Target person matching method and device based on knowledge graph, equipment and medium

Abstract

The application discloses a target personnel matching method and device based on a knowledge graph, equipment and a medium. The method comprises the following steps: determining the knowledge graph feature of a to-be-processed project, and acquiring the knowledge graph feature of at least one candidate personnel in a pre-established personnel feature library; wherein the knowledge graph feature is determined based on target word statistical information in knowledge graph data; determining the ranking result of each candidate personnel according to the knowledge graph feature of the to-be-processed project and the knowledge graph feature of each candidate personnel; and determining the target personnel matched with the to-be-processed project according to the ranking result. The technical scheme solves the problems of low precision and large error of target personnel matching, and can improve the matching efficiency while improving the accuracy of target personnel matching.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a method, apparatus, device, and medium for matching target personnel based on knowledge graphs. Background Technology

[0002] Currently, the selection of reviewers for science and technology projects is usually based on matching keywords from the reviewers' fields with keywords from the project's field to obtain a list of candidate reviewers. Then, the required number of reviewers are manually selected from the list of candidate reviewers as target reviewers.

[0003] However, a reviewer typically has expertise in multiple fields, and within each field, they may only be familiar with one or a few specific areas. Therefore, existing technologies based on domain keywords struggle to achieve precise matching of reviewers, and when projects fall into interdisciplinary areas, the matching methods of existing technologies are prone to significant errors. Summary of the Invention

[0004] This invention provides a target person matching method, apparatus, equipment, and medium based on knowledge graphs to solve the problems of low accuracy and large error in target person matching, thereby improving matching efficiency while increasing the accuracy of target person matching.

[0005] According to one aspect of the present invention, a target person matching method based on knowledge graph is provided, the method comprising:

[0006] The knowledge graph features of the project to be processed are determined, and the knowledge graph features of at least one candidate are obtained from a pre-established personnel feature database; wherein, the knowledge graph features are determined based on the target word statistical information in the knowledge graph data;

[0007] Based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate, the ranking results of each candidate are determined.

[0008] Based on the sorting results, target personnel matching the projects to be processed are determined.

[0009] According to another aspect of the present invention, a target person matching device based on a knowledge graph is provided, the device comprising:

[0010] The feature determination module is used to determine the knowledge graph features of the project to be processed, and to obtain the knowledge graph features of at least one candidate from a pre-established personnel feature database; wherein, the knowledge graph features are determined based on the target word statistical information in the knowledge graph data;

[0011] The ranking result determination module is used to determine the ranking result of each candidate based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate.

[0012] The target personnel identification module is used to identify target personnel that match the project to be processed based on the sorting results.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target person matching method based on knowledge graph according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the knowledge graph-based target person matching method according to any embodiment of the present invention.

[0018] The technical solution of this invention determines the knowledge graph features of the project to be processed and the knowledge graph features of the candidates by using statistical information of target words in knowledge graph data; then, based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, the ranking result of each candidate is determined; and finally, based on the ranking result, the target personnel matching the project to be processed are determined. This technical solution solves the problems of low accuracy and large error in target personnel matching, and can improve the matching efficiency while improving the accuracy of target personnel matching.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1This is a flowchart of a target person matching method based on knowledge graphs according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a target person matching method based on a knowledge graph according to Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of a target person matching device based on a knowledge graph according to Embodiment 3 of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the target person matching method based on knowledge graphs according to embodiments of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0027] Example 1

[0028] Figure 1 This invention provides a flowchart of a target personnel matching method based on a knowledge graph, as described in Embodiment 1. This embodiment is applicable to expert matching scenarios in science and technology projects. The method can be executed by a target personnel matching device based on a knowledge graph. This device can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0029] S110. Determine the knowledge graph features of the project to be processed, and obtain the knowledge graph features of at least one candidate from the pre-established personnel feature database.

[0030] This solution can be implemented by a project management platform, which can be used to manage tasks such as project creation, submission, review, and execution. Project leaders can submit project application documents through the project management platform for review, task allocation, and other processing.

[0031] The project management platform can generate a knowledge graph for the project to be processed based on application documents, applicant information, and other data, and extract knowledge graph features. These features can be determined based on statistical information of target words within the knowledge graph data. The platform can segment the knowledge graph data of the project to be processed into words and statistically analyze the frequency and location of target words. These target words can be thematic terms within the project's domain. The platform can assign weights to each target word based on the statistical information, and then determine the knowledge graph features of the project to be processed based on each target word and its weight. Specifically, the platform can encode each target word and use the weighted sum of these encodings as the knowledge graph features of the project to be processed.

