Information processing device, information processing method, and program

Abstract

To provide an information processing device, information processing method, and program that suitably support the creation of job messages.SOLUTION: An information processing device includes: a request information acquisition unit configured to receive request information for sending a job message; an object person information acquisition unit configured to acquire expanded object person information for an object person based on object person's attribute information; a job text acquisition unit configured to acquire job text by inputting and the object person information into a trained model configured to receive the request information and the object person information and generate job text by learning, as training data, job content, job seeker attributes, and performance information including sample text corresponding to the job content and the job seeker attributes; and an output unit configured to output the job text.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] As the labor market becomes increasingly mobile, new technologies have been proposed to efficiently conduct recruitment activities using job postings or recruitment messages.

[0003] According to Patent Document 1, the similarity learning system analyzes information registered in a job posting database and a resume database using a topic model, compiles vocabulary from documents by topic, and the similarity learning unit performs similarity learning on a topic-by-topic basis.

[0004] The device described in Patent Document 2 manages the profile information of job seekers, generates scouting documents including groups of words extracted from the profile information, generates a trained model by learning the correlation between a first parameter and the groups of words, and extracts the groups of words based on this trained model.

[0005] According to Patent Document 3, the information processing system accepts input of the persona of the person sought by the employer, obtains the corresponding job seeker information, inputs the persona information into artificial intelligence, and creates a job posting corresponding to the profile of the persona. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-134732 [Patent Document 2] Japanese Patent Application Publication No. 2023-105444 [Patent Document 3] Patent No. 7329159 Summary of the Invention [Problem to be solved by the invention]

[0007] However, it is not easy for HR 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 favorably supports the creation of a recruitment message. [Means for solving the problem]

[0009] The information processing device according to the present disclosure includes a request information acquisition unit, a target person information acquisition unit, a job offer text acquisition unit, and an output unit. The request information acquisition unit receives request information for sending a job offer message. The target person information acquisition unit acquires target person information of the target person expanded based on the target person's attribute information. The job offer text acquisition unit inputs the request information and the target person information into a trained model configured to receive the request information and the target person information and generate the job offer text by learning from training data including job offer content, job seeker attributes, and performance information including sample text corresponding to the job offer content and job seeker attributes. The output unit outputs the job offer text.

[0010] In the information processing method according to the present disclosure, a computer executes the following method. The computer receives request information for sending a job recruitment message. The computer acquires target information for the target that is expanded based on the target's attribute information. The computer learns from training data the job content, the attributes of the job seeker, and performance information including sample sentences corresponding to the job content and the attributes of the job seeker, thereby inputting the request information and the target information into a trained model configured to receive the request information and the target information and generate the job recruitment sentence, thereby acquiring the job recruitment sentence. The computer outputs the job recruitment sentence.

[0011] A program according to the present disclosure causes a computer to execute the following method. The computer receives request information for sending a job message. The computer acquires target information for the target that is expanded based on the target's attribute information. The computer learns from training data the job content, the job seeker's attributes, and performance information including sample sentences corresponding to the job content and the job seeker's attributes, and inputs the request information and target information into a trained model configured to receive the request information and target information and generate the job text, thereby acquiring the job text. The computer outputs the job text. [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 suitably support the creation of a job recruitment message. [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 first flowchart of an information processing method according to the present disclosure. [Figure 3] 1 is a first block diagram of an information processing system 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] 10 is a second flowchart of the information processing method according to the present disclosure. [Figure 6] FIG. 10 is a diagram illustrating processing by a subject information acquisition unit. [Figure 7] FIG. 10 is a diagram illustrating the learning state of a learning model. [Figure 8] FIG. 1 is a diagram illustrating the operational status of a trained model. [Figure 9] FIG. 10 is a diagram showing the structure of a job offer message. [Figure 10] FIG. 10 is a third block diagram of the information processing device according to the present disclosure. [Figure 11] This is the first diagram showing the input and output of information of a trained model. [Figure 12] This is a second diagram showing the input and output of information of a trained model. [Figure 13] FIG. 10 is a diagram showing response information. [Figure 14] 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 and transmission of job recruitment messages to be sent to job seekers. A job recruitment message in the present disclosure is a message sent individually to a job seeker. The information processing device 10 sends the job recruitment message by email (electronic mail), for example. However, instead of email, the means for sending the job recruitment message may be a direct message sent directly to a personal account on a social networking service (SNS). A job recruitment message is a message sent individually. Therefore, the content of the job recruitment message can be generated for each job seeker to whom it is sent. In the following description, a job seeker to whom a job recruitment message is sent will be referred to as a target. 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 request information acquisition unit 111, a target person information acquisition unit 112, a job offer text acquisition unit 113, and an output unit 114.

