill word vector is used to screen demand effective words from the plurality of professional demand word segments and supply effective words from the plurality of training supply word segments, including: The similarity between the preset skill word vector and each of the demand word vectors and the similarity between the preset skill word vector and each of the supply word vectors are determined. The professional demand word segment corresponding to the demand word vector with the similarity greater than or equal to the target threshold is determined as the demand effective word, and the training supply word segment corresponding to the supply word vector with the similarity greater than or equal to the target threshold is determined as the supply effective word.

[0052] Here, when determining the similarity, the cosine triangle similarity can be specifically determined. The closer the semantics corresponding to the two word vectors are, the closer the positions of the two word vectors in the semantic space are. The closer the semantics corresponding to the two word vectors are, the greater the cosine triangle similarity between the two word vectors is, so that the cosine triangle similarity can be used to estimate the semantic similarity between the two words, thereby guaranteeing the accuracy of the word vector matching.

[0053] Here, the specific value of the target threshold is determined according to actual screening needs, which is not specifically limited here.

[0054] In this embodiment, the threshold used when screening the demand effective word and the supply effective word is the same, that is, the target threshold, so that the demand side word screening and the supply side word screening are performed according to a unified standard, and the reliability of the word screening is improved.

[0055] Optionally, in the case where the similarity of the professional demand word segment corresponding to the demand word vector is greater than or equal to the target threshold, the professional demand word segment corresponding to the demand word vector with the similarity greater than or equal to the target threshold can be considered as a professional demand word segment containing skill description, and further, the professional demand word segment corresponding to the demand word vector with the similarity greater than or equal to the target threshold can be manually screened, and the professional demand word segment after manual screening is determined as the demand effective word. Similarly, in the case where the similarity of the training supply word segment corresponding to the supply word vector is greater than or equal to the target threshold, the training supply word segment corresponding to the supply word vector with the similarity greater than or equal to the target threshold can be considered as a training supply word segment containing skill description, for example, the word "professional introduction" will not be screened and retained, and further, the training supply word segment corresponding to the supply word vector with the similarity greater than or equal to the target threshold can be manually screened, and the training supply word segment after manual screening is determined as the supply effective word. Thus, the accuracy of the demand effective word and the supply effective word is effectively improved.

[0056] In this way, based on the comparison of the preset skill word vector with the demand word vector and the supply word vector, the word closely related to the skill can be effectively screened, the interference of the word irrelevant to the skill is avoided, the accuracy and reliability of the word screening are improved, and the effectiveness of subsequent analysis is ensured.

[0057] In some possible implementation manners, the clustering processing is performed on the supply-demand effective vocabulary to obtain a supply-demand skill vocabulary composed of skill words corresponding to each cluster. The clustering processing is performed on the supply-demand effective vocabulary to obtain at least one cluster. For each cluster, a skill word matched with the cluster is generated based on the supply-demand effective vocabulary included in the cluster. The supply-demand skill vocabulary is composed of the skill words.

[0058] Here, when the clustering processing is performed on the supply-demand effective vocabulary, a supply-demand word vector corresponding to the supply-demand effective vocabulary can be determined, and a clustering algorithm, for example, a k-means algorithm, is used to perform the clustering processing on the supply-demand word vector to obtain at least one cluster.

[0059] In this way, the word vector can better reflect the association between words than the vocabulary, and the clustering result is more accurate.

[0060] The supply-demand word vector can also be obtained by processing the supply-demand effective vocabulary through the target neural network.

[0061] As known from the foregoing, the word vector is the result processed by the target neural network, and in actual application, the word vector is often high-dimensional. For example, the word vector output by the BERT model is a pytorch tensor, and generally has a dimension of 768.

[0062] In a high-dimensional space, data points are generally sparse, and it is difficult to form dense clusters. Therefore, the dense areas on which most clustering algorithms depend often fail in a high-dimensional space, and thus high-dimensional word vectors are often difficult to cluster.

[0063] In some possible implementation manners, the supply-demand word vector can be first processed by dimension reduction, for example, to 30 dimensions, and then the supply-demand word vector processed by dimension reduction is clustered.

[0064] In some other possible implementation manners, the supply-demand word vector can be converted into a NumPy array, the NumPy array is processed by dimension reduction, and the NumPy array processed by dimension reduction is clustered.