[0032] The project management platform can pre-establish a personnel feature database to match suitable personnel for each project. This database may include feature databases for reviewers and executors. Similar to the projects, the platform can pre-build a knowledge graph for each individual based on their submitted personal information. This knowledge graph may include information such as representative publications, relationships with other individuals, project work undertaken, and educational background. The platform can then extract the features from these knowledge graphs to establish its own personnel feature database.

[0033] It should be noted that the project management platform can extract knowledge graph features from personnel feature databases for different purposes using the same or different methods. For example, the knowledge graph features in the reviewer feature database can be determined based on the information related to project review work in the reviewers' knowledge graph data. The knowledge graph features in the executor feature database can be determined based on the information related to project execution work in the executor's knowledge graph data.

[0034] The project management platform can use all personnel in the personnel feature database as candidates and obtain the knowledge graph features of each candidate. Alternatively, the platform can determine a target personnel category based on pre-defined personnel categories in the database, and use personnel within that target category as candidates, obtaining the knowledge graph features of each candidate. The personnel classification can be based on the personnel's location or their field of expertise. The personnel classification can be single-level or multi-level. This embodiment does not limit the method of personnel classification.

[0035] S120. Based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate, determine the ranking result of each candidate.

[0036] The project management platform can compare the knowledge graph features of the project to be processed with the knowledge graph features of each candidate, and determine the ranking of each candidate based on the comparison results.

[0037] Optionally, in this solution, determining the ranking result of each candidate based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate includes:

[0038] Based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, the feature similarity between the project to be processed and each candidate is calculated respectively.

[0039] The ranking of each candidate is determined based on feature similarity.

[0040] The project management platform can calculate the feature similarity between the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, and then rank the candidates according to the feature similarity. The feature similarity can be determined based on the distance between the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, such as Euclidean distance, cosine distance, or Hamming distance. The ranking of the candidates can be in descending order of similarity or in ascending order of similarity.

[0041] In a specific example, the formula for calculating feature similarity can be expressed as:

[0042] similarity(x,y)=D(x,y) / bitcount;

[0043] Where x represents the knowledge graph feature vector of the project to be processed, y represents the knowledge graph feature vector of the candidate, D(x,y) represents the distance between feature vectors x and y, and bitcount represents the bit length of the feature vector.

[0044] This scheme uses bit-by-bit comparison calculations, with each comparison calculation taking only milliseconds, enabling large-scale personnel search and matching and improving the real-time performance of personnel matching.

[0045] S130. Based on the sorting results, determine the target personnel that match the project to be processed.

[0046] The project management platform can select candidates whose feature similarity meets preset similarity requirements from among the candidates based on the ranking results. For example, candidates with a feature similarity higher than 80% can be selected as target personnel for the project to be processed. The platform can also select a preset number of candidates from among the candidates based on the ranking results. For example, it can select three candidates with high feature similarity as target personnel.

[0047] This technical solution uses statistical information of target words in knowledge graph data to determine the knowledge graph features of the project to be processed and the knowledge graph features of the candidates. Then, based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, the ranking results of each candidate are determined. Finally, based on the ranking results, the target personnel matching the project to be processed are determined. This technical solution solves the problems of low accuracy and large error in target personnel matching, and can improve the matching efficiency while improving the accuracy of target personnel matching.

[0048] Example 2

[0049] Figure 2 This is a flowchart of a target person matching method based on knowledge graphs provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2 As shown, the method includes:

[0050] S210. If a target personnel matching request for the project to be processed is detected, the knowledge graph data of the project to be processed is determined.

[0051] When the project management platform detects a target personnel matching request for a project to be processed, it can obtain the knowledge graph data of the project. The target personnel matching request may include reviewer matching requests, executor matching requests, etc. The knowledge graph data of the project to be processed may include information such as the project name, expected completion time, and project application content.

[0052] S220. Segment the knowledge graph data of the project to be processed into words and determine the statistical information of the first target word.

[0053] The project management platform can aggregate the knowledge graph data of projects to be processed, generate a summary text, and segment the summary text using a word segmentation model to obtain statistical information such as the word segmentation list, word count, and word frequency. The platform can remove non-professional topic words from the word segmentation list to obtain professional topic words, which are then used as target words. These non-professional topic words may include relation transformation terms and commonly used non-professional terms. The statistical information for the first target word may include the number of times each target word appears, its frequency, and its central location within the knowledge graph data of the projects to be processed.

