Text creation support system, information processing method and program

Abstract

To provide an information processing system, etc. capable of facilitating creation of a text relating to work experience of a job applicant.SOLUTION: There is provided a text creation support system. The text creation support system including a processor, causes the processor to execute: an input step of displaying an input screen for receiving input of job applicant information relating to a job applicant; and an instruction step of instructing artificial intelligence to create a text relating to work experience of the job applicant based on the job applicant information, where the artificial intelligence has a learning model taking the job applicant information as input and the text as output. In the display step, the text output by the artificial intelligence is displayed based on the instruction.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Conventionally, devices have been proposed that use templates to assist in creating documents (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2009-230705 A Summary of the Invention [Problem to be solved by the invention]

[0004] When job seekers are looking for a job or changing jobs, they need to prepare documents such as resumes or curriculum vitae that include text about their work history in order to communicate their job duties and skills to companies and other employers, but preparing such documents takes time and effort.

[0005] In view of the above circumstances, the present invention provides an information processing system etc. that can facilitate the creation of documents relating to a job seeker's work history. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided a writing support system. The writing support system includes a processor, and in an input step, the processor displays an input screen for accepting input of job seeker information related to a job seeker. In an instruction step, the processor instructs an artificial intelligence to write a sentence related to the job seeker's work history based on the job seeker information, and the artificial intelligence has a learning model that receives the job seeker information as input and outputs a sentence. In a display step, the processor displays the sentence output by the artificial intelligence based on the instruction.

[0007] According to this embodiment, it is possible to easily create a resume. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an overall configuration of a writing support system 1. [Diagram 2] FIG. 2 is a diagram illustrating a hardware configuration of a server device 10. [Diagram 3] FIG. 2 is a diagram illustrating a hardware configuration of a job seeker terminal 20. [Figure 4] FIG. 2 is a diagram illustrating the functional configuration of a control unit of each device. [Diagram 5] FIG. 11 is an activity diagram showing an example of a sentence generation process. [Figure 6] FIG. 13 illustrates an example of a registration screen. [Figure 7] FIG. 13 is a diagram showing an example of a creation screen. [Figure 8] FIG. 13 is a diagram illustrating an example of an input screen. [Figure 9] FIG. 13 is a diagram showing an example of displayed input candidates. [Figure 10] FIG. 11 is a diagram showing another example of the input screen. [Figure 11] FIG. 11 is a diagram showing another example of the input screen. [Figure 12] FIG. 11 is a diagram showing another example of the input screen. [Figure 13] FIG. 13 is a diagram showing an example of a screen prompting a user to create a document regarding work history. [Figure 14] FIG. 13 is a diagram showing an example of the progress of a displayed text regarding work history. [Figure 15] FIG. 13 is a diagram showing an example of a completed text for an entire chapter. [Figure 16] FIG. 13 is a diagram showing an example of a displayed text regarding work history. [Figure 17] FIG. 11 is a diagram showing an example of the input screen that is displayed again. [Figure 18] FIG. 13 is a diagram illustrating an example of a table. [Figure 19]FIG. 13 is a diagram illustrating another example of the table. [Figure 20] FIG. 13 is a diagram illustrating another example of the table. [Figure 21] FIG. 13 is a diagram illustrating another example of the table. [Figure 22] FIG. 13 is a diagram showing another example of a text regarding a displayed work history. [Diagram 23] FIG. 13 is a diagram illustrating an example of a table. [Figure 24] FIG. 13 is a diagram illustrating another example of the table. [Diagram 25] FIG. 13 is a diagram illustrating another example of the table. [Figure 26] FIG. 13 is a diagram illustrating another example of the table. [Figure 27] FIG. 13 is a diagram illustrating another example of the table. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic features shown in the following embodiments can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in this 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 started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] In addition, in this 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 addition, in this embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit group 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.

[0012] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. 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.

[0013] 1. Hardware Configuration In this section, the hardware configuration of the writing support system according to this embodiment will be described.

[0014] Fig. 1 is a diagram showing the overall configuration of the writing support system 1. Fig. 1 shows an overview of each device provided in the writing support system 1 and users who use those devices. Each overview will be explained as appropriate with reference to other figures.

[0015] The writing support system 1 is an information processing system that executes writing generation processing, which is information processing for supporting the creation of writing about work history included in documents related to a job seeker, such as a curriculum vitae. A curriculum vitae, also called a resume, is a document in which a job seeker conveys to an employer his or her work history, skills, qualifications, etc. that the job seeker possesses. In this embodiment, the writing support system 1 supports the creation of writing about work history by a job seeker U1. Writing about work history is writing that describes the work and tasks that the job seeker has experienced. Note that, although a curriculum vitae is used as an example of a document to be created, the description is not limited to this, and any document that includes writing about work history may be used.

[0016] The writing support system 1 comprises a communication line 2, a server device 10, and a job seeker terminal 20. The communication line 2 may be configured by the Internet, although it is not particularly limited thereto. The communication line 2 may also include a local area network, a mobile communication network, or a VPN (Virtual Private Network), etc. The communication line 2 mediates data exchange between devices connected to the communication line. The server device 10 is connected to the communication line 2 by wire, and the job seeker terminal 20 is connected wirelessly. The connection of each device to the communication line 2 may be wired or wireless.

[0017] The server device 10 is an information processing device that executes a sentence generation process while exchanging data with the job seeker terminal 20 via the communication line 2. The server device 10 stores a phrase database DB1 and a registered information database DB2. The phrase database DB1 stores phrases used in the sentence generation process. The registered information database DB2 stores registered information that is registered in advance by the job seeker U1. The server device 10 has an artificial intelligence (AI) function, and generates and outputs sentences related to work history using the information stored in the phrase database DB1 and the registered information database DB2.

[0018] The job seeker terminal 20 is a terminal for which the job seeker U1 is the user. The job seeker terminal 20 is a smartphone, a tablet terminal, a personal computer, etc. The job seeker terminal 20 accepts inputs necessary for the writing generation process and displays the generated writings related to work history.

[0019] 2 is a diagram showing a hardware configuration of server device 10. Server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a bus 14. Bus 14 electrically connects each unit included in server device 10.

[0020] (Control unit 11) The control unit 11 may include at least one processor. The at least one processor may be configured, for example, by a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), one or more integrated circuits, one or more discrete circuits, or a combination of these (not shown). The control unit 11 is a computer that realizes various functions related to the writing support system 1 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 may be implemented to have multiple control units 11 for each function. Also, a combination of these may be used.

[0021] (Storage unit 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) or a hard disk drive (HDD) that stores various programs and the like related to the writing support system 1 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 writing support system 1 executed by the control unit 11.

[0022] (Communications Department 13) The communication unit 13 is configured by a communication module. The communication module may be a wireless communication module conforming to standards such as IEEE802.11a / b / g / n / ac / ax, LTE, 5G, and 6G, or may be a wired communication module conforming to standards such as IEEE802.3. The communication unit 13 is configured to be capable of transmitting various electrical signals from the server device 10 to external components. The communication unit 13 is also configured to be capable of receiving various electrical signals from the external components to the server device 10. More preferably, the communication unit 13 has a network communication function, and may be capable of communicating various information between the server device 10 and an external device via the communication line 2.

[0023] Fig. 3 is a diagram showing the hardware configuration of the job seeker terminal 20. The job seeker terminal 20 includes a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a bus 26. The bus 26 electrically connects the various units included in the job seeker terminal 20. The control unit 21, the memory unit 22, and the communication unit 23 are similar hardware to the control unit 11, the memory unit 12, and the communication unit 13 shown in Fig. 2, although the specifications, model, etc. may be different.

[0024] (Input section 24) The input unit 24 has keys, buttons, a touch screen, a mouse, etc., and receives input from the user. The input unit 24 may also have a microphone and receive voice input from the user.

[0025] (Output section 25) The output unit 25 has a display, a speaker, and the like, and displays visual information generated in a manner that is visible to the user, such as screens, images, icons, text, and the like, on the display surface of the display, and outputs sounds including voice.

[0026] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. As described above, information processing by software stored in the storage unit of each device is specifically realized by a control unit, which is an example of hardware, so that each functional unit included in the control unit can be executed.