[0065] Here, the NumPy array itself carries a principal component analysis (PCA) function, and by directly using the PCA function carried by the NumPy array itself, the dimension reduction processing of the NumPy array can be conveniently and quickly implemented, and the data processing efficiency is improved.

[0066] When performing clustering, you can first set a target cluster number range, and then perform clustering according to the target cluster number range. Optionally, you can use the Silhouette Score method to determine the target cluster number range, for example, between 100-500.

[0067] After the clusters are obtained, for each cluster, skill words matching the cluster are generated based on the effective supply and demand vocabulary included in the cluster. For example, the effective supply and demand vocabulary included in the cluster can be imported into a large language model, and the large language model can be used to summarize and name the cluster based on the effective supply and demand vocabulary included in the cluster to generate skill words matching the cluster.

[0068] A set consisting of the skill words is used as a supply and demand skill word library.

[0069] In this way, the effective supply and demand vocabulary is clustered and integrated into multiple clusters. Each cluster corresponds to a skill word, forming a structured supply and demand skill vocabulary. This systematic integration method allows the originally scattered vocabulary to be presented in a concentrated manner, and can more accurately generate skill words that match demand and supply.

[0070] To more clearly illustrate the process of determining the supply and demand skill vocabulary, you can also refer to Figure 2 , is a schematic diagram of a process for determining a supply and demand skill vocabulary provided by an embodiment of the present disclosure. Figure 2 As shown in , the occupational demand information and the training supply information are segmented separately to obtain multiple occupational demand segmentations and multiple training supply segmentations. Corresponding word vectors are obtained through target neural network processing. Based on the preset word vectors, effective demand vocabulary and effective supply vocabulary are screened and obtained. The effective demand vocabulary and the effective supply vocabulary are aggregated and deduplicated to obtain effective supply and demand vocabulary. The effective supply and demand vocabulary are clustered to obtain at least one cluster. Each cluster is summarized and named to generate skill words to form a supply and demand skill vocabulary. The specific steps are described with reference to the previous embodiment and will not be repeated here.

[0071] In some possible implementations, determining the demand skill words and the supply skill words from the supply and demand skill word library based on the demand effective words and the supply effective words includes: For each of the skill words in the supply and demand skill vocabulary, the supply and demand valid vocabulary included in the cluster corresponding to the skill word is matched with the demand valid vocabulary and the supply valid vocabulary respectively to determine the type of the supply and demand valid vocabulary included in the cluster corresponding to the skill word; the type corresponding to the skill word is a demand skill word and / or a supply skill word.

[0072] Thus, if the cluster corresponding to the skill word includes supply-demand effective words that match the demand effective words successfully and cannot match the supply effective words, it is determined that the skill word belongs to the demand skill word; if the cluster corresponding to the skill word includes supply-demand effective words that cannot match the demand effective words and match the supply effective words successfully, it is determined that the skill word belongs to the supply skill word; if the cluster corresponding to the skill word includes supply-demand effective words that match the demand effective words successfully and match the supply effective words successfully, it is determined that the skill word belongs to both the demand skill word and the supply skill word.

[0073] In this way, by matching the supply-demand effective words included in the cluster with the demand effective words and the supply effective words obtained previously, the type of each skill word is determined, which helps to accurately match the demand skill and the supply skill, improves the accuracy and efficiency of talent skill matching, and provides a more accurate basis for subsequent identification of talent skill gaps.

[0074] In some possible implementation manners, the generating, by matching the demand skill words and the supply skill words, a target identification result of a talent skill gap of at least one industry in the target region comprises: matching the demand skill words and the supply skill words to determine a first skill word, a second skill word, and a third skill word, the first skill word being an intersection between the demand skill words and the supply skill words, the second skill word being a difference set of the demand skill words relative to the supply skill words, and the third skill word being a difference set of the supply skill words relative to the demand skill words; generating, based on the first skill word, the second skill word, and the third skill word, the target identification result of the talent skill gap of the at least one industry in the target region.