[0054] S230. Based on the statistical information of the first target word, determine the knowledge graph features of the project to be processed.

[0055] The project management platform can determine the weight of each primary target word based on the statistical information of the primary target words, and determine the knowledge graph features of the project to be processed based on each primary target word and its weight.

[0056] In this scheme, optionally, determining the knowledge graph features of the item to be processed based on the statistical information of the first target word includes:

[0057] Based on the preset encoding method, determine the feature encoding of each first target word;

[0058] Based on the feature encoding of each first target word and the word frequency of each first target word, the knowledge graph features of the project to be processed are determined;

[0059] The project management platform can perform feature encoding on each primary target word, which can be implemented based on hash encoding. The platform can use the word frequency of each primary target word as a weight for matching it. Based on the feature encoding of each primary target word and its matching weight, a weighted sum of the primary target words is calculated. The platform can directly use this weighted sum as the knowledge graph feature of the project to be processed, or it can reduce the dimensionality of the weighted sum to obtain the knowledge graph feature of the project.

[0060] In one feasible scheme, determining the knowledge graph features of the project to be processed based on the feature encoding of each first target word and the word frequency of each first target word includes:

[0061] If the first target word is a keyword in the knowledge graph data of the project to be processed, then the knowledge graph features of the project to be processed are determined based on the feature encoding of each first target word, the word frequency of each first target word, and the weight of keyword matching.

[0062] The project management platform can extract keywords from the project application of the projects to be processed. If the primary target keyword is a keyword in the knowledge graph data of the project to be processed, the platform can determine whether the keyword frequency meets the preset weight requirements. If the keyword frequency is higher than or equal to the preset weight requirements, the keyword weight will not be adjusted. If the keyword frequency is lower than the preset weight requirements, the keyword frequency can be adjusted using keyword matching weights to increase the keyword weight.

[0063] The project management platform can calculate the weighted sum of each first target word by taking the adjusted keyword weights, the feature codes of each first target word, and the word frequencies of each first target word other than the keywords, and use the weighted sum as the knowledge graph features of the project to be processed.

[0064] This approach adjusts the weights of keywords to better match the knowledge graph characteristics of the project to be processed, which helps to avoid the deviation in the description of the project by the knowledge graph characteristics caused by low keyword frequency.

[0065] S240. Obtain at least one candidate's knowledge graph features from a pre-established personnel feature database.

[0066] The process of establishing the personnel feature database includes:

[0067] The knowledge graph data of each candidate are segmented into words to determine the statistical information of the second target word;

[0068] Based on the statistical information of the second target word, the knowledge graph characteristics of each candidate are determined, and the fields involved by each candidate are identified.

[0069] Based on the fields involved in each candidate and the characteristics of each candidate's knowledge graph, a personnel feature database is determined.

[0070] The project management platform can aggregate the knowledge graph data of each candidate, generate a summary text, and segment the summary text using a word segmentation model to obtain statistical information such as the word segmentation list, word count, and word frequency. The platform can then remove non-professional keywords from the segmentation list to obtain professional keywords, which will be used as target keywords. These non-professional keywords may include relation transformation terms and commonly used non-professional terms. The statistical information for the second target keyword may include the number of times each target keyword appears, its frequency, and its central location within the candidate's knowledge graph data.

[0071] The project management platform can determine the weight of each second target term based on its statistical information, and then determine the knowledge graph features of each candidate based on the second target term and its weight. Simultaneously, the platform can also determine the domains involved in each candidate based on the second target term statistical information. Specifically, the platform can consider the domains associated with each second target term as the domains involved in the candidate, or it can consider the domains associated with second target terms that appear more than a preset threshold as the domains involved in the candidate. This embodiment does not limit the method for determining the domains involved in the candidate.

[0072] The project management platform can categorize personnel by domain, grouping candidates within the same domain together to create a personnel feature database encompassing all domains. It's important to note that a single candidate can be involved in one or multiple domains. If a candidate is involved in multiple domains, their knowledge graph features will be included in each domain's database.

[0073] In a preferred embodiment, after determining the statistical information of the first target word, the method further includes:

[0074] Based on the statistical information of the first target words, the target areas involved in the projects to be processed are determined;

[0075] The step of obtaining the knowledge graph features of at least one candidate from a pre-established personnel feature database includes:

[0076] Obtain the knowledge graph features of each candidate in the target domain from a pre-established personnel feature database.

