Information processing system, information processing method, and program

Abstract

An information processing system, method, and program are provided that enable recruiters to efficiently create job postings. [Solution] In the information processing system, the server device displays a job posting creation screen on the employer terminal in a first display control step, accepts the details of the available position entered into the first column and a request to create a sentence to be entered into the second column in a first reception step, inputs the details of the available position into an artificial intelligence module to create a sentence based on the request to create the sentence to be entered into the second column in a first creation step, outputs the sentence created in the first creation step into the second column in a first output step, accepts the details of the available position entered into the first column and a request to create a sentence to be entered into the third column in a second creation step, inputs the details of the available position into an artificial intelligence module to create a sentence based on the request to create the sentence to be entered into the third column in a second creation step, and outputs the sentence created in the second creation step into the third column in a second output step.

Description

[Technical field]

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

[0002] Patent Document 1 describes accepting input of personnel requirements and having artificial intelligence output a job posting. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7373091 Summary of the Invention [Problem to be solved by the invention]

[0004] This calls for technology that allows employers to create job postings efficiently.

[0005] In view of the above circumstances, the present invention provides an information processing system etc. that enables employers to efficiently create job postings. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system for supporting the creation of a job posting, the system including at least one processor, the processor being configured to execute each of the following steps by reading out a program: in a first display control step, a job posting creation screen is displayed to an employer, and the creation screen displays at least a first column, a second column, and a third column, the first column is a column in which a position to be recruited in the job posting is input, the second column is a column in which one type of item among a plurality of items corresponding to the recruited position is input, and the third column is a column in which one type of item among a plurality of items corresponding to the recruited position, which is different from the item input in the second column, in a first reception step, a request to create text relating to the type of item to be input in the second column together with the content of the recruited position input in the first column is received from the employer, and a first creation step is performed. In the first step, based on receiving a request for creating a sentence related to a type of item to be input in the second column, at least the content of the recruiting position is input into an artificial intelligence module to individually create a sentence related to a type of item to be input in the second column; in a first output step, the sentence created in the first creation step is output in the second column; in a second reception step, a request for creating a sentence related to a type of item to be input in the third column is received from an employer along with the content of the recruiting position input in the first column; in a second creation step, based on receiving a request for creating a sentence related to a type of item to be input in the third column, at least the content of the recruiting position is input into the artificial intelligence module to individually create a sentence related to a type of item to be input in the third column; and in a second output step, the sentence created in the second creation step is output in the third column.

[0007] According to this aspect, an information processing system or the like is provided that allows recruiters to efficiently create job postings. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of the server device 10. FIG. [Diagram 3] FIG. 2 is a block diagram showing the hardware configuration of a recruiter terminal 20 and a job seeker terminal 30. [Figure 4] FIG. 2 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiter terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Diagram 5] FIG. 2 is an activity diagram showing an example of the flow of information processing (processing of creating a job posting) executed by the information processing system 1. [Figure 6] FIG. 13 is a diagram showing an overview of a job posting creation screen. [Figure 7] FIG. 13 is a diagram for explaining the process of outputting the generated text in the second column. [Figure 8] FIG. 13 is a diagram showing the state in which the generated sentence is output in the second column. [Figure 9] FIG. 13 is a diagram for explaining the process of outputting the generated text in the third column. [Figure 10] FIG. 13 is a diagram for explaining a process for specifying a job type in a job posting. [Figure 11] FIG. 2 is a diagram showing an example of an input screen IS in this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present invention will be described. Note that various features shown in the following embodiments can be combined with each other.

[0010] That is, the information processing system of this embodiment is as follows. An information processing system for supporting the creation of a job posting, At least one processor; The processor is configured to execute the following steps by reading the program: In the first display control step, a job recruiter is caused to display a job posting creation screen, and at least a first column, a second column, and a third column are displayed on the creation screen. The first field is a field in which the recruitment position of the job posting is input, The second field is a field in which one of a plurality of items corresponding to the recruitment position is input, The third field is a field in which an item that is one of a plurality of items corresponding to the recruitment position and is different from the item that is input in the second field is input, In the first reception step, a request for creating a document regarding the type of item to be entered in the second field is received from the recruiter along with the content of the recruitment position entered in the first field; In the first creation step, based on receiving a request to create a sentence related to the one type of item to be inputted into the second field, at least the content of the job opening is inputted into an artificial intelligence module to individually create a sentence related to the one type of item to be inputted into the second field; In a first output step, the text created in the first creation step is output to the second column; In a second reception step, a request for creating a document regarding the type of item to be entered in the third field is received from the recruiter along with the content of the recruitment position entered in the first field; In a second creation step, based on receiving a request to create a sentence related to the one type of item to be inputted in the third field, at least the content of the job opening is inputted into an artificial intelligence module to individually create a sentence related to the one type of item to be inputted in the third field; In a second output step, the text created in the second creation step is output to the third column in the information processing system.

[0011] Incidentally, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0012] In addition, in various information processing according to an embodiment, an input and an output according to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a judgment formula such as a regression formula constructed by a statistical method), or may be a trained model that has previously trained the correlation between the input and the output, or may be a large-scale language model that can output a desired result by inputting a prompt.

[0013] In one embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented by, for example, physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0014] Furthermore, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and a memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0015] 1. Hardware Configuration This section describes the hardware configuration.

[0016] <Information Processing System 1> FIG. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 of this embodiment supports the creation of job advertisements. In a typical embodiment, the information processing system 1 comprises a communication line 2, a server device 10, a plurality of recruiter terminals 20, and a plurality of job seeker terminals 30. The server device 10, the recruiter terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the recruiter terminals 20, and the job seeker terminals 30 may be wired or wireless.

[0017] The information processing system 1 constitutes at least a part of a recruitment and job search system used by, for example, multiple recruiters (a first recruiter U1 and a second recruiter U2) and multiple job seekers (a first job seeker U3 and a second job seeker U4). The information processing system 1 mainly performs the creation of recruitment advertisements by recruiters and searches for job seekers. In one embodiment, the information processing system 1 is made up of one or more devices or components. These components will be described below.

[0018] <Server device 10> 2 is a block diagram showing a hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected to each other inside the server device 10 via the communication bus 14.

[0019] <Control unit 11> The control unit 11 performs processing and control of the overall operation related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 can be specifically realized by the control unit 11, which is an example of hardware, and executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have multiple control units 11 for each function. Also, a combination of these may be used.

[0020] <Storage section 12> The storage unit 12 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0021] <Communications Division 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0022] The server device 10 may be in an on-premise form or in a cloud form. The server device 10 in a cloud form may provide the above-mentioned functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0023] <Employer Terminal 20> Fig. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the recruiter terminal 20 comprises a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected via the communication bus 26 inside the recruiter terminal 20. The recruiter terminal 20 is an information processing terminal used in the course of business by each recruiter who is a user belonging to an organization that receives the services provided by the server device 10. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here as they are the same as the explanation of each unit in the server device 10.

