Program, method, information processing device, and system
The system addresses the lack of suitable evaluation reports by analyzing user performance data through a server and large-scale language model, providing personalized and secure feedback while ensuring privacy, thereby enhancing user engagement.
Patent Information
- Application Number
- JP2024081822
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-05-20
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-05-20
AI Technical Summary
Existing systems fail to provide suitable evaluation reports that accurately reflect an individual's performance and offer personalized improvement measures, lacking in-depth analysis and privacy considerations.
An information processing system that utilizes a server, user terminal, and large-scale language model to collect and analyze performance and evaluation data, generate personalized support information, and present it in a user-friendly format while ensuring privacy by anonymizing sensitive information.
The system provides tailored evaluation reports and improvement measures based on actual user data, enhancing user engagement and privacy protection by excluding personal information, thus offering a more meaningful and secure assessment.
Smart Images

Figure 0007586561000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a program, a method, an information processing device, and a system. [Background technology]
[0002] 2. Description of the Related Art Techniques for outputting evaluation reports regarding business performance and the like are known. Patent Document 1 discloses a technique for providing appropriate instructions and advice regarding sales activities to each salesperson, regardless of the skill level of the manager. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2004-318865 A Summary of the Invention [Problem to be solved by the invention]
[0004] There is a problem in that suitable evaluation reports cannot be presented. Therefore, the present disclosure has been made to solve the above problem, and has an object to provide a technique for presenting a suitable evaluation report. [Means for solving the problem]
[0005] A program to be executed by a computer having a processor and a memory unit, the program executing the following steps: a result reception step in which the processor receives input of result data indicating result for each item in a business; a document reception step in which the processor receives input of document data for the result data received in the result reception step from an administrator; a storage step in which each of the multiple result data received in the result reception step is associated with the multiple document data received in the document reception step and stored as accumulated data; an assistance identification step in which, based on predetermined first result data indicating result for each item of a first user, the accumulated data stored in the storage step is referenced to identify first accumulated data including one or more document data; and an assistance presentation step in which first support information is presented based on the first accumulated data identified in the assistance identification step. Effect of the Invention
[0006] According to the present disclosure, a suitable evaluation report can be presented. [Brief description of the drawings]
[0007] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Diagram 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Diagram 3] 2 is a block diagram showing a functional configuration of a first user terminal 20. FIG. [Figure 4] 2 is a block diagram showing a functional configuration of an administrator terminal 30. FIG. [Diagram 5] FIG. 13 is a diagram showing the data structure of a user table 1012. [Figure 6] FIG. 13 is a diagram showing the data structure of a performance table 1013. [Figure 7] FIG. 13 is a diagram showing the data structure of an evaluation table 1014. [Figure 8] FIG. 10 is a diagram showing the data structure of a prompt table 1015. [Figure 9] FIG. 13 is a diagram showing the data structure of a support table 1016. [Figure 10] 13 is a flowchart showing the operation of a support process. [Figure 11] 11 is a screen example showing the operation of the support process. [Figure 12] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0008] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In all the drawings explaining the embodiment, the same reference numerals are given to common components, and repeated explanations are omitted. Note that the following embodiment does not unduly limit the contents of the present disclosure described in the claims. In addition, not all of the components shown in the embodiment are essential components of the present disclosure. In addition, each figure is a schematic diagram and is not necessarily illustrated strictly.
[0009] <System 1 Configuration> The system 1 in the present disclosure is an information processing system that provides support information related to business. The system 1 includes a server 10, a first user terminal 20, an administrator terminal 30, and an information processing device for a large-scale language model 50, all of which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the first user terminal 20. As shown in FIG. FIG. 4 is a block diagram showing the functional configuration of the administrator terminal 30. As shown in FIG.
[0010] Each information processing device is composed of a computer having a calculation device and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the first user terminal 20, the administrator terminal 30, and the large-scale language model 50, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.
[0011] <Server 10 Configuration> The server 10 is an information processing device that provides an information processing service that provides support information. The server 10 includes a storage unit 101 and a control unit 104 .
[0012] <Configuration of the storage unit 101 of the server 10> The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a performance table 1013 , an evaluation table 1014 , a prompt table 1015 , and a support table 1016 .
[0013] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. Application programs 1011 include applications such as a web browser application.
[0014] User table 1012 is a table that stores and manages information about member users (hereinafter, users) who use the service. When a user registers to use the service, the user's information is stored in a new record in user table 1012. This allows the user to use the service according to the present disclosure. The user table 1012 is a table having columns of user ID, user name, and user data, with the user ID as the primary key. FIG. 5 is a diagram showing the data structure of the user table 1012. As shown in FIG.
[0015] The user ID is an item for storing user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name. The user data includes unique information about the individual user and attribute information about the user's characteristics and background. The user's unique information includes information unique to the user, such as the user's date of birth (age), sex, and the like. The user's attribute information includes information such as the user's educational history (highest level of education, major, graduation year), occupation, work history, interests, place of residence, and language.
[0016] The results table 1013 is a table for storing and managing results information related to the user's business activities, etc. Specifically, a quantitative index (results data) is stored in association with each business item. The performance table 1013 is a table having columns of user ID, item name, performance data, and target period. FIG. 6 is a diagram showing the data structure of the performance table 1013. As shown in FIG.