[0016] The request information acquisition unit 111 receives request information regarding the sending of a job message. The request information includes information about the job desired by a requester, which is a person or corporation that is making a job offer. More specifically, the request information may include at least one of the attributes of the requester, the content of the job being offered, the working method, the working location, and the treatment. The request information may be the content of a job posting. The request information acquisition unit 111 may acquire the request information by receiving it directly from the requester. The request information acquisition unit 111 may also indirectly acquire the information notified by the requester from a user who uses the information processing device 10.

[0017] The target information acquisition unit 112 acquires target information. The target information includes attribute information of a target to whom a job offer message is to be sent. The target attribute information is information uniquely associated with the target and may be relevant when the target is searching for a job. The target attribute information includes the target's occupation, skills, and qualifications. The target attribute information may also include information such as the target's address and age. The target information also includes information expanded from the target's attribute information. That is, the target information acquisition unit 112 accepts the target's attribute information and expands words included in the target's attribute information. In this way, the target information acquisition unit 112 acquires the target information. Here, "expanding words included in the attribute information" refers to adding expansion words of given words to the attribute information. In this case, the expansion words are, for example, words having a similar concept or meaning to the given word. The expansion words may also include words having a different meaning from the given word but a closely related meaning. The expansion words may be selected, for example, using natural language processing. The expansion words may be selected by statistical methods.

[0018] The job posting text acquisition unit 113 acquires the job posting text by inputting the request information and target information described above into a trained model that has undergone predetermined training in advance. The job posting text includes at least the content of the body of the job posting message. The job posting text may also include the title of the job posting message.

[0019] The trained model that outputs the job posting text is configured to receive request information and target information and generate the job posting text. This trained model generates the job posting text by learning from training data including job posting details, job seeker attributes, and performance information including sample text corresponding to the job posting details and job seeker attributes.

[0020] The output unit 114 outputs the job posting text.

[0021] 2 is a first flowchart of the information processing method according to the present disclosure. The information processing device 10 executes the following information processing method.

[0022] First, the request information acquisition unit 111 acquires request information related to sending a job offer message (step S11). The request information acquisition unit 111 supplies the acquired request information to the job offer text acquisition unit 113.

[0023] Next, the target information acquisition unit 112 receives attribute information of the target of the sending of the job message, and acquires target information by expanding words included in the target attribute information (step S12). The target information acquisition unit 112 supplies the acquired target information to the job message acquisition unit 113.

[0024] Next, the job posting text acquisition unit 113 acquires the job posting text by inputting the request information and the target person information into a trained model that is configured to receive the request information and the target person information and generate the job posting text by learning using predetermined performance information as training data (step S13). After acquiring the job posting text from the trained model, the job posting text acquisition unit 113 supplies the acquired job posting text to the output unit 114.

[0025] Next, output unit 114 generates a job message using the job text received from job text acquisition unit 113. Furthermore, output unit 114 outputs the job message including at least the job text to a predetermined output destination (step S14). The destination to which output unit 114 outputs the job message is, for example, a target person. The destination to which output unit 114 outputs the job message may be an administrator of information processing device 20. The destination to which the job message is output may be a client.

[0026] The above describes the information processing method executed by the information processing device 10. According to the above method, the information processing device 10 outputs a job offer message.

[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 suitably support the creation of a job recruitment message.

[0030] <Embodiment 2>

[0031] The information processing system 2 will be described with reference to Fig. 3. Fig. 3 is a block diagram of the information processing system 2 according to the present disclosure. The information processing system 2 mainly includes an information processing device 20, a trained model 200, a requester terminal 300, and a target terminal 400. Each of the above components is communicably connected to a network N1.