[0027] 4 is a diagram showing the functional configuration of the control unit of each device. The control unit 11 of the server device 10 includes a server display unit 111, a memory control unit 112, an AI control unit 113, an artificial intelligence unit 114, a parameter acquisition unit 115, and a candidate designation unit 116. The job seeker terminal 20 includes a user display unit 211 and an operation reception unit 212.

[0028] The server display unit 111 executes processing for displaying on each terminal a system screen relating to the writing support system 1. For example, the server display unit 111 performs processing such as generating and transmitting an HTML (Hyper Text Markup Language) file, and displays a web page showing the system screen on the job seeker terminal 20. The server display unit 111 may also perform processing such as generating and transmitting display data for an application for using the writing support system 1.

[0029] The server display unit 111 displays a registration screen and an input screen for job seeker information on a job seeker. The job seeker information is information on a job seeker, including job seeker information (registration information) entered on the registration screen and registered in advance, and job seeker information (input information) entered on an input screen for creating a sentence related to work history, and includes all information on the job seeker that has been registered or input. The job seeker information is, for example, information such as the age, address, occupation, and job title of the job seeker. The memory control unit 112 controls the memory unit 12 of the device itself, and writes and reads data to and from the memory unit 12. The memory control unit 112 stores, for example, the job seeker information (registration information) registered on the registration screen and the job seeker information (input information) entered on the input screen. The AI ​​control unit 113 controls input to the artificial intelligence unit 114. The AI ​​control unit 113 generates a prompt that indicates that a sentence related to work history is to be output, using, for example, the job seeker information entered on the input screen for job seeker information as input.

[0030] The artificial intelligence unit 114 is an AI equipped with learning models such as language models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, and GPT-3), BERT (Bidirectional Encoder Representations from Transformers), or BART (Bidirectional and Auto-regressive Transformer).

[0031] A learning model (also called a machine learning model) refers to a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include the nearest neighbor method, the naive Bayes method, a decision tree, and a support vector machine. Another example is deep learning, which uses a neural network to generate features and connection weighting coefficients for learning. The artificial intelligence unit 114 can apply the above algorithms as appropriate.

[0032] The artificial intelligence unit 114 performs machine learning using teacher data. Teacher data refers to learning data, and is composed of a pair of input data for learning and output data (correct answer data). Note that a trained model refers to a model that has been trained (learned) in advance using appropriate teacher data (learning data) for a machine learning model according to an arbitrary machine learning algorithm such as deep learning.

[0033] However, although the trained model has obtained appropriate training data in advance, it is not the case that no further training is performed, and additional training can be performed. Additional training is also performed after the device is installed at the usage site. The artificial intelligence unit 114 may perform machine learning by so-called unsupervised learning to construct the trained model. Unsupervised learning is a method in which a large amount of input data alone is given to learn the input data, and processing is learned without giving output data corresponding to the input data.

[0034] The artificial intelligence unit 114 receives job seeker information as input and outputs text related to work history based on a prompt generated by the AI ​​control unit 113. The parameter acquisition unit 115 acquires predetermined parameters related to the job seeker. The parameters include, for example, input information already entered and included in the input screen, and registered information related to the job seeker that has been registered in advance. Details of each parameter will be described later. The candidate designation unit 116 determines words and phrases according to the acquired parameters as input candidates. The input candidates referred to here are candidates for words and phrases that are input or selected by the job seeker as job seeker information on the input screen.

[0035] The user display unit 211 of the job seeker terminal 20 displays a system screen relating to the writing support system 1 indicated by the screen data transmitted from the server device 10. The operation reception unit 212 receives operations by a user using the job seeker terminal 20. When a job seeker U1 operates the job seeker terminal 20 as a user to use the writing support system 1, he or she logs in by entering a user ID (Identification) and a password. This associates the user ID with information generated in the job seeker terminal 20, making it possible to know which user the information pertains to.

[0036] 3. Information Processing In this section, in this embodiment, information processing (writing generation processing for generating writing on work history) that causes a computer that controls the writing support system 1 to execute a program will be described. The writing support system 1 includes a processor that can execute a program so as to perform each step shown in the following FIG. 5 and the like.

[0037] Fig. 5 is an activity diagram showing an example of a writing generation process. The writing generation process shown in Fig. 5 is started when a job seeker U1 operates the job seeker terminal 20 to display a registration screen for registering basic information about the job seeker as registration information in advance. First, the job seeker terminal 20 receives an operation to display the registration screen via the operation reception unit 212 (A11). The operation reception unit 212 transmits first request data to the server device 10, which requests the display of the registration screen.

[0038] The server device 10 generates, via the server display unit 111, registration screen data showing the registration screen requested by the transmitted first request data (A12). The server display unit 111 transmits the generated registration screen data to the job seeker terminal 20. The job seeker terminal 20 displays, via the user display unit 211, the registration screen shown in the transmitted registration screen data.

[0039] FIG. 6 is a diagram showing an example of a registration screen. In the example of FIG. 6, the user display unit 211 displays a writing support system screen G1. The writing support system screen G1 displays a character string saying "Please enter registration information.", an input field C1 for registration information, and a registration button B11. The input field C1 is an area for inputting registration information including "basic information" such as "name", "age", "address", "date of birth" and "current annual income", "desired conditions" such as "desired job type", "desired industry", "desired place of work" and "desired annual income", "educational background" such as "school name" and "year of graduation", "work history" such as "company name", "department name", "job title" and "tenure period", and other items such as "awards", "experienced job type", "experienced industry", "qualifications", and "language ability".

[0040] In "Occupational Experience" and "Industry of Experience", the number of years of experience for each occupation or industry can be input. In addition, "Work Experience" includes a Details button B12 for displaying a screen for inputting "Work Experience Details" or writing a document related to the work experience.

[0041] The job seeker terminal 20, through the operation receiving unit 212, receives as a registration operation the operation on the registration button B11 while input has been made to the input field C1 (A14), and transmits the input registration information to the server device 10. The server device 10, through the storage control unit 112, stores the transmitted registration information in the registration information database DB2 as job seeker information (A15).

[0042] Next, the job seeker U1 performs an operation to display a creation screen for creating a document related to his / her work history on the job seeker terminal 20, for example, by pressing the details button B12. The job seeker terminal 20 receives an operation to display the creation screen through the operation reception unit 212 (A21). The operation reception unit 212 transmits second request data requesting the display of the creation screen to the server device 10. When the second request data is transmitted, the server device 10 generates creation screen data showing the creation screen through the server display unit 111 (A22). The server display unit 111 transmits the generated creation screen data to the job seeker terminal 20. The job seeker terminal 20 displays the creation screen shown by the transmitted creation screen data through the user display unit 211.

[0043] Fig. 7 is a diagram showing an example of a creation screen. In the example of Fig. 7, the user display unit 211 displays the writing support system screen G2. The writing support system screen G2 displays a character string "Edit position / project name", input fields C21, C22, and C23 for the position name or project name, work period, and work content, respectively, and an automatic generation button B2. The job seeker U1 inputs the position name or project name and work period into the input fields C21 and C22, respectively.

[0044] The input field C23 is an area for inputting text explaining the work content as text related to work history. Text explaining the work content is text describing the actual work performed by the job seeker U1 in the jobs he / she has had, the results, and the selling points to the employer, and is an example of text related to work history. Here, the work content corresponding to the job title or project name and work period entered in the input fields C21 and C22 is entered in the input field C23.

[0045] The job seeker U1 can input information into the input field C23 by himself / herself, but even if he / she does not input information by himself / herself, he / she can operate the automatic generation button B2 to automatically generate a text explaining the work content as a text related to the work history. When the job seeker terminal 20 accepts an operation on the automatic generation button B2 by the operation acceptance unit 212, it transmits third request data requesting automatic generation of a text related to the work history to the server device 10 (A24).