[0017] The user ID is an item for storing user identification information for identifying a user. The item name is an item that stores information for identifying a task item. For example, as the item name, text data for identifying the following business results is stored. 1. Sales activity indicators Number of rounds, number of phone calls, number of visits to existing customers, appointment acquisition rate at visits, number of quotations created and time to submit them 2. Indicators related to new business development Number of new customers acquired 3. Indicators related to orders - Negotiation progress, number of contracts concluded, contract amount, contract rate (ratio of contracts to number of proposals) 4. Sales-related indicators Sales target achievement rate, sales growth rate 5. Customer Satisfaction Indicators Customer satisfaction survey scores, complaint response speed and resolution rate 6. Sales Efficiency Indicators Efficiency of sales activities (contract rate relative to number of visits or phone calls), submission rate of sales reports and their completeness, utilization of sales tools (data entry rate for CRM system, etc.) 7. Skills and knowledge indicators Product knowledge test scores, participation rate and comprehension rate in sales skills training 8. Indicators for internal evaluation Evaluations from colleagues and other departments (e.g. survey results on communication skills, cooperation, etc.) The performance data is an item that stores quantitative indicators (number of times, achievement rate, score, etc.) of the task item specified by the item name. Note that the performance data does not necessarily need to be an item that stores quantitative indicators, and may be configured to store text data, audio data, image data, etc. that indicate the activity status of the task item etc. described in text. The target period is an item for storing the target period of the performance data. For example, the performance information of the user can be stored and managed in any period unit such as one year, half year, quarter, month, or week. Additionally, the performance data may include text indicating the achievement status of business goals (weekly, monthly, quarterly, half-yearly, yearly, etc.). For example, the performance data may include information regarding the goal of "receiving 10 orders by month A" and text indicating the achievement status and difference of the goal, such as "receiving 6 orders in month B."
[0018] The evaluation table 1014 is a table for storing and managing information relating to evaluations (evaluation information). The evaluation table 1014 is a table having columns of evaluation target ID, evaluator ID, KPI data, evaluation data, and target period. FIG. 7 is a diagram showing the data structure of the evaluation table 1014. As shown in FIG.
[0019] The evaluation target ID is an item for storing user identification information for identifying the person to be evaluated. The evaluator ID is an item for storing user identification information for identifying the evaluator. The KPI data is an item that stores performance data to be evaluated regarding the work of an evaluation target person during a target period. Specifically, the KPI data is stored in such a manner that a plurality of work items and performance data regarding the work items are associated with each other. The evaluation data is an item that stores the evaluation results of the evaluator's evaluation of the KPI data of the person to be evaluated during the target period. For example, the evaluation data stores text data related to the following evaluation results. Specifically, the evaluation data includes the following feedback, advice, etc. provided by the evaluator to the person to be evaluated (evaluated person): 1. Evaluation of each indicator Degree of achievement against targets, comparison with previous period or same period last year, comparison with other sales representatives 2. Identifying strengths and weaknesses Indicators that are performing well and the reasons for their success, as well as indicators with room for improvement and the reasons for their success 3. Specific improvement measures Action plans to overcome weaknesses, strategies to further develop strengths, and suggestions for acquiring new skills or knowledge 4. Goal Setting Set short-term and long-term goals and identify milestones to achieve them 5. Providing resources - Providing tools and information necessary for sales activities, and ensuring support systems both inside and outside the company 6. Increased motivation Praise and recognition for achievements and expectations for future growth 7. Frequency and method of feedback Setting up regular meetings and emphasizing the importance of daily communication 8. Overall evaluation and future direction Evaluation of current sales activities overall and discussion of long-term career development direction Additionally, the evaluation data may include text indicating the achievement status of business goals (business goals such as weekly, monthly, quarterly, half-yearly, and yearly goals). For example, the performance data includes information on the goal of "receiving 10 orders by month A" and text indicating the achievement status and difference of the goal, such as "receiving 6 orders in month B."
[0020] The prompt table 1015 is a table for storing and managing information relating to prompts (prompt information). The prompt table 1015 is a table having columns for user ID, input data, output data, and target period. FIG. 8 is a diagram showing the data structure of the prompt table 1015.
[0021] The user ID is an item for storing user identification information for identifying a user. The input data is an item that stores prompts to be input to a large-scale language model, etc. In this disclosure, a prompt written in a character string is described as an example, but the input data may also include binary data such as images and audio. The output data is an item that stores the output data output by the large-scale language model 50 in response to the input data. The target period is an item for storing the target period of the performance data, evaluation data, KPI data, etc. used when creating the input data.
[0022] The support table 1016 is a table for storing and managing information related to support (support information). The support table 1016 is a table having columns for user ID, support data, and target period. FIG. 9 is a diagram showing the data structure of the support table 1016. As shown in FIG.
[0023] The user ID is an item for storing user identification information for identifying a user. The assistance data is an item that stores the evaluation results output from the large-scale language model. Specifically, the support data stores evaluation data including information such as feedback and advice for the evaluatee, similar to the items of evaluation data in the evaluation table 1014. In addition, in the present disclosure, the support data includes graphs and the like visually depicting numerical indicators and the like of performance data for each task item. The target period is an item for storing the target period of the performance data, evaluation data, KPI data, etc. used when creating the assistance data.
[0024] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.
[0025] The user registration control unit 1041 performs processing to store, in the user table 1012, information on users who wish to use the service according to the present disclosure. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a specific input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers user information in the user table 1012, the service provider may carry out a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or an arbitrary character string or number may be automatically set by the user registration control unit 1041.
[0026] <Configuration of First User Terminal 20> The first user terminal 20 is an information processing device operated by a user who uses a service. The first user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary PC (Personal Computer), or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. The first user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .
