Information processing system, information processing method, and program

Abstract

To make it possible to present the viewing status of a video. [Solution] The information processing system is characterized by comprising a viewing history memory unit that stores viewing history of videos related to employers that have been viewed by job seekers, an interest identification unit that identifies the job seeker's interests based on the viewing history, and a provision unit that provides the interests to employers.

Description

[Technical field]

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

[0002] Video viewing behavior is analyzed to provide personalized videos (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-092517 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the system described in Patent Document 1, videos are personalized according to the viewing conditions of the viewer, but it is difficult for the user to understand what the viewing conditions were.

[0005] The present invention has been made in view of the above background, and has an object to provide a technique capable of presenting the viewing status of a video. [Means for solving the problem]

[0006] The main invention of the present invention for solving the above problem is an information processing system comprising a viewing history memory unit that stores a viewing history of videos related to employers that a job seeker has viewed, an interest identification unit that identifies an interest of the job seeker based on the viewing history, and a provision unit that provides the interest to the employer.

[0007] Other problems and solutions disclosed in this application will be made clear in the description of the preferred embodiments of the invention and the drawings. Effect of the Invention

[0008] According to the present invention, the viewing status of a video can be presented. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of an overall configuration of an information processing system. [Diagram 2] 2 is a diagram illustrating an example of a hardware configuration of a management server 2. FIG. [Diagram 3] 2 illustrates an example of the software configuration of a management server 2. FIG. [Figure 4] 1 is a diagram showing an example of a video playback screen 10 on a job seeker terminal 3. FIG. [Diagram 5] FIG. 13 is a diagram illustrating an example in which a video is clicked. [Figure 6] FIG. 13 is a diagram illustrating the operation of the management server 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] <System Overview> An information processing system according to one embodiment of the present invention will be described below. The information processing system of this embodiment is intended to support employers by having job seekers view videos of company information, etc. in advance, analyzing the job seekers' video viewing trends, and providing the results to employers so that they can use them as a reference for job interviews, etc.

[0011] 1 is a diagram showing an example of the overall configuration of an information processing system. The information processing system of this embodiment is configured to include a management server 2. The management server 2 is communicatively connected to an employer terminal 1 and a job seeker terminal 3 via a communication network. The communication network is, for example, the Internet, and is constructed by a public telephone line network, a mobile phone line network, a wireless communication path, Ethernet (registered trademark), etc.

[0012] The recruiter terminal 1 and the job seeker terminal 3 are computers operated by the recruiter and the job seeker, respectively. The recruiter terminal 1 and the job seeker terminal 3 may be, for example, a smartphone, a tablet computer, a personal computer, etc.

[0013] The management server 2 may be a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing.

[0014] <Management Server> FIG. 2 is a diagram showing an example of the hardware configuration of the management server 2. Note that the illustrated configuration is an example, and other configurations may be used. The management server 2 includes a CPU 201, a memory 202, a storage device 203, a communication interface 204, an input device 205, and an output device 206. The storage device 203 is, for example, a hard disk drive, a solid state drive, or a flash memory that stores various data and programs. The communication interface 204 is an interface for connecting to a communication network, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone line network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc. The input device 205 is, for example, a keyboard, a mouse, a touch panel, a button, a microphone, etc. that input data. The output device 206 is, for example, a display, a printer, a speaker, etc. that output data. Each functional unit of the management server 2 described below is realized by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it, and each storage unit of the management server 2 is realized as part of the storage area provided by the memory 202 and the storage device 203.

[0015] 3 is a diagram showing an example of the software configuration of the management server 2. The management server 2 includes a video information storage unit 231, a related information storage unit 232, a viewing history storage unit 233, a video distribution unit 211, an interest target identification unit 212, a provision unit 213, a reaction area acquisition unit 214, a behavior analysis unit 215, and a needs analysis unit 216.

[0016] <Storage section> The video information storage unit 231 stores information about each video (hereinafter, video information) for each video. The video information may include video data for playing the video. The video information may include a video ID that is identification information for the video. The video information may include content data that indicates the content of the video. The content data may be, for example, text data that explains the content of the video. When video data is stored as a file, the path to the file and the file name may be used as the video ID, and the file name may include text (content data) that indicates the content of the video.