[0075] Here, for better understanding of the present embodiment, the foregoing description can be simultaneously referred to Figure 3 A schematic diagram of the present embodiment for matching the demand skill words and the supply skill words is provided. As shown in Figure 3 As shown in the foregoing description, circle A represents the demand skill word, and circle B represents the supply skill word. The demand skill word A and the supply skill word B are matched by statistical software, for example, the demand skill word A and the supply skill word B are matched by the stata software, to determine that the intersection between the demand skill word A and the supply skill word B is the first skill word a, the difference set of the demand skill word A relative to the supply skill word B is the second skill word b, and the difference set of the supply skill word B relative to the demand skill word A is the third skill word c.

[0076] In combination with Figure 3It can be understood that the first skill word a is the same part in the demand skill word A and the supply skill word B, which is regarded as the skill of the industrial development reaching the supply and demand balance at the labor level; the second skill word b is the part included in the demand skill word A but not included in the supply skill word B, that is, the in-demand skill, which is the skill that the demand end needs but the supply end does not supply; the third skill word c is the part included in the supply skill word B but not included in the demand skill word A, that is, the oversupply skill, which is the skill that the supply end has supplied but the demand end does not need.

[0077] In this way, based on the first skill word, the second skill word and the third skill word, a target recognition result of a talent skill gap of at least one industry in the target area is generated, and the target recognition result is used to indicate that the first skill word represents the skill of the industrial development reaching the supply and demand balance at the labor level, the second skill word represents the skill that the demand end needs but the supply end does not supply, and the third skill word represents the skill that the supply end has supplied but the demand end does not need.

[0078] In this way, by comparing the demand skill word and the supply skill word, different parts such as the intersection and the difference set are determined, the matching and the difference of the talent skill between the demand and the supply are effectively recognized, the skill supply and demand conditions from both the demand and the supply ends are fully presented, and then a clear recognition result is generated, thereby providing a strong basis for the regional industrial talent development.

[0079] In some possible implementation manners, the processor is further configured to perform: Based on the target recognition result, a development strategy of the at least one industry in the target area is generated, and the development strategy is used to indicate adjustment information of each skill belonging to the at least one industry, and the development strategy is displayed through the display; An editing processing result of the displayed development strategy is received, and the editing processing result is published.

[0080] Specifically, the development strategy is used to indicate that the industrial development and talent training corresponding to the first skill word are maintained, the talent training corresponding to the second skill word is added, and the talent training corresponding to the third skill word is reduced, cancelled or converted.

[0081] After the processor generates the development strategy, the display is used to display the development strategy. A user can edit the displayed development strategy according to actual development needs, and the processor can further receive an editing processing result of the displayed development strategy and publish the editing processing result.

[0082] In this way, by generating and displaying the development strategy based on the target identification result, clear guidance is provided for subsequent adjustment of the skill-related industrial development and talent training direction, while allowing the development strategy to be edited, so that the demand side or the supply side can flexibly optimize the strategy according to their own needs and environmental changes, thereby enhancing the pertinence and practicality of the development strategy, and better promoting the matching of industrial development and talent training.

[0083] In some possible implementation manners, the processor is further configured to perform: For the target region, based on the target identification result of the talent skill gap of each industry of the target region, the talent matching situation of each industry is determined, so that the industry with poor matching degree of talent training can be developed; and the industry demand situation of each skill can be determined, and the skill with high industry demand but less supply can be preferentially trained.

[0084] In other possible implementation manners, the processor is further configured to perform: For a plurality of target regions, based on the first skill word, the second skill word and the third skill word of each target region, the talent skill gap proportion of each target region is determined, and the development strategy of each target region is determined according to the talent skill gap proportion of each target region.

[0085] In still other possible implementation manners, the processor is further configured to perform: For the target region, based on the second skill word of the target region and the third skill word of other target regions, the matching value of the target region and the other target regions is determined, in the case that the matching value is greater than or equal to a matching threshold, corresponding talent introduction can be performed from the other target regions to the target region according to the second skill word of the target region, and in the case that the matching value is less than the matching threshold, the target region can train talents by itself.

[0086] In still other possible implementation manners, the processor is further configured to perform: The first skill word, the second skill word and the third skill word of the target region in the historical development stage are acquired, and the supply and demand development change index of the target region is determined according to the first skill word, the second skill word and the third skill word of the historical development stage and the first skill word, the second skill word and the third skill word of the current development stage; and the development strategy of each target region is determined based on the supply and demand development change index of each target region.