[0046] When the third request data is transmitted, the server device 10 first acquires, by the parameter acquisition unit 115, predetermined parameters related to the job seeker (A31). At the stage when the parameter acquisition unit 115 receives the third request data, it acquires, as parameters related to the job seeker, the registration information of the job seeker U1 stored in the registration information database DB2 in A15 and the information entered on the writing support system screen G2 (job title or project name and work period). Next, the server device 10, by the server display unit 111, generates input screen data showing an input screen for entering information necessary to generate writing related to work history, and transmits the generated data to the job seeker terminal 20 (A32). The job seeker terminal 20 displays, by the user display unit 211, the input screen shown by the transmitted input screen data (A33).

[0047] Fig. 8 is a diagram showing an example of an input screen. In the example of Fig. 8, the user display unit 211 displays the writing support system screen G3. The writing support system screen G3 displays a character string "Input information for creating work history", a stage image D3 indicating a stage of information input, a character string "Please tell us your occupation (up to three)", an occupation input field C31, a list of occupations recommended for the job seeker U1 C32, a back button B31, and a forward button B32.

[0048] The job seeker information to be input to create a document about work history includes "job type," "position," "mission," and "business area," all of which are information about the job seeker, and are hereinafter referred to as "input information." In this embodiment, the stage image D3 indicates that the first stage (job type input stage) of five information input stages is being reached.

[0049] An upper limit (three in the example of FIG. 8) is set for the number of job types that can be entered in the input field C31. The server display unit 111 sets this upper limit of the number that can be entered based on the registration information, which is the acquired parameter. For example, the server display unit 111 stores a table that associates the number of years of experience indicated by the "experienced job type" included in the registration information with the upper limit of the number that can be entered, and sets the number associated with the number of years of experience indicated by the "experienced job type" included in the registration information acquired as a parameter as the upper limit.

[0050] Furthermore, the candidates designation unit 116 stores, for example, a table in which the "experienced occupation" included in the registration information is associated with the recommended occupation, and determines the recommended occupation (occupation A, occupation B, and occupation C, etc. in the example of FIG. 8) associated with the "experienced occupation" included in the registration information acquired as a parameter. Note that other information associated with the recommended occupation may be "company name," "department name," and "job title" input as work history on the screen shown in FIG. 6, or "job title" and "project name" input as work history details on the screen shown in FIG. 7. The server display unit 111 displays the determined recommended occupation in the occupation list C32. The job seeker terminal 20 accepts an input operation into the occupation input field C31 by the operation acceptance unit 212 (A34).

[0051] Input into the input field C31 may be an operation of selecting from the job type list C32, or an operation of inputting one character at a time using a keyboard. When the operation receiving unit 212 receives an input operation of one character at a time, it transmits operation data indicating the input characters to the server device 10. The server device 10 stores a job type master including the names of various job types, and the candidate designator 116 searches the job type master for job types including the characters indicated by the operation data, and determines the search results as input candidates (A35). The candidate designator 116 transmits the determined input candidates to the job seeker terminal 20. The job seeker terminal 20 displays the transmitted input candidates by the user display unit 211 (A36).

[0052] FIG. 9 is a diagram showing an example of displayed input candidates. In the example of FIG. 9, the user display unit 211 displays an input candidate list C33 corresponding to the input field C31 shown in FIG. 8. In the example of FIG. 9, the character "e" is input in the input field C31, and the input candidates "sales planning", "sales administration" and "sales promotion" are displayed in the input candidate list C33. In this way, the candidate designator 116 performs a so-called incremental search that displays input candidates based on the input characters. The operation accepting unit 212 accepts, as an input operation, the selection of a job type from the job type list C32 shown in FIG. 8, the selection of a job type from the input candidate list C33, or the input of a character string indicating a job type from a keyboard.

[0053] When the operation acceptance unit 212 accepts an operation on the back button B31, the job seeker terminal 20 displays the previous screen (the writing support system screen G2 shown in FIG. 7 in the case of the back button B31 in FIG. 8) on the user display unit 211. When the operation acceptance unit 212 accepts an operation on the forward button B32, the job seeker terminal 20 transmits to the server device 10 input information entered in the input field C31 to generate a text on work history in association with the writing support system screen G3 (A41). The server device 10 acquires the transmitted input information as job seeker information by the storage control unit 112 (A42), and stores the acquired job seeker information in association with the writing support system screen G3 (A43).

[0054] If there is any input information that has not been entered, the server device 10 returns to A31 and continues the operation. When the input of the input information for generating the text related to the work history progresses, the parameter acquisition unit 115 acquires the input information saved in A43 as parameters related to the job seeker, in addition to the registration information of the job seeker U1 described above. Then, A32 (generation of an input screen) and A33 (display of an input screen) are performed.

[0055] Fig. 10 is a diagram showing another example of the input screen. In the example of Fig. 10, the user display unit 211 displays the writing support system screen G4. The writing support system screen G4 displays a character string "Input information for creating work history", a stage image D4 indicating the stage of information input, a character string "Please tell us your position (up to one)", a position input field C41, a list of positions recommended for the job seeker U1 C42, a back button B41, and a forward button B42. The position is a name that indicates the job title in a more general way, such as member, leader, manager, department head, or division head.

[0056] The stage image D4 indicates that it is the second stage (position input stage) out of five information input stages. An upper limit (1 in the example of FIG. 10) is set for the number of positions that can be input in the input field C41. For example, the server display unit 111 sets this upper limit of the number that can be input based on at least one of the registered information and the input information, which are the acquired parameters. For example, the server display unit 111 stores a table that associates the upper limit number with either or both of the "experienced occupation" included in the registered information and the "occupation" included in the input information entered in the input field C31, and sets the upper limit to the number associated with either or both of the "experienced occupation" included in the registered information acquired as a parameter and the "occupation" included in the acquired input information.

[0057] Furthermore, the candidates designator 116 stores a table in which, for example, either or both of the "experienced occupation" included in the registration information and the "occupation" included in the input information are associated with recommended positions, and determines recommended positions (such as position A, position B, and position C in the example of FIG. 10) associated with either or both of the "experienced occupation" included in the registration information acquired as a parameter and the "occupation" included in the acquired input information. The server display unit 111 displays the determined recommended positions in the position list C42.

[0058] The job seeker terminal 20 accepts an input operation into the position input field C41 through the operation acceptance unit 212 (A34). The input method into the input field C41 is performed in the same manner as for the input field C31 shown in Fig. 8 (selection from the list of recommended positions C42, selection from the list of input candidates, or input of a character string). Furthermore, when an operation is performed on the forward button B42, the processes from A41 to A43 are executed in the same manner as when an operation is performed on the forward button B32 shown in Fig. 8, and the input position is saved in the server device 10 as input information.

[0059] After the position is entered, since there is input information that has not been entered, A31 (obtaining parameters), A32 (generating an input screen), and A33 (displaying the input screen) are performed. Fig. 11 is a diagram showing another example of the input screen. In the example of Fig. 11, the user display unit 211 displays the writing support system screen G5. The writing support system screen G5 displays a character string "Input information for creating a work history", a stage image D5 indicating a stage of information input, a character string "Please tell us your mission", a mission input field C51, a list of recommended missions C52 for the job seeker U1, a back button B51, and a forward button B52.

[0060] The stage image D4 indicates that it is the third stage (mission input stage) of the five information input stages. A mission is a business objective or goal, such as "improving the order rate" or "successful initial operation." In the input field C51, there is no upper limit set on the number of missions that can be input. The candidate determination unit 116 stores a table that associates one or more parameters of "experienced occupation" included in the registration information, "occupation" and "position" included in the input information with recommended missions, and determines recommended missions (such as mission A, mission B, and mission C in the example of FIG. 11) that correspond to one or more parameters of "experienced occupation" included in the registration information acquired as a parameter, and "occupation" and "position" included in the acquired input information. The server display unit 111 displays the determined recommended missions in the mission list C52.

[0061] The job seeker terminal 20 accepts an input operation into the mission input field C51 through the operation acceptance unit 212 (A34). The input method into the input field C51 is the same as that for the input field C31 shown in Fig. 8 (selection from the recommended mission list C52, selection from the input candidate list, or input of a character string). Furthermore, when an operation is performed on the forward button B52, the processes from A41 to A43 are executed in the same manner as when an operation is performed on the forward button B32 shown in Fig. 8, and the inputted mission is stored in the server device 10 as input information.