[0017] The related information storage unit 232 stores information related to the video (hereinafter referred to as related information). The related information can include data (related data) for displaying information related to the video. The related data can be, for example, text data or image data, a video, or screen data such as a web page. The related data can be a URL where a web page, video, or the like is stored. The related data can be information for displaying a form for data input on the video (it can be screen data written in HTML or the like, or an instruction for displaying a form in a program transmitted in advance to the job seeker terminal 1). The related information can also include information for displaying a tag at a specific position during a specific period during playback of the video. For example, the related information can include information for identifying the related data (e.g., related data ID), information for identifying the video (e.g., video ID), a period for displaying the tag, information for identifying an area on the display screen of the video corresponding to the tag (for example, it can be specified by vertices or lengths constituting a rectangle, circle, polygon, or the like. The unit can be, for example, pixels), the related data, and content data. The period can be, for example, the time from the start to the end of the video playback during which the tag is to be displayed, and can be specified by the start time and end time (both of which may be relative times from the playback start time). The content data is information that explains the content of the related data, and can be, for example, text data that explains the content of the related data. The tag can be transparent (invisible).

[0018] The viewing history storage unit 233 stores information on the viewing history of videos related to employers that a job seeker has viewed (hereinafter, viewing history information). The viewing history information is created regarding the job seeker's viewing of a video, the job seeker's taking an action while viewing the video, and the job seeker's viewing of related information. The viewing history information includes information identifying the job seeker (e.g., a user ID), date and time, information identifying the video (e.g., a video ID), and action data. The action data included in the viewing history information regarding the job seeker's viewing of a video includes information indicating that the video was viewed. The action data included in the viewing history information regarding the job seeker's taking an action while viewing a video may include, for example, information indicating that the job seeker clicked (or tapped) on the video and information indicating the clicked area. The action data included in the viewing history information regarding the job seeker's viewing of related information may include information indicating that the job seeker viewed related data and information identifying the related data (e.g., a related data ID). In addition, if a job seeker fills in a form displayed on the video, the action data can include information indicating that the job seeker has filled in the form and the data that was entered (form data).

[0019] <Functional section> The video distribution unit 211 distributes videos to job seekers. The video to be distributed is assumed to be specified in advance by the employer. For example, the employer may provide the job seeker with a URL including information (e.g., a video ID) for identifying the video using a QR code (registered trademark) or the like, and the job seeker may access the URL from the job seeker terminal 3 to specify the video to be distributed. The video distribution unit 211 can create screen data for playing the video and transmit it to the job seeker terminal 3, and then transmit the video data in response to a request from the job seeker terminal 3. The screen data can be written in HTML, for example. The screen data can include, for example, a JavaScript program that runs on the job seeker terminal 3. The video distribution unit 211 can transmit the screen data accompanied by a JavaScript code that is programmed to transmit the position on the video clicked on by the job seeker to the management server 2 when the video is clicked on by the job seeker.

[0020] 4 is a diagram showing an example of a video playback screen 10 on the job seeker terminal 3. The playback screen 10 has a video display field 11, and a video 111 distributed by a video distribution unit 211 is played in the display field 11. A tag 133 may be displayed on the video.

[0021] The interest target identifying unit 212 identifies the interest target of the job seeker based on the viewing history. The interest target identifying unit 212 can identify the interest target according to the video viewed by the job seeker. The interest target identifying unit 212 can identify the interest target based on content data included in content information corresponding to the video viewed by the job seeker (video ID indicated by the viewing history information), for example. The interest target identifying unit 212 can reproduce the interest target of the job seeker by, for example, reading the viewing history information corresponding to the job seeker from the viewing history storage unit 233 and providing the large-scale language model with a prompt including the read viewing history information and an instruction to explain the interest target from the viewing history.

[0022] The subject of interest identified by the subject of interest identifying unit 212 may include, for example, the following information: (1) Information about the types of jobs the job seeker is interested in Job classifications such as sales, technical, and planning positions -Specific duties of the job Required skills and qualifications Career path prospects (2) Information about the corporate culture and environment that job seekers are interested in ·Work style (flextime, remote work, etc.) Benefits The atmosphere and interpersonal relationships within the company Training system and human resource development policy (3) Information about business activities that interest job seekers Specific products and services - Positioning of clients and markets ·Business prospects and growth strategies ·Technical capabilities and competitive advantages (4) Information about benefits that interest job seekers Salary system Evaluation system Promotion and salary increase system Overtime and vacation status (5) Information about the characteristics of companies that job seekers are interested in ·Company size History since the company's founding Management philosophy and corporate vision Social contribution activities and environmental initiatives