[0024] <Input section 24> The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 may execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter terminal 20, or may be externally attached. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, and the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, and the like can be adopted instead of a touch panel.

[0025] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the recruiter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, a plasma display, or the like. It is preferable that these display devices are implemented by using different devices depending on the type of recruiter terminal 20.

[0026] <Job Seeker Terminal 30> 3B, the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected inside the job seeker terminal 30 via the communication bus 36. The job seeker terminal 30 is an information processing terminal used by each job seeker who is a user who receives the services provided by the server device 10. The explanation of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are the same as the explanation of each unit in the job seeker terminal 20.

[0027] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (at least one processor included in the information processing system 1).

[0028] FIG. 4 is a block diagram showing functions realized by the server device 10 (control unit 11), the recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0029] As shown in Fig. 4A, server device 10 (control unit 11) includes a display control unit 111, a reception unit 112, a creation unit 113, an output unit 114, an acquisition unit 115, a tag extraction unit 116, and an artificial intelligence unit 120. As shown in Fig. 4B, recruiter terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in Fig. 4C, job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0030] <Display control unit 111> The display control unit 111 is configured to display various information on the recruiter terminal 20 and the job seeker terminal 30. For example, the display control unit 111 displays the job posting and scouting document created by the recruiter, the registration information created by the job seeker, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30. In the present embodiment, the display control unit 111 displays a job posting creation screen on the recruiter (recruiter terminal 20) as a first display control step. Here, the creation screen shows at least a first column, a second column, and a third column. The first column is a column in which the recruiting position in the job posting is input. The second column is a column in which one of a plurality of items corresponding to the recruiting position is input. The third column is a column in which one of a plurality of items corresponding to the recruiting position, and is different from the item input in the second column, is input. In one embodiment, the display control unit 111 displays an input screen separate from the creation screen on the recruiter (recruiter terminal 20) as a second display control step. The creation screen and input screen will be explained in detail later.

[0031] <Reception Department 112> The reception unit 112 is configured to receive various information from the recruiter terminal 20 and the job seeker terminal 30. In this embodiment, the reception unit 112 receives, as a first reception step, from the recruiter, a request to create a document related to one type of item to be entered in the second field, together with the content of the recruiting position entered in the first field. Furthermore, the reception unit 112 receives, as a second reception step, from the recruiter, a request to create a document related to one type of item to be entered in the third field, together with the content of the recruiting position entered in the first field. Furthermore, the reception unit 112 receives, as a first correction request reception step, from the recruiter, a request to correct the document created in the first creation step. Furthermore, the reception unit 112 receives, as a second correction request reception step, from the recruiter, a request to correct the document created in the second creation step. Details of the various information received by the reception unit 112 will be described later.

[0032] <Creation Department 113> The creation unit 113 is configured to create various texts based on a creation request (text creation request) from a recruiter. In this embodiment, the creation unit 113, based on receiving a request to create a text related to a type of item to be input in the second field as a first creation step, inputs at least the content of the recruiting position into the artificial intelligence module (artificial intelligence unit 120) to create a text related to a type of item to be input in the second field individually. Also, based on receiving a request to create a text related to a type of item to be input in the third field as a second creation step, the creation unit 113, based on receiving a request to create a text related to a type of item to be input in the third field as a second creation step, inputs at least the content of the recruiting position into the artificial intelligence module (artificial intelligence unit 120) to create a text related to a type of item to be input in the third field individually. Also, the creation unit 113, based on receiving a request to create a text related to a type of item to be input in the third field as a first revision text creation step, inputs at least the text created in the first creation step and a revision request into the artificial intelligence module (artificial intelligence unit 120) to create a revised text in which the text created in the first creation step is revised. Furthermore, as a second revised sentence creation step, the creation unit 113 creates a revised sentence by correcting the sentence created in the second creation step by inputting at least the sentence created in the second creation step and the correction request to an artificial intelligence module (artificial intelligence unit 120). Details of the sentence creation process will be described later.

[0033] <Output unit 114> The output unit 114 is configured to output the text etc. created by the creation unit 113 to a predetermined column. In this embodiment, the output unit 114 outputs the text created in the first creation step to the second column as the first output step. Also, the output unit 114 outputs the text created in the second creation step to the third column as the second output step. Also, the output unit 114 outputs the revised text revised in the first revised text creation step to the second column. Furthermore, the output unit 114 outputs the revised text revised in the second revised text creation step to the third column. Details of the text output mode will be described later.

[0034] <Acquisition part 115> The acquisition unit 115 is configured to acquire various pieces of information that contribute to writing. The details of the information acquired by the acquisition unit 115 will be described later.

[0035] <Tag extraction unit 116> The tag extraction unit 116 is configured to extract tags to be displayed on the recruiter terminal 20 or the like. In a typical embodiment, the tag extraction unit 116 selects and extracts tags that meet a predetermined condition from a tag master prepared in advance. Here, the tag may be read as a keyword or a label, and any keyword can be displayed by the tag function. An example of this tag is a tag that specifies the job type described in the job posting. Here, the tag that specifies the job type is suggested, for example, by the function of the tag extraction unit 116 based on the contents already entered by the recruiter on the creation screen. In a more specific embodiment, the tag extraction unit 116 extracts tags from a predetermined job type master. Here, the job type master is, for example, a list of names (job type names) that indicate job types. Details of this tag will be explained later.

[0036] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0037] The artificial intelligence unit 120 is an AI (Artificial Intelligence) equipped with learning models such as Transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), etc., and language models such as Recurrent Neural Networks (RNN), and may include a generative AI.

[0038] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0039] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data is composed of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

[0040] The artificial intelligence unit 120 may be a general-purpose natural language processing learning model such as a large language model (LLM) that has learned a huge amount of data as an artificial intelligence. The LLM is a learning model that has learned a large amount of large data (for example, (i) web content on the Internet, or (ii) data stored in a specified database) composed of text data and the like in advance, and can execute various language processing tasks by giving tasks. According to a given prompt, it can perform a wide range of natural language processing tasks such as grasping sentence patterns and contexts, answering questions, and generating sentences. Such a general-purpose learning model includes a language model that can handle various tasks without fine tuning by One-shot Learning, Few-shot Learning, etc. In addition, the general-purpose learning model may be configured to be able to handle various tasks by Zero-shot Learning as well. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

[0041] The learning model included in the artificial intelligence unit 120 can perform additional learning as transfer learning or fine tuning. For example, each time new job seeker registration information, job posting registration, etc. are generated, the artificial intelligence unit 120 may perform additional learning and fine tuning using these as new teacher data. This improves the accuracy of the information output from the learning model.

[0042] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using an original learning model. In knowledge distillation, a learned model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted so that the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model is reduced, thereby learning the student model, and the student model becomes a distilled model. In addition, the student model may be learned so that the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model) is reduced. Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while having performance close to the learning model. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0043] For example, the trained model may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as a trained model, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as a trained model to be used for writing.

[0044] <Display> The display unit 211 of the recruiter terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen indicated by the screen data transmitted from the server device 10.