[0032] 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 trained model 200, a requester terminal 300, and a target terminal 400 via a network N1 so that they can communicate with each other.

[0033] The information processing device 20 receives request information from the requester terminal 300. The information processing device 20 also receives attribute information of the target person from the target person terminal 400. The information processing device 20 generates a job offer message from the information received from the requester terminal 300 and the target person terminal 400, and is capable of transmitting the generated job offer message to the requester terminal 300 and the target person terminal 400, respectively. The information processing device 20 is also communicatively connected to the trained model 200. The information processing device 20 receives the job offer text from the trained model 200 by supplying the request information and target person information to the trained model 200.

[0034] The trained model 200 receives request information and target person information as input from the information processing device 20 via the network N1. The trained model 200 generates a job offer text from the received request information and target person information and outputs it to the information processing device 20.

[0035] The requester terminal 300 is a computer managed by a requester who requests the output of a job offer message. The requester is, for example, a corporation that is recruiting. The requester uses the requester terminal 300 to provide request information related to the job offer to the information processing device 20. The requester terminal 300 also receives the job offer message generated by the information processing device 20 from the information processing device 20.

[0036] The target person terminal 400 is a terminal used by the target person to whom the job offer message is sent. The target person terminal 400 is, for example, a computer, tablet PC, smartphone, or mobile phone. The target person uses the target person terminal 400 to provide a profile including their own attribute information to the information processing device 20. The target person terminal 400 also receives the job offer message from the information processing device 20. Note that the target person terminal 400 is not limited to being owned by the target person. The target person terminal 400 may also be a terminal shared by multiple people, as long as it is a terminal from which the target person can receive the job offer message.

[0037] 3 includes one requester terminal 300 and one target terminal 400. However, the information processing system 2 may include multiple requester terminals 300 managed by multiple different requesters. Similarly, the information processing system 2 may include multiple target terminals 400 used by multiple different targets.

[0038] 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. The information processing device 20 mainly includes a request information acquisition unit 111, a target person information acquisition unit 112, a job offer text acquisition unit 113, an output unit 114, and a storage unit 130.

[0039] The request information acquisition unit 111 of the information processing device 20 acquires request information from the requester terminal 300 via the information input / output unit 120. The request information acquisition unit 111 may acquire the request information via the information input / output unit 120 by accepting information input by an administrator of the information processing device 20.

[0040] The subject information acquisition unit 112 of the information processing device 20 receives attribute information of the subject from the subject terminal 400 via the information input / output unit 120. The subject information acquisition unit 112 also acquires subject information by expanding the received attribute information.

[0041] The job posting text acquisition unit 113 of the information processing device 20 acquires the job posting text from the trained model 200 by supplying request information and target person information to the trained model 200 connected via the network N1.

[0042] The output unit 114 outputs the job posting acquired by the job posting acquisition unit 113. The output unit 114 may output a job posting message including the job posting. In this case, the job posting message may be the job posting processed into, for example, an email format. The job posting message includes at least a title and a body. The job posting message may include an addressee. The job posting message is not limited to plain text. The job posting message may be written in, for example, HTML (Hyper Text Markup Language). The job posting message may include a link to a website. However, the job posting message may be the job posting itself. The output unit 114 outputs the generated job posting message to, for example, the requester terminal 300 or the target terminal 400. The output unit 114 may output the job posting message to the administrator of the information processing device 20 via the information input / output unit 120.

[0043] The output unit 114 may send the target person a job offer message that includes an open notification to let the target person know that the job offer message has been opened. In this case, the output unit 114 adds an open confirmation function to the email job offer message that includes the job offer text. By having such a function, the information processing device 20 can collect information on whether the target person has opened the job offer message.

[0044] The output unit 114 may link a unique identifier to the job message and output the job message in which the unique identifier is further linked to a link URL (Uniform Resource Locator) described in the job message. This allows the information processing device 20 to collect information on whether the target person viewed a link to a job site or the like after opening the job message.