[0062] After the mission is input, since there is input information that has not been input, A31 (acquire parameters), A32 (generate input screen), and A33 (display input screen) are performed. Fig. 12 is a diagram showing another example of the input screen. In the example of Fig. 12, the user display unit 211 displays the writing support system screen G6. The writing support system screen G6 displays a character string "Input information for creating a work history", a stage image D6 indicating a stage of information input, a character string "Please tell us your business area", an input field C61 for a business area, a list C62 of recommended business areas for the job seeker U1, a back button B61, and a forward button B62.

[0063] The stage image D4 indicates that it is the fourth stage (input stage of business domain) among five information input stages. A business domain is a specific content of a job, such as "obtaining an appointment" for a sales job, or "managing advertising" for a marketing job. In the input field C61, there is no upper limit set on the number of business domains that can be input. The candidate determination unit 116 stores a table that associates one or more parameters of "experienced job type" included in the registration information, "job type", "position", and "mission" included in the input information with recommended business domains, and determines recommended business domains (such as business domain A, business domain B, and business domain C in the example of FIG. 12) that correspond to one or more parameters of "experienced job type" included in the registration information acquired as a parameter, and "job type", "position", and "mission" included in the acquired input information. The server display unit 111 displays the determined recommended business domains in the business domain list C62.

[0064] The job seeker terminal 20 receives an input operation into the input field C61 for a business area through the operation receiving unit 212 (A34). An input method into the input field C61 is performed in the same manner as in the case of the input field C31 shown in Fig. 8 (selection from the list of recommended business areas C62, selection from the list of input candidates, or input of a character string). Furthermore, when an operation is performed on the forward button B62, the processes from A41 to A43 are executed in the same manner as when an operation is performed on the forward button B32 shown in Fig. 8, and the input business area is saved in the server device 10 as input information.

[0065] After the business domain is input, the server device 10 causes the server display unit 111 to generate screen data showing a creation instruction screen for instructing the creation of a statement regarding work history, and transmits the generated screen data to the job seeker terminal 20. The job seeker terminal 20 causes the user display unit 211 to display the creation instruction screen regarding work history shown in the transmitted screen data (A51).

[0066] Fig. 13 is a diagram showing an example of a screen for instructing the creation of a text about work history. In the example of Fig. 13, the user display unit 211 displays a text creation support system screen G7. The text creation support system screen G7 displays a character string "Automatically generate work content", a stage image D5 showing a stage of information input, character strings "Automatically generate work content" and "Generate approximately 400 characters of work content. Please wait without closing the screen until generation is complete", a consent button B71 for handling of personal information, a start button B72 for automatically generating text about work history, and a back button B73.

[0067] The stage image D7 indicates that the information input is at the fifth stage (automatic generation) among five stages. The consent button B71 for handling of personal information is a button that the job seeker U1 presses by an operation such as clicking when the job seeker U1 consents to the handling of personal information included in the job seeker information including the registration information and the input information. When the operation receiving unit 212 receives the operation on the consent button B71 and the start button B72 as an operation for generating a text related to work history (text related to work content in this case), the job seeker terminal 20 transmits fourth request data to the server device 10 requesting the start of automatic generation of a text related to work history (text related to work content) (A52). The start button B72 is controlled so that it cannot be operated until the consent button B71 is operated.

[0068] When the fourth request data is transmitted, the server device 10 determines the text structure of the work history to be generated by the AI ​​control unit 113 (A53). The AI ​​control unit 113 stores, for example, a plurality of text structure templates. Each of the plurality of text structure templates shows a text structure of the work history consisting of a plurality of chapters. The "chapter" here refers to a large group of parts that make up a text. A text includes a plurality of chapters. A "paragraph" indented by one character on a new line may become a chapter, or a plurality of paragraphs may be combined to become a chapter. Also, a chapter may be divided in the middle of a paragraph. In this embodiment, the number of chapters, the contents of each chapter, the order of each chapter, and the amount of each chapter are respectively determined in each template.

[0069] The contents of each chapter may include, for example, the purpose of the work, main work, and other work, if the work is related to the work content included in the work history text. The amount of each chapter is expressed by a guideline of the number of characters, the maximum number of characters, or the range of the number of characters. The AI ​​control unit 113 stores, for example, a table that associates one or more parameters of the registered information and the input information with templates of text structures, and determines the text structure indicated by the template associated with the registered information and the input information acquired as parameters as the text structure related to the work history to be generated.

[0070] Next, the server device 10 instructs the artificial intelligence unit 114 to generate sentences for each chapter indicated by the determined sentence structure by the AI ​​control unit 113 (A54). The AI ​​control unit 113 generates a prompt indicating the generation of sentences for each chapter based on the job seeker information including the input information. The AI ​​control unit 113 may generate a prompt based on the registered information registered in advance in addition to the input information. In order to indicate the contents to be described in each chapter, the AI ​​control unit 113 generates a prompt including characteristic words and phrases (such as "experience" and "work history") used in sentences related to work history, a description of work (such as work procedures and work contents), a description of organization (such as organization name and organization role), or a description of results (such as target value and achievement level). These words and phrases are stored in the word and phrase database DB1 shown in FIG. 1.

[0071] The AI ​​control unit 113 generates a prompt, for example, "Generate text about the work history of a job seeker who has 10 years of management experience." In this case, "management" and "10 years" are information based on the input job seeker information, and "experience" and "work history" are words and phrases used in text about work history. The AI ​​control unit 113 also generates a prompt, for example, "Generate results including target values ​​of projects in which the job seeker participated as an engineer." In this case, "engineer" and "project" are information based on the input information, "target value" is a description of the outcome, and "achievements" is a word and phrase used in text about work history.

[0072] The AI ​​control unit 113 also generates a prompt, for example, "Generate the work procedures and work contents of the accounting department to which the job seeker belonged as a sentence explaining the main work." In this case, "accounting department" is information based on the input information, and "work procedures" and "work contents" are descriptions of the work. The AI ​​control unit 113 also generates a prompt, for example, "Generate a list of departments that the job seeker was involved in during the period he / she belonged to the management department." In this case, "management department" is information based on the input information, and "department" is a description of the organization.

[0073] The AI ​​control unit 113 instructs the artificial intelligence unit 114 to generate sentences for each chapter using the generated prompts. The artificial intelligence unit 114 executes the sentence generation process for each chapter based on the instructions of each prompt (A55). The artificial intelligence unit 114 creates sentences using words and phrases stored in the word and phrase database DB1. The artificial intelligence unit 114 transmits each completed sentence for each chapter to the job seeker terminal 20. The job seeker terminal 20 displays the transmitted sentences for each chapter in order from the one transmitted, on the user display unit 211 (A56).

[0074] Fig. 14 is a diagram showing an example of the progress of a displayed text on work history. In the example of Fig. 14, the user display unit 211 displays a text writing support system screen G8. The text writing support system screen G8 displays a character string "Job content", a text S11 of chapter 1, a text S14 of chapter 4, a confirm button B81, and a regenerate button B82. In this embodiment, it is assumed that a text on work content with a text structure of chapters 1 to 5 is created as a text on work history.

[0075] In the example of Fig. 14, the sentences in chapters 1 and 4 are completed and displayed in order, but the sentences in chapters 2, 3, and 5 are not yet completed and are not displayed. Therefore, the Confirm button B81 for confirming the sentences related to the work content cannot be operated. The server device 10 and the job seeker terminal 20 repeatedly execute the processes of A55 (sentence generation process) and A56 (display of sentences related to work history) until the sentences in all chapters are completed.

[0076] Fig. 15 is a diagram showing an example of the completed sentences for all chapters. All sentences S10 from sentences S11 to S15 for chapters 1 to 5 are displayed in order from the top on the writing support system screen G8 shown in Fig. 15. If the job seeker U1 determines that there is no problem with the generated all sentences S10, he or she operates the confirm button B81. Then, the job seeker terminal 20 displays the completed sentences related to the work content in order from the top on the user display unit 211 (A57).

[0077] Fig. 16 is a diagram showing an example of a displayed text relating to work history. In the example of Fig. 16, the user display unit 211 displays the text creation support system screen G2 shown in Fig. 7. The user display unit 211 displays all text S10 relating to work content generated as text relating to work history in the input field C23 for work content. The text displayed in the input field C23 is editable, and can be manually corrected by the job seeker U1.

