Information processing device, information processing method, and program

Abstract

To provide an information processing device, an information processing method, and a program that support creation of effective job opening sentences.SOLUTION: An information processing device comprises: a candidate word extraction unit that extracts a plurality of candidate words for generating a summary sentence from job opening information for describing a job offer slip of a client; a reference information acquisition unit that acquires reference information related to the job opening information of the client; a selection unit that selects selection words from the candidate words on the basis of a relationship with words included in the reference information; and a sentence generation unit that generates and presents a sentence including the selection words as a summary sentence of the job offer slip.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] The labor market is becoming increasingly mobile, and as a result, technology is evolving to support job posting-based talent matching services.

[0003] The information processing device described in Patent Document 1 extracts entities from information on at least one of job seekers and recruiters, and classifies the extracted entities on at least one of job seekers and recruiters into predetermined categories.

[0004] The information provision method described in Patent Document 2 uses information on multiple job listings stored in a storage device to display the job listings on a display medium, and when a job listing with specified conditions set and a job listing without specified conditions are detected, new conditions are displayed for the job listing without specified conditions.

[0005] According to Patent Document 3, the information processing system uses a processor to accept the personnel requirements desired by the employer, acquire related information, input the acquired information into artificial intelligence to output a job posting, and further acquire additional personnel requirements from the artificial intelligence. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2024-008344 [Patent Document 2] Patent Publication No. 2021-093121 [Patent Document 3] Patent No. 7373091 Summary of the Invention [Problem to be solved by the invention]

[0007] However, it is not easy for human resources personnel to create effective recruitment documents for all job seekers.

[0008] In view of the above-mentioned problems, an object of the present disclosure is to provide an information processing device and the like that supports the creation of effective job posting texts. [Means for solving the problem]

[0009] The information processing device according to the present disclosure has a candidate word extraction unit, a reference information acquisition unit, a selection unit, and a sentence generation unit. The candidate word extraction unit extracts a plurality of candidate words for generating a summary from job information for filling out a job posting of a client. The reference information acquisition unit acquires reference information related to the job posting by the client. The selection unit selects selected words from the candidate words based on their relationship with words included in the reference information. The sentence generation unit generates and presents a sentence including the selected words as a summary of the job posting.

[0010] In the information processing method according to the present disclosure, a computer executes the following processes: The computer extracts a plurality of candidate words for generating a summary from job information for filling out a job posting for a client; The computer acquires reference information related to the job information; The computer selects selected words from the candidate words based on their relationship with words included in the reference information; and The computer generates and presents a sentence including the selected words as a summary of the job posting.

[0011] The program according to the present disclosure causes a computer to execute the following method. The computer extracts a plurality of candidate words for generating a summary from job information for filling out a client's job posting. The computer obtains reference information related to the job information. The computer selects selected words from the candidate words based on their relationship with words included in the reference information. The computer generates and presents a sentence including the selected words as a summary of the job posting. [Effects of the Invention]

[0012] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and a program that support the creation of effective job posting text. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a first block diagram of an information processing device according to the present disclosure. [Figure 2] 1 is a flowchart of an information processing method according to the present disclosure. [Figure 3] 1 is a block diagram of a system including an information processing device according to the present disclosure. [Figure 4] FIG. 2 is a second block diagram of the information processing device according to the present disclosure. [Figure 5] FIG. 1 is a first diagram showing the flow of information in an information processing device according to the present disclosure. [Figure 6] FIG. 1 illustrates the learning stages of a learning model according to the present disclosure. [Figure 7] FIG. 1 is a diagram illustrating the operational stages of a trained model according to the present disclosure. [Figure 8] FIG. 10 is a diagram showing a sentence presented by an information processing device. [Figure 9] FIG. 10 is a third block diagram of the information processing device according to the present disclosure. [Figure 10] FIG. 2 is a second diagram showing the flow of information in the information processing device according to the present disclosure. [Figure 11] FIG. 10 is a diagram illustrating the processing of a sentence generation unit. [Figure 12] FIG. 2 is a block diagram illustrating an example of a hardware configuration of a computer. DETAILED DESCRIPTION OF THE INVENTION

[0014] The present invention will be described below through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential means for solving the problems. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are assigned the same reference numerals, and duplicate explanations are omitted as necessary.

