Information processing system, information processing method and program

Abstract

An information processing system that can reduce the workload of store managers is provided. [Solution] According to one aspect of the present invention, there is provided an information system for supporting store operations, comprising at least one processor, the processor being configured to execute the following steps by reading a program: an acquisition step for acquiring historical information relating to the store's business history; an identification step for identifying the store's standard routine tasks based on the historical information and predetermined reference information; a notification step for notifying a store operator, who is the operator of the store, of confirmation information including whether or not processing corresponding to the identified routine tasks can be performed; and a processing step for executing the processing if the store operator approves the processing.

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a method and device for generating script descriptions that can reduce the burden on administrators by automatically extracting routine tasks from a large number of policy descriptions and converting them into script descriptions, and a method for providing a storage medium that stores a script description generation program. This method extracts policy descriptions with pre-conditions that are activated by a change in the object state that is executed when the post-condition of the policy description is successful, extracts policy descriptions with pre-conditions that are activated by a change in the object state that is executed when the post-condition of the policy description fails, presents policy description flows included in the extracted policy description group to the user after extraction, allows the user to select the policy description flow to be converted into a script description, and generates a script description so as to associate the selected policy description with a subreach in the script description. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-227855 Summary of the Invention [Problem to be solved by the invention]

[0004] Meanwhile, there is a demand for technology that automates routine business processes performed by store managers and further reduces the workload of store managers.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can reduce the workload of store managers. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information system for supporting store operations, the system comprising at least one processor, the processor being configured to execute the following steps by reading a program: an acquisition step for acquiring historical information relating to the store's business history; an identification step for identifying the store's standard routine tasks based on the historical information and predetermined reference information; a notification step for notifying a store operator, who is the operator of the store, of confirmation information including whether or not processing corresponding to the identified routine tasks can be performed; and a processing step for executing the processing if the store operator approves the processing.

[0007] According to this aspect, the workload of the store manager can be further reduced. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1 according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing a hardware configuration of an information processing device 2. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a user terminal 3. [Figure 4] 2 is a functional block diagram showing functions of an information processing device 2 according to an embodiment. FIG. [Figure 5] 2 is a flowchart showing an outline of processing executed by the information processing system 1. [Figure 6] 2 is an activity diagram showing a specific example of processing executed by the information processing system 1. FIG. [Figure 7] 1 shows an example of a shift adjustment screen 5 displayed on the display unit 34 of the user terminal 3. [Figure 8] 1 shows an example of a notification screen 6 displayed on the display unit 34 of the user terminal 3 (store manager terminal). [Figure 9] 1 shows an example of a report screen 7 displayed on the user terminal 3. [Figure 10]1 shows an example of a customer response screen 8 displayed on the user terminal 3. [Figure 11] 1 shows an example of a sales promotion screen 9 displayed on a user terminal 3. DETAILED DESCRIPTION OF THE INVENTION

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

[0010] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously learned the correlation between input and output, or a generative AI such as a large-scale language model (these models include parameters that establish the correlation between input and output) or a visual language model that can output a desired result in response to a prompt.

[0012] In one embodiment, a "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] [Embodiment] 1. Hardware Configuration

[0015] This section explains the hardware configuration.

[0016] 1.1 Information Processing System 1 FIG. 1 is a configuration diagram illustrating an information processing system 1 according to an embodiment. The information processing system 1 includes an information processing device 2 and a user terminal 3, which are connected via a communication network 11. These components will be further described. Here, a system exemplified as the information processing system 1 is made up of one or more devices or components. Therefore, even the information processing device 2 or the user terminal 3 alone is an example of a system. More specifically, the information processing system 1 may include an element selected from the group consisting of the information processing device 2 and the user terminal 3. Furthermore, multiple information processing devices 2 or user terminals 3 may be used. The unselected elements may not be included in the information processing system 1, but may be electrically connected to the selected elements as external elements.

[0017] 1.2 Information processing device 2 2 is a block diagram showing the hardware configuration of the information processing device 2. The information processing device 2 includes a communication bus 20, a communication unit 21, a storage unit 22, and a processor 23. The communication unit 21, the storage unit 22, and the processor 23 are electrically connected via the communication bus 20 inside the information processing device 2.

[0018] <Communications Department 21> The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as needed. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the information processing device 2 may communicate various information from the outside via the communication unit 21 and the network.

[0019] <Storage section 22> The storage unit 22 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the information processing device 2 executed by the processor 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the processor 23.

[0020] <Processor 23> The processor 23 processes and controls the overall operations related to the information processing device 2. The processor 23 is, for example, a central processing unit (CPU) not shown. The processor 23 realizes various functions related to the information processing device 2 by reading out predetermined programs stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23. These will be described in more detail in the next section. Note that the processor 23 is not limited to being single, and multiple processors 23 may be provided for each function. A combination of these may also be used. Furthermore, instead of the processor 23, some or all of these components may be realized by dedicated hardware such as the broadly defined circuit described above.

[0021] 1.3 User terminal 3 3 is a block diagram showing the hardware configuration of the user terminal 3. The user terminal 3 may be in any form, such as a smartphone, a tablet terminal, a computer, or any other device that can access the information processing device 2 via a telecommunications line. The user terminal 3 includes a communication bus 30, a communication unit 31, a storage unit 32, a processor 33, a display unit 34, and an input unit 35. The communication unit 31, the storage unit 32, the processor 33, the display unit 34, and the input unit 35 are electrically connected via the communication bus 30 inside the user terminal 3. The description of the communication unit 31, the storage unit 32, and the