[0045] <Operation acquisition part> The operation acquisition unit 212 of the recruiter terminal 20 accepts operations by a user (recruiter) who uses the recruiter terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

[0046] 3. Information processing method This section describes an information processing method of the server device 10. This information processing method is executed by each unit of the server device 10.

[0047] 5 is an activity diagram showing an example of the flow of information processing (job posting creation processing) executed by information processing system 1. Below, the information processing will be described along with each activity in this activity diagram.

[0048] This job posting creation process is executed by displaying a prescribed creation screen on the recruiter terminal 20. That is, in this embodiment, the recruiter makes a display request to the server device 10 to display a creation screen via the recruiter terminal 20, and the server device 10 accepts this display request (activities A101, A102). In response to this display request, the server device 10 performs prescribed display control, thereby displaying the job posting creation screen on the recruiter terminal 20 (activities A103, A104).

[0049] Fig. 6 is a diagram showing an overall overview of a job posting creation screen. The creation screen CS shown in Fig. 6 shows various items (items I1 to I6, etc.) such as the position name, job content, working conditions, application qualifications, job type, and work location as items to be written in the job posting. Note that the creation screen CS of this embodiment may display each item in a different manner, such as by displaying [Required] for items that must be written in the job posting. Also, the items provided in the job posting are not limited to those shown in Fig. 6, and various other items may be adopted.

[0050] As described above, the creation screen CS of this embodiment shows at least the first, second and third columns. Here, the first column is a column in which the recruiting position in the job posting is input, the second column is a column in which one of the multiple items corresponding to the recruiting position is input, and the third column is a column in which one of the multiple items corresponding to the recruiting position, which is different from the item input in the second column, is input.

[0051] In the example shown in FIG. 6, each column corresponds as follows. First, the first column corresponds to the column C1 in which the "position name (i.e., the recruiting position)" shown as item I1 is input. The "recruiting position" indicates the recruitment target for which personnel are recruited in the recruitment advertisement, and may be read as the "title of the recruitment advertisement" or the "job name". The second column is a column in which the work content corresponding to the recruiting position is input. That is, in the example shown in FIG. 6, the second column corresponds to the column C2 in which the "job content (work content)" shown as item I2 is input. The third column is a column in which the application qualifications corresponding to the recruiting position are input. That is, in the example shown in FIG. 6, the third column corresponds to the column C31 and column C32 in which the "application qualifications" shown as item I4 are input. As shown in the embodiment shown as column C31 and column C32, the second column and the third column do not necessarily have to be composed of only one column as long as they correspond to one type of item. In other words, a combination of columns that correspond to a type of item and input related content can be used as the second column or the third column. In this specification, "column" is treated as a general term referring to a certain division on the screen. In other words, some "columns" in this specification are divisions for the purpose of screen layout, etc., and are not necessarily intended to accept information input from recruiters, etc. (for example, column C20 in Figure 7).

[0052] The contents of the second and third columns may be combinations other than those described above. For example, the second column may be a column for inputting the application qualifications, and the third column may be a column for inputting the job content. The second and / or third columns may be columns for inputting various items that may be included in the text to be written in the job advertisement. For example, the second and / or third columns may be configured to be configured to input text related to the employer's PR to job seekers, the attractiveness of the recruitment position, the advantages of the employer over other companies, etc.

[0053] In the job posting creation process of this embodiment, the position being advertised is entered into the first column (activity A105). That is, in the example shown in Fig. 6, the position being advertised (UI / UX designer) is entered into column C1, and in the information processing method of this embodiment, subsequent processing is performed based on this input content.

[0054] When predetermined information is thus entered in the first column, the recruiter makes a request to create text related to the second column, and the server device 10 accepts the request to create the text (activities A106, A107). In a typical embodiment, the reception unit 112 of the server device 10 accepts a request to create text related to one item to be entered in the second column, based on the recruiter's operation of a first object associated with the second column on the creation screen CS. That is, the recruiter who has entered the available position in the column C1 makes a request to create text to be entered in the second column (column C2) by pressing button BT2 (first object) in FIG. 6, and the server device 10 accepts this request to create the text.

[0055] In this way, when the reception unit 112 of the server device 10 receives a request to create a sentence related to one of the items to be entered in the second column, the creation unit 113 of the server device 10 inputs at least the content of the recruiting position into the artificial intelligence module (artificial intelligence unit 120) and creates the sentence. In this way, a sentence related to one of the items to be entered in the second column is individually created (activity A108). In addition, the output unit 114 of the server device 10 outputs the created sentence to the second column and displays it on the recruiter terminal 20 (activities A109, A110).

[0056] In a typical embodiment, when creating a sentence to be input in the second column (or the third column), the creation unit 113 of the server device 10 instructs the artificial intelligence module (artificial intelligence unit 120) as follows. That is, the creation unit 113 of the server device 10 instructs (inputs a prompt) the artificial intelligence module (artificial intelligence unit 120) to create a sentence to be input in the second column (or the third column) based on the information of the available position input in the first column, and outputs the sentence to be input in the second column (or the third column). In addition, in order to further improve the accuracy of creating the sentence, the acquisition unit 115 of the server device 10 may acquire predetermined information and input it to the artificial intelligence module (artificial intelligence unit 120). The contents acquired by the acquisition unit 115 will be described in detail later.

[0057] The instructions given by the creation unit 113 to the artificial intelligence module (artificial intelligence unit 120) can be set as appropriate, but typical examples include the following instructions. That is, the instructions given by the creation unit 113 are instructions to output text related to the item corresponding to the second column (or third column) based on the information on the recruiting position input in the first column. For example, when the second column is a column for inputting the "job content (task content)", the creation unit 113 instructs the artificial intelligence module (artificial intelligence unit 120) to generate text for the "job content (task content)" to be input in the second column based on the information on the recruiting position input in the first column. In addition, when the third column is a column for inputting the "qualifications for application", the creation unit 113 instructs the artificial intelligence module (artificial intelligence unit 120) to generate text for the "qualifications for application" to be input in the third column based on the information on the recruiting position input in the first column. An example of an instruction given by the creation unit 113 is an instruction to extract elements (appeal elements) that the employer appeals to the job seeker from various viewpoints based on the information of the recruiting position input in the first column, and to compose a sentence based on the extracted elements. The various viewpoints here include, for example, the image of the human resources the employer is looking for, such as "what kind of human resources do you want to hire?", as well as "what kind of work is it?", "recruitment background", "what kind of environment can be provided", "application qualifications and skills", "job content and specific tasks", and "career path and growth opportunities", but are not limited to these. The creation unit 113 can extract appeal elements from various viewpoints related to the job posting. In addition, the creation unit 113 may give an instruction to extract two or more appeal elements, not limited to one. After extracting such appeal elements, an appeal element that is appropriate to be output in the second column (or the third column) can be selected, and the appeal element can be adjusted to become a natural sentence, thereby creating a sentence to be output in the second or third column. In addition, this also relates to the information that can be input to the artificial intelligence module (artificial intelligence unit 120), but the appeal elements extracted and selected by the artificial intelligence module (artificial intelligence unit 120) may be associated with various information acquired by the acquisition unit 115, which will be described later.As mentioned above, the learning model included in the artificial intelligence module (artificial intelligence unit 120) may be a general-purpose learning model such as a large-scale language model, or it may be a learning model trained to input information about the open position, etc., and output sentences related to the items corresponding to the second column (or third column).