[0078] When the job seeker U1 wishes to rewrite the generated work history-related text (text related to job content) on the writing support system screen G8 shown in Fig. 15, he / she operates the regenerate button B82. When this regenerate operation is performed, the server device 10 returns to the operation of A31 (acquisition of parameters) shown in Fig. 5. When generating input screen data in A32, the server device 10 generates input screen data in a state where input information has been entered in the job type input field C31.

[0079] FIG. 17 is a diagram showing an example of an input screen that is displayed again. In the example of FIG. 17, the user display unit 211 displays the writing support system screen G3 shown in FIG. 8. In the writing support system screen G3, the input field C31 is displayed with the previously input "occupation B" input. The input fields for the other stages are also displayed with the previously input information input. When the input information is input again and the artificial intelligence unit 114 automatically generates a text about the work history, the server display unit 111 displays, for example, the writing support system screen G2 on which the generated text about the work history is overwritten.

[0080] The server display unit 111 may leave the previous text about work history and display the new work history in a separate input field C23, or may add and display the new work history under the same input field. When regenerating the text about work history, the AI ​​control unit 113 may also input the previously generated text about work history to the artificial intelligence unit 114 and use it to regenerate the text about work history.

[0081] As described above, in the writing support system 1, the server display unit 111 functions as an example of an input unit that displays an input screen that accepts the input of job seeker information related to a job seeker. Writing support system screens G3, G4, G5, and G6 shown in Figures 8, 10, 11, and 12 are each an example of an input screen. In addition, "job type," "position," "mission," and "business area" input on these input screens are each an example of job seeker information.

[0082] Furthermore, the AI ​​control unit 113 functions as an example of an instruction unit that instructs the artificial intelligence unit 114 to create a sentence related to the work history of the job seeker based on the job seeker information including the registered information and the input information. The job seeker information here includes the input input information and the registered information registered in advance. The artificial intelligence unit 114 is an example of artificial intelligence, and has a learning model that receives as input job seeker information related to the job seeker (the input job seeker information and the registered information registered in advance) and outputs a sentence related to the work history.

[0083] This learning model is a trained model that has been machine-learned from training job seeker information. Training job seeker information is job seeker information used as training data for training the learning model. Training job seeker information is information about a job seeker other than job seeker U1, who is a user of writing support system 1, but may include registration information and input information about job seeker U1.

[0084] In addition, this learning model may be a model generated by performing so-called supervised machine learning, in which, for example, job seeker information of a job seeker who has previously conducted a job search is trained as input data for learning (explanatory variables) and documents relating to the job history, such as a resume, submitted by the job seeker to the company or other entity where the job seeker actually found employment (i.e., the documents relating to the job history that were the most effective) are trained as paired corresponding teacher data for learning output data (objective variables).

[0085] The learning model may be generated by learning from any corpus (a database in which natural language sentences are structured and accumulated on a large scale), and includes job seeker information for learning as one of the large number of corpora. The artificial intelligence unit 114 uses this learning model to create optimal sentences related to work history derived from the input information on the job seeker, and outputs the created sentences. The server display unit 111 also functions as an example of a display unit that displays the sentences related to work history output by the artificial intelligence unit 114 based on instructions from the AI ​​control unit 113.

[0086] According to this embodiment, even if the job seeker U1 does not know how to give instructions to the artificial intelligence unit 114 or how to create prompts, he or she can create documents related to his or her work history, such as documents explaining the details of the work, simply by registering information about the job seeker in advance as registration information or by selecting or inputting information in order according to instructions on the screen. This makes it easier to create documents related to the work history than if the job seeker U1 were to give instructions to the artificial intelligence unit 114 himself or herself.

[0087] Furthermore, in the writing support system 1, the server display unit 111 functions as an example of a re-input unit that displays, as an input screen, a screen (hereinafter referred to as a "re-input screen") that displays, in an editable manner, the job seeker information that was input when the AI ​​control unit 113 gave an instruction to the artificial intelligence unit 114. The writing support system screen G3 shown in Fig. 17 is an example of a re-input screen that displays, in an editable manner, the job seeker information that was input ("job type B" in the example of Fig. 17).

[0088] The AI ​​control unit 113 (an example of an instruction unit) again instructs the user to create a statement regarding work history based on the job seeker information edited on the re-input screen. According to this embodiment, the user can easily repeat the tasks of inputting job seeker information, creating a statement regarding work history, determining whether the statement is correct, re-inputting job seeker information, and re-creating the statement regarding work history. Furthermore, the user can easily repeat the task of repeatedly creating a statement regarding work history compared to when the re-input screen is not displayed.

[0089] Furthermore, in the writing support system 1, the job seeker information includes information on a number of items (in this embodiment, "job type," "position," "mission," and "business area") that are input to the artificial intelligence unit 114 and used to output writing. The server display unit 111 (an example of an input unit) switches between and displays, as input screens, individual input screens for each of at least two or more items (in this embodiment, writing support system screens G3, G4, G5, G6) that request the input of job seeker information corresponding to each of at least two or more items among the multiple items.

[0090] When there are multiple items of information to be entered on one input screen, for example, if the input fields are adjacent, it is possible that information in an adjacent item may be entered by mistake, but such mistakes will not occur if separate input screens are displayed as described above. Thus, according to this embodiment, compared to when separate input screens are not displayed, input errors can be reduced and the psychological burden on the user regarding input can be reduced. Furthermore, compared to when separate input screens are not displayed, input information (job type, etc.) required to generate text regarding work history can be obtained more reliably.

[0091] In addition, in the writing support system 1, the server display unit 111 (an example of an input unit) displays a plurality of objects corresponding to each of the individual input screens in all of the individual input screens described above, and displays the object corresponding to the individual input screen being input among the plurality of objects in a manner different from other objects. The object is, for example, an image indicating "job type", "position", "mission", "business area", and "automatic generation" included in the stage image D3 shown in FIG.

[0092] In the example of Fig. 8, the server display unit 111 shows the edge of the image of "job type" corresponding to the input screen being input with a solid line, and the edges of the other images with a dotted line. By displaying these objects, the job seeker U1 can understand that there are five stages to the automatic generation of text, and that he / she is currently in the first stage. According to this embodiment, the overall picture of the input work can be more easily grasped than when the above objects are not displayed.

[0093] Furthermore, in writing support system 1, parameter acquisition unit 115 functions as an example of an acquisition unit that acquires predetermined parameters (registration information and input information) related to a job seeker. Then, server display unit 111 (input unit) displays words corresponding to the acquired parameters as input candidates for each input item. Each word ("sales planning," "sales administration," and "sales promotion") shown in input candidate list C33 of FIG. 9 is an example of an input candidate. According to this embodiment, words that suit the job seeker can be displayed as input candidates, and input can be made easier than when input candidates are not displayed.

[0094] The above parameters include registration information related to the job seeker that has been registered in advance. Each piece of information shown in FIG. 6 (such as "basic information," "desired conditions," "educational background," and "work history") is an example of the registration information. The registration information may also be other information such as that written on a resume. The parameters also include job seeker information (input information) that has been entered in the specified items included in the input screen. "Job type," "Position," "Mission," and "Business area" shown in FIG. 8, FIG. 10, FIG. 11, and FIG. 12 are each an example of the specified items. The specified items are not limited to these, and may be limited to the first few items or important items, etc.

[0095] If the parameters include registration information, the input candidates can be optimized from the first input item on the input screen that has not yet been filled in. On the other hand, if the parameters include input information, the input candidates can be optimized without any prior work, simply by entering information on the input screen.

[0096] In addition, in the writing support system 1, the server display unit 111 (an example of an input unit) displays search results of words corresponding to the input characters as input candidates every time one character is input on the input screen. The server display unit 111 performs a forward match search every time a character for search is input by the user, and displays the search results as input candidates. "e" shown in FIG. 9 is an example of an input character, and "sales planning", "sales administration" and "sales promotion" are examples of search results. In incremental search, every time a character is input and acquired, a search is performed for a word corresponding to the characters obtained by adding the newly input character to one or more characters already acquired. In this way, an incremental search is performed in which the search results are refreshed every time one character is input, making it easier to input compared to when the search results are fixed.