[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 storage unit 130 is a storage device including a non-volatile memory such as a flash memory. The storage unit 130 stores, for example, a program for performing the functions of the present disclosure. The storage unit 130 may also store, for example, multiple pieces of request information or target person information.

[0047] Next, the processing executed by the information processing device 20 will be described with reference to Fig. 5. Fig. 5 is a second flowchart of the information processing method according to the present disclosure.

[0048] First, the request information acquisition unit 111 acquires request information related to sending a job offer message from the requester terminal 300 via the network N1 (step S21). The request information acquisition unit 111 supplies the acquired request information to the job offer text acquisition unit 113.

[0049] Next, the target information acquisition unit 112 receives attribute information of the target of the sending of the job offer message (step S22), and acquires target information by expanding words included in the target attribute information (step S23). The target information acquisition unit 112 supplies the acquired target information to the job offer message acquisition unit 113.

[0050] Next, the job offer text acquisition unit 113 inputs the request information and the target person information into the trained model to acquire the job offer text (step S24). After acquiring the job offer text from the trained model, the job offer text acquisition unit 113 supplies the acquired job offer text to the output unit 114.

[0051] Next, output unit 114 generates a job message using the job text received from job text acquisition unit 113. Furthermore, output unit 114 outputs the job message including at least the job text to requester terminal 300 (step S25).

[0052] Next, the output unit 114 requests feedback from the client terminal 300 (step S26).

[0053] Next, the output unit 114 determines whether or not a correction request has been made from the client terminal 300 (step S27). If the output unit 114 determines that a correction request has been made from the client terminal 300 (step S27: YES), the information processing device 20 proceeds to step S28. On the other hand, if the output unit 114 does not determine that a correction request has been made from the client terminal 300 (step S27: NO), the information processing device 20 proceeds to step S29.

[0054] In step S28, the output unit 114 accepts the correction from the subject terminal 400 via the information input / output unit 120 (step S28). After accepting the correction, the information processing device 20 returns to step S27 again.

[0055] In step S29, the output unit 114 outputs the job offer message to the client terminal 300 (step S29).

[0056] The above describes the processing executed by the information processing device 20. The information processing device 20 can transmit the job offer message to which the requester has made corrections to the target user terminal 400 by executing the above-mentioned information processing method.

[0057] Next, the subject information acquisition unit 112 will be further described with reference to Fig. 6. Fig. 6 is a diagram showing the processing of the subject information acquisition unit 112. The subject information acquisition unit 112 includes an extension processing unit 112b. The subject information acquisition unit 112 is also connected to a language database 112c.

[0058] The extension processing unit 112b of the subject information acquisition unit 112 extends the attribute information by collecting extension words for words included in the attribute information from a predetermined language database 112c. The language database 112c includes a non-volatile memory that stores multiple languages. The language database 112c can supply multiple languages ​​to the extension processing unit 112b. The subject information acquisition unit 112 having such a configuration executes the following process.

[0059] The subject information acquisition unit 112 acquires attribute information of the subject from the subject terminal 400. Next, the expansion processing unit 112b collects expansion words for words included in the acquired attribute information from the language database 112c. The expansion processing unit 112b may use, for example, a commonly known technique to collect the expansion words. Commonly known techniques include, for example, a technique for vectorizing words or sentences and a technique for referencing a preset dictionary. More specifically, when using the vectorization technique, the expansion processing unit 112b collects expansion words having vectors close to the vectors of the words in the attribute information from the language database 112c. When using the dictionary reference technique, the language database 112c stores multiple words or sentences grouped according to their respective meanings. The expansion processing unit 112b collects words or sentences that are in the same group as the group containing the words in the attribute information but are not included in the attribute information. With this configuration, the expansion processing unit 112b expands the attribute information. The subject information acquisition unit 112 sets the subject information as a combination of the attribute information acquired from the subject terminal 400 and the extended attribute information collected by the extension processing unit 112b. Note that the subject information acquisition unit 112 may acquire the subject information from a source other than the subject terminal 400. In this case, for example, the subject information acquisition unit 112 acquires subject information stored in advance in the information processing device 20 or a server different from the information processing device 20.