[0058] FIG. 7 is a diagram for explaining the process of outputting the generated text to the second column. FIG. 8 is a diagram showing the state in which the generated text is output to the second column. As shown in FIG. 7, when a request for creating text related to an item to be entered in the second column (column C2) is made, a column C20 is inserted in a manner corresponding to the second column (column C2). In this column C20, a column C21 showing the generated text (text related to the generated work content) and a column C22 in which text information for additional instructions (request for correction) can be entered are shown. Also shown in column C20 are a button BT5 for canceling the process of creating the text, a button BT6 for regenerating the text, and a button BT7 for applying the created text to the second column (column C2).

[0059] That is, a recruiter viewing the screen shown in Fig. 7 can check the content of the text generated in column C21, and then press button BT7 to output the generated text in column C2. That is, by pressing button BT7, the generated text is inserted in column C2 as shown in Fig. 8. Note that when text is inserted in column C2 in this manner, column C20, which was displayed in Fig. 7, may be configured to be hidden. The generated text may also be output directly to the second column (column C2).

[0060] In this embodiment, the creation unit 113 of the server device 10 can create multiple sentences related to one type of item to be entered in the second column. Furthermore, the output unit 114 may present the multiple sentences created to the recruiter in a manner that allows the recruiter to select one of the multiple sentences, and output the sentence selected by the recruiter from the multiple sentences presented to the second column.

[0061] That is, in the example of FIG. 7, the creation unit 113 creates two types of sentences related to the job content, and the display control unit 111 controls to display one of the two types of sentences created in the column C21. That is, the display "1 / 2" in the column C20 indicates to the recruiter that the first candidate of the two candidates of sentences created is displayed. The recruiter who comes across the screen of FIG. 7 can confirm a sentence other than the candidate of sentences currently displayed on the creation screen CS by operating the object OBJ1. In addition, the recruiter can select one of the candidates of sentences created and press the button BT7 to determine the sentence to be output in the second column (column C2). As described above, the determined sentence is output in the second column (column C2).

[0062] When creating multiple types of sentences in this way, the creation unit 113 instructs the artificial intelligence module (artificial intelligence unit 120) to create multiple different sentences. To explain an example of creating two types of sentences, the creation unit 113 instructs the artificial intelligence module (artificial intelligence unit 120) to create multiple sentences so that the content of the sentences to be created will be different, for example, one of them will be formal and the other will be casual. Of course, the content to be made different for the multiple sentences to be created is not limited to this, and the content may be changed from various perspectives depending on the needs of the employer, etc.

[0063] In this embodiment, the text displayed in column C21 (text created in the first creation step) may be output as is to the second column (column C2), or a modified version of the text displayed in column C21 (text created in the first creation step) may be output to the second column (column C2).

[0064] That is, the receiving unit 112 may receive, as a first correction request receiving step, a correction request for the text created in the first creation step from the recruiter. Furthermore, the creating unit 113 may, as a first correction text creating step, create a corrected text in which the text created in the first creation step is corrected by inputting at least the text created in the first creation step and the correction request to an artificial intelligence module (artificial intelligence unit 120). Furthermore, the output unit 114 may output the corrected text in the second column.

[0065] 7, the created text (text shown in field C21) can be modified by pressing the button BT6 labeled "Regenerate." That is, the receiving unit 112 receives a request to modify the text created in the first creation step, based on the fact that the recruiter has operated the third object (button BT6) associated with the second field (C2) on the creation screen CS.

[0066] When a correction request is received in this manner, the creation unit 113 inputs the sentence shown in column C21 (sentence once created by the creation unit 113) to the artificial intelligence module (artificial intelligence unit 120) and instructs the artificial intelligence module (artificial intelligence unit 120) to correct the input sentence, thereby regenerating the sentence related to the work content. Note that such regeneration of the sentence may be performed based only on the sentence shown in column C21, but the accuracy of the regeneration of the sentence can be improved by adopting the following aspects.

[0067] That is, the above-mentioned correction request may include text information input by the recruiter. Specifically, in the example shown in FIG. 7, the recruiter's correction guidelines and the like are configured to be input as text information in the field C22, and when the recruiter presses the button BT6, the creation unit 113 can input this text information to the artificial intelligence module (artificial intelligence unit 120) and regenerate the text. From this perspective, it can be said that the corrected text is created based on the text information. The regenerated corrected text is also displayed in the field C21 in the same way as the text created in the first creation step, and the recruiter who comes across this display can output the corrected text to the second field (field C2) by pressing the button BT7. In this case, the learning model included in the artificial intelligence module (artificial intelligence unit 120) may be a general-purpose learning model such as a large-scale language model, or may be a learning model that is trained to input a text created once and text information such as a correction guideline input by the recruiter, and output a text obtained by correcting the input text.

[0068] It should be noted that even if there is no input of revision guidelines by the employer in column C22, it is possible to revise (regenerate) the text. Since the artificial intelligence module (artificial intelligence unit 120) is configured to create the text to be output after extracting it with a predetermined probability, it is possible to output a different text in column C21 even if there is no input of any particular revision guidelines.

[0069] In this manner, the text created in the second column can be output. Note that the recruiter may operate the recruiter terminal 20 to make appropriate modifications to the text output in the second column (column C2).

[0070] After the text is inserted in the second column (column C2) in this way, a process for creating the text to be inserted in the third column is performed. The process for creating the text to be inserted in the third column is triggered by the recruiter making a request to create the text, as in the case of the second column described above. That is, the reception unit 112 receives a request to create a text for a type of item to be entered in the third column, based on the fact that the recruiter has operated a second object, which is different from the first object and is associated with the third column on the creation screen. That is, in the example shown in FIG. 6, a request to create a text to be entered in the third column (columns C31 and C32) is made by pressing button BT3 (second object), and the server device 10 receives this request (activities A111, A112).

[0071] In this way, when the reception unit 112 of the server device 10 receives a request to create a sentence related to one of the items to be entered in the third column, the creation unit 113 of the server device 10 inputs at least the content of the recruiting position into the artificial intelligence module (artificial intelligence unit 120) and creates the sentence. In this way, a sentence related to one of the items to be entered in the third column is individually created (activity A113). In addition, the output unit 114 of the server device 10 outputs the created sentence to the third column and displays it on the recruiter terminal 20 (activities A114, A115).

[0072] The basic process flow when outputting text to the third column is almost the same as the process flow when outputting text to the second column, but will be explained with reference to Fig. 9. Fig. 9 is a diagram for explaining the process of outputting generated text to the third column.