[0027] <Configuration of the storage unit 201 of the first user terminal 20> The storage unit 201 of the first user terminal 20 includes a first user ID 2011 and an application program 2012 .
[0028] The first user ID 2011 is an account ID of the user. The user transmits the first user ID 2011 from the first user terminal 20 to the server 10. The server 10 identifies the user based on the first user ID 2011 and provides the user with the service according to the present disclosure. The first user ID 2011 includes information such as a session ID temporarily assigned by the server 10 when identifying the user using the first user terminal 20.
[0029] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript™ that runs on a web browser application stored on the first user terminal 20.
[0030] <Configuration of the control unit 204 of the first user terminal 20> The control unit 204 of the first user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.
[0031] <Configuration of the input device 206 of the first user terminal 20> The input device 206 of the first user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .
[0032] <Configuration of the output device 208 of the first user terminal 20> The output device 208 of the first user terminal 20 includes a display 2081 and a speaker 2082 .
[0033] <Configuration of administrator terminal 30> The administrator terminal 30 is an information processing device operated by an administrator who manages a service. The administrator terminal 30 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary PC (Personal Computer), or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. The administrator terminal 30 includes a storage unit 301 , a control unit 304 , an input device 306 , and an output device 308 .
[0034] <Configuration of the storage unit 301 of the administrator terminal 30> The storage unit 301 of the administrator terminal 30 includes an administrator ID 3011 and an application program 3012 .
[0035] The administrator ID 3011 is a user's account ID. The user transmits the administrator ID 3011 from the administrator terminal 30 to the server 10. The server 10 identifies the user based on the administrator ID 3011 and provides the user with the services disclosed herein. The administrator ID 3011 includes information such as a session ID that is temporarily assigned by the server 10 to identify the user who is using the administrator terminal 30.
[0036] The application program 3012 may be prestored in the storage unit 301, or may be downloaded from a web server operated by a service provider via a communication IF. The application program 3012 includes an interpreter-type programming language such as JavaScript (registered trademark) that is executed on a web browser application stored in the administrator terminal 30.
[0037] <Configuration of the control unit 304 of the administrator terminal 30> The control unit 304 of the administrator terminal 30 includes an input control unit 3041 and an output control unit 3042. The control unit 304 executes an application program 3012 stored in the storage unit 301, thereby realizing each functional unit.
[0038] <Configuration of the input device 306 of the administrator terminal 30> The input device 306 of the administrator terminal 30 includes a camera 3061 , a microphone 3062 , a position information sensor 3063 , a motion sensor 3064 , and a keyboard 3065 .
[0039] <Configuration of the output device 308 of the administrator terminal 30> The output device 308 of the administrator terminal 30 includes a display 3081 and a speaker 3082 .
[0040] <50 large-scale language models> The large-scale language model 50 is an artificial intelligence system trained using huge amounts of text data, image data, audio data, etc. The large-scale language model 50 is a type of generative AI and can generate various contents such as text, images, and audio. The large-scale language model 50 includes ChatGPT, Claude, StableDiffusion, etc.
[0041] <System 1 Operation> Each process of the system 1 will be described below. FIG. 10 is a flowchart showing the operation of the support process. FIG. 11 is a screen example showing the operation of the support process.
[0042] <Support Process> The support process is a process of presenting support information (advice, feedback) including evaluations and improvement measures regarding a particular user's business activities, etc., based on performance data regarding the business activities, etc., of the user.
[0043] <Summary of support process> The assistance process is a series of processes that include acquiring and accumulating performance data of a large number of users, acquiring and accumulating evaluation data from administrators (supervisors, managers, etc.) based on the performance data, accepting input of information identifying a specific first user ID, acquiring performance data for the first user in a specific target period, searching for evaluation data based on the performance data, generating a prompt based on the evaluation data, acquiring output data by inputting the prompt into a large-scale language model, creating assistance data based on the output data, and presenting the created assistance data.
[0044] <Details of support process> The support process will be described in detail below.
[0045] In step S101, the control unit 104 of the server 10 executes a result receiving step of receiving input of result data indicating the result for each item in the business. Specifically, a user such as an employee operates the input device 206 of the first user terminal 20 to input the URL of a page for inputting performance data (performance data input page) into a web browser or the like, and opens the performance data input page. The control unit 204 of the first user terminal 20 sends a request to the server 10 to open the performance data input page. The control unit 104 of the server 10 generates a performance data input page based on the received request, and sends it to the first user terminal 20. The control unit 204 of the first user terminal 20 displays the received performance data input page on the display 2081 of the first user terminal 20. The performance data input page includes an input field for inputting performance data for each task item, and an input field for the target period of the performance data. The user operates the input device 206 of the first user terminal 20 to input the performance data for each task item and the target period in the input fields. The control unit 204 of the first user terminal 20 transmits the first user ID 2011, the input performance data for each task item, and the target period to the server 10. The control unit 104 of the server 10 stores the received performance data and target period for each task item in the items of item name, performance data, and target period of a new record in the performance table 1013, respectively. As a result, the results of the user's daily work content are stored in the results table 1013. Note that the results data may be input by an administrator such as a superior or manager, rather than an employee, through the administrator terminal 30. Also, the user's work results may be collected by any information processing terminal other than the first user terminal 20, automatically transmitted to the server 10, and stored and accumulated in the results table 1013.