[0060] 6 is shown as existing outside the subject information acquisition unit 112. In this case, the language database 112c may be part of the storage unit 130. Furthermore, unlike the configuration shown in FIG. 6, the language database 112c may be included in the subject information acquisition unit 112. In other words, the subject information acquisition unit 112 may have an extension processing unit 112b and a language database 112c.

[0061] Next, the learning stage of the trained model 200 will be described with reference to FIG. 7. FIG. 7 is a diagram showing the learning state of the training model 190. The training model 190 shown in FIG. 7 is the training stage of the trained model 200 incorporated in the information processing system 2 shown in FIG. 3. The training model 190 is the stage before the trained model 200 is put into operation. The training model 190 includes, for example, multiple neural networks and is constructed by deep learning. The training model 190 may be a large language model (LLM).

[0062] The learning model 190 shown in FIG. 7 learns by importing training data. The training data is a plurality of pieces of performance information 190a. The performance information includes job content and job seeker attributes. Job content includes, for example, the name of the person or corporation making the job, the job type being applied for, and the benefits to be offered if the applicant is hired. Job content is information corresponding to items equivalent to the request information. Job seeker attributes include the job seeker's name, current occupation, etc. Job seeker attributes are information corresponding to items equivalent to the target information. Performance information includes sample sentences to be used in job recruitment messages corresponding to the job content and the job seeker attributes. The sample sentences are information equivalent to job recruitment sentences.

[0063] Of these, the job description and job seeker attributes are labeled as training data as input. The sample sentences are also labeled as output corresponding to the job description and job seeker attributes. In this way, the learning model 190 learns from performance information as training data.

[0064] The performance information 190a may be, for example, a collection of successful introductions between employers and job seekers in past recruitment activities. The performance information 190a may also be a collection of job messages sent to job seekers in the past that received favorable responses from job seekers. This performance information may, for example, be artificially collected in advance to train a learning model. The performance information may also be information obtained by automatically sorting responses from job seekers. In this case, as a means for automatic sorting, the information processing device 20 may have, for example, a function to collect information on whether or not a target person has opened a job message. The information processing device 20 may also have, for example, a function to detect when a target person who opened a job message accessed an application link and collect this information.

[0065] Next, a state in which the learned learning model 190 is operated as a trained model will be described with reference to Fig. 8. Fig. 8 is a diagram showing the operational state of the trained model 200. The trained model 200 shown in Fig. 8 shows a state in which the learning model 190 shown in Fig. 7 is incorporated into the information processing system 2 and operated.

[0066] The trained model 200 receives request information and target person information as input. The request information includes the name of the requester, the job type applied for, and the treatment of the applicant if hired, etc. The requester information is, for example, information acquired by the request information acquisition unit 111 from the requester terminal 300.

[0067] The subject information includes the subject's attributes, such as the subject's name and current occupation. The subject's attributes are information that the subject information acquisition unit 112 has received from the subject terminal 400. The subject information includes extended attribute information. The extended attribute information includes, for example, the subject's income level, educational background, etc., which are extended words related to the subject's occupation. The extended attribute information is acquired by the extension processing unit 112b of the subject information acquisition unit 112 through extension processing.

[0068] Upon receiving this information, the trained model 200 outputs a job posting. The job posting includes, for example, a job title and a job body. In this way, the trained model 200 receives the request information and the target person information as input and generates the job posting.

[0069] Next, the job offer message generated by output unit 114 will be described with reference to Fig. 9. Fig. 9 is a diagram showing the structure of a job offer message 140. Job offer message 140 includes a header section 141 and a body section 142. Note that job offer message 140 shown in Fig. 9 is generated as an email.

[0070] Header section 141 includes, for example, the address of the email destination, the address of the sender, the message title, etc. Header section 141 shown in FIG. 9 shows "△△@a**b.jp" as the destination and "○○@x**y.jp" as the sender address. Header section 141 also shows the title of the email, "Regarding application to ** Company." The address shown as the destination is included in the attributes of the target person. The sender address is included in the requester information. In addition to this information, header section 141 may also include, for example, a unique identifier for this email. In addition to this information, header section 141 also includes information required as the header section of an email.