[0077] Similar to the statistical information of the second target term, the project management platform can also determine the target domains involved in the project to be processed based on the statistical information of the first target term. Specifically, the project management platform can use the domains associated with each first target term as the target domains involved in the project to be processed, or it can use the domains associated with first target terms that appear more than a preset threshold as the target domains involved in the project to be processed. This embodiment does not limit the method for determining the target domains involved in the project to be processed.

[0078] It should be noted that the target domain of the project to be processed can be one or more, such as cross-domain projects. For projects involving multiple target domains, the project management platform can perform knowledge graph matching of candidates for each target domain.

[0079] This scheme can classify candidates by field, which helps to narrow down the range of personnel to be matched for projects, and improves matching efficiency and accuracy.

[0080] Specifically, determining the knowledge graph features of each candidate based on the statistical information of the second target word includes:

[0081] Based on the preset encoding method, determine the feature encoding of each second target word;

[0082] Based on the feature encoding of each second target word and the word frequency of each second target word, the knowledge graph features of each candidate are determined.

[0083] The project management platform can perform feature encoding on each second target word, which can be implemented based on hash encoding. The platform can use the word frequency of each second target word as a weight for matching it with other second target words. Based on the feature encoding of each second target word and its matching weight, the platform calculates a weighted sum of the second target words. The platform can directly use this weighted sum as the knowledge graph feature of each candidate, or it can perform dimensionality reduction on the weighted sum to obtain the knowledge graph feature of each candidate.

[0084] In a specific example, the formula for calculating the knowledge graph features of a candidate can be expressed as:

[0085]

[0086] Where i represents the second target word index, j represents the candidate index, and w i This represents the encoding of the second target word, h(w) i ) represents the weight of the second target word matching, and n represents the number of second target words.

[0087] S250. Based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate, determine the ranking result of each candidate.

[0088] Based on the above scheme, the step of determining the ranking result of each candidate according to the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate includes:

[0089] If there is more than one target domain, then for each target domain, the ranking result of each candidate in the target domain is determined based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate in the target domain.

[0090] The ranking results of each target domain are merged to obtain the ranking results of each candidate.

[0091] If there are multiple target domains, the project management platform can compare the knowledge graph features of the project to be processed with the knowledge graph features of each candidate in the current target domain for each target domain, and determine the ranking of each candidate in the current target domain.

[0092] After obtaining the candidate ranking results for each target domain, the project management platform can merge the ranking results to prevent duplicate candidate matching. For candidates who appear multiple times in different ranking results, the platform can randomly retain one of the ranking results or retain the highest-ranked result. The platform can then use the merged ranking results from each target domain as the final ranking result for all candidates. Specifically, the platform can re-rank the ranking results from each target domain according to feature similarity to obtain the final ranking result for each candidate.

[0093] The above solution can avoid duplicate matching of projects involving multiple fields during the personnel matching process, which helps to improve the reliability of personnel matching.

[0094] S260. Based on the sorting results, determine the target personnel that match the project to be processed.

[0095] This technical solution uses statistical information of target words in knowledge graph data to determine the knowledge graph features of the project to be processed and the knowledge graph features of the candidates. Then, based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, the ranking results of each candidate are determined. Finally, based on the ranking results, the target personnel matching the project to be processed are determined. This technical solution solves the problems of low accuracy and large error in target personnel matching, and can improve the matching efficiency while improving the accuracy of target personnel matching.

[0096] Example 3

[0097] Figure 3 This is a schematic diagram of a target person matching device based on a knowledge graph, provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0098] The feature determination module 310 is used to determine the knowledge graph features of the project to be processed, and to obtain the knowledge graph features of at least one candidate from a pre-established personnel feature database; wherein, the knowledge graph features are determined based on the target word statistical information in the knowledge graph data;

[0099] The ranking result determination module 320 is used to determine the ranking result of each candidate based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate.

[0100] The target personnel determination module 330 is used to determine the target personnel that match the project to be processed based on the sorting results.

[0101] In this solution, optionally, the feature determination module 310 includes:

[0102] The data determination unit is used to determine the knowledge graph data of the project to be processed if a target personnel matching request for the project to be processed is detected.

[0103] The first statistical information determination unit is used to segment the knowledge graph data of the project to be processed and determine the statistical information of the first target word.

[0104] The project feature determination unit is used to determine the knowledge graph features of the project to be processed based on the statistical information of the first target word;

[0105] The personnel feature acquisition unit is used to acquire the knowledge graph features of at least one candidate from a pre-established personnel feature database.