[0087] The identification device for the regional industrial talent skill gap provided by the embodiments of the present disclosure uses the occupation demand information and the training supply information of the target regional industry when identifying the regional industrial talent skill gap, so that the industrial talent present situation can be analyzed comprehensively and in detail from the two dimensions of demand and supply, the skills that the industry actually expects the talents to have are considered, and the skills that the talent training system can provide are also included, so that the limitations caused by considering from a single dimension are avoided, the comprehensiveness and accuracy of the talent skill gap identification are ensured, and the actual needs of the industrial development are met. Moreover, the occupation demand information and the training supply information are segmented, filtered and clustered to obtain the supply and demand skill library, so that the scattered corpus information is converted into corresponding skills, the complex industrial information is effectively integrated, and the distribution of industrial skills is more systematically presented, laying a solid foundation for positioning the gap.

[0088] The embodiments of the present disclosure also provide an identification method for a regional industrial talent skill gap. Next, the identification method for a regional industrial talent skill gap provided by the embodiments of the present disclosure will be described in detail. The execution subject of the identification method for a regional industrial talent skill gap provided by the embodiments of the present disclosure is generally the identification device for a regional industrial talent skill gap described above. The identification device for a regional industrial talent skill gap can be a terminal device or other processing device. The terminal device can be a mobile device, a terminal and a computing device, etc. The other processing device can be a device including a processor and a memory, which is not limited here.

[0089] Referring to Figure 4 FIG. 4 is a flowchart of an identification method for a regional industrial talent skill gap provided by the embodiments of the present disclosure, as shown in Figure 4 The identification method for a regional industrial talent skill gap provided by the embodiments of the present disclosure includes steps S401-S405, wherein: S401: Obtain industrial information corresponding to at least one industry of a target region, wherein the industrial information includes occupation demand information and training supply information.

[0090] S402: Perform word segmentation processing on the occupation demand information and the training supply information respectively, and filter the word segmentation results to obtain effective supply and demand words, wherein the effective supply and demand words include effective demand words and effective supply words.

[0091] In some possible implementation manners, the word segmentation processing on the occupation demand information and the training supply information respectively, and the filtering of the word segmentation results to obtain the effective supply and demand words include: Perform word segmentation processing on the occupation demand information and the training supply information respectively to obtain a plurality of occupation demand words and a plurality of training supply words. The target neural network is used to process each of the professional demand word segmentation and each of the training supply word segmentation, to obtain a demand word vector corresponding to each of the professional demand word segmentation and a supply word vector corresponding to each of the training supply word segmentation; Based on the preset skill word vector, demand effective vocabularies are screened out from the plurality of professional demand word segmentations, and supply effective vocabularies are screened out from the plurality of training supply word segmentations; the preset skill word vector is obtained by processing a preset skill word through the target neural network; The demand effective vocabularies and the supply effective vocabularies are summarized and de-duplicated to obtain supply-demand effective vocabularies.

[0092] In some possible implementation manners, the screening of the demand effective vocabularies from the plurality of professional demand word segmentations and the screening of the supply effective vocabularies from the plurality of training supply word segmentations based on the preset skill word vector include: The similarity between the preset skill word vector and each of the demand word vectors and the similarity between the preset skill word vector and each of the supply word vectors are determined; The professional demand word segmentation corresponding to the demand word vector with a similarity greater than or equal to a target threshold is determined as the demand effective vocabulary, and the training supply word segmentation corresponding to the supply word vector with a similarity greater than or equal to the target threshold is determined as the supply effective vocabulary.

[0093] S403: The supply-demand effective vocabularies are clustered to obtain a supply-demand skill word library composed of skill words corresponding to each cluster.

[0094] In some possible implementation manners, the clustering of the supply-demand effective vocabularies to obtain a supply-demand skill word library composed of skill words corresponding to each cluster includes: The supply-demand effective vocabularies are clustered to obtain at least one cluster; For each of the clusters, a skill word matched with the cluster is generated based on the supply-demand effective vocabularies included in the cluster; The supply-demand skill word library is composed of the skill words.

[0095] S404: Demand skill words and supply skill words are determined from the supply-demand skill word library based on the demand effective vocabularies and the supply effective vocabularies.