[0023] The subject of interest identifying unit 212 can identify the subject of interest as described above, for example, in the following manner. (1) Identification based on viewing time -Long viewing time for videos on specific topics Repeatedly watching videos on a particular topic ·Watching videos about a particular topic to the end (2) Interaction-based identification Clicking to see related information on a particular topic - Actively looking for detailed information on a particular topic Pausing and rewinding videos on specific topics (3) Identification based on viewing order -Starting watching from a specific topic -Preferentially watching videos about specific topics -Watching videos on related topics consecutively (4) Identification based on viewing patterns - Focusing on a specific topic at a specific time · Regularly check out videos on a particular topic · Watch multiple related topics across multiple channels

[0024] The interest target identification unit 212 can identify the interest target more accurately by combining these identification methods. For example, if a job seeker watches a video about "sales work content" for a long time (viewing time), pauses and rewinds the video at the part about "business negotiation method with customers" (interaction), and then watches a video about "sales performance evaluation method" (viewing order), it can be identified that the job seeker has a strong interest in practical skills and evaluation criteria in sales jobs.

[0025] The interest subject identification unit 212 can also calculate the degree of certainty of the identified interest subject. The degree of certainty can be calculated taking into consideration the following factors, for example: (1) Number of views and viewing time (2) Number of times related information has been confirmed (3) Continued interest in similar topics (4) Consistency of viewing behavior (5) Recent viewing trends The certainty can be expressed, for example, as a numerical value from 0 to 100 or a graded evaluation such as "high", "medium", "low", etc. The providing unit 213 can provide this certainty to the recruiter together with the identified subject of interest.

[0026] An example of a prompt that the interest identifier 212 provides to the large-scale language model is shown below. Analyze job seekers' interests by viewing the following content: -Videos watched: [Video ID], [Title], [Watching time] Clicked related information: [Related information ID], [Content] Viewing patterns: [viewing order], [interaction] format: 1. Main Interests (Ordered by Confidence) 2. Viewing behavior that supports each interest 3. Possible complementary interests

[0027] The subject of interest identification unit 212 may identify a subject of interest from a viewing history in the following manner, without using a large-scale language model.

[0028] (1) Scoring-based identification method The interest identification unit 212 can assign scores to various actions in the viewing history and identify the interest based on the accumulated scores. Scores can be set for the following elements: · Video viewing completed: 10 points Video viewing time (per minute): 1 point Related information clicks: 5 points - Video pause: 2 points Video rewind: 3 points - Fast forwarding videos: -1 point -Continuous viewing of videos in the same category (per video): 3 points The scores of each element can be weighted, for example, according to the following formula: Overall score = Σ(score of each element × weighting coefficient) The weighting coefficient can be adjusted, for example, according to the following factors: -The more recent the action, the higher the weighting factor. The higher the consistency of behavior within the same category, the higher the weighting factor. -Adjust weighting factors according to viewing order

[0029] (2) Clustering-based identification method The interest target identification unit 212 can generate a feature vector from the viewing history and identify the interest target by clustering. The interest target identification unit 212 can generate a feature vector from, for example, the viewing time for each category, the number of clicks for each category, the viewing completion rate for each category, the viewing pattern in time series, etc. In addition, the interest target identification unit 212 can identify clusters by clustering methods such as clustering by the k-means method, hierarchical clustering, and density-based clustering, and extract candidates for the interest target from the center of the identified cluster.

[0030] (3) Identification method based on sequence analysis The interest target identification unit 212 can identify the interest target by analyzing the order of actions and time series patterns in the viewing history. The interest target identification unit 212 can identify the interest target by, for example, analysis using a Markov chain model (calculation of state transition probability, analysis of stationary state, identification of absorption state) or time series pattern mining (extraction of frequent patterns, analysis of periodicity, analysis of trends).

[0031] (4) Hybrid Method The interest subject identification unit 212 can identify an interest subject with higher accuracy by combining the above-mentioned multiple methods. For example, the following combinations are possible. Combining scoring and clustering -Use the scores as elements of the feature vector -Correct the score with the clustering result Combining clustering and sequence analysis -Use time series patterns as features for clustering -Sequence analysis within clusters Combining scoring and sequence analysis - Score adjustment based on sequence patterns -Analysis of score fluctuations over time

[0032] The interests identified by these methods can be structured in the following form: (1) Hierarchical structure Major categories: Job type, corporate culture, benefits, etc. Subcategory: Specific job duties, working style, salary system, etc. Subcategory: Detailed business content, specific systems, specific conditions, etc. (2) Relevance Main Interests Secondary Interests Potential Interests (3) Chronology Early interests · Interests after change · Sustained interest

[0033] The providing unit 213 can provide the identified subject of interest to the recruiter.