[0097] The server display unit 111 may perform not only an exact match but also a fuzzy search including ambiguity such as spelling variations and synonymous expressions as a search for a phrase corresponding to the input characters. The server display unit 111 may also perform an interactive search individualized for each job seeker according to acquired parameters related to the job seeker as a search for a phrase corresponding to the input characters. For example, when the job type "engineer" is acquired as a parameter, the server display unit 111 searches for phrases related to engineers. This makes it possible to display input candidates optimized for each job seeker even when the same characters are input.

[0098] Furthermore, in the writing support system 1, writing on work history has two or more chapters. Chapters 1 to 5 shown in FIG. 15 are examples of two or more chapters. The AI ​​control unit 113 (an example of an instruction unit) issues instructions to create writing on work history for each of those chapters. Then, the server display unit 111 (an example of a display unit) displays two or more chapters output by the artificial intelligence unit 114 side by side as writing. The entire writing S10 shown in FIG. 15 is an example of writing in which the output chapters are lined up. By issuing instructions to create writing for each chapter in this way, it is possible to issue more appropriate instructions that are more in line with the contents of the chapters, and to create writing on work history with more appropriate content, compared to when instructions to create writing are issued for the entire writing.

[0099] Furthermore, in the writing support system 1, when the artificial intelligence unit 114 outputs a plurality of chapters in sequence, the server display unit 111 (an example of a display unit) displays the chapters output from the artificial intelligence unit 114 in sequence, without waiting for all the chapters to be complete. Chapters 1 and 4 shown in FIG. 14 are an example of chapters output without waiting for all the chapters to be complete. According to this embodiment, completed chapters are displayed in sequence, allowing the user to experience the responsiveness of the automatic writing generation by the artificial intelligence unit 114.

[0100] Furthermore, in the writing support system 1, the AI ​​control unit 113 (an example of an instruction unit) issues instructions using instruction data including words and phrases used in writing about work history, a description of work, a description of organization, or a description of results, as described above. The instruction data is data indicating instructions to the artificial intelligence unit 114, and a prompt is an example of such data. According to this embodiment, it is possible to more reliably include necessary content in writing about work history, compared to when the instruction data is not used.

[0101] <Other embodiments> The job seeker information is not limited to the information shown in FIG. 8 and the like. The job seeker information may include, for example, skills, qualifications, language ability, years of experience, desired industry, desired job type, desired work area, desired commuting time, and selling points. In this way, information included in the registration information may be input as the job seeker information. Furthermore, the contents of each chapter included in the text regarding work history are not limited to those shown in FIG. 15. For example, the contents of each chapter may include business plans, organizational structure, customer status, products, etc.

[0102] <Artificial Intelligence> The artificial intelligence unit 114 may use a language model (for example, a language model using a neural network). A language model is a model of human language using the occurrence probability of words. This makes it possible to generate more natural sentences compared to when a language model is not used.

[0103] Furthermore, in the writing support system 1, the artificial intelligence may be an external component. Even in this case, the AI ​​control unit 113 instructs the external artificial intelligence to generate a sentence, and the server display unit 111 displays the sentence output by the artificial intelligence on the job seeker terminal 20, thereby generating a sentence related to work history. In this way, a variety of external artificial intelligence services can be utilized to generate a sentence related to work history.

[0104] <Learning model> In the embodiment, the learning model is a model that is machine-learned from learning job seeker information, but is not limited thereto. For example, the learning model may be a model that is machine-learned from learning job seeker information (general job seeker information) and a job posting as learning data. A job posting is a document created to convey to a job seeker an overview of the personnel required by an employer. A job posting may be created for an actual job seeker, or may be created for a fictitious job seeker. According to this embodiment, a document regarding work history that takes into account the content required by the employer can be created.

[0105] <Chapter structure for work history essay> In the embodiment, the number of chapters of the text regarding work history, the content of each chapter, the order of each chapter, and the amount of each chapter were determined respectively, but it is not limited to this. For example, the AI control unit 113 (an example of an instruction unit) may give an instruction to generate the text regarding work history so that the text regarding work history has the number of chapters, the content of each chapter, the display order of each chapter, or the amount of each chapter according to the input on the presented input screen. The AI control unit 113 gives an instruction to generate the text, for example, using a table in which job seeker information is associated with the content and number of each chapter, etc.

[0106] FIG. 18 is a diagram showing an example of a table. In the example of FIG. 18, when the number of years of experience is input as input information, a table TB1 in which the number of years of experience as input information is associated with the number of chapters is shown. In the table TB1, the number of chapters “N1”, “N2”, and “N3” (N1 < N2 < N3) are associated with the number of years of experience “less than Th1”, “greater than or equal to Th1 and less than Th2”, and “greater than or equal to Th2”. The AI control unit 113 instructs the artificial intelligence unit 114 to generate the text of each chapter the same number of times as the number of chapters associated with the number of years of experience acquired as job seeker information in the table TB1.

[0107] Thereby, as the number of years of experience of the job seeker is longer, the content to be explained tends to be more, so in order to explain as much of those contents as possible, it is possible to generate a text regarding work history with a larger number of chapters. Note that job seeker information other than the number of years of experience may be associated with the number of chapters. In any case, compared with the case where the number of chapters is fixed, the number of chapters can be more appropriately controlled according to the job seeker information acquired as a parameter.

[0108] FIG. 19 is a diagram showing another example of a table. In the example of FIG. 19, a table TB2 is shown in which the job type, which is input information, is associated with the contents of the chapter when the job type is input as input information. In table TB2, the job types "management-oriented", "professional", and "clerical" are associated with the chapter contents "oriented toward management", "skills and qualifications-oriented", and "business process-oriented". The AI ​​control unit 113 instructs the artificial intelligence unit 114 to generate a text about work history including a chapter whose contents are associated in table TB2 with the job type acquired as input information.

[0109] This allows for the generation of work history documents that include chapters with content that is more relevant to each job type. Job seeker information other than the job type may also be associated with the content of the chapter. In either case, the content of the chapter can be more appropriately controlled according to the job seeker information acquired as parameters, compared to when the content of the chapter is fixed.

[0110] FIG. 20 is a diagram showing another example of a table. In the example of FIG. 20, a table TB3 is shown in which the job type, which is job seeker information, is associated with the order of chapters when the job type is input as input information. In table TB3, the job type "management-related chapter" is associated with the order of "other chapters" afterwards. Also, the job type "professional" is associated with the order of "skills and qualifications-related chapter" beforewards. Also, the job type "clerical work" is associated with the order of "business process-related chapter" beforewards.

[0111] The AI ​​control unit 113 instructs the job seeker terminal 20 to display the chapters in the order in which they are associated in table TB3 with the job types acquired as input information. This makes it possible to generate text on work history in which chapters with content more closely related to each job type are listed first. Note that job seeker information other than the job type may also be associated with the order of the chapters. In either case, the order of the chapters can be more appropriately controlled according to the job seeker information acquired as a parameter, compared to when the order of the chapters is fixed.

[0112] FIG. 21 is a diagram showing another example of a table. In the example of FIG. 21, a table TB4 is shown in which job types, which are job seeker information, are associated with the amount of chapters in a job when a job type is input as input information. In table TB4, the job type "management" is associated with an amount of "management-related chapters" that is "large" and "other chapters" that is "small." In addition, the job type "professional" is associated with an amount of "skill / qualification-related chapters" that is "large" and "other chapters" that is "small." In addition, the job type "clerical work" is associated with an amount of "business process-related chapters" that is "large" and "other chapters" that is "small."

[0113] The AI ​​control unit 113 instructs the artificial intelligence unit 114 to generate each chapter with the amount of text associated in table TB4 with the job type acquired as input information. This makes it possible to generate text on work history with a larger amount of text in chapters with content more closely related to each job type. Note that job seeker information other than the job type may be associated with the amount of chapter. In either case, the amount of chapter can be more appropriately controlled according to the job seeker information acquired as a parameter, compared to when the amount of chapter is fixed.