[0071] The body section 142 is the main text of the job recruitment message 140. The body section 142 contains a message such as "Nice to meet you. My name is XX from X**Y Company." The body section 142 also contains a link to a website for applying. The body section 142 may also contain a link to a questionnaire for the target applicant.

[0072] The information processing device 20 has been described above. However, the information processing device 20 is not limited to the above-described configuration. For example, the subject information acquisition unit 112 may perform the extension process by reading a language database held by a device external to the information processing device 20. In this case, the language database 112c may exist in a predetermined cloud as part of SaaS, IaaS, or PaaS, for example.

[0073] With the above-described configuration, the information processing device 20 expands the target person's attribute information and acquires a wide range of words associated with the target person. Furthermore, the job posting acquisition unit 113 causes the trained model 200 to create a job posting from target person information including the expanded words associated with the target person. This allows the information processing device 20 to output a job posting that is likely to leave a favorable impression on the target person from information uniquely associated with the target person. Therefore, according to this embodiment, an information processing device, information processing method, and program that favorably support the creation of a job posting message can be provided.

[0074] <Third Embodiment>

[0075] Next, a third embodiment will be described. Fig. 10 is a block diagram of an information processing system 3 including an information processing device 30. The information processing system 3 has the information processing device 30, a requester terminal 300, and a target terminal 400. The information processing device 30 according to this embodiment includes a response management unit 115 and a trained model 200.

[0076] The response management unit 115 collects response information regarding responses from targets after receiving a job offer message. The response information is information for updating performance information. The response management unit 115 updates the performance information based on the response information.

[0077] In this case, the trained model 200 learns the performance information updated based on the response information as training data. That is, in this case, the trained model 200 re-trains using the updated performance information as training data, receives the request information and target information as input, and generates a job posting. With this configuration, the information processing device 30 can make the job posting message generated by the output unit 114 more suitable.

[0078] The trained model 200 of the information processing device 30 also outputs evidence information indicating the basis for generating the job posting. More specifically, the trained model 200 outputs evidence information indicating the association between the job posting and at least one of the job content and the target information.

[0079] The basis information will be further explained with reference to Figure 11. Figure 11 is the first diagram showing the input and output of information to the trained model 200. The trained model 200 shown in Figure 11 receives request information and target person information, and outputs a job posting corresponding to the received information. The trained model 200 also outputs the basis information that forms the basis for generating the job posting. The trained model 200 shown in Figure 11 indicates, as the basis information, "This job posting is written as... based on the target person's information ***."

[0080] In this way, the trained model 200 is configured to indicate input information corresponding to the description of the job posting. In this case, the trained model 200 is, for example, a large-scale language model. When the job posting acquisition unit 113 receives the basis information along with the job posting, it supplies the received basis information to the output unit 114. The output unit 114 generates a job message from the job posting and outputs the generated job message and the basis information received from the job posting acquisition unit 113 to the requester terminal 300. With this configuration, the information processing device 30 can provide the requester with basis information that makes it easier to confirm or evaluate the job posting message.

[0081] Next, variations in job posting texts output by the trained model 200 will be described with reference to Fig. 12. Fig. 12 is a second diagram showing the input and output of information of the trained model. The trained model 200 shown in Fig. 12 generates multiple different patterns of job posting texts for multiple subjects who have common attributes among their attribute information.

[0082] The trained model 200 receives as input request information and target person information from the job posting text acquisition unit 113. The trained model 200 also receives target attributes for the AB test. The target attributes for the AB test may be selected, for example, from the attributes of the target person. The target attributes for the AB test are input by the administrator of the information processing device 30 via the information input / output unit 120.

[0083] The AB test in this disclosure is conducted with the aim of improving the content of recruitment messages. In the AB test, recruitment messages of two patterns, pattern A and pattern B, are generated, and then each is sent to multiple different target individuals, and the response information for each pattern is compared. This allows the administrator of information processing device 30 to evaluate which recruitment message, pattern A or pattern B, is more effective for the target individuals.