[0073] 9 shows an example in which a column C33 showing text related to the generated application qualifications is displayed when the button BT3 for generating application qualifications is pressed. The third column described in this embodiment relates to "application qualifications" and has columns for two perspectives, [MUST] and [WANT] (see columns C31 and C32). In contrast, the text generated by the creation unit 113 is created for each of the above-mentioned two perspectives, one of which is shown in column C34 and the other in column C35.

[0074] In Fig. 9, object OBJ2 is an object having the same function as object OBJ1 in Fig. 7, and switches the display from the candidate sentences currently displayed on the creation screen CS to another candidate sentence. Buttons BT8, BT9, and BT10 are buttons having the same function as buttons BT5, BT6, and BT7 in Fig. 7. When button BT9 is pressed, the text information input in field C36 is also input to the artificial intelligence module (artificial intelligence unit 120), and then a corrected sentence can be created. When button BT10 is pressed, the content displayed in field C34 is output to field C31, and the content displayed in field C35 is output to field C32.

[0075] That is, like the text to be output in the second column, when creating the text to be output in the third column, the text can be corrected. That is, the reception unit 112 may receive from the recruiter a request to correct the text created in the second creation step. Here, the reception unit 112 can receive a request to correct the text created in the second creation step based on the fact that the recruiter has operated a fourth object (button BT9) associated with the third column on the creation screen CS.

[0076] Furthermore, the creation unit 113 can create a corrected sentence by correcting the sentence created in the second creation step by inputting at least the sentence created in the second creation step and a correction request to the artificial intelligence module (artificial intelligence unit 120). Furthermore, this corrected sentence is output to the third column (columns C31 and C32) by pressing button BT10.

[0077] In this way, the employer requests confirmation of the job posting by pressing button BT4 in Fig. 6 after inputting the specified information into the first column, as well as the second and third columns (activity A116). The server device 10 accepts this confirmation request and confirms the job posting (activities A117, A118). The employer confirmed in this way will be made available for viewing by job seekers, etc. as appropriate.

[0078] Note that before a request to confirm the job posting is made, input may be made into columns other than the second and third columns. For example, in the example of FIG. 6, a column C3 is provided in which "working conditions" can be input as item I3, and by the employer manually inputting information into this column C3, the information can be reflected in the contents of the job posting. Of course, the items provided in the job posting made available for viewing by job seekers are not limited to the contents shown in FIG. 6. Items related to the place of work, remuneration, information on employee benefits, etc. may be entered in the job posting as information desired by job seekers.

[0079] The creation screen CS may further show an area where the job type in the job posting can be specified. In the example of Fig. 6, an item I5 corresponds to the job type, and an area (field C4) for specifying (inputting) this is displayed on the creation screen CS. In the example of this embodiment, this area is configured so that the employer can select a tag to specify the job type to be described in the job posting.

[0080] A specific embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram for explaining the process of specifying a job type in a job posting. In Fig. 10, the content to be entered as "job type" is displayed in a field C4 as a group of tags TG1. The system is configured so that the recruiter can select a part of the tags TG1 to specify the tags to be entered as the job type.

[0081] The tag TG1 here may be suggested based on the content already entered by the recruiter on the creation screen CS. In other words, if there is content already entered on the creation screen CS at the stage when the recruiter is about to enter the "job type" item, the tag TG1 with content highly related to the entered content may be configured to be displayed in the field C4.

[0082] More specifically, the following process may be performed. That is, the tag extraction unit 116 of the server device 10 may be configured to extract the tag TG1 from a predetermined job type master. Then, the display control unit 111 may display the extracted tag TG1 in the area of ​​the creation screen. In a typical embodiment, such tag extraction process can be made efficient by the function of an artificial intelligence module (artificial intelligence unit 120). That is, the tag extraction unit 116 may extract the tag TG1 by inputting at least the contents already input by the recruiter to the creation screen CS and the job type master to the artificial intelligence module (artificial intelligence unit 120).

[0083] That is, the server device 10 can prepare a plurality of keywords (job titles, etc.) related to various job types in a predetermined storage area (typically, the storage unit 12) and store them as a job type master. In this state, the tag extraction unit 116 inputs the content entered in the creation screen CS (typically, the content entered in the first, second, and third columns, as well as various other columns present in the creation screen CS) and the job type master to the artificial intelligence module (artificial intelligence unit 120), and instructs the artificial intelligence module (artificial intelligence unit 120) to extract keywords highly related to the assumed job type from the content entered in the creation screen CS. Although not necessarily limited to this, such extraction processing may be performed as follows. First, the tag extraction unit 116 instructs the artificial intelligence module (artificial intelligence unit 120) to convert the text of the content entered in the creation screen CS into vector data. Meanwhile, the tag extraction unit 116 instructs the artificial intelligence module (artificial intelligence unit 120) to convert the keywords of the job types present in the job type master into vector data in the same manner. Then, the tag extraction unit 116 causes the artificial intelligence module (artificial intelligence unit 120) to extract keywords that are highly correlated with the content entered in the creation screen CS from among the keywords present in the occupation master based on the closeness of the distance between both sets of vector data. Note that the closeness of the distance between the vector data here may be evaluated by various methods, but is typically evaluated by the angle between the two vectors (cosine similarity), etc. Also, the correlation here may be scored. Then, the keywords may be displayed in column C4 in descending order of the score.

[0084] In addition, in the above, when creating the text to be entered in the second and third columns, the embodiment has been shown in which the recruiting position entered in the first column is entered into the artificial intelligence module (artificial intelligence unit 120), but the content to be entered into the artificial intelligence module (artificial intelligence unit 120) may include various information acquired by the acquisition unit 115. A typical embodiment will be described below.

[0085] That is, when the acquisition unit 115 receives a creation request in the first or second reception step, if there is input information entered in the creation screen CS other than the content of the recruiting position, the acquisition unit 115 can acquire the input information. Then, the creation unit 113 can create a sentence related to a type of item to be entered in the second or third field by inputting the input information together with the recruiting position to the artificial intelligence module (artificial intelligence unit 120).

[0086] This input information is information entered for various items provided on the creation screen CS. That is, the input information may include information entered in the second and / or third columns. In addition, if there is information already entered in the field itself for which text is to be created, the already entered text can be used as part of the input information. In other words, when creating a new text to be entered in the second field, if there is text already entered in the second field (typically a draft or text used in a past job posting, etc.), the text already entered in the second field can be used as part of the input information, thereby improving the accuracy of the text to be created. Of course, the information entered in the creation screen CS that can be included in the input information is not limited to the contents described in the second and third fields, and may be various information that can be entered into the creation screen CS. For example, in the example of FIG. 6, the information may be information related to items separate from the second and third fields, such as the information entered in the fields C3 and C4.

[0087] The acquisition unit 115 can also acquire information different from the information input to the creation screen CS. That is, the display control unit 111 of the server device 10 can display a screen different from the creation screen CS to the recruiter and cause the acquisition unit 115 to acquire predetermined information in response to the input on this different screen.

[0088] In a more typical embodiment, the display control unit 111 can cause the recruiter to display an input screen separate from the creation screen CS. The acquisition unit 115 may then execute information acquisition processing based on the content entered by the recruiter on the input screen.