[0114] Note that the tables shown in Figures 18 to 21 are all examples, and although three correspondences are performed for each, two, four or more correspondences may be used. Furthermore, the job seeker information associated in each table may be registered information. In this case, the AI ​​control unit 113 (an example of an instruction unit) instructs the generation of text regarding work history so that the text regarding work history has the number of chapters, the content of each chapter, the display order of each chapter, or the amount of each chapter according to the registered information. In either case, a text regarding work history with more appropriate content can be created compared to a case where no instruction is given to generate text according to the input on the presented input screen or the registered information.

[0115] <Input options> The AI ​​control unit 113 (an example of an instruction unit) may instruct the artificial intelligence unit 114 to output two or more sentence options for one chapter. In this case, the artificial intelligence unit 114 generates two or more sentences for one chapter. The server display unit 111 (an example of a display unit) displays the two or more sentence options output by the artificial intelligence unit 114 in a selectable manner, and displays a sentence in which the selected sentences are arranged.

[0116] FIG. 22 is a diagram showing another example of a displayed text about work history. In the example of FIG. 22, the user display unit 211 displays the text creation support system screen G2 shown in FIG. 7. The user display unit 211 displays a character string "Please select 'Main Business'" and options S121, S122, and S123 for the text of "Main Business" in the input field C23 for the business content. For example, the AI ​​control unit 113 generates three types of prompts with different contents for the chapter "Main Business" and instructs text generation. As a result, the options S121, S122, and S123 are texts with different contents.

[0117] When the job seeker U1 selects one of the options, the server display unit 111 deletes the options not selected and displays the text related to the work history with only the text of the selected option remaining. According to this embodiment, the job seeker U1 can select the text that he / she thinks is most appropriate from two or more text options, and therefore can create a text related to the work history that better reflects the job seeker's intentions compared to a case where the text options are not displayed.

[0118] <Changes in input screen configuration> In the writing support system 1, the input screen may include a variable input screen in which the configuration of the input information to be accepted varies according to predetermined parameters related to the job seeker. In this case, the server display unit 111 (an example of an input unit) displays a variable input screen according to the parameters acquired by the parameter acquisition unit 115. More specifically, the server display unit 111 displays, as the variable input screen, a screen configured to allow input according to the input items, number of input items, input order, input method, or input amount according to the acquired parameters. The server display unit 111 issues instructions for writing using, for example, a table in which job seeker information is associated with input items, etc.

[0119] Fig. 23 is a diagram showing an example of a table. In the example of Fig. 23, a table TB11 is shown in which the job type, which is the input information, is associated with the input item when the job type is input as the input information. In table TB11, the input items "efforts to improve productivity", "skills" and "experienced business process" are associated with the job types "managerial", "professional", and "clerical work". The server display unit 111 first displays an input screen for inputting the job type as inputter information.

[0120] Then, since job seeker information indicating the job type is acquired as a parameter, when the server display unit 111 displays the next input screen, it causes the job seeker terminal 20 to display the input items associated with the acquired job type in the table TB11. As a result, it is possible to input more relevant job seeker information for each job type. Note that job seeker information other than the job type may be associated with the input items. In any case, compared with the case where the input items are fixed, the input items can be more appropriately controlled according to the job seeker information acquired as a parameter.

[0121] FIG. 24 is a diagram showing another example of a table. In the example of FIG. 24, when the number of years of experience is input as input information, a table TB12 associating the number of years of experience as the input information with the number of input items is shown. In the table TB12, the number of input items “N11”, “N12” and “N13” (N11 < N12 < N13) are associated with the number of years of experience “less than Th1”, “equal to or more than Th1 and less than Th2” and “equal to or more than Th2”. The server display unit 111 first displays an input screen for inputting the number of years of experience as job seeker information.

[0122] Then, since job seeker information indicating the number of years of experience is acquired as a parameter, when the server display unit 111 displays the remaining input screens, it controls the display of the input screens so that the total number of input screens associated with the acquired number of years of experience in the table TB12 is displayed. As a result, the longer the job seeker's years of experience, the more likely it is that more job seeker information can be acquired. Therefore, in order to input as much of that job seeker information as possible, it is possible to display an input screen with a larger number of input items. Note that job seeker information other than the number of years of experience may be associated with the number of input items. In any case, compared with the case where the number of input items is fixed, the number of input items can be more appropriately controlled according to the job seeker information acquired as a parameter.

[0123] Fig. 25 is a diagram showing another example of a table. In the example of Fig. 25, a table TB13 is shown in which the job type, which is input information, is associated with the input order when the job type is input as input information. In table TB13, the job type "management" is associated with an order in which "management-related input items" come first, followed by "other input items." Also, the job type "professional" is associated with an order in which "skill / qualification-related input items" come first, followed by "other input items."

[0124] Further, the job type "clerical work" is associated with an order in which "business process related input items" come first, followed by "other input items." The server display unit 111 causes the job seeker terminal 20 to display each input item in the order in which it is associated in table TB13 with the job type acquired as the job seeker information. This allows the input item with the content that is more closely related to each job type to be input first. Note that job seeker information other than the job type may also be associated with the input order. In either case, the input order can be more appropriately controlled according to the job seeker information acquired as a parameter, compared to when the input order is fixed.

[0125] FIG. 26 is a diagram showing another example of a table. In the example of FIG. 26, a table TB14 is shown in which the job type, which is input information, is associated with the input method when the job type is input as input information. In table TB14, the job types "management", "professional", and "clerical work" are associated with the input methods "multiple choice", "input type + multiple choice", and "multiple choice". The "multiple choice" is a method of presenting options for input information to be input using a pull-down list or the like, and the "input" is a method of inputting characters one by one using a keyboard. The server display unit 111 first displays an input screen for inputting the job type as input information.

[0126] Then, job seeker information indicating the occupation type is acquired as a parameter, and the server display unit 111, when displaying the next input screen, causes the job seeker terminal 20 to display an input screen that allows input using the input method associated with the acquired occupation type in table TB14. The selection formula is applied, for example, when the job seeker information to be input is somewhat fixed, and the input formula is applied, for example, when there is a large amount of job seeker information to be input and it is not possible to list all the options. Note that job seeker information other than the occupation type may be associated with the input method. In either case, the input method can be more appropriately controlled according to the job seeker information acquired as a parameter, compared to when the input method is fixed.

[0127] Fig. 27 is a diagram showing another example of a table. In the example of Fig. 27, a table TB15 is shown in which the job type, which is the input information, is associated with the input amount in the case where the job type is input as the input information. The input amount is, for example, the number of pieces of input information to be input. In table TB15, for the job type "managerial position", an input amount of "large" is associated with an input amount of "management-related input items" and an input amount of "small" is associated with an input amount of "other input items".

[0128] In addition, in the job category of "professional", the amount of input "large" is associated with the "skill / qualification related input items" and the amount of input "small" is associated with the "other input items". In addition, in the job category of "clerical work", the amount of input "large" is associated with the "business process related input items" and the amount of input "small" is associated with the "other input items". The server display unit 111 displays each input item on the job seeker terminal 20 with the amount of input associated in table TB15 with the job category acquired as job seeker information.

[0129] This allows the amount of input of content more closely related to each job type to be increased. The amount of input may be represented by the number of characters or lines of job seeker information to be input, the size of the input field, etc. Job seeker information other than the job type may also be associated with the amount of input. In either case, the amount of input can be more appropriately controlled according to the job seeker information acquired as a parameter, compared to when the amount of input is fixed.

[0130] Note that the tables shown in Figs. 23 to 27 are all examples, and although three correspondences are made for each, two, four or more correspondences may be used. Furthermore, the job seeker information associated in each table may be registered information. In this case, the server display unit 111 displays, as a variable input screen, a screen configured to allow input according to the input items, number of input items, input order, input method, or input amount corresponding to the acquired parameters (registered information). Furthermore, as described above, by including a variable input screen whose configuration changes according to predetermined parameters in the input screen, it is possible to allow the user to input more appropriate items than when the configuration of the input screen is fixed.