[0084] Next, the processing of the response management unit 115 will be described with reference to Fig. 13. Fig. 13 is a diagram showing response information 115a. The response information 115a shown in Fig. 13 shows target person identifiers and response information corresponding to each target person identifier. The response information corresponding to the target person identifiers includes, for example, items such as "email opened," "application link accessed," "application," "hired," "score," and "AB test pattern."

[0085] Of these, "email opened" is information indicating whether the target person opened the email that is the job offer message. In this case, the job offer message output by the information processing device 30 to the target person terminal 400 is an email with an open confirmation. "application link accessed" is information indicating whether the application website was accessed from the link included in the job offer message. "application" is information indicating whether the target person applied for the job from the application website. "hired" is information indicating whether the target person who applied was hired by the requester.

[0086] The "score" is an index that indicates the effectiveness of the recruitment message. The score is calculated from the responses of the target person described above. The recruitment information, target person information, and recruitment message associated with the target person identifier with a high score are adopted as performance information.

[0087] For example, in the response information 115a shown in FIG. 13, the subject associated with subject identifier 0001 opened the email, accessed the application link, and applied. The subject associated with subject identifier 0001 was not hired. In this case, the score for subject identifier 0001 is "3." On the other hand, the subject associated with subject identifier 0002 opened the email but did not access the application link. In this case, the score for subject identifier 0002 is "1." In this case, for example, the information associated with subject identifier 0001 is adopted as performance information and used for retraining the trained model 200. The information associated with subject identifier 0002 is not adopted as performance information.

[0088] "AB test pattern" is information indicating the pattern of the job recruitment message sent to the subject when an AB test is conducted. The response management unit 115 collects response information 115a by linking it to the pattern of the job recruitment message. By the response management unit 115 generating the response information 115a in this manner, the administrator of the information processing device 30 can easily tally up the scores and the AB test pattern. This also allows the administrator of the information processing device 30 to easily evaluate the effectiveness of the AB test.

[0089] The above describes the information processing device 30. Note that the response information 115a shown in FIG. 13 is an example, and the response information 115a may include other items. The information processing device 30 has a function for increasing the effectiveness of a job recruitment message. Therefore, according to the present disclosure, it is possible to provide an information processing device, an information processing method, and a program that favorably support the creation of a job recruitment message.

[0090] <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.

[0091] FIG. 14 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) a request information acquisition unit that receives request information related to job offers; a subject information acquisition unit that acquires subject information of the subject expanded based on attribute information of the subject; a job posting acquisition unit that acquires the job posting by inputting the request information and the target person information into a trained model that is configured to receive the request information and the target person information and generate a job posting by learning, as training data, job posting details, job seeker attributes, and performance information including sample text corresponding to the job posting details and the job seeker attributes; an output unit that outputs the job posting text; Information processing device. (Appendix 1.1) The output unit outputs the job posting message including at least a part of the job posting text in a body portion and a title or an addressee in a header portion. 10. The information processing device according to claim 1. (Appendix 2) the subject information acquisition unit expands the attribute information by collecting words related to words included in the attribute information from a predetermined language database; 10. The information processing device according to claim 1. (Appendix 3) The output unit transmits the job offer message to the target person including an opening notification for understanding that the target person has opened the job offer message including the job offer text. 10. The information processing device according to claim 1. (Appendix 4) the output unit links a unique identifier to a job posting message including the job posting text, and outputs the job posting message further linking a link URL described in the job posting message with the unique identifier. 10. The information processing device according to claim 1. (Appendix 5) The system further includes a trained model that learns the performance information as training data, receives the request information and the target person information as input, and generates the job offer text. 5. The information processing device according to any one of Supplementary Notes 1 to 4. (Appendix 6) A response management unit is further provided that collects response information regarding the responses of the target person after receiving the message including the job offer text as information for updating the performance information. 6. The information processing device according to claim 5. (Appendix 6.1) the response management unit updates the performance information based on the response information; The trained model learns the performance information updated based on the response information as the training data. 6. The information processing device according to claim 5. (Appendix 7) The trained model also outputs basis information indicating the basis for generating the job posting text. 6. The information processing device according to claim 5. (Appendix 7.1) The trained model outputs the basis information indicating a relationship between the job offer content and / or the target person information and the job offer document. 8. The information processing device according to claim 7. (Appendix 8) The trained model generates a plurality of different patterns of the job offer text for a plurality of the subjects having a common attribute among the attribute information, the response management unit collects the response information in association with the pattern; 7. The information processing device according to claim 6. (Appendix 9) The computer Accepting request information regarding sending job messages, Acquire expanded subject information of the subject based on the subject's attribute information; By learning performance information including job content, job seeker attributes, and sample sentences corresponding to the job content and the job seeker attributes as training data, the request information and the target person information are input into a trained model configured to receive the request information and the target person information and generate job content sentences, thereby obtaining the job content sentences; Output the job offer text. Information processing methods. (Appendix 10) Accepting request information regarding sending job messages, Acquire expanded subject information of the subject based on the subject's attribute information; By learning performance information including job content, job seeker attributes, and sample sentences corresponding to the job content and the job seeker attributes as training data, the request information and the target person information are input into a trained model configured to receive the request information and the target person information and generate job content sentences, thereby obtaining the job content sentences; Output the job offer text. Making a computer execute an information processing method program.