[0034] The reaction area acquisition unit 214 acquires the area on the display screen of the video to which the job seeker responded. The reaction area acquisition unit 214 can receive, for example, the position on the video that was clicked from the screen data job seeker terminal 3, search for related information that corresponds to the distributed video and to the area that includes the received position from the related information storage unit 232, and when the related information is found, detect that the job seeker responded to the area specified in the related information.

[0035] When a specific area is clicked, the video distribution unit 211 can distribute related data to the job seeker terminal 3. FIG. 5 is a diagram for explaining an example in which a video is clicked. When the tag 133 is clicked (tapped in the example of FIG. 5) in the display field 11 of the video on the playback screen 10, the reaction area acquisition unit 214 determines that the area corresponding to the tag 133 has been clicked, and the video distribution unit 211 distributes related data included in the searched related information to the job seeker terminal 3, and can display the related information 112 in the display field 11 instead of the video 111 or by superimposing it on the video 111. Note that, in the example of FIG. 5, the related information 112 is a still screen, but the related information 112 can be a video, and the related information 112 of the video can be played instead of the initially distributed video 111 or by superimposing it on the video 111.

[0036] The interest target identifying unit 212 may identify the interest target based on the related data corresponding to the area acquired by the reaction area acquiring unit 214. The interest target identifying unit 212 may identify the interest target based on the video watched by the job seeker and the related information to which the job seeker reacted. The interest target identifying unit 212 can identify the interest target based on, for example, content data corresponding to the video watched by the job seeker and content data of the related data corresponding to the area to which the job seeker reacted. The interest target identifying unit 212 can generate an interest target according to the content of the video and the related information by providing, for example, a prompt including content data corresponding to the video watched by the job seeker, content data of the related data corresponding to the area to which the job seeker reacted, and an instruction to identify the interest target of the job seeker according to these content data, to the large-scale language model.

[0037] The behavioral analysis unit 215 can analyze the viewing behavior of the job seeker based on the viewing history. The behavioral analysis unit 215 can, for example, provide a prompt including the viewing history and an instruction to explain the viewing behavior of the job seeker based on the viewing history to the large-scale language model to generate an explanation of the viewing behavior.

[0038] An example of a prompt that the behavioral analysis unit 215 provides to the large-scale language model is shown below. Get insights for HR professionals into job seekers' viewing behavior with the following viewing histories: Overall viewing trends: [Viewing time distribution] Points of interest: [Click information] Viewing context: [viewing order] format: 1. Characteristics of viewing behavior 2. Distinctive Interactions 3. Interpreting viewing patterns

[0039] The needs analysis unit 216 may also analyze the needs of the job seeker based on the viewing history. For example, the needs analysis unit 216 may provide a prompt including the viewing history and an instruction to describe the job seeker's job search needs based on the viewing history to the large-scale language model to generate a description of the needs.

[0040] An example of a prompt that the needs analyzer 216 provides to the large-scale language model is shown below. Analyze what job seekers need from employers by viewing the following videos: · Main viewing content: [Content category] Confirmed details: [Related information content] Viewing response: [Interaction pattern] format: 1. Primary Needs 2. Specific needs 3. Prioritize your needs

[0041] For example, if a viewer watches a video and related data related to a sales job, and then watches related data on the details, the behavioral analysis can generate an explanation of the viewing behavior of the job seeker so that it is easy for the employer to read, such as "The viewer shows a strong interest in information related to sales jobs, and in particular, the behavior of clicking the details button to select a story is noticeable. In addition, the movement of using the pagination function to go forward and back through the information suggests that the viewer is looking for deeper information." In addition, the needs analysis can generate an explanation of the needs of the job seeker regarding jobs so that it is easy for the employer to read, such as "The viewer is looking for specific information and details about sales jobs, and wants to deepen his understanding of the job type. In particular, it is assumed that he needs specific data and stories about the job content and career path of sales."

[0042] The providing unit 213 can provide the employer with the analysis results related to the job seeker based on the viewing history. The providing unit 213 can provide the job seeker with the interests of the job seeker. The providing unit 213 can provide the employer with a description of the viewing behavior and / or a description of the needs. The providing unit 213 can transmit, for example, information identifying the job seeker and the interests, the viewing behavior, and / or the needs of the job seeker to the employer terminal 1.

[0043] <Operation> 6 is a diagram explaining the operation of the management server 2. The management server 2 distributes a video (S301), registers viewing history information related to the distributed video (S302), and when the video is clicked (S303: YES), searches for the clicked tag (area), distributes the corresponding related information (S304), and registers viewing history information related to the related information (S305). The management server 2 creates an explanation of the job seeker's interests, viewing behavior, and needs based on the viewing history (S306), and can provide these to the employer (S307).