[0015] <First Embodiment> An embodiment will be described with reference to FIG. 1. FIG. 1 is a block diagram of an information processing device 10 according to the present disclosure. The information processing device 10 supports the generation of text related to job information to be viewed by job seekers. More specifically, the information processing device 10 generates a summary that summarizes the contents of a job posting in a manner that allows it to be presented. The information processing device 10 is used by a recruitment agency that receives a job request from a client, who is a person or corporation that is recruiting. The recruitment agency publishes the job information created using the information processing device 10 on a website or the like so that it can be viewed.

[0016] The information processing device 10 is, for example, a computer or a server having a communication function. The information processing device 10 mainly includes a candidate word extraction unit 111, a reference information acquisition unit 112, a selection unit 113, and a sentence generation unit 114.

[0017] The candidate word extraction unit 111 extracts multiple candidate words for generating a summary from the job information to be used to fill out the client's job posting. The summary is information contained in the job posting or job information, and is a sentence that provides a summary of the job information to be presented to the job seeker. The summary may be a short phrase. Candidate words include elements such as proper nouns, words, phrases, and symbols. Note that the summary does not have to be a sentence summarized based solely on the information contained in the job posting or job information; similar terms may be substituted or inserted to summarize the sentence.

[0018] The reference information acquisition unit 112 acquires reference information related to the job posting by the client. The reference information may include various information related to the information contained in the job posting. For example, the reference information may be job posting by another person that is similar to the job posting by the client. The reference information may be information such as news articles or papers related to the industry or job type of the job posting.

[0019] The selection unit 113 selects a selected word from the candidate words based on a relationship with a word included in the reference information. The selected word is a word included in the candidate words. The selection unit 113 selects a selected word based on a relationship between the word included in the reference information and the candidate word in accordance with a predetermined process.

[0020] The sentence generation unit 114 generates and presents a sentence including the selected words as a summary of the job posting. The sentence generation unit 114 presents the summary including the selected words to, for example, a business operator using the information processing device 10. The sentence generation unit 114 may present the summary to a client. The sentence generation unit 114 may present the summary to a job seeker.

[0021] Next, processing executed by the information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a flowchart of the information processing method according to the present disclosure.

[0022] First, the candidate word extraction unit 111 extracts a plurality of candidate words for generating an abstract from the job information to be filled in the client's job posting (step S11).

[0023] Next, the reference information acquisition unit 112 acquires reference information related to the job information (step S12).

[0024] Next, the selection unit 113 selects a selection word from the candidate words based on the relationship with the word included in the reference information (step S13).

[0025] Next, the sentence generation unit 114 generates and presents a sentence including the selected words as a summary of the job posting (step S14).

[0026] This concludes the description of the information processing method executed by the information processing device 10. Using the above-described method, the information processing device 10 preferably generates and presents a summary of a job posting.

[0027] The information processing device 10 may include a processor and a storage device (not shown). In this case, the storage device may include a nonvolatile memory such as a flash memory or a solid-state drive (SSD). In this case, the storage device may store a computer program (hereinafter simply referred to as a program) for executing the above-described method. The processor loads the computer program from the storage device into a buffer memory such as a dynamic random access memory (DRAM) and executes the program.

[0028] Each component of the information processing device 10 may be realized by dedicated hardware. Furthermore, some or all of the components may be realized by general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), etc. may be used as the processor. Furthermore, at least some of the functions of this embodiment may be provided in the form of IaaS (Infrastructure as a Service), PaaS (Platform as a Service), SaaS (Software as a Service), etc.

[0029] As described above, according to the present embodiment, it is possible to provide an information processing device, an information processing method, and a program that support the creation of effective job advertisement texts.

[0030] <Embodiment 2> Next, a second embodiment will be described. Fig. 3 is a block diagram of an information processing system 2 including an information processing device 20 according to the present disclosure. The information processing system 2 mainly includes the information processing device 20, a client terminal 300, and an external site 400. These components are connected to each other via a network N1 so as to be able to communicate with each other.

[0031] The information processing device 20 is, for example, a computer owned by a business that provides a service that introduces corporations seeking employment to job seekers. The information processing device 20 is connected to a client terminal 300 via a network N1 so that they can communicate with each other. The information processing device 20 receives information about job offers from the client terminal 300. The client terminal 300 is a computer managed by the client who is making the job offer.

[0032] The information processing device 20 is also set to be able to access an external site 400 via the network N1. The information processing device 20 acquires various information from the external site 400 via the network N1. The external site 400 is, for example, a news site, a social networking service (SNS), or a database that stores various documents.