[0106] The device further includes a personnel feature database establishment module, which includes:

[0107] The second statistical information determination unit is used to segment the knowledge graph data of each candidate and determine the statistical information of the second target word.

[0108] The personnel feature determination unit is used to determine the knowledge graph features of each candidate based on the statistical information of the second target word, and to determine the fields involved by each candidate;

[0109] The personnel feature database determination unit is used to determine the personnel feature database based on the fields involved in each candidate and the knowledge graph characteristics of each candidate.

[0110] Based on the above scheme, the target word statistics information includes the word frequency of each target word;

[0111] The project feature determination unit is specifically used for:

[0112] Based on the preset encoding method, determine the feature encoding of each first target word;

[0113] Based on the feature encoding of each first target word and the word frequency of each first target word, the knowledge graph features of the project to be processed are determined;

[0114] The personnel characteristic determination unit is specifically used for:

[0115] Based on the preset encoding method, determine the feature encoding of each second target word;

[0116] Based on the feature encoding of each second target word and the word frequency of each second target word, the knowledge graph features of each candidate are determined.

[0117] In one feasible embodiment, the project feature determination unit is further configured to:

[0118] If the first target word is a keyword in the knowledge graph data of the project to be processed, then the knowledge graph features of the project to be processed are determined based on the feature encoding of each first target word, the word frequency of each first target word, and the weight of keyword matching.

[0119] In this embodiment, optionally, the sorting result determination module 320 includes:

[0120] The similarity calculation unit is used to calculate the feature similarity between the project to be processed and each candidate based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate.

[0121] The ranking result determination unit is used to determine the ranking result of each candidate based on feature similarity.

[0122] In one feasible embodiment, the first statistical information determining unit is further configured to:

[0123] Based on the statistical information of the first target words, the target areas involved in the projects to be processed are determined;

[0124] The personnel feature acquisition unit is specifically used for:

[0125] Obtain the knowledge graph features of each candidate in the target domain from a pre-established personnel feature database.

[0126] Based on the above scheme, optionally, the sorting result determination module 320 includes:

[0127] The domain ranking result determination unit is used to determine the ranking result of each candidate in the target domain for each target domain if the number of target domains is greater than one, based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate in the target domain.

[0128] The merge sorting result determination unit is used to merge the sorting results of each target domain to obtain the sorting result of each candidate.

[0129] The target personnel matching device based on knowledge graph provided in the embodiments of the present invention can execute the target personnel matching method based on knowledge graph provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0130] Example 4

[0131] Figure 4A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0132] like Figure 4 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0133] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0134] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as target person matching methods based on knowledge graphs.

[0135] In some embodiments, the knowledge graph-based target person matching method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the knowledge graph-based target person matching method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the knowledge graph-based target person matching method by any other suitable means (e.g., by means of firmware).

[0136] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0137] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0138] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0139] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0140] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0141] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0142] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0143] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A knowledge graph-based target personnel matching method, characterized in that, The method includes: If a target personnel matching request for a project to be processed is detected, the knowledge graph data of the project to be processed is determined. The knowledge graph data of the project to be processed is segmented into words to determine the statistical information of the first target word; Based on the statistical information of the first target word, the knowledge graph features of the project to be processed are determined; Obtain at least one candidate's knowledge graph features from a pre-established personnel feature database; Based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate, the ranking results of each candidate are determined. Based on the sorting results, target personnel matching the projects to be processed are determined; The process of establishing the personnel feature database includes: The knowledge graph data of each candidate are segmented into words to determine the statistical information of the second target word; Based on the statistical information of the second target word, the knowledge graph characteristics of each candidate are determined, and the fields involved by each candidate are identified. Based on the fields involved in each candidate and the knowledge graph characteristics of each candidate, a personnel feature database is determined; The step of determining the knowledge graph features of the project to be processed based on the statistical information of the first target word includes: Based on the preset encoding method, determine the feature encoding of each first target word; Based on the feature encoding of each first target word and the word frequency of each first target word, the knowledge graph features of the project to be processed are determined; The step of determining the knowledge graph features of each candidate based on the statistical information of the second target word includes: Based on the preset encoding method, determine the feature encoding of each second target word; Based on the feature encoding of each second target word and the word frequency of each second target word, the knowledge graph features of each candidate are determined; The formula for calculating the knowledge graph features of the candidates is as follows: ; denotes a second target word index, denotes a candidate person index, denotes a second target word encoding, denotes a weight of the second target word matching, denotes a second target word quantity; The step of determining the knowledge graph features of the project to be processed based on the feature encoding and word frequency of each first target word includes: If the first target word is a keyword in the knowledge graph data of the project to be processed, then it is determined whether the word frequency of the keyword meets the preset weight requirement. If the word frequency of the keyword is higher than or equal to the preset weight requirement, the weight of the keyword is not adjusted. If the word frequency of the keyword is lower than the preset weight requirement, the word frequency of the keyword is adjusted by using the weight of keyword matching to increase the weight of the keyword. The adjusted keyword weights, feature codes of each first target word, and word frequencies of each first target word other than the keywords are used to calculate the weighted sum of each first target word. The weighted sum is then used as the knowledge graph feature of the project to be processed.