[0044] As described above, the information processing system of this embodiment can identify the job seeker's interests based on the job seeker's viewing history of videos that the recruiter has made the job seeker view, and provide the recruiter with an explanation of the job seeker's viewing behavior and needs along with the interests. Therefore, the recruiter can use these as a reference when conducting interviews and deciding whether to hire the job seeker.

[0045] Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The present invention may be modified or improved without departing from the spirit of the present invention, and equivalents thereof are also included in the present invention.

[0046] For example, the processes performed by each of the functional units of the management server 2 described above may be executed by any of the functional units. Also, a different functional unit that executes part of the processes performed by each of the functional units described above may be added. Also, the functional units of the management server 2 may be provided in a distributed manner on multiple computers.

[0047] Furthermore, the information stored in each storage unit of the management server 2 may be stored by any storage unit. That is, the information stored in the above-mentioned multiple storage units may be stored by one storage unit, or part of the information stored in one of the above-mentioned storage units may be stored by another storage unit.

[0048] <Variation 1> In the above-described embodiment, the employer provides the job seeker with an explanation of the job seeker's interests and viewing behavior, an explanation of the job seeker's needs regarding the job search, etc. based on the job seeker's viewing history, but the present invention can also be applied to sales situations.

[0049] For example, a sales representative could have their sales target watch a video explaining the company or products in advance, and then provide the sales representative with information about the targets' interests, viewing behavior, and anticipated needs, allowing the sales representative to use this information as a reference for their sales activities.

[0050] The viewing history storage unit 233 in this modified example stores viewing history of videos related to sales viewed by the sales partner. Specifically, it stores viewing history of product explanation videos, service explanation videos, company explanation videos, etc. It also stores the browsing history of related information such as detailed explanation materials, technical materials, price lists, and implementation examples related to each video. The viewing history includes the viewing start time of the video, the viewing end time, operation information such as pausing and rewinding during the viewing period, the playback speed at the time of viewing, device information at the time of viewing, etc. Furthermore, a reaction history to points of interest regarding product specifications, service features, prices, delivery dates, etc. set in the video is also stored.

[0051] The reaction area acquisition unit 214 acquires the area on the display screen of the video to which the sales partner reacted. For example, it is possible to identify the part to which the sales partner paid particular attention, such as stopping at a part explaining a specific function of the product, accessing price information multiple times, or checking detailed information on comparison with competitors. It is also possible to grasp which items of related materials such as catalogs and specifications were checked in detail.

[0052] The interest identification unit 212 identifies the interest of the sales partner based on the viewing history. For example, if the sales partner repeatedly views the part about the cost reduction effect of the product, it can be determined that the sales partner is highly interested in the return on investment. Also, if the sales partner confirms in detail the explanation about the operation procedure and the maintenance service, it can be determined that the sales partner is highly interested in the practical issues after the implementation. Furthermore, if the sales partner is highly interested in the implementation cases of other companies and the performance data, it can be determined that the sales partner is focusing on verifying the implementation risks.

[0053] The interest target identification unit 212 can also identify an interest target based on related information corresponding to the acquired area. For example, it can infer the product characteristics and introduction conditions that the sales partner considers important from the detailed items of the specifications that the sales partner has checked and the contents of the technical documents that the sales partner has downloaded. It can also infer budgetary constraints and investment decision criteria by analyzing which items of a price list or quotation have attracted attention.

[0054] In this modified example, a viewing detection unit 217 can be newly provided. The viewing detection unit 217 detects that a sales target has viewed a video. The viewing detection unit 217 can send a notification to the sales representative, for example, when playback of the video starts. In addition, a notification can be sent when viewing of the video is completed or when a particularly important part has been viewed. Furthermore, a notification can be sent when viewing of related materials starts or when important materials are downloaded.

[0055] The providing unit 213 provides the salesperson with an explanation of the interests, viewing behavior, and needs, together with a notice that the viewing detection unit 217 has detected viewing. This allows the salesperson to make contact by calling the salesperson, etc., without missing the timing when the salesperson becomes interested in the company's products. In addition, it is possible to communicate with the salesperson after preparing effective proposal content by referring to the viewing behavior and needs of the salesperson. Advice to the salesperson at the time of calling may be generated here. In this case, the management server 2 can be equipped with an advice generating unit that generates advice to the salesperson, and the providing unit 213 can provide the advice generated by the advice generating unit to the salesperson.