[0046] Employees and managers may operate any information processing terminal to send document-formatted performance data such as daily, weekly, or monthly reports to the server 10 via email or chat tools such as Slack, Chatwork, or Line Works, and store the data in the performance data item of the performance table 1013. Alternatively, data may be input by voice into a microphone or the like provided on the information processing terminal. This allows users such as employees and managers to accumulate daily performance data in the performance table 1013 simply by performing operations similar to those used for regular reporting tasks such as daily, weekly, and monthly reports (including oral reports).
[0047] In step S102, the control unit 104 of the server 10 executes a document receiving step of receiving, from the administrator, input of document data for the result data received in the result receiving step. Specifically, the manager, at a predetermined timing, considers the business situation including the performance information of the employees (subordinates) that the manager manages, and performs user evaluation (including business evaluation, performance evaluation, work evaluation, etc.) of the employees, etc. For example, the work performance of the employees, etc. is evaluated quarterly, half-yearly, or annually. Specifically, a user such as an administrator operates the input device 306 of the administrator terminal 30 to input the URL of a page for inputting evaluation data (evaluation data input page) into a web browser or the like, and opens the evaluation data input page. The control unit 304 of the administrator terminal 30 sends a request to the server 10 to open the evaluation data input page. The control unit 104 of the server 10 generates an evaluation data input page based on the received request, and sends it to the administrator terminal 30. The control unit 304 of the administrator terminal 30 displays the received evaluation data input page on the display 3081 of the administrator terminal 30. The evaluation input page includes an evaluation target ID input field for inputting the user ID of the person to be evaluated, and an input field for evaluation data. The administrator operates the input device 306 of administrator unit 0 to input the user ID (evaluation target ID) of the person to be evaluated and the evaluation data in the input fields. The control unit 304 of the administrator terminal 30 transmits the administrator ID 3011, the evaluation target ID, and the evaluation data to the server 10.
[0048] In step S102, the control unit 104 of the server 10 executes a storage step of storing, as accumulated data, each of the plurality of result data accepted in the result acceptance step in association with the plurality of document data accepted in the document acceptance step. Specifically, the control unit 104 of the server 10 stores the received administrator ID 3011, evaluation target ID, and evaluation data in the items of evaluator ID, evaluation target ID, and evaluation data of a new record in the evaluation table 1014, respectively. The control unit 104 of the server 10 may receive performance data from the administrator terminal, or may search the user ID field in the performance table 1013 based on the evaluation target ID to acquire all or a part of the performance data of the person being evaluated, and store it in the KPI data field of the target record in the evaluation table 1014. The KPI data field may store data that has been subjected to any processing or alteration of the performance data, or that has been added with comments from the administrator, etc.
[0049] The evaluation data may be input by an employee or the like, instead of an administrator or the like, through the first user terminal 20. Also, the evaluation results of users may be collected by any information processing terminal other than the administrator terminal 30, automatically transmitted to the server 10, and stored and accumulated in the evaluation table 1014.
[0050] Employees and managers may operate any information processing terminal to send evaluation data in text format such as daily, weekly, or monthly reports to the server 10 via email or chat tools such as Slack, Chatwork, or Line Works, and store the data in the evaluation data item of the evaluation table 1014. Alternatively, the data may be input by voice into a microphone or the like provided on the information processing terminal. This allows users such as employees and managers to accumulate daily evaluation data in the evaluation table 1014 simply by performing operations similar to those used for regular reporting tasks such as daily reports, weekly reports, and monthly reports (including oral reports).
[0051] Also, a configuration may be adopted in which users such as employees and managers transmit data including both achievement data and evaluation data to the server 10 in a text format such as a daily report, weekly report, or monthly report via email or a chat tool such as Slack, Chatwork, or Line Works, and the data is stored in the items of achievement data in the achievement table 1013 and evaluation data in the evaluation table 1014. Note that the control unit 104 of the server 10 may be configured to apply the large-scale language model 50 or the like to the acquired text data, to extract items of achievement data and evaluation data, and to store the achievement data and evaluation data in the items of achievement data in the achievement table 1013 and evaluation data in the evaluation table 1014, respectively. Specifically, this is because a sales representative's daily report or the like generally includes both performance data relating to performance and evaluation data relating to evaluation.
[0052] In the support process of the present disclosure, steps S101 and S102 are executed asynchronously with steps S103 and after. As a result, the result table 1013 and the evaluation table 1014 of the server 10 store result data and evaluation data, respectively, at any time.
[0053] In step S103, the control unit 104 of the server 10 executes a first user input step of accepting input of a first user ID for identifying the first user. Specifically, the first user operates the input device 206 of the first user terminal 20, executes a browser application or the like, and opens the support page D1 by inputting the URL of a web page (support page) for executing the support process. The control unit 204 of the first user terminal 20 transmits a request including the first user ID 2011 for opening the support page to the server 10. In the present disclosure, an example in which step S103 and subsequent steps are executed by the first user is disclosed as an example, but the steps may be executed by any user, such as an administrator or another user.
[0054] In step S104, the control unit 104 of the server 10 executes a first achievement acquisition step of acquiring first achievement data of the first user based on the first user ID input in the first user input step. Specifically, the control unit 104 of the server 10 searches the user ID item in the performance table 1013 based on the first user ID 2011, and acquires performance information (first performance information) including the item name and performance data for the latest target period. Note that the acquired performance information does not necessarily have to be for the latest target period, and the configuration may be such that performance information for a target period specified by an information terminal or the like is acquired.