2. The method of claim 1, wherein, The process of determining the ranking of each candidate based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate includes: Based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate, the feature similarity between the project to be processed and each candidate is calculated respectively. The ranking of each candidate is determined based on feature similarity.

3. The method of claim 1, wherein, After determining the statistical information of the first target word, the method further includes: Based on the statistical information of the first target words, the target areas involved in the projects to be processed are determined; The step of obtaining the knowledge graph features of at least one candidate from a pre-established personnel feature database includes: Obtain the knowledge graph features of each candidate in the target domain from a pre-established personnel feature database.

4. The method of claim 3, wherein, The process of determining the ranking of each candidate based on the knowledge graph features of the project to be processed and the knowledge graph features of each candidate includes: If there is more than one target domain, then for each target domain, the ranking result of each candidate in the target domain is determined based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate in the target domain. The ranking results of each target domain are merged to obtain the ranking results of each candidate. 5.A knowledge graph based target personnel matching apparatus, characterized in that, include: The feature determination module is used to determine the knowledge graph features of the project to be processed, and to obtain the knowledge graph features of at least one candidate from a pre-established personnel feature database; wherein, the knowledge graph features are determined based on the target word statistical information in the knowledge graph data; The ranking result determination module is used to determine the ranking result of each candidate based on the knowledge graph characteristics of the project to be processed and the knowledge graph characteristics of each candidate. The target personnel identification module is used to identify target personnel that match the project to be processed based on the sorting results. The feature determination module includes: The data determination unit is used to determine the knowledge graph data of the project to be processed if a target personnel matching request for the project to be processed is detected. The first statistical information determination unit is used to segment the knowledge graph data of the project to be processed and determine the statistical information of the first target word. The project feature determination unit is used to determine the knowledge graph features of the project to be processed based on the statistical information of the first target word; The personnel feature acquisition unit is used to acquire the knowledge graph features of at least one candidate from a pre-established personnel feature database. The formula for calculating the knowledge graph features of the candidates is as follows: ; denotes a second target word index, denotes a candidate person index, denotes a second target word encoding, denotes a weight of a second target word match, denotes a second target word quantity; The device also includes a personnel feature database establishment module, comprising: The second statistical information determination unit is used to segment the knowledge graph data of each candidate and determine the statistical information of the second target word. The personnel feature determination unit is used to determine the knowledge graph features of each candidate based on the statistical information of the second target word, and to determine the fields involved by each candidate; The personnel feature database determination unit is used to determine the personnel feature database based on the fields involved by each candidate and the knowledge graph features of each candidate; The project feature determination unit is specifically used for: Based on the preset encoding method, determine the feature encoding of each first target word; Based on the feature encoding of each first target word and the word frequency of each first target word, the knowledge graph features of the project to be processed are determined; The personnel feature determination unit is specifically used for: Based on the preset encoding method, determine the feature encoding of each second target word; Based on the feature encoding of each second target word and the word frequency of each second target word, the knowledge graph features of each candidate are determined; The project feature determination unit is also used for: If the first target word is a keyword in the knowledge graph data of the project to be processed, then it is determined whether the word frequency of the keyword meets the preset weight requirement. If the word frequency of the keyword is higher than or equal to the preset weight requirement, the weight of the keyword is not adjusted. If the word frequency of the keyword is lower than the preset weight requirement, the word frequency of the keyword is adjusted by using the weight of keyword matching to increase the weight of the keyword. The adjusted keyword weights, feature codes of each first target word, and word frequencies of each first target word other than the keywords are used to calculate the weighted sum of each first target word. The weighted sum is then used as the knowledge graph feature of the project to be processed.

6. An electronic device, comprising: The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the knowledge graph-based target person matching method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the target person matching method based on any one of claims 1-4.

Images