[0096] In some possible implementation manners, the determination of the demand skill words and the supply skill words from the supply-demand skill word library based on the demand effective vocabularies and the supply effective vocabularies includes: For each of the skill words in the supply-demand skill library, the supply-demand effective words included in the cluster corresponding to the skill word are matched with the demand effective words and the supply effective words respectively to determine the type of the supply-demand effective words included in the cluster corresponding to the skill word; the type corresponding to the skill word is a demand skill word and / or a supply skill word.

[0097] S405: generating a target recognition result of a talent skill gap of at least one industry in the target region by performing comparison processing between the demand skill words and the supply skill words.

[0098] In some possible implementation manners, the generating a target recognition result of a talent skill gap of at least one industry in the target region by performing comparison processing between the demand skill words and the supply skill words includes: performing comparison between the demand skill words and the supply skill words to determine a first skill word, a second skill word and a third skill word, the first skill word being an intersection between the demand skill words and the supply skill words, the second skill word being a difference set of the demand skill words relative to the supply skill words, and the third skill word being a difference set of the supply skill words relative to the demand skill words; generating a target recognition result of a talent skill gap of at least one industry in the target region based on the first skill word, the second skill word and the third skill word.

[0099] In some possible implementation manners, the method further includes: generating a development strategy of the at least one industry in the target region based on the target recognition result, and displaying the development strategy, the development strategy being used to indicate adjustment information of each skill belonging to the at least one industry; receiving an editing processing result of the displayed development strategy, and publishing the editing processing result.

[0100] Those skilled in the art can understand that, in the above method of the specific implementation manner, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process, and the specific execution order of each step should be determined according to its function and possible internal logic.

[0101] It should be noted that the above method provided by the embodiment of the present application can realize all steps realized by the above device embodiment and achieve the same technical effects, and thus the same parts and beneficial effects of the method embodiment as the device embodiment will not be described in detail.

[0102] Based on the same inventive concept, the disclosure embodiments also provide a device for identifying regional industrial talent skill gap corresponding to the method for identifying regional industrial talent skill gap. Since the device for identifying regional industrial talent skill gap in the disclosure embodiments solves the problem in a similar principle to the above-mentioned method for identifying regional industrial talent skill gap in the disclosure embodiments, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0103] Please refer to Figure 5 , Figure 5 A schematic diagram of a device for identifying regional industrial talent skill gap provided by the disclosure embodiments. As shown in Figure 5 The device for identifying regional industrial talent skill gap 500 provided by the disclosure embodiments comprises: The collection module 510 is configured to obtain industrial information corresponding to at least one industry in a target region, wherein the industrial information comprises occupation demand information and training supply information; The screening module 520 is configured to perform word segmentation processing on the occupation demand information and the training supply information respectively, and screen the word segmentation results to obtain effective supply and demand words, wherein the effective supply and demand words comprise effective demand words and effective supply words; The clustering module 530 is configured to perform clustering processing on the effective supply and demand words to obtain a supply and demand skill word library composed of skill words corresponding to each cluster; The classification module 540 is configured to determine demand skill words and supply skill words from the supply and demand skill word library based on the effective demand words and the effective supply words; The comparison module 550 is configured to generate a target identification result of talent skill gap for at least one industry in the target region by comparing the demand skill words and the supply skill words.

[0104] In an optional implementation, the screening module 520 is specifically configured to: perform word segmentation processing on the occupation demand information and the training supply information respectively to obtain a plurality of occupation demand words and a plurality of training supply words; process each of the occupation demand words and each of the training supply words through a target neural network to obtain a demand word vector corresponding to each of the occupation demand words and a supply word vector corresponding to each of the training supply words; screen the effective demand words from the plurality of occupation demand words and the effective supply words from the plurality of training supply words based on a preset skill word vector, wherein the preset skill word vector is obtained by processing a preset skill word through the target neural network; perform summarization and deduplication processing on the effective demand words and the effective supply words to obtain effective supply and demand words.

[0105] In an optional implementation, when the screening module 520 is configured to screen demand valid words from the plurality of professional demand words based on the preset skill word vector and screen supply valid words from the plurality of training supply words, the screening module 520 is specifically configured to: determine similarities between the preset skill word vector and each of the demand word vectors and similarities between the preset skill word vector and each of the supply word vectors; determine the professional demand words corresponding to the demand word vectors with similarities greater than or equal to a target threshold as the demand valid words and determine the training supply words corresponding to the supply word vectors with similarities greater than or equal to the target threshold as the supply valid words.