[0055] In step S105, the control unit 104 of the server 10 executes an assistance identification step of identifying first accumulated data including one or more document data by referring to the accumulated data stored in the storage step based on predetermined first performance data indicating the performance of the first user for each item. Specifically, the control unit 104 of the server 10 refers to the performance data item of the performance table 1013 based on the first performance information acquired in step S104, and acquires one or more pieces of performance information (first accumulated data) similar to the first performance data. The following methods are available for calculating the similarity of performance data. 1. Euclidean Distance The performance data for one or more business items is treated as vectors in a multidimensional space, and the linear distance between the vectors is used as a measure of similarity. The closer the distance, the more similar the performance information is. 2. Cosine Similarity The performance data for one or more business items is treated as vectors in a multidimensional space, and the cosine angle between the vectors is used as a measure of similarity. The closer the distance, the more similar the performance information is. In addition, the similarity between performance information can be calculated using Pearson correlation coefficient, Jaccard similarity, Mahalanobis distance, as well as machine learning, deep learning, and other arbitrary artificial intelligence models. Additionally, the control unit 104 of the server 10 may acquire one or more pieces of performance information having a similar tendency or pattern to the first performance data.
[0056] In step S105, the support specifying step executes a step of specifying first accumulated data by referring to accumulated data including the performance data of a second user different from the first user stored in the storing step. Specifically, the accumulated data may include only the past performance information of the first user, or may include the past performance information of a user (a second user) other than the first user. In the present disclosure, by referring to past performance information of other users, it is possible to provide more useful support information to the first user. The control unit 104 of the server 10 searches for items such as the target period of the evaluation table 1014 based on information such as the target period of the performance information included in the first accumulated data, and acquires one or more evaluation data input by an administrator or the like for the first accumulated data. Note that each piece of performance information stored in the performance table 1013 and each piece of evaluation information stored in the evaluation table 1014 may be linked by identification information such as an ID, and the evaluation data (first accumulated data) may be acquired based on the ID or the like. The first accumulated data of the present disclosure may include both performance information and evaluation information.
[0057] In step S106, the control unit 104 of the server 10 executes a prompt generating step of generating a prompt for suggesting improvement measures for the work of the first user, based on the first performance data and the first accumulated data. Specifically, the control unit 104 of the server 10 generates a prompt, which is a command statement for the large-scale language model, using the first result data and the first stored data. An example of a prompt is shown below. 〔prompt〕 #Orders Based on the KPI indicators for User A below, and referring to the past accumulated data A to C, please output information to support User A's work, such as an evaluation and advice on his / her work, and improvement measures. #User A's KPI indicators (first performance data) Number of rounds: Number of new customers acquired: Number of contracts signed: Sales target achievement rate: #Past accumulated data A (first accumulated data) KPI indicator: Target period YMD~YMD Number of rounds: Number of new customers acquired: Number of contracts signed: Sales target achievement rate: Evaluation from my boss: · Relationships with existing customers are good, but developing new customers is an issue The content of the proposal needs to be improved. Need to deepen product knowledge Advice from my boss: Participate in industry events and exhibitions to develop new business. - When preparing a proposal, seek advice from the sales planning department. Participate in our in-house training to deepen your product knowledge #Past accumulated data B... (first accumulated data) #Past accumulated data C···(First accumulated data)
[0058] The prompt generation step executes a prompt generation step that excludes information about the user and customer from the first accumulated data and personal information of the second user from the first accumulated data, and generates a prompt that proposes improvement measures for the first user's business. Specifically, when generating a prompt, the control unit 104 of the server 10 excludes information about users and customers such as the second user, employees, and managers that are related to the performance data and evaluation data contained in the first accumulated data. For example, information about users and customers includes the following information: 1. Personal Information Sales representative's name, contact details, address, date of birth, etc. Name, contact information, job title, etc. of customer representative Personally identifiable information or privacy-related information 2.Customer information -Name, address, contact details of client companies, etc. -Business details, scale, financial status, etc. of client companies -Customer company transaction history, purchase history, contract details, etc. 3. Details of sales activities -Specific business details, proposal details, negotiation process, etc. Information about competitors and sales strategies 4. Confidential information - Your company's sales know-how, unique sales methods, etc. - Detailed specifications and pricing of your products and services Your company's business strategy, business plan, financial information, etc. The control unit 104 of the server 10 deletes, anonymizes, generalizes, or otherwise processes information relating to users and customers from the first accumulated data, and removes the information from the first accumulated data.
[0059] In step S107, the control unit 104 of the server 10 executes a support acquiring step of acquiring first support information including output data that is output by inputting the first accumulated data identified in the support identifying step into the large-scale language model. The support acquisition step acquires first support information including output data outputted by inputting a prompt for proposing improvement measures related to the work of the first user to the large-scale language model based on the first stored data. Specifically, in step S107, the control unit 104 of the server 10 transmits a request including the prompt generated in the prompt generating step of step S106 to a URL such as an API endpoint provided by the large-scale language model 50. The control unit 104 of the server 10 receives a response including output data output by the large-scale language model 50 in response to the request.
[0060] In step S107, a sentence generating step is executed to generate a sentence referring to the achievements of one or more items related to the first user based on the first accumulated data. Specifically, the following output data can be acquired from the large-scale language model 50. The acquired output data includes sentences that mention one or more items (for example, "number of new customers acquired", "number of rounds made"). [Output data (text describing the performance of the item)] Evaluation from your boss: The issue is that the number of new customers we have acquired has not reached our target. Although we have increased the number of visits, this has not resulted in new acquisition. We need to reconsider the content of our proposals when we visit and the method of selecting target customers. Advice from my boss: In order to strengthen new business development, work with the sales planning department to create a list of target customers. Then, prepare proposals tailored to the needs of each target customer and improve the quality of your visits.