[0131] <Configuration variations> The configuration shown in FIG. 1 and the like is an example, and other aspects may be adopted as long as there is no inconvenience in implementation. For example, one device may be distributed to two or more devices, or may be replaced by a cloud computing system. Furthermore, the functions of one device may be distributed and realized to two or more devices, or the functions of two or more devices may be concentrated and realized by one device. Furthermore, the operation performed by one function may be distributed to two or more functions, or two or more functions may be integrated into one function. In short, as long as each function required for the entire writing support system 1 is realized, the devices that realize those functions may have any configuration.

[0132] The above-described embodiment is an information processing device such as the server device 10, or an information processing system such as the writing support system 1 including the server device 10, but may be an information processing method. The information processing method includes each step executed by the writing support system. The above-described embodiment may be a program. The program causes a computer to execute each step executed by the writing support system.

[0133] <Other variations> The output destination of information or data (hereinafter referred to as "information, etc.") may be another device, a display, a memory unit (including a built-in memory unit and an external memory unit), etc. Acquisition of information, etc. includes acquiring information, etc. generated by the device itself, in addition to acquiring information, etc. transmitted from another device. The table in which parameters are associated is not limited to the table shown in the figure, and the number of parameters may be reduced or increased. Furthermore, information, etc. corresponding to parameters may be obtained by a formula, a conditional formula, etc., without using a table.

[0134] <Additional Notes> Furthermore, it may be provided in the following aspects:

[0135] (1) A writing support system comprising a processor, in an input step, the processor displays an input screen that accepts input of job seeker information about a job seeker, and in an instruction step, instructs an artificial intelligence to create a writing about the job seeker's work history based on the job seeker information, the artificial intelligence having a learning model that receives the job seeker information as input and outputs the writing, and in a display step, displays the writing output by the artificial intelligence based on the instructions.

[0136] According to this embodiment, it is possible to facilitate the creation of documents relating to the job seeker's work history.

[0137] (2) In the writing support system described in (1) above, the learning model is a model that is machine-learned from learning job seeker information and job postings.

[0138] According to this embodiment, it is possible to create a document that takes into account the content required for the job offer.

[0139] (3) In the writing support system described in (1) or (2) above, in the re-input step, the processor displays as the input screen a screen showing, in an editable manner, the job seeker information that was input when the instruction was given, and in the instruction step, re-gives the instruction based on the job seeker information edited on the input screen.

[0140] According to this embodiment, the task of repeatedly creating a sentence can be made easier.

[0141] (4) In the writing support system described in any one of (1) to (3) above, the job seeker information includes a plurality of items of information that are input to the artificial intelligence and used to output the writing, and in the input step, the processor switches between displaying, as the input screen, individual input screens for each of at least two or more items that request input of the job seeker information corresponding to each of at least two or more items among the plurality of items.

[0142] According to this embodiment, input errors can be reduced.

[0143] (5) In the writing support system described in (4) above, in the input step, the processor displays a plurality of objects corresponding to each of the individual input screens in all of the individual input screens, and displays the object among the plurality of objects corresponding to the individual input screen being input in a manner different from other objects.

[0144] According to this embodiment, the entire input operation can be easily grasped.

[0145] (6) In the writing support system described in any one of (1) to (5) above, the input screen includes a variable input screen whose configuration for inputting the job seeker information changes according to predetermined parameters related to the job seeker, and the processor acquires the parameters in the acquisition step, and displays the variable input screen according to the acquired parameters in the input step.

[0146] According to this embodiment, it is possible to allow the user to input more appropriate items.

[0147] (7) In the writing support system described in (6) above, in the input step, the processor displays as the variable input screen a screen configured to allow input of input items, number of input items, input order, input method or input amount according to the acquired parameters.

[0148] According to this embodiment, it is possible to allow the user to input more appropriate items.

[0149] (8) In the writing support system described in (4) above, in the acquisition step, the processor acquires predetermined parameters related to the job seeker, and in the input step, displays words corresponding to the acquired parameters as input candidates for each of the items input.

[0150] According to this embodiment, input can be simplified.

[0151] (9) In the writing support system described in (8) above, in the input step, the processor displays search results for words corresponding to the input characters as input candidates each time one character is input into the input screen.

[0152] According to this embodiment, input can be made easier.

[0153] (10) In the writing support system described in any one of (6) to (9) above, the parameters include the job seeker information that has been entered in a predetermined field included in the input screen.

[0154] According to this embodiment, optimization can be achieved without any prior work.

[0155] (11) In the writing support system according to any one of (6) to (10) above, the parameters include registered information relating to the job seeker that has been registered in advance.

[0156] According to this embodiment, optimization can be achieved from the very first input item.

[0157] (12) A writing support system according to any one of (1) to (11) above, wherein the writing has two or more chapters, and the processor, in the instruction step, issues the instruction for each chapter, and in the display step, arranges the chapters output by the artificial intelligence and displays them as the writing.

[0158] According to this embodiment, it is possible to create text with more appropriate content.

[0159] (13) In the writing support system described in (12) above, in the instruction step, the processor gives the instructions so that the number of chapters, the content of each chapter, the display order of each chapter, or the amount of each chapter of the writing corresponds to the input on the presented input screen.

[0160] According to this embodiment, it is possible to create text with more appropriate content.

[0161] (14) In the writing support system described in (12) or (13) above, in the instructing step, the processor instructs the artificial intelligence to output two or more sentence options for one chapter, and in the displaying step, displays the two or more sentence options output by the artificial intelligence in a selectable manner, and displays a sentence in which the selected sentences are arranged.

[0162] According to this embodiment, a text that better reflects the job seeker's intentions can be created.

[0163] (15) In the writing support system described in any one of (12) to (14) above, in the display step, when the artificial intelligence outputs multiple chapters sequentially, the processor displays the output chapters sequentially without waiting for all of the chapters to be collected.

[0164] According to this embodiment, the response performance can be experienced.

[0165] (16) In the writing support system described in any one of (1) to (15) above, in the instruction step, the processor gives the instruction using instruction data including words and phrases used in writing about work history, a description of work, a description of organization, or a description of results.

[0166] According to this embodiment, necessary contents can be included in the text more reliably.

[0167] (17) An information processing method, comprising the steps of the writing support system according to any one of (1) to (16) above.

[0168] (18) A program for causing a computer to execute each step of the writing support system according to any one of (1) to (16) above. Of course, this is not the case. Furthermore, the above-described embodiments and modifications may be combined in any desired manner.

[0169] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The new embodiments 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 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]

[0170] 1: Writing support system 10: Server device 11: Control section 20: Job Seeker Terminal 21: Control section 111: Server display section 112: Memory control unit 113:AI control section 114: Artificial Intelligence Department 115: Parameter acquisition section 116: Candidate Selection Division 211: User display section 212: Operation reception section

Claims

1. A writing support system, a processor, the processor comprising: In the acquisition step, the job seeker's registration information is acquired, In the instruction step, the registered information and an instruction to create a text about the work history of the job seeker based on the registered information are input to the artificial intelligence, wherein the instruction includes either content specifying the structure of the text or content specifying the length of the text; In the display step, the text creation support system displays the text output by the artificial intelligence based on the instruction.

2. In the writing support system according to claim 1, In the input step, an input of the job type of the job seeker is accepted, In the instruction step, the instruction includes either content specifying the structure according to the job type or content specifying the amount according to the job type, and is input to the artificial intelligence in the writing support system.

3. In the writing support system according to claim 2, In the input step, a list of candidates for the job type according to the registered information is displayed, and a selection of the job type from the candidate list is accepted.

4. In the writing support system according to claim 1, In the instruction step, the artificial intelligence is caused to output two or more options for the sentence; In the display step, two or more of the options are displayed in a selectable manner.

5. In the writing support system according to claim 1, In the input step, an input of either the configuration or the quantity is accepted; In the instruction step, the instruction including the content specifying the input structure or the input amount is input to the artificial intelligence.

6. In the writing support system according to claim 1, In the instruction step, the instruction further including content for generating the sentence for each chapter is input to the artificial intelligence.

7. An information processing method, comprising: An information processing method in which an information processing device executes each step of the writing support system according to any one of claims 1 to 6.

8. A program, A program that causes a computer to execute each step of the writing support system according to any one of claims 1 to 6.

Images