[0106] In an optional implementation, the clustering module 530 is specifically configured to: perform clustering processing on the demand-supply valid words to obtain at least one cluster; for each of the clusters, generate a skill word matched with the cluster based on the demand-supply valid words included in the cluster; compose a demand-supply skill word library through the skill words.

[0107] In an optional implementation, the classification module 540 is specifically configured to: for each of the skill words in the demand-supply skill word library, match the demand-supply valid words included in the cluster corresponding to the skill word with the demand valid words and the supply valid words respectively, and determine the type of the demand-supply valid words included in the cluster corresponding to the skill word; the type corresponding to the skill word is a demand skill word and / or a supply skill word.

[0108] In an optional implementation, the comparison module 550 is specifically configured to: compare the demand skill words and the supply skill words to determine a first skill word, a second skill word, and a third skill word, the first skill word is an intersection between the demand skill words and the supply skill words, the second skill word is a difference set of the demand skill words relative to the supply skill words, and the third skill word is a difference set of the supply skill words relative to the demand skill words; generate a target recognition result of a talent skill gap of at least one industry in the target region based on the first skill word, the second skill word, and the third skill word.

[0109] In an optional implementation, the comparison module 550 is further configured to: Based on the target recognition result, a development strategy of the at least one industry in the target region is generated, and the development strategy is displayed, wherein the development strategy is used to indicate adjustment information of each skill belonging to the at least one industry. An editing processing result for the displayed development strategy is received, and the editing processing result is published.

[0110] The description of the processing flow of each module in the device and the interaction flow between the modules can refer to the related description in the above method embodiments, and will not be described in detail here.

[0111] It should be noted that the above device provided by the embodiments of the present disclosure can realize all the steps realized by the above device embodiments and achieve the same technical effects. Therefore, the same parts and beneficial effects of the device embodiments as the device embodiments will not be described in detail here.

[0112] The embodiments of the present disclosure also provide a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the method for identifying the regional industrial talent skill gap described in the above method embodiments are executed. The storage medium can be a volatile or non-volatile computer readable storage medium.

[0113] The embodiments of the present disclosure also provide a computer program product. When the computer program product is invoked by a computer, the computer executes the steps of the method for identifying the regional industrial talent skill gap described in the above method embodiments. For details, please refer to the above method embodiments, which will not be described here.

[0114] The above computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device and the apparatus described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here. In several embodiments provided in the present disclosure, it should be understood that the disclosed device, apparatus and method can be implemented in other ways. The apparatus embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there can be another division in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0116] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0117] In addition, the functional units in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0118] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present disclosure essentially or the part of the prior art or the part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present disclosure. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, and various program code storage media.

[0119] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, and are not intended to limit the present disclosure. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can make modifications or easy changes to the technical solutions described in the foregoing embodiments, or easily think of changes or equivalent replacements for some of the technical features; and these modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A device for identifying regional industry talent skill gaps, characterized by: The processor, memory, display are connected through a bus, the processor is used to store computer instructions, the display is used to display the processing result of the processor, and the processing result includes the target identification result generated by the processor; the processor is used to read the computer instructions stored in the memory to perform the following operations: Obtain industry information corresponding to at least one industry of a target area, the industry information including occupation demand information and training supply information; The occupation demand information and the training supply information are respectively subjected to word segmentation processing, and the word segmentation results are screened to obtain supply and demand effective words, the supply and demand effective words including demand effective words and supply effective words; The supply and demand effective words are subjected to clustering processing to obtain a supply and demand skill word library composed of skill words corresponding to each cluster; Based on the demand effective words and the supply effective words, demand skill words and supply skill words are determined from the supply and demand skill word library; By comparing the demand skill words and the supply skill words, a target identification result of talent skill gap for at least one industry of the target area is generated.

2. The apparatus of claim 1, wherein, The occupation demand information and the training supply information are respectively subjected to word segmentation processing, and the word segmentation results are screened to obtain supply and demand effective words, including: The occupation demand information and the training supply information are respectively subjected to word segmentation processing to obtain a plurality of occupation demand words and a plurality of training supply words; Each of the occupation demand words and each of the training supply words is processed by a target neural network to obtain a demand word vector corresponding to each of the occupation demand words and a supply word vector corresponding to each of the training supply words; Based on a preset skill word vector, demand effective words are screened from the plurality of occupation demand words, and supply effective words are screened from the plurality of training supply words; the preset skill word vector is obtained by processing a preset skill word by the target neural network; The demand effective words and the supply effective words are summarized and de-duplicated to obtain supply and demand effective words.