[0089] That is, in the example of the creation screen CS shown in Fig. 6, a button BT1 is shown on the screen, and when the recruiter presses this button BT1, another input screen is displayed. Fig. 11 is a diagram showing an example of the input screen IS in this embodiment. This input screen IS is configured so that when predetermined information is input and then button BT13 is pressed, the input information is acquired by the acquisition unit 115. Note that if such an acquisition process is not to be performed, the recruiter can return to the creation screen CS described above by pressing button BT12.

[0090] In a typical embodiment, the acquisition unit 115 can acquire information about the type of human resource desired by the recruiter based on an operation on the input screen IS by the recruiter. The acquisition of information about the type of human resource may also be achieved by an operation on the field C5 or field C6. The input screen IS shown in FIG. 11 is configured so that the type of human resource desired by the recruiter can be input as field C5. In the example of the input screen IS in FIG. 11, field C51 in field C5 is configured so that text information can be input, and a tag TG2 indicating the recruitment background and work content is displayed in field C61 based on the input text information. Then, when the tag TG2 is selected by the recruiter, the acquisition unit 115 can acquire information about the type of human resource desired by the recruiter.

[0091] The group of tags TG2 presented in the field C61 may be extracted and displayed (suggested) by the function of the tag extraction unit 116. That is, the server device 10 may store a master of tags representing the recruitment background and the business content in advance, and may be configured to extract appropriate tags from the master by collating with the text information input by the recruiter in the field C51, and display them in the field C61 as tags TG2. In addition, when performing the extraction here, for example, if there is information already input in the creation screen CS, the accuracy of the extraction may be improved by referring to such input information. The extraction process of the tag TG2 here may be performed based on the same process as the tag TG1 described above. That is, first, the tag extraction unit 116 instructs the artificial intelligence module (artificial intelligence unit 120) to convert the text input in the field C51 into vector data. On the other hand, the tag extraction unit 116 instructs the artificial intelligence module (artificial intelligence unit 120) to convert the keywords present in the master of tags representing the recruitment background and the business content into vector data in the same way. Then, the tag extraction unit 116 causes the artificial intelligence module (artificial intelligence unit 120) to extract keywords that are highly correlated with the content entered in the column C51 from among the keywords present in the master, based on the closeness of the distance between both sets of vector data. Note that the closeness of the distance between the vector data here may be evaluated by the angle between the two vectors (cosine similarity) or the like, as in the extraction process of the tag TG1. In addition, the correlation here may also be scored, and the keywords may be displayed in column C61 in descending order of the score.

[0092] Although this group of tags TG2 is automatically extracted and displayed by the function of the server device 10, the recruiter who accesses the input screen IS can also manually input the recruitment background and the job content. That is, the field C62 is configured so that the recruitment background and the job content can be input as text information. After inputting the text information in the field C62, the recruiting background and the job content related to the recruitment can be specified by pressing the button BT11.

[0093] In this way, based on the selection of tag TG2 and the contents entered by the recruiter in the field C62, the acquisition unit 115 can acquire information about the type of employee desired by the recruiter. Specifically, when the button BT13 in the input screen IS is pressed after the recruiter enters the specified information, the acquisition unit 115 can acquire the information entered in the input screen IS. As a result, the server device 10 can obtain information about the type of employee desired by the recruiter, and the creation unit 113 can create a sentence about a type of item to be entered in the second or third field by inputting information about the employee type together with the contents of the recruiting position to the artificial intelligence module (artificial intelligence unit 120).

[0094] On the other hand, the acquisition unit 115 can also acquire information about the employer. When the acquisition unit 115 acquires information about the employer in this way, the creation unit 113 can create a sentence about a type of item to be entered in the second or third column by inputting the information about the employer together with the recruiting position to the artificial intelligence module (artificial intelligence unit 120).

[0095] The information about the recruiter may be acquired based on a text input by the recruiter, but in the server device 10 of this embodiment, the acquisition unit 115 is configured to acquire information about the recruiter from public information on the network. That is, in the example shown in FIG. 11, an area for acquiring information about the recruiter is provided as a field C7. Specifically, a field C71 in the field C7 is configured to allow input of the URL of the recruiter's site (typically a corporate homepage, etc.) or the recruiter's recruitment site. In a typical example, the acquisition unit 115 can acquire information about the recruiter based on the URL input by the recruiter in the field C71. That is, when the button BT13 is pressed with a specific URL input in the field C71, the acquisition unit 115 collects information about the web page corresponding to the input URL by crawling, scraping, or the like, and thereby can acquire the characteristics of the recruiter. The "information about the employer" includes, for example, information indicating the business content, information indicating the type of business, information indicating the size of the organization, information indicating business performance, information indicating the merchandise handled (products or services), information indicating the financial situation, information indicating the business plan, information regarding the business vision, etc., but is not limited thereto, and may be appropriately selected from the information that the acquisition unit 115 can acquire. The information about the employer acquired in this way can be reflected in the text to be output in the second and third columns. For example, the creation unit 113 can create various texts after arranging keywords highly related to the information about the employer at the beginning as text to be output in the second and third columns. In other words, when the text about the second and third columns is created after appropriately arranging the information about the employer, it is easier for the job seeker who sees the job posting to recall an image of the employer. As a result, it is considered that this can contribute to smooth matching between the employer and the job seeker.

[0096] 4. Effect The operation of this embodiment can be summarized as follows. That is, in this embodiment, the text to be entered in the second column and the text to be entered in the third column are created separately and then output to each column. This allows the job advertisement to be created while checking the content of each item, allowing the employer to create the job advertisement efficiently.

[0097] 5.Other In the above embodiment, the server device 10 performs various storage and control, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 120, which is an external configuration, is provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of the server device 10, receive a request to execute an artificial intelligence service, and return an instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides a service using a language model as a learning model, or may be a server that executes a language processing task using a language model. The artificial intelligence service server may be constructed by LLM. The artificial intelligence service server receives input of a prompt by text, image, voice, etc., and generates and responds to the prompt.

[0098] In the above embodiment, the mode of inputting the recruiting position in the first column has been described, but the content to be input in the first column can be content other than the recruiting position. That is, one of the items required for creating a job posting can be input in the first column, and the text to be input in the second and third columns can be automatically generated accordingly.

[0099] In the above embodiment, a separate column C20 is displayed before the text created in the second column (column C2) is output, allowing the recruiter to check the created text. However, the text created in the second column (column C2) can also be output without displaying column C20. That is, the created text may be directly output to the second column (column C2) when button BT2 on the creation screen CS is pressed (the created text may be output to the second column by one-clicking button BT2). Similarly, the created text may be directly output to the third column (columns C31 and C32) when button BT3 on the creation screen CS is pressed (the created text may be output to the third column by one-clicking button BT3).

[0100] In the above embodiment, a field for inputting correction instructions for the second column and a field for inputting correction instructions for the third column are provided separately, but a field for inputting correction instructions for the entire creation screen CS may be provided in the creation screen CS. In such an example, it becomes possible to perform correction processing on both the text related to the second column and the text related to the third column at the same time based on the input correction instructions.