[0061] Based on the prompt generated in the prompt generating step of step S106, the first support information shown below can be acquired.
[0062] The support acquiring step acquires first support information including output data outputted by inputting information, obtained by excluding information related to the user and the customer from the first stored data, into the large-scale language model. The accumulated data accumulated for another user (second user) may include information (personal information, etc.) of the other user or customer. It may be undesirable from the viewpoint of privacy or confidential information management to include such individual information in the first support information for the performance data of the first user. Even in such a case, it is possible to prevent information about other users, customer information, and the like from being included in the first support information.
[0063] The support acquiring step acquires first support information including output data outputted by inputting information obtained by excluding personal information of the second user from the first stored data to the large-scale language model. The accumulated data accumulated for another user (second user) may include personal information such as individual information about the second user. It may be undesirable to include such individual information in the first support information for the performance data of the first user from the viewpoint of privacy and confidential information management. Even in such a case, it is possible to prevent the second user's personal information and the like from being included in the first support information.
[0064] In this disclosure, an example in which support information is output from stored data using the large-scale language model 50 has been disclosed as an example, but the present invention is not limited to this. For example, support information may be output by applying stored data to a machine learning model, a deep learning model, or an arbitrary artificial intelligence model.
[0065] In step S107, the control unit 104 of the server 10 stores the first user ID 2011, the prompt generated in step S106, the output data obtained in step S107, and the target period in the user ID, input data, output data, and target period fields of a new record in the prompt table 1015, respectively.
[0066] In step S108, the control unit 104 of the server 10 creates first support information based on the output data output from the large-scale language model acquired in step S107. The first support information may be the output data itself output from the large-scale language model, or may include any information obtained by processing the output data or adding additional information. Specifically, the control unit 104 of the server 10 identifies one or more items mentioned in the output data output from the large-scale language model 50. For example, the control unit 104 of the server 10 identifies performance items such as "the number of new customers acquired" and "the number of times the company makes sales calls." The control unit 104 of the server 10 identifies performance data corresponding to the one or more performance items from the first performance data. Specifically, the control unit 104 of the server 10 identifies performance data including "number of new customers developed: A cases", "number of outside visits: B times", etc. based on the first performance data.
[0067] The control unit 104 of the server 10 executes an indicator drawing step of drawing numerical indicators relating to one or more items mentioned in the sentence generated in the sentence generating step. Specifically, the control unit 104 of the server 10 generates a graph depicting numerical indicators of one or more items mentioned in the output data from the large-scale language model 50, based on the identified first performance information. The graph may be generated in any format, such as png, jpg, svg, etc., or in a data structure such as json.
[0068] In step S109, the control unit 104 of the server 10 executes a support providing step of providing first support information based on the first accumulated data identified in the support identifying step. The support providing step executes a step of providing the first support information acquired in the support acquiring step. Specifically, the server 10 generates a support page and transmits it to the first user terminal 20. The control unit 204 of the first user terminal 20 displays the support page on the display 2081 of the first user terminal 20 and presents it.
[0069] The support presentation step includes a sentence generation step of generating a sentence referring to the achievements of one or more items related to the first user based on the first accumulated data, and an indicator drawing step of drawing a numerical indicator related to the one or more items mentioned in the sentence generated in the sentence generation step, and executes a step of presenting first support information including the sentence generated in the sentence generation step and the numerical indicator drawn in the indicator drawing step. The support providing step executes a step of presenting both the sentence generated in the sentence generating step and the numerical indicator drawn in the indicator drawing step. The indicator drawing step executes a step of drawing numerical indicators for one or more items mentioned in the sentence generated in the sentence generation step, and not drawing numerical indicators for one or more items not mentioned in the sentence generated in the sentence generation step.
[0070] 11 is an example of a support screen in the support process. A support page D1 is displayed on the display 2081 of the first user terminal 20. The support page D1 includes an evaluation report D101, a graph D102 related to the evaluation report D101, and a link D111 to a performance data input page. The evaluation report D101 is an item that displays a sentence based on the output data output from the large-scale language model 50. The graph D102 is an item that displays a graph that depicts, based on the first performance information, numerical indicators of one or more items related to the first performance information. The graph D102 does not need to display all of the first performance information. The graph D102 may be a graph that plots only the numerical indicators of one or more items mentioned in the text displayed in the evaluation report D101 from among the first performance information, and excludes the numerical indicators of items not mentioned in the text displayed in the evaluation report D101. 11, for example, the evaluation report includes the item "number of acquisitions" (D1011). In this case, the graph D102 can display the results of tallying up performance information regarding the number of acquisitions. This allows the user to be presented with a graph depicting numerical indicators of one or more items mentioned in a sentence based on the performance data of the first user. When the performance data includes many items such as behavioral indicators and performance indicators, it is possible to present only graphs related to the items mentioned in the text. This makes it possible to avoid presenting cumbersome information by not displaying graphs of other irrelevant indicators such as many other behavioral indicators and performance indicators.
[0071] In step S109, the control unit 104 of the server 10 stores the first user ID 2011, the created first support information, and the target period in the user ID, support data, and target period items of a new record in the support table 1016, respectively.
[0072] The support information can be presented using any output device 208 of the first user terminal 20. For example, the support information may be presented visually using a display 2081, or a text explaining the content of the support information may be output (presented) from a speaker 2082 using a text reading program or the like. For example, by outputting the support information from the speaker 2082, the first user terminal 20 can provide the support information to an employee or the like related to the first user in a natural manner, similar to an oral interview or oral advice provided by a normal superior or the like.