3. The apparatus of claim 2, wherein, The demand effective words are screened from the plurality of occupation demand words based on a preset skill word vector, and the supply effective words are screened from the plurality of training supply words based on the preset skill word vector, including: The similarity between the preset skill word vector and each of the demand word vectors and the similarity between the preset skill word vector and each of the supply word vectors are determined; The occupation demand words corresponding to the demand word vectors with a similarity greater than or equal to a target threshold value are determined as the demand effective words, and the training supply words corresponding to the supply word vectors with a similarity greater than or equal to the target threshold value are determined as the supply effective words.

4. The apparatus of claim 1, wherein, The supply and demand effective words are subjected to clustering processing to obtain a supply and demand skill word library composed of skill words corresponding to each cluster, including: The supply and demand effective words are subjected to clustering processing to obtain at least one cluster; For each of the clusters, a skill word matching the cluster is generated based on the supply-demand effective words included in the cluster; The supply-demand skill word library is composed of the skill words.

5. The apparatus of claim 1, wherein, The determination of the demand skill words and the supply skill words from the supply-demand skill word library based on the demand effective words and the supply effective words comprises: For each of the skill words in the supply-demand skill word library, the supply-demand effective words included in the cluster corresponding to the skill word are matched with the demand effective words and the supply effective words respectively to determine the type of the supply-demand effective words included in the cluster corresponding to the skill word; the type corresponding to the skill word is the demand skill word and / or the supply skill word.

6. The apparatus of claim 1, wherein, The generation of the target recognition result of the talent skill gap of at least one industry in the target area by comparing the demand skill words and the supply skill words comprises: The demand skill words and the supply skill words are compared to determine a first skill word, a second skill word and a third skill word, the first skill word is the intersection between the demand skill words and the supply skill words, the second skill word is the difference set of the demand skill words relative to the supply skill words, and the third skill word is the difference set of the supply skill words relative to the demand skill words; The target recognition result of the talent skill gap of at least one industry in the target area is generated based on the first skill word, the second skill word and the third skill word.

7. The apparatus of claim 1, wherein, The processor is further configured to perform: Based on the target recognition result, a development strategy of the at least one industry in the target area is generated, the development strategy is used to indicate the adjustment information of each skill belonging to the at least one industry, and the development strategy is displayed through the display; An editing processing result for the displayed development strategy is received, and the editing processing result is published.

8. A method for identifying regional industry talent skill gap, characterized in that, The method comprises: Obtaining industry information corresponding to at least one industry in a target area, the industry information comprising occupation demand information and cultivation supply information; Performing word segmentation processing on the occupation demand information and the cultivation supply information respectively, and screening the word segmentation results to obtain supply-demand effective words, the supply-demand effective words comprising demand effective words and supply effective words; Performing clustering processing on the supply-demand effective words to obtain a supply-demand skill word library composed of skill words corresponding to respective clusters; Determining demand skill words and supply skill words from the supply-demand skill word library based on the demand effective words and the supply effective words; Generating a target recognition result of a talent skill gap of at least one industry in the target area by comparing the demand skill words and the supply skill words.

9. A device for identifying regional industry talent skill gap, characterized in that, The device comprises: A collection module configured to obtain industry information corresponding to at least one industry in a target area, the industry information comprising occupation demand information and cultivation supply information; The screening module is configured to perform word segmentation on the professional demand information and the cultivation supply information respectively, and screen the word segmentation results to obtain supply-demand effective words, wherein the supply-demand effective words include demand effective words and supply effective words; The clustering module is configured to perform clustering on the supply-demand effective words to obtain a supply-demand skill word library composed of skill word groups corresponding to respective clusters; The classification module is configured to determine demand skill words and supply skill words from the supply-demand skill word library based on the demand effective words and the supply effective words; The comparison module is configured to generate a target recognition result of talent skill gaps of at least one industry in the target region by comparing the demand skill words and the supply skill words.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is run by the processor to perform the steps of the method for identifying talent skill gaps of a regional industry according to claim 9.

Images