[0056] The advice generation unit can generate advice for a sales representative when making a call to the analyzed customer by providing a prompt to the large-scale language model that includes, for example, at least one of the customer's interests in products, etc. identified by the interest identification unit 212, a description of the customer's video viewing behavior generated by the behavior analysis unit 215, and a description of the customer's needs generated by the needs analysis unit 216, and instructions to generate advice for the sales representative when making a call based on these.

[0057] Furthermore, the providing unit 213 can adjust the content and granularity of the information to be provided according to the role and authority of the sales target within the organization. For example, it is possible to provide detailed information on technical matters of interest to technical personnel, and information focusing on investment effects and relevance to management issues to management personnel. Also, depending on the stage of progress of the business negotiation, it is possible to provide information focusing on general interests in the early stages and information focusing on specific recognition of issues in the detailed consideration stage.

[0058] Here, the advice generating unit can also generate advice for business negotiations. The advice generating unit can generate advice for the salesperson during business negotiations with the analyzed customer by providing the large-scale language model with a prompt including at least one of the customer's interests in products, etc. identified by the interest identifying unit 212, the explanation of the customer's video viewing behavior generated by the behavior analyzing unit 215, and the explanation of the customer's needs generated by the needs analyzing unit 216, and an instruction to generate advice for the salesperson when conducting business negotiations based on these.

[0059] According to this modified example, the sales representative can conduct sales activities after understanding the interests and needs of the sales target in advance, which enables efficient and effective business negotiations. In addition, the sales target can check the information on products and services at their own pace and contact the sales representative after they are prepared, which realizes more productive business negotiations. Furthermore, in organized sales activities, multiple sales representatives can share the interests and needs of the sales target, which enables consistent proposals and support.

[0060] <Variation 2> In the above-described embodiment, the interest analysis, behavior analysis, and needs analysis are based on the viewing history, but CRM information may be used in addition to the viewing history.

[0061] The CRM information may include, for example, transaction status, negotiation history, visit record, proposal content, quotation history, inquiry content, response history, complaint record, email record, telephone record, etc. In this case, the management server 2 is provided with a CRM information storage unit that stores CRM information for each user.

[0062] The interest identification unit 212, the behavior analysis unit 215, and the needs analysis unit 216 can read out CRM information corresponding to the customer being analyzed from the CRM information storage unit during analysis and include it in the prompt.

[0063] <Variation 3> In addition to the job seeker's interests with respect to the employer, the explanation of the job seeker's viewing behavior, and the explanation of the job seeker's needs in the above-mentioned embodiment, advice for the recruiter may be generated. In this case, the management server 2 is provided with an advice generation unit that generates advice for the recruiter. The advice generation unit can provide the large-scale language model with a prompt including at least one of the customer's interests in the product, etc. identified by the interest identification unit 212, the explanation of the customer's video viewing behavior generated by the behavior analysis unit 215, and the explanation of the customer's needs generated by the needs analysis unit 216, and an instruction to generate advice for the recruiter to interview the job seeker based on these, thereby generating advice for the recruiter at the time of the interview with the customer being the subject of analysis.

[0064] <Disclosures> The present disclosure also includes the following configurations. [Item 1] a viewing history storage unit that stores a viewing history of videos related to recruiters that have been viewed by a job seeker; an interest identification unit that identifies an interest of the job seeker based on the viewing history; A providing unit for providing the subject of interest to the recruiter; An information processing system comprising: [Item 2] The information processing system according to item 1, a related information storage unit that stores related information related to an area on a display screen of the moving image in association with information identifying the area; a reaction area acquisition unit that acquires an area on a display screen of the video to which the job seeker reacts; Equipped with the interest identification unit identifies the interest based on the related information corresponding to the acquired area; An information processing system comprising: [Item 3] Item 2. An information processing system according to the present invention, a video information storage unit that stores content information indicating a content of each of the videos, the interest identification unit identifies the interest based on the content information corresponding to the video viewed by the job seeker and the related information corresponding to the acquired area; An information processing system comprising: [Item 4] The information processing system according to item 1, a behavioral analysis unit that provides the viewing history and a prompt including an instruction to describe a viewing behavior of the job seeker based on the viewing history to a large scale language model to generate a description of the viewing behavior; Equipped with the providing unit providing a description of the viewing behavior; An information processing system comprising: [Item 5] The information processing system according to item 1, a needs analysis unit that provides a large-scale language model with a prompt including an instruction to explain the needs of the job seeker to the recruiter based on the viewing history and the viewing history, thereby generating an explanation of the needs; Equipped with the providing unit providing a description of the needs; An information processing system comprising: [Item 6] storing a viewing history of videos related to recruiters that have been viewed by the job seeker; identifying interests of the job seeker based on the viewing history; providing said interests to said recruiter; An information processing method characterized by being executed by a computer. [Item 7] storing a viewing history of videos related to recruiters that have been viewed by the job seeker; identifying interests of the job seeker based on the viewing history; providing said interests to said recruiter; A program for causing a computer to execute the following.