[0073] <Basic computer hardware configuration> 12 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (interface). These are electrically connected to each other by a communication bus 921.
[0074] The processor 901 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.
[0075] The main memory device 902 is for temporarily storing programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).
[0076] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.
[0077] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks that can connect to the Internet via a specified access point (e.g., Wi-Fi (registered trademark)), etc. In the case of wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. In the case of wired connection, the network also includes a network that is directly connected by a USB (Universal Serial Bus) cable or the like.
[0078] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration among multiple computers 90 and connecting them together via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.
[0079] <Basic functional configuration of computer 90> A description will now be given of the functional configuration of a computer realized by the basic hardware configuration (FIG. 12) of a computer 90. The computer comprises at least the functional units of a control unit, a storage unit, and a communication unit.
[0080] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 connected to each other via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.
[0081] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding the programs in the main storage device 902, and executing processes according to the programs. The control unit can realize functional units that perform various information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.
[0082] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general purpose processors, application specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the functions described. Processors include transistors and other circuits and are considered to be circuitry or processing circuitry. A processor may be a programmed processor that executes a program stored in a memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed in this specification or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.
[0083] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with a program. Furthermore, the control unit can cause the processor 901 to execute processes of adding, updating, and deleting data stored in the storage unit in accordance with the various programs.
[0084] The term database refers to a relational database, which is used to manage sets of data called masters and tables in a tabular format structurally defined by rows and columns, by associating them with each other. In a database, a table is called a table or master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Usually, a column that serves as a primary key for uniquely identifying a record is set in each table and each master, but setting a primary key in a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in a specific table or master stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.
[0085] In addition, the database and master in this disclosure may include any data structure (such as a list, a dictionary, an associative array, or an object) in which information is structurally defined. The data structure also includes data that can be considered as a data structure by combining data with a function, class, method, or the like written in any programming language.
[0086] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.
[0087] <Additional Notes> The matters described in the above embodiments will be supplemented below.
[0088] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, the program comprising: a result receiving step (S101) in which the processor receives input of result data indicating result for each item in a business; a document receiving step (S102) in which the processor receives input of document data for the result data received in the result receiving step from an administrator; a storage step (S102) in which each of the multiple result data received in the result receiving step is associated with the multiple document data received in the document receiving step and stored as accumulated data; a support identification step (S105) in which, based on predetermined first result data indicating the result for each item of a first user, the accumulated data stored in the storage step is referenced to identify first accumulated data including one or more document data; and a support presentation step (S109) in which first support information is presented based on the first accumulated data identified in the support identification step. This makes it possible to present a suitable evaluation report for the performance data of the first user that is based on a document created in the past by an actual person such as a manager, rather than an evaluation report that is simply generated from a template.
[0089] (Appendix 2) The program described in Appendix 1, wherein a processor executes an assistance acquisition step (S107) of acquiring first assistance information including output data that is output by inputting the first accumulated data identified in the assistance identification step into a large-scale language model, and an assistance presentation step (S109) is a step of presenting the first assistance information acquired in the assistance acquisition step. This makes it possible to present a natural evaluation report that looks like one that has actually been created manually, rather than an evaluation report that is simply generated from a template for the performance data of the first user.
[0090] (Appendix 3) The program according to claim 2, wherein the support specifying step (S105) is a step of specifying the first accumulated data by referring to accumulated data including the performance data of a second user different from the first user stored in the storing step. This makes it possible to present a suitable evaluation report based on documents accumulated for users other than the first user, for the performance data of the first user.
[0091] (Appendix 4) The program described in Appendix 3, wherein the support acquisition step (S107) is a step of acquiring first support information including output data output by inputting information excluding information regarding the user and customer from the first accumulated data into a large-scale language model. The accumulated data accumulated for another user (second user) may include information (personal information, etc.) of the other user or customer. It may be undesirable from the viewpoint of privacy or confidential information management to include such individual information in the first support information for the performance data of the first user. Even in such a case, it is possible to prevent information about other users, customer information, and the like from being included in the first support information.
[0092] (Appendix 5) The program described in Appendix 4, wherein the support acquisition step (S107) is a step of acquiring first support information including output data output by inputting information excluding personal information of the second user from the first accumulated data into a large-scale language model. The accumulated data accumulated for another user (second user) may include personal information such as individual information about the second user. It may be undesirable to include such individual information in the first support information for the performance data of the first user from the viewpoint of privacy and confidential information management. Even in such a case, it is possible to prevent the second user's personal information and the like from being included in the first support information.
[0093] (Appendix 6) A program described in any one of Appendices 2 to 5, wherein the support acquisition step (S107) is a step of acquiring first support information including output data that is output by inputting a prompt that suggests improvement measures related to the first user's work into a large-scale language model based on the first accumulated data. This allows the first user to check improvement measures for improving the business.
[0094] (Appendix 7) The support presentation step (S109) includes a sentence generation step of generating a sentence referring to the achievements of one or more items related to the first user based on the first accumulated data, and an indicator drawing step of drawing a numerical indicator related to the one or more items mentioned in the sentence generated in the sentence generation step, and is a step of presenting first support information including the sentence generated in the sentence generation step and the numerical indicator drawn in the indicator drawing step, the program described in Appendix 1. This allows the user to be presented with a graph depicting numerical indicators of one or more items mentioned in a sentence based on the performance data of the first user. When the performance data includes many items such as behavioral indicators and performance indicators, it is possible to present only graphs related to the items mentioned in the text. This makes it possible to avoid presenting cumbersome information by not displaying graphs of other irrelevant indicators such as many other behavioral indicators and performance indicators.