[0033] Next, the information processing device 20 will be further described with reference to Fig. 4. Fig. 4 is a block diagram of the information processing device 20 according to the present disclosure. The information processing device 20 mainly includes a candidate word extraction unit 111, a reference information acquisition unit 112, a selection unit 113, a sentence generation unit 114, an information input / output unit 120, and a storage unit 130.

[0034] The reference information acquisition unit 112 of the information processing device 20 compares the job information from the requester with the job information from other people, extracts similar job information from other people, and acquires reference information from the similar job information.

[0035] The reference information acquisition unit 112 may have a function of searching a predetermined external site 400 via a network using words contained in job information as search words and acquiring reference information based on the search results. In this case, the reference information acquisition unit 112 realizes the above-mentioned function by using website tracking technology such as RSS (Rich Site Summaries). The reference information acquisition unit 112 may also use an API (Application Programming Interface) that includes a search function. The external site 400 is, for example, a website publicly available on the Internet. The external site 400 may also be a site on an intranet that is accessible to specific users.

[0036] The selection unit 113 of the information processing device 20 selects a selected word from the candidate words based on the relationship with the word included in the reference information by at least one of the following first and second means. Note that the selection unit 113 may selectively operate the following two means, or may operate them in combination. Also, the selected word may be one or multiple.

[0037] As a first method, the selection unit 113 of the information processing device 20 selects candidate words associated with at least one of words indicating an industry or occupation that are farther from the vectors of words included in the reference information than a predetermined standard. A word vector is also referred to as a language vector. In this case, the selection unit 113 selects candidate words that co-occur with words indicating an industry or occupation that are farther from the vectors of words included in the reference information than a predetermined standard. The predetermined standard may be set appropriately depending on the method for evaluating the distance between vectors. For example, when evaluating the distance between vectors by calculating cosine similarity, the closer the value is to -1, the less similar the two vectors are. In this case, the selection unit 113 selects candidate words that are closer to -1 than a threshold as farther from the predetermined standard. Alternatively, the selection unit 113 may calculate cosine similarity for each of multiple words and select the word evaluated to be the farthest as a candidate word. The threshold may be set arbitrarily by the user or automatically by the system depending on the purpose.

[0038] As a result, the information processing device 20 selects words that are different from the context of other job information from a plurality of candidate words, and can include information that is characteristic of the job offer of the client and different from other job offers in the summary.

[0039] The candidate word extraction unit 111 may determine whether a candidate word co-occurs with a word indicating an industry or occupation.

[0040] As a second method, the selection unit 113 selects candidate words associated with at least one of words indicating an industry or occupation whose frequency of appearance in the reference information is lower than a predetermined standard. For example, the selection unit 113 calculates the number of occurrences of each word that appears within a range of 100 words from the word indicating the industry or occupation. Then, the selection unit 113 selects words whose frequency of appearance is lower than a threshold as candidate words. In this way, the selection unit 113 can select candidate words whose frequency of appearance is lower than a predetermined standard. The selection unit 113 may also calculate the frequency of appearance of multiple words and select the candidate word with the lowest frequency of appearance. In this case, the selection unit 113 selects the candidate word with the lowest frequency of appearance in the reference information from candidate words that co-occur with words indicating the industry or occupation. Note that the above method is merely an example, and the threshold and the range for counting the number of occurrences may be set arbitrarily by the user or automatically by the system depending on the purpose. Furthermore, the method is not limited to this, and the number of occurrences may be calculated using a known method.

[0041] As a result, the information processing device 20 selects words that rarely appear in other job information from a plurality of candidate words, and can include information that is characteristic of the job offer of the client and different from other job offers in the summary.

[0042] The sentence generation unit 114 of the information processing device 20 includes a trained model that has learned to generate sentences in accordance with predetermined conditions. More specifically, the sentence generation unit 114 may include, for example, a large language model (LLM). Alternatively, the sentence generation unit 114 may be the large language model itself.

[0043] That is, the sentence generation unit 114 includes a trained model configured to receive job information and selected words and generate a job sentence by learning predetermined training data. In this case, the training data includes sample information about the job, sample words, and sample sentences corresponding to the sample information and sample words.