[0101] The aspect of the present embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0102] It may be provided in any of the following ways:

[0103] (1) An information processing system for supporting the creation of a job posting, comprising at least one processor, the processor being configured to execute each of the following steps by reading out a program: a first display control step causes a job recruiter to display a job posting creation screen, wherein the creation screen displays at least a first column, a second column, and a third column, the first column being a column for inputting a position for which information is to be advertised in the job posting, the second column being a column for inputting one type of item among a plurality of items corresponding to the position, and the third column being a column for inputting one type of item among a plurality of items corresponding to the position, which is different from the item entered in the second column; a first reception step receives from the job recruiter a request for creating text relating to the type of item to be entered in the second column together with the content of the position for which information is to be advertised in the first column; an information processing system which, based on receiving a request for creating text related to the one type of item to be input into the second column, inputs at least the content of the recruiting position into an artificial intelligence module to individually create text related to the one type of item to be input into the second column; in a first output step, outputs the text created in the first creation step into the second column; in a second reception step, receives from the employer a request for creating text related to the one type of item to be input into the third column along with the content of the recruiting position input into the first column; in a second creation step, based on receiving a request for creating text related to the one type of item to be input into the third column, inputs at least the content of the recruiting position into an artificial intelligence module to individually create text related to the one type of item to be input into the third column; and in a second output step, outputs the text created in the second creation step into the third column.

[0104] (2) In the information processing system described in (1) above, in the first reception step, a request for creation of text regarding the type of item to be entered into the second column is accepted based on the employer operating a first object associated with the second column on the creation screen, and in the second reception step, a request for creation of text regarding the type of item to be entered into the third column is accepted based on the employer operating a second object different from the first object that is associated with the third column on the creation screen.

[0105] (3) In the information processing system described in (1) or (2) above, in the acquisition step, information regarding the type of employee desired by the employer is acquired, and in the first creation step, information regarding the type of employee is input into the artificial intelligence module along with the content of the recruitment position, thereby creating a sentence regarding the type of item to be entered in the second field.

[0106] (4) An information processing system according to any one of (1) to (3) above, wherein in the acquisition step, information about the employer is acquired, and in the first creation step, the information about the employer is input together with the advertised position into the artificial intelligence module to create a sentence about the type of item to be entered in the second field.

[0107] (5) In the information processing system described in (4) above, in the acquisition step, information about the recruiter is acquired from public information on a network.

[0108] (6) In the information processing system described in (5) above, in the acquisition step, information about the employer is acquired based on a URL input by the employer.

[0109] (7) An information processing system according to any one of (3) to (6) above, wherein in the second display control step, an input screen separate from the creation screen is displayed to the employer, and in the acquisition step, information acquisition processing is performed based on the content entered by the employer on the input screen.

[0110] (8) In the information processing system described in any one of (1) to (7) above, in the acquisition step, when the creation request is received, if there is input information entered into the creation screen other than the content of the advertised position, the input information is acquired, and in the first creation step, the input information together with the advertised position is entered into the artificial intelligence module to create a sentence regarding the type of item to be entered into the second column.

[0111] (9) In the information processing system described in (8) above, the input information includes information entered in the second column and / or the third column.

[0112] (10) In the information processing system described in any one of (1) to (9) above, in the first creation step, a plurality of sentences relating to the one type of item to be entered in the second column are created, and in the first output step, the plurality of sentences created are presented to the recruiter in a manner allowing the recruiter to select one of the plurality of sentences, and the sentence selected by the recruiter from the plurality of presented sentences is output to the second column.

[0113] (11) An information processing system according to any one of (1) to (10) above, wherein in a first revision request receiving step, a revision request for the text created in the first creation step is received from the employer, and in a first revised text creating step, at least the text created in the first creation step and the revision request are input into an artificial intelligence module to create a revised text in which the text created in the first creation step is revised, and in the first output step, the revised revised text is output to the second column.

[0114] (12) In the information processing system described in (11) above, in the first correction request receiving step, a correction request for the text created in the first creation step is received based on the employer operating a third object associated with the second field on the creation screen.

[0115] (13) An information processing system according to any one of (1) to (12) above, wherein in a second revision request receiving step, a revision request for the text created in the second creation step is received from the employer, and in a second revised text creating step, at least the text created in the second creation step and the revision request are input into an artificial intelligence module to create a revised text in which the text created in the second creation step is revised, and in the second output step, the revised revised text is output to the third column.

[0116] (14) In the information processing system described in (13) above, in the second correction request receiving step, a correction request for the text created in the second creation step is received based on the employer operating a fourth object associated with the third field on the creation screen.

[0117] (15) In the information processing system described in any one of (11) to (14) above, the correction request includes text information input by the employer, and the corrected text is created based on the text information.

[0118] (16) In the information processing system described in any one of (1) to (15) above, the creation screen further shows an area in which the job type in the job posting can be specified, and the area is configured so that the employer can specify the job type to be described in the job posting by selecting a tag, and the tag is suggested based on the content already entered by the employer on the creation screen.

[0119] (17) In the information processing system described in (16) above, in the tag extraction step, the tag is extracted from a predetermined job type master, and in the first display control step, the extracted tag is displayed in the area of ​​the creation screen.

[0120] (18) In the information processing system described in (17) above, in the tag extraction step, the tag is extracted by inputting at least the content already entered by the employer on the creation screen and the job type master into an artificial intelligence module.

[0121] (19) An information processing system according to any one of (1) to (18) above, wherein the second column is a column in which job details corresponding to the advertised position are entered, and the third column is a column in which application qualifications corresponding to the advertised position are entered.

[0122] (20) An information management method, comprising steps executed by an information processing system according to any one of (1) to (19) above.

[0123] (21) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (19) above. Of course, this is not the case.

[0124] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0125] 1: Information processing system 2: Communication lines 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter terminal 21: Control section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job Seeker Terminal 31: Control section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 111: Display control unit 112: Reception 113: Creation Department 114: Output section 115: Acquisition Department 116: Tag extraction part 120: Artificial Intelligence Department 211:Display section 212: Operation acquisition section 311: Display section 312: Operation acquisition section BT1~BT13: Buttons C1~C7, C20~C22, C31~C36, C51, C61~C62, C71: Column CS: Creation screen I1~I6: Item IS: Input screen OBJ1, OBJ2: Objects TG1, TG2: Tags U1: 1st job applicant U2: Second Recruiter U3: 1st job applicant U4: 2nd job applicant