[0095] (Appendix 8) The program according to claim 7, wherein the support providing step (S109) is a step of presenting both the sentence generated in the sentence generating step and the numerical indicator drawn in the indicator drawing step. In this way, by presenting the text together with a graph depicting numerical indicators, the content of the first support information can be more intuitively understood.
[0096] (Appendix 9) The program described in Appendix 7, wherein the indicator drawing step (S109) is a step of drawing numerical indicators for one or more items mentioned in the sentence generated in the sentence generation step, and not drawing numerical indicators for one or more items not mentioned in the sentence generated in the sentence generation step. In this way, by presenting the text together with a graph depicting numerical indicators, the content of the first support information can be more intuitively understood.
[0097] (Appendix 10) A method implemented on a computer having a processor and a memory, the processor performing all of the steps performed in an invention according to any one of appendices 1 to 9. This makes it possible to present a suitable evaluation report for the performance data of the first user that is based on a document created in the past by an actual person such as a manager, rather than an evaluation report that is simply generated from a template.
[0098] (Appendix 11) An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 9. This makes it possible to present a suitable evaluation report for the performance data of the first user that is based on a document created in the past by an actual person such as a manager, rather than an evaluation report that is simply generated from a template.
[0099] (Appendix 12) A system comprising means for performing all the steps performed in any one of the inventions according to appendix 1 to appendix 9. This makes it possible to present a suitable evaluation report for the performance data of the first user that is based on a document created in the past by an actual person such as a manager, rather than an evaluation report that is simply generated from a template. [Explanation of symbols]
[0100] 1 system, 10 server, 101 memory unit, 104 control unit, 106 input device, 108 output device, 20 first user terminal, 201 memory unit, 204 control unit, 206 input device, 208 output device, 30 administrator terminal, 301 memory unit, 304 control unit, 306 input device, 308 output device, 50 large-scale language model, 501 memory unit, 504 control unit, 506 input device, 508 output device
Claims
1. A program to be executed by a computer having a processor and a storage unit, the processor comprising: A result receiving step of receiving input of result data indicating results for each item in a business; a document receiving step of receiving document data relating to evaluation content input from an administrator for the performance data received in the performance receiving step; a storage step of storing the plurality of result data received in the result receiving step as accumulated data in association with the plurality of document data received in the document receiving step; a support specifying step of specifying, from the accumulated data stored in the storage step, first accumulated data including one or more pieces of performance data similar to a predetermined first performance data indicating performance for each item of the first user, and one or more pieces of document data stored in association with the one or more pieces of performance data; a prompt creating step of creating a prompt by including the first accumulated data identified in the assistance identifying step in an instruction to output assistance information based on accumulated data; a support acquisition step of acquiring first support information including output data outputted by inputting the prompt generated in the prompt generation step into a large-scale language model; a support presentation step of presenting the first support information based on the first accumulated data acquired in the support acquisition step,
2. 2. The program according to claim 1, wherein the support specification step specifies the first accumulated data based on the accumulated data including performance data of a second user different from the first user stored in the storage step.
3. 3. The program according to claim 2, wherein the assistance acquisition step is a step of acquiring the first assistance information including output data output by inputting information excluding information about users and customers from the first accumulated data into the large-scale language model.
4. The program according to claim 3, wherein the support acquisition step is a step of acquiring the first support information including output data output by inputting information excluding personal information of the second user from the first accumulated data into the large-scale language model.
5. 2. The program according to claim 1, wherein the prompt creating step creates the prompt by including an instruction for proposing improvement measures for the first user's work in an instruction for outputting support information based on accumulated data.
6. The assistance providing step includes: A sentence generating step of generating a sentence referring to achievements of one or more items related to the first user based on the first accumulated data; an indicator drawing step of identifying the one or more items mentioned in the sentence generated in the sentence generating step and drawing the identified numerical indicators; 2. The program according to claim 1, further comprising a step of presenting the first support information including the sentence generated in the sentence generating step and the numerical indicator drawn in the indicator drawing step.
7. The assistance providing step includes:
7. The program according to claim 6, further comprising a step of presenting both the sentence generated in the sentence generating step and the numerical indicator drawn in the indicator drawing step.
8. The index drawing step includes: plotting numerical indicators relating to the one or more items mentioned in the sentence generated in the sentence generating step; 7. The program according to claim 6, further comprising a step of not drawing numerical indicators relating to the one or more items not mentioned in the sentence generated in the sentence generating step.
9. A method implemented on a computer having a processor and a memory, the processor performing all of the steps performed in any one of claims 1 to 8.
10. 9. An information processing apparatus comprising a control unit and a storage unit, the control unit executing all steps executed in the invention according to any one of claims 1 to 8.
11. A system comprising means for executing all the steps performed in any one of claims 1 to 8.
Citation Information
Patent Citations
Sales activity management system, server device, program and recording medium
JP2004318865A
Organization improvement activity support apparatus, organization improvement activity support method and organization improvement activity support program
JP2015165364A
Sales support system and sales support program
JP2020144642A
JPP7357066B
Cited By
Organization value improvement support apparatus
JP2026091224A
Program, method, information processing apparatus, and system
JP2026093191A
Information processing apparatus, method, and system
JP2026103897A
Sales management system and sales management program
JP2026138942A
system
JP2026155271A