[0044] The sentence generation unit 114 may have a function of analyzing the emotion score. In this case, the sentence generation unit 114 performs emotion analysis to generate and present a summary sentence in which the positive emotion score is equal to or greater than a predetermined value. Alternatively, the sentence generation unit 114 performs emotion analysis to generate and present a summary sentence in which the negative emotion score is less than a predetermined value. In this case, the sentence generation unit 114 may calculate the emotion score by referring to a dictionary that associates emotion indicators with words. The sentence generation unit 114 may use a model that has been trained in advance by machine learning or deep learning.

[0045] The information input / output unit 120 is responsible for the function of inputting and outputting information to and from the outside of the information processing device 20. The information processing device 20 includes, for example, a communication function. The information processing device 20 may also have a function of accepting operations from an administrator who manages the information processing device 20. The information processing device 20 may also include an interface that outputs information to a predetermined display device.

[0046] The memory unit 130 is a storage device including a non-volatile memory such as a flash memory. The memory unit 130 stores, for example, a program for performing the functions of the present disclosure. The memory unit 130 also stores multiple job information 131. In this case, the job information 131 includes information about other people's job postings. In this case, the job information 131 is used as reference information acquired by the reference information acquisition unit 112.

[0047] Next, the information handled by the information processing device 20 will be described with reference to Fig. 5. Fig. 5 is a diagram showing the flow of information in the information processing device 20.

[0048] The information processing device 20 receives job information from the client terminal 300. The job information includes, for example, job content, working conditions, company information, etc. The job information received by the information processing device 20 is supplied to the candidate word extraction unit 111 and the sentence generation unit 114.

[0049] The candidate word extraction unit 111 extracts candidate words from the received job information. The candidate word extraction unit 111 uses natural language processing to divide words and phrases from sentences or words contained in the job information. This division process is a technique known as tokenization. Through this process, the candidate word extraction unit 111 extracts candidate words such as "Ruby," "remote work," "flexible working hours," and "20s." The candidate word extraction unit 111 supplies the extracted candidate words to the selection unit 113.

[0050] Meanwhile, the information processing device 20 acquires reference information. The reference information acquired by the information processing device 20 may include information acquired by searching the external site 400. The reference information acquired by the information processing device 20 may include job information of other people stored in the memory unit 130. The information processing device 20 may also receive reference information from, for example, a client who manages the client terminal 300. The reference information acquisition unit 112 may tokenize the acquired information. The reference information acquisition unit 112 supplies the acquired reference information to the selection unit 113.

[0051] The selection unit 113 receives candidate words from the candidate word extraction unit 111 and reference information from the reference information acquisition unit 112. The selection unit 113 then selects selected words from the candidate words by performing at least one or both of the two processes described above. For example, the selection unit 113 selects words such as "freedom" and "twenties" from the candidate words described above. The selection unit 113 supplies information on the selected words to the sentence generation unit 114.

[0052] The sentence generation unit 114 receives the job information and the selected words. The sentence generation unit 114 summarizes the received job information. In this case, the sentence generation unit 114 generates a summary sentence using the selected words. For example, the sentence generation unit 114 uses the selected words "freedom" and "people in their 20s" to generate a summary sentence such as "People in their 20s are thriving in a free environment!" and outputs it to the outside of the information processing device 20.

[0053] Next, the sentence generation unit 114 will be further described with reference to Fig. 6. Fig. 6 is a diagram showing the learning stages of the learning model according to the present disclosure. Fig. 6 shows the status of the learning stages of the learning model 190. The learning model 190 performs learning to assume at least part of the functions of the sentence generation unit 114.

[0054] The learning model 190 learns from "job content," "selected words," and "summary" as training data. The "job content," "selected words," and "summary" as training data correspond to each other. In other words, the "job content" in 1 contains words included in the "selected words" or words similar to words included in the "selected words." Furthermore, the "summary" corresponding to this "job content" and "selected words" contains the selected words and is a sentence that summarizes the "job content."

[0055] These pieces of training data are labeled as input data or correct answer data. The learning model 190 performs supervised learning using these pieces of training data. Note that the learning model 190 may be a large-scale language model. When the learning model 190 is a large-scale language model, the learning model 190 performs self-supervised learning in addition to the above-mentioned supervised learning. When performing self-supervised learning, the learning model 190 learns text data other than the above-mentioned training data.

[0056] Next, the operation stage of the learning model 190 will be described with reference to FIG. 7. FIG. 7 is a diagram showing the operation stage of the trained model 191 according to the present disclosure. The trained model 191 receives job information and selected words as input. The job information includes job content, working conditions, company information, etc. In this case, the job information is, for example, information received from the client terminal 300.