Claims

1. An information processing system for supporting the creation of a job posting, At least one processor; The processor is configured to execute the following steps by reading the program: In the first display control step, a job recruiter is caused to display a job posting creation screen, and at least a first column, a second column, and a third column are displayed on the creation screen. The first field is a field in which the recruitment position of the job posting is input, The second field is a field in which one of a plurality of items corresponding to the recruiting position is input, The third field is a field in which an item that is one of a plurality of items corresponding to the recruiting position and is different from the item that is input in the second field is input, In the first reception step, a request for creating a document regarding the type of item to be entered in the second field is received from the recruiter along with the content of the recruiting position entered in the first field; In the first creation step, based on receiving a request to create a sentence related to the one type of item to be inputted into the second field, at least the content of the recruitment position is inputted into an artificial intelligence module, thereby individually creating a sentence related to the one type of item to be inputted into the second field; Here, the artificial intelligence module used in the first creation step has a large-scale language model or a learning model trained to receive information about the recruiting position as input and output sentences related to the items corresponding to the second column, When the artificial intelligence module used in the first creation step has the large-scale language model, the first creation step is executed by inputting a prompt to the large-scale language model to output a sentence related to an item corresponding to the second column based on the recruitment position accepted in the first acceptance step, When the artificial intelligence module used in the first creation step has the learning model, the first creation step is executed by inputting the recruitment position accepted in the first acceptance step into the learning model and outputting a sentence related to the item corresponding to the second column, In a first output step, the text created in the first creation step is output to the second column; In a second reception step, a request for creating a document regarding the type of item to be entered in the third field is received from the recruiter along with the content of the recruiting position entered in the first field; In a second creation step, based on receiving a request to create a sentence related to the one type of item to be inputted in the third field, at least the content of the recruitment position is inputted into an artificial intelligence module, thereby individually creating a sentence related to the one type of item to be inputted in the third field; Here, the artificial intelligence module used in the second creation step has a large-scale language model or a learning model trained to receive information about the recruiting position as input and output a sentence related to the item corresponding to the third column, When the artificial intelligence module used in the second creation step has the large-scale language model, the second creation step is executed by inputting a prompt to the large-scale language model to output a sentence related to an item corresponding to the third column based on the recruitment position accepted in the first acceptance step, When the artificial intelligence module used in the second creation step has the learning model, the second creation step is executed by inputting the recruitment position accepted in the first acceptance step into the learning model and outputting a sentence related to the item corresponding to the third column, In a second output step, the text created in the second creation step is output to the third column.

2. 2. The information processing system according to claim 1, In the first reception step, a request for creating a document related to the one type of item to be input into the second field is received based on an operation by the recruiter of a first object associated with the second field on the creation screen; In the second reception step, the information processing system accepts a request to create a document regarding the type of item to be entered into the third column based on the employer operating a second object different from the first object that is associated with the third column on the creation screen.

3. 2. The information processing system according to claim 1, In the acquisition step, information regarding the type of human resources desired by the recruiter is acquired, In the first creation step, the information processing system creates a sentence regarding the type of item to be entered in the second column by inputting information regarding the profile of the employee along with the content of the recruiting position into the artificial intelligence module.

4. 2. The information processing system according to claim 1, In the acquisition step, information regarding the recruiter is acquired, In the first creation step, information about the employer along with the recruiting position is input into the artificial intelligence module to create a sentence regarding the type of item to be entered into the second field, in an information processing system.

5. 5. The information processing system according to claim 4, In the acquiring step, information about the recruiter is acquired from public information on a network, the information processing system.

6. 6. The information processing system according to claim 5, In the acquiring step, an information processing system acquires information about the recruiter based on a URL input by the recruiter.

7. 4. The information processing system according to claim 3, In the second display control step, an input screen separate from the creation screen is displayed to the recruiter, In the acquisition step, information acquisition processing is performed based on the contents input by the recruiter on the input screen, in an information processing system.

8. 2. The information processing system according to claim 1, In the acquisition step, when the creation request is received, if there is input information entered on the creation screen other than the content of the recruiting position, the input information is acquired, In the first creation step, the information processing system creates a sentence regarding the type of item to be entered in the second column by inputting the input information together with the recruiting position into the artificial intelligence module.

9. 9. The information processing system according to claim 8, An information processing system, wherein the input information includes information entered in the second field and / or the third field.

10. 2. The information processing system according to claim 1, In the first creation step, a plurality of sentences relating to the one type of item to be inputted into the second column are created; Here, when the artificial intelligence module used in the first creation step has the large-scale language model, the first creation step is executed by inputting a prompt to the large-scale language model to output a plurality of sentences related to the item corresponding to the second column based on the recruitment position accepted in the first acceptance step, When the artificial intelligence module used in the first creation step has the learning model, a learning model that is trained to input information about the recruiting position and output a plurality of sentences related to the item corresponding to the second column is used as the learning model; The first creation step is executed by inputting the recruiting position accepted in the first acceptance step into the learning model and outputting a plurality of sentences related to the item corresponding to the second column, In the first output step, the information processing system presents the created plurality of sentences to the employer in a manner allowing the employer to select one of the plurality of sentences, and outputs the sentence selected by the employer from the presented plurality of sentences in the second column.

11. 2. The information processing system according to claim 1, In a first revision request receiving step, a revision request for the text created in the first creation step is received from the recruiter, In the first revised sentence creation step, at least the sentence created in the first creation step and the correction request are input to an artificial intelligence module to create a revised sentence in which the sentence created in the first creation step is corrected; In the first output step, the corrected sentence is output to the second column.

12. 12. The information processing system according to claim 11, In the first correction request receiving step, an information processing system receives a correction request for the text created in the first creation step based on the employer operating a third object associated with the second field on the creation screen.

13. 2. The information processing system according to claim 1, In a second revision request receiving step, a revision request for the text created in the second creation step is received from the recruiter, In a second revised sentence creation step, at least the sentence created in the second creation step and the correction request are input to an artificial intelligence module to create a revised sentence in which the sentence created in the second creation step is corrected; In the second output step, the corrected sentence is output to the third column.

14. 14. The information processing system according to claim 13, In the second correction request receiving step, an information processing system receives a correction request for the text created in the second creation step based on the employer operating a fourth object associated with the third field on the creation screen.

15. 12. The information processing system according to claim 11, The correction request includes text information entered by the recruiter, An information processing system, wherein the revised sentence is created based on the text information.

16. 2. The information processing system according to claim 1, The creation screen further shows an area in which a job type in the job posting can be specified, An information processing system configured in the area to allow the employer to specify the job type to be described in the job posting by selecting a tag, where the tag is suggested based on the content already entered by the employer on the creation screen.

17. 17. The information processing system according to claim 16, In the tag extraction step, at least the content already input by the recruiter on the creation screen and a predetermined job type master are input into an artificial intelligence module to extract the tag from the predetermined job type master; wherein the artificial intelligence module used in the tag extraction step is: Converting the text of the content into first vector data; Converting keywords of occupations present in the predetermined occupation master into second vector data; and The tag is extracted based on a proximity of a distance between the first vector data and the second vector data. In the first display control step, the extracted tag is displayed in the area of ​​the creation screen.

18. 2. The information processing system according to claim 1, The second field is a field in which the job content corresponding to the recruited position is input, An information processing system, wherein the third column is a column in which application qualifications corresponding to the recruiting position are entered.

19. 1. An information management method, comprising: An information processing method comprising the steps executed by the information processing system according to any one of claims 1 to 18.

20. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 18.

Images