[0065] <Other disclosures> [Second item 1] a video information storage unit that stores content information indicating the content of the video; a related information storage unit that stores related information related to an area on a display screen of the moving image in association with information identifying the area; a viewing history storage unit that stores a viewing history including the content information corresponding to the video viewed by a viewer and the related information corresponding to the area to which the viewer responded while viewing the video; a behavior analysis unit that provides a large scale language model with a prompt including an instruction to describe a viewing behavior of the viewer based on the viewing history and the viewing history to generate a description of the viewing behavior; An information processing system comprising: [3rd item 1] a video information storage unit that stores content information indicating the content of the video; a related information storage unit that stores related information related to an area on a display screen of the moving image in association with information identifying the area; a viewing history storage unit that stores a viewing history including the content information corresponding to the video viewed by a viewer and the related information corresponding to the area to which the viewer responded while viewing the video; a needs analysis unit that provides a prompt to a large scale language model, the prompt including an instruction to describe a need of the viewer based on the viewing history and the viewing history, to generate a description of the need; An information processing system comprising: [4th item 1] a viewing history storage unit that stores viewing history of videos related to sales viewed by a sales partner; an interest identification unit that identifies an interest of the sales partner based on the viewing history; a providing unit for providing the subject of interest to a salesperson; An information processing system comprising: [4th item 2] 4. An information processing system according to claim 1, a related information storage unit that stores related information related to an area on a display screen of the moving image in association with information identifying the area; a reaction area acquisition unit that acquires an area on a display screen of the video to which the sales partner has reacted; Equipped with the interest identification unit identifies the interest based on the related information corresponding to the acquired area; An information processing system comprising: [4th item 3] 4. An information processing system according to claim 2, a video information storage unit that stores content information indicating a content of each of the videos, the interest identification unit identifies the interest based on the content information corresponding to the video viewed by the job seeker and the related information corresponding to the acquired area; An information processing system comprising: [4th item 4] 4. An information processing system according to claim 1, a behavior analysis unit that provides a large-scale language model with a prompt including an instruction to describe the viewing behavior of the sales partner based on the viewing history and the viewing history, to generate a description of the viewing behavior; Equipped with the providing unit providing a description of the viewing behavior; An information processing system comprising: [4th item 5] 4. An information processing system according to claim 1, a needs analysis unit that provides a large-scale language model with a prompt including an instruction to explain the needs of the job seeker to the recruiter based on the viewing history and the viewing history, thereby generating an explanation of the needs; Equipped with the providing unit providing a description of the needs; An information processing system comprising: [Explanation of symbols]

[0066] 1. Recruiter terminal 2 Management Server 3 Job Seeker Terminal

Claims

1. a viewing history storage unit that stores a viewing history of videos viewed by a viewer; an interest identification unit that identifies an interest of the viewer based on the viewing history; an advice generator configured to provide prompts to a large scale language model, the prompts including the subject of interest and instructions for generating advice for the viewer based on the subject of interest, to generate the advice; An information processing system comprising:

2. a viewing history storage unit that stores a viewing history of videos related to recruiters that have been viewed by a job seeker; an interest identification unit that identifies an interest of the job seeker based on the viewing history; an advice generator that generates the advice by providing a large-scale language model with a prompt including an instruction to generate advice for a recruiter to interview the job seeker based on the subject of interest and the subject of interest; An information processing system comprising:

3. 3. The information processing system according to claim 2, a behavioral analysis unit that provides the large-scale language model with a prompt including an instruction to describe a viewing behavior of the job seeker based on the viewing history and the viewing history, to generate a description of the viewing behavior; the advice generation unit generates the advice by providing a prompt to the large-scale language model, the prompt including the subject of interest, a description of the viewing behavior, and an instruction to generate the advice based on the subject of interest and the description of the viewing behavior; An information processing system comprising:

4. 3. The information processing system according to claim 2, a needs analysis unit that generates an explanation of the needs by providing the large-scale language model with a prompt including an instruction to explain the needs of the job seeker to the recruiter based on the viewing history and the viewing history; the advice generator generates the advice by providing a prompt to the large-scale language model, the prompt including the subject of interest, a description of the need, and an instruction to generate the advice based on the subject of interest and the description of the need; An information processing system comprising:

5. 3. The information processing system according to claim 2, a behavioral analysis unit that provides the viewing history and a prompt including an instruction to describe a viewing behavior of the job seeker based on the viewing history to the large-scale language model to generate a description of the viewing behavior; a needs analysis unit that generates an explanation of the needs by providing the large-scale language model with a prompt including an instruction to explain the needs of the job seeker to the recruiter based on the viewing history and the viewing history; and Equipped with the advice generation unit generates the advice by providing a prompt to the large-scale language model, the prompt including the subject of interest, a description of the viewing behavior, a description of the need, and an instruction to generate the advice based on the subject of interest, the description of the viewing behavior, and the description of the need; An information processing system comprising:

6. a viewing history storage unit that stores viewing history of videos related to sales viewed by a sales partner; an interest identification unit that identifies an interest of the sales partner based on the viewing history; an advice generating unit that generates the advice by providing a prompt including an instruction to generate advice for a sales representative to make a phone call to the sales partner or advice for the sales representative to negotiate with the sales partner based on the subject of interest and the subject of interest to a large-scale language model; An information processing system comprising:

7. 7. The information processing system according to claim 6, a behavior analysis unit that provides the large-scale language model with a prompt including an instruction to describe the viewing behavior of the sales partner based on the viewing history and the viewing history, to generate a description of the viewing behavior; the advice generation unit generates the advice by providing a prompt to the large-scale language model, the prompt including the subject of interest, a description of the viewing behavior, and an instruction to generate the advice based on the subject of interest and the description of the viewing behavior; An information processing system comprising:

8. 7. The information processing system according to claim 6, a behavior analysis unit that provides the large-scale language model with a prompt including an instruction to explain the needs of the sales partner based on the viewing history and the viewing history, to generate an explanation of the needs; the advice generator generates the advice by providing a prompt to the large-scale language model, the prompt including the subject of interest, a description of the need, and an instruction to generate the advice based on the subject of interest and the description of the need; An information processing system comprising:

9. 7. The information processing system according to claim 6, a behavior analysis unit that provides the large-scale language model with a prompt including an instruction to describe the viewing behavior of the sales partner based on the viewing history and the viewing history, thereby generating a description of the viewing behavior; a behavior analysis unit that provides the large-scale language model with a prompt including an instruction to explain the needs of the sales partner based on the viewing history and the viewing history, thereby generating an explanation of the needs; Equipped with the advice generation unit generates the advice by providing a prompt to the large-scale language model, the prompt including the subject of interest, a description of the viewing behavior, a description of the need, and an instruction to generate the advice based on the subject of interest, the description of the viewing behavior, and the description of the need; An information processing system comprising:

10. storing a viewing history of videos viewed by the viewer; identifying interests of the viewer based on the viewing history; providing prompts to a large scale language model, the prompts including the interests and instructions for generating advice for the viewer based on the interests, to generate the advice; An information processing method characterized by being executed by a computer.

11. storing a viewing history of videos related to recruiters that have been viewed by the job seeker; identifying interests of the job seeker based on the viewing history; providing prompts to a large scale language model, the prompts including instructions for generating advice for a recruiter to interview the job seeker based on the interests and the interests, to generate the advice; An information processing method characterized by being executed by a computer.

12. A step of storing a viewing history of videos related to sales viewed by the sales partner; Identifying an interest of the business partner based on the viewing history; providing a prompt including an instruction for generating advice for a sales representative to call the sales partner or advice for the sales representative to negotiate with the sales partner based on the subject of interest and the subject of interest to a large-scale language model to generate the advice; An information processing method characterized by being executed by a computer.

13. storing a viewing history of videos viewed by the viewer; identifying interests of the viewer based on the viewing history; providing prompts to a large scale language model, the prompts including the interests and instructions for generating advice for the viewer based on the interests, to generate the advice; A program for causing a computer to execute the following.

14. storing a viewing history of videos related to recruiters that have been viewed by the job seeker; identifying interests of the job seeker based on the viewing history; providing prompts to a large scale language model, the prompts including instructions for generating advice for a recruiter to interview the job seeker based on the interests and the interests, to generate the advice; A program for causing a computer to execute the following.

15. A step of storing a viewing history of videos related to sales viewed by the sales partner; Identifying an interest of the business partner based on the viewing history; providing a prompt including an instruction for generating advice for a sales representative to call the sales partner or advice for the sales representative to negotiate with the sales partner based on the subject of interest and the subject of interest to a large-scale language model to generate the advice; A program for causing a computer to execute the following.

Images