[0057] The selected words are words selected by the selection unit 113 from the reference information and candidate words, as described with reference to Fig. 5. That is, in this case, for example, the selected words include "freedom" and "twenties".

[0058] When the trained model 191 receives the job information and the selected words, it generates a summary. The summary may include a sentence such as "People in their 20s are active in a free environment." In addition to the sentences mentioned above, the summary may also include a sentence summarizing the gist of the job information in a short sentence.

[0059] The trained model 191 has been described above. The sentence generation unit 114 of the present disclosure includes at least the trained model 191 described above. The sentence generation unit 114 may have a function of sentiment analysis in addition to the trained model 191. The sentence generation unit 114 may include a function for making additions or adjustments when generating a summary. In this case, the sentence generation unit 114 may have a prompt reception unit for receiving additions or adjustments.

[0060] Next, the summary text presented by the information processing device 20 will be further described with reference to Fig. 8. Fig. 8 is a diagram showing a text presented by the information processing device. Fig. 8 shows an image 201. The image 201 is, for example, a screen of an application provided to job seekers by a recruitment agency. The image 201 includes a title section 202 and a main body section 203.

[0061] The title section 202 includes the sentence "People in their 20s are active in a free environment," which is the summary generated by the sentence generation section 114. By including the words selected by the selection section 113 in the summary in the title section 202, the information processing device 20 can present to the job seeker a sentence that appeals to the job seeker about features that are different from other similar job information.

[0062] The main body section 203 may or may not include the selected words. The main body section 203 is a concise description of the job information. By presenting the title section 202 and the main body section 203, the information processing device 20 presents information that is highly appealing to job seekers. At the bottom of the image 201, buttons such as "View job posting" and "Add to favorites" are displayed. In this way, the image 201 is displayed to encourage job seekers who view the summary to proceed to the next step.

[0063] The above describes the second embodiment. According to this embodiment, it is possible to provide an information processing device, an information processing method, and a program that support the creation of effective job advertisement texts.

[0064] <Third Embodiment>

[0065] Next, a third embodiment will be described. Fig. 9 is a block diagram of an information processing device 30 according to the present disclosure. In addition to the above-described configuration, the information processing device 30 further includes an extension processing unit 115. Furthermore, a storage unit 130 of the information processing device 30 stores a word database 132.

[0066] The expansion processing unit 115 expands a candidate word by extracting words related to the candidate word from a predetermined word database 132. Here, "expanding a candidate word" means adding a word (expansion word) associated with the candidate word as given information. In this case, the expansion word is, for example, a word having a concept or meaning similar to the given word. The expansion word may include a word that has a different meaning from the given word but a closely related meaning.

[0067] In accordance with the above-described configuration, the selection unit 113 of the information processing device 30 selects selected words from the expanded candidate words. Accordingly, the sentence generation unit 114 generates and presents a summary from the selected words selected from the expanded candidate words. With this configuration, the information processing device 30 can generate a more effective summary.

[0068] The expansion processor 115 may expand the reference information by extracting words related to the reference information from a predetermined word database, in which case the selector 113 selects a selection word from the candidate words based on its relationship with the words included in the expanded reference information.

[0069] Furthermore, the expansion processing unit 115 of the information processing device 30 may expand the reference information in addition to expanding the candidate words. With this configuration, the information processing device 30 can generate more effective summaries from a wider range of word combinations.

[0070] 10 is a second diagram showing the flow of information in the information processing device according to the present disclosure. The diagram shown in Fig. 10 differs from the diagram shown in Fig. 6 in that it includes processing related to the extension processing unit 115.

[0071] When the information processing device 30 receives job information, the candidate word extraction unit 111 extracts candidate words. The candidate words extracted by the candidate word extraction unit 111 include, for example, "Ruby," "remote work," "flexible work hours," and "20s." The candidate word extraction unit 111 supplies the extracted candidate words to the expansion processing unit 115.

[0072] When the expansion processing unit 115 receives the above-mentioned candidate words, it performs a process of expanding the candidate words. In this case, the expansion processing unit 115 extracts words related to the candidate words from the word database 132. Specifically, the expansion processing unit 115 adds "development" related to "Ruby," "open-minded" related to "flexible work hours," and "young person" related to "people in their 20s" to the above-mentioned candidate words.