[0099] 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]

[0100] 2. Information Processing Systems 3. Information Processing Systems 10. Information processing equipment 20 Information processing equipment 30 Information processing equipment 111 Request information acquisition unit 112 Subject Information Acquisition Department 112b Extended processing unit 112c Language Database 113 Recruitment text acquisition department 114 Output section 115 Response Management Department 115a Response Information 120 Information input / output section 130 Storage section 140 Recruitment Messages 141 Header section 142 Body 190 Learning Model 190a Performance Information 200 pre-trained models 300 Requester terminal 400 Target Device 500 computers 502 Bus 504 processor 506 memory 508 Storage Devices 510 Input / Output I / F 512 Network I / F N1 Network

Claims

1. a request information acquisition unit that receives request information related to job offers; a subject information acquisition unit that acquires subject information of the subject expanded based on attribute information of the subject; a job posting acquisition unit that acquires the job posting by inputting the request information and the target person information into a trained model that is configured to receive the request information and the target person information and generate a job posting by learning, as training data, job posting details, job seeker attributes, and performance information including sample text corresponding to the job posting details and the job seeker attributes; an output unit that outputs the job posting text; Information processing device.

2. the subject information acquisition unit expands the attribute information by collecting words related to words included in the attribute information from a predetermined language database; The information processing device according to claim 1 .

3. The output unit transmits the job offer message to the target person including an opening notification for understanding that the target person has opened the job offer message including the job offer text. The information processing device according to claim 1 .

4. The output unit links a unique identifier to a job posting message including the job posting text, and outputs the job posting message further linking a link URL described in the job posting message with the unique identifier. The information processing device according to claim 1 .

5. The system further includes a trained model that learns the performance information as training data, receives the request information and the target person information as input, and generates the job offer text. The information processing device according to any one of claims 1 to 4.

6. A response management unit is further provided that collects response information regarding the responses of the target person after receiving the message including the job offer text as information for updating the performance information. The information processing device according to claim 5 .

7. The trained model also outputs basis information indicating the basis for generating the job posting text. The information processing device according to claim 5 .

8. The trained model generates a plurality of different patterns of the job offer text for a plurality of the subjects having a common attribute among the attribute information, the response management unit collects the response information in association with the pattern; The information processing device according to claim 6 .

9. The computer Accepting request information regarding sending job messages, Acquire expanded subject information of the subject based on the subject's attribute information; By learning performance information including job content, job seeker attributes, and sample sentences corresponding to the job content and the job seeker attributes as training data, the request information and the target person information are input into a trained model configured to receive the request information and the target person information and generate job content sentences, thereby obtaining the job content sentences; Output the job offer text. Information processing methods.

10. Accepting request information regarding sending job messages, Acquire expanded subject information of the subject based on the subject's attribute information; By learning performance information including job content, job seeker attributes, and sample sentences corresponding to the job content and the job seeker attributes as training data, the request information and the target person information are input into a trained model configured to receive the request information and the target person information and generate job content sentences, thereby obtaining the job content sentences; Output the job offer text. Making a computer execute an information processing method program.

Images