[0073] Thereafter, the selection unit 113 selects "freedom," "open-minded," and "twenties" from the expanded candidate words, and the sentence generation unit 114 generates a summary sentence, "You can thrive in a free and open-minded environment!" from the job information and the selected words. In this way, the information processing device 30 generates a summary sentence using the expanded candidate words.

[0074] Next, variations in the processing of the sentence generation unit 114 will be described with reference to Fig. 11. Fig. 11 is a diagram showing the processing of the sentence generation unit 114. The sentence generation unit 114 of the information processing device 30 generates basis information indicating the basis for generating the summary sentence, and presents the basis information together with the summary sentence.

[0075] The sentence generation unit 114 shown in FIG. 11 receives the job information and the selected words, generates a summary, and includes information supporting the generation of the summary as evidence information, such as "This sentence is written as... based on the information 'free'." The sentence generation unit 114 generates the evidence information by learning how to generate such evidence in advance as a large-scale language model. This allows the information processing device 30 to provide information that makes it easy for the user to confirm the summary.

[0076] As described above, according to the present embodiment, it is possible to provide an information processing device, an information processing method, and a program that support the creation of effective job advertisement texts.

[0077] <Example of hardware configuration> Hereinafter, an example will be described in which each functional configuration of an information processing device according to the present disclosure is realized by a combination of hardware and software.

[0078] FIG. 12 is a block diagram illustrating an example of a hardware configuration of a computer. The information processing device of the present disclosure can realize the above-described functions by a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 500 can realize desired functions by installing a predetermined application.

[0079] The computer 500 has a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface (I / F) 510, and a network interface (I / F) 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method for connecting the processor 504 and the like to each other is not limited to a bus connection.

[0080] The processor 504 is one of various processors such as a CPU, a GPU, an FPGA, etc. The memory 506 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0081] The storage device 508 is an auxiliary storage device realized using a hard disk, an SSD, a memory card, a ROM (Read Only Memory), or the like. The storage device 508 stores programs for realizing desired functions. The processor 504 reads the programs into the memory 506 and executes them to realize the respective functional components of each device.

[0082] The input / output interface 510 is an interface for connecting the computer 500 to an input / output device. For example, an input device such as a keyboard and an output device such as a display device are connected to the input / output interface 510. The network interface 512 is an interface for connecting the computer 500 to a network.

[0083] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0084] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but also to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0085] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) a candidate word extraction unit that extracts a plurality of candidate words for generating an abstract from the job information to be filled in the job posting of the client; a reference information acquisition unit that acquires reference information related to the job information provided by the client; a selection unit that selects a selected word from the candidate words based on a relationship with a word included in the reference information; a sentence generation unit that generates and presents a sentence including the selected words as the summary of the job posting. Information processing device. (Appendix 2) the selection unit selects, from the candidate words associated with at least one of words indicating an industry or an occupation, a candidate word that is farther from a vector of a word included in the reference information than a predetermined criterion; 2. The information processing device according to claim 1. (Appendix 2.1) the selection unit selects, from among the candidate words that co-occur with the words indicating the industry or the occupation, the candidate words that are farther from the vectors of the words included in the reference information than a predetermined criterion. 3. The information processing device according to claim 2. (Appendix 3) the selection unit selects, from the candidate words associated with at least one of words indicating an industry or an occupation, the candidate words whose frequency of appearance in the reference information is lower than a predetermined standard; 2. The information processing device according to claim 1. (Appendix 3.1) the selection unit selects, from the candidate words that co-occur with the words that indicate the industry or the occupation, a candidate word that appears less frequently in the reference information than a predetermined standard. 4. The information processing device according to claim 3. (Appendix 4) the sentence generation unit generates and presents the summary sentence having a positive emotion score equal to or greater than a predetermined value or a negative emotion score less than a predetermined value by performing emotion analysis; 2. The information processing device according to claim 1. (Appendix 4.1) The sentence generation unit includes a trained model configured to receive the job information and the selected words and generate a job sentence by learning training data including sample information related to a job offer, sample words, and sample sentences corresponding to the sample information and the sample words, 2. The information processing device according to claim 1. (Appendix 5) the reference information acquisition unit compares the job information by the client with job information by other people to extract similar job information by other people, and acquires the reference information from the similar job information; 2. The information processing device according to claim 1. (Appendix 5.1) the reference information acquisition unit searches a predetermined network using a word included in the job information as a search word, and acquires the reference information based on the search result; 2. The information processing device according to claim 1. (Appendix 6) the sentence generation unit generates and presents basis information indicating the basis for generating the summary sentence; 2. The information processing device according to claim 1. (Appendix 7) an expansion processor for expanding the candidate words by extracting words related to the candidate words from a predetermined word database; the selection unit selects the selected word from the expanded candidate words. 7. The information processing device according to any one of Supplementary Notes 1 to 6. (Appendix 8) an expansion processor for expanding the reference information by extracting words related to the reference information from a predetermined word database; the selection unit selects the selected word from the candidate words based on a relationship with a word included in the expanded reference information. 7. The information processing device according to any one of Supplementary Notes 1 to 6. (Appendix 9) The computer Extracting a plurality of candidate words for generating a summary sentence from the job information to be filled in the client's job posting; Obtaining reference information related to the job posting; selecting a selection word from the candidate words based on its relationship to a word included in the reference information; generating and presenting a sentence including the selected words as the summary of the job posting; Information processing methods. (Appendix 10) Extracting a plurality of candidate words for generating a summary sentence from the job information to be filled in the client's job posting; Obtaining reference information related to the job posting; selecting a selection word from the candidate words based on its relationship to a word included in the reference information; generating and presenting a sentence including the selected words as the summary of the job posting; Making a computer execute an information processing method, program.

[0086] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 9 and 10 in the same dependency relationship as Supplementary Notes 2 to 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0087] 2. Information Processing Systems 10. Information processing equipment 20 Information processing equipment 30 Information processing equipment 111 Candidate word extraction unit 112 Reference information acquisition unit 113 Selection Section 114 Sentence generation section 115 Extended Processing Unit 120 Information input / output unit 130 Storage section 131 Job Information 132 Word Database 190 Learning Model 191 trained models 201 images 202 Title section 203 Main body 300 Requester terminal 400 External Site 500 computers 502 Bus 504 processor 506 memory 508 Storage Devices 510 Input / Output Interface 512 Network I / F N1 Network

Claims

1. a candidate word extraction unit that extracts a plurality of candidate words for generating an abstract from the job information to be filled in the job posting of the client; a reference information acquisition unit that acquires reference information related to the job information provided by the client; a selection unit that selects a selected word from the candidate words based on a relationship with a word included in the reference information; a sentence generation unit that generates and presents a sentence including the selected words as the summary of the job posting. Information processing device.

2. the selection unit selects, from the candidate words associated with at least one of words indicating an industry or an occupation, the candidate words that are farther from a vector of a word included in the reference information than a predetermined criterion; The information processing device according to claim 1 .

3. the selection unit selects, from the candidate words associated with at least one of words indicating an industry or an occupation, the candidate words whose frequency of appearance in the reference information is lower than a predetermined standard; The information processing device according to claim 1 .

4. the sentence generation unit generates and presents the summary sentence having a positive emotion score equal to or greater than a predetermined value or a negative emotion score less than a predetermined value by performing emotion analysis; The information processing device according to claim 1 .

5. the reference information acquisition unit compares the job information by the client with job information by other people to extract similar job information by other people, and acquires the reference information from the similar job information; The information processing device according to claim 1 .

6. the sentence generation unit generates and presents basis information indicating the basis for generating the summary sentence; The information processing device according to claim 1 .

7. an expansion processor for expanding the candidate words by extracting words related to the candidate words from a predetermined word database; the selection unit selects the selected word from the expanded candidate words. The information processing device according to any one of claims 1 to 6.

8. an expansion processor for expanding the reference information by extracting words related to the reference information from a predetermined word database; the selection unit selects the selected word from the candidate words based on a relationship with a word included in the expanded reference information. The information processing device according to any one of claims 1 to 6.

9. The computer Extracting a plurality of candidate words for generating a summary sentence from the job information to be filled in the client's job posting; Obtaining reference information related to the job posting; selecting a selection word from the candidate words based on its relationship to a word included in the reference information; generating and presenting a sentence including the selected words as the summary of the job posting; Information processing methods.

10. Extracting a plurality of candidate words for generating a summary sentence from the job information to be filled in the client's job posting; Obtaining reference information related to the job posting; selecting a selection word from the candidate words based on its relationship to a word included in the reference information; generating and presenting a sentence including the selected words as the summary of the job posting; Making a computer execute an information processing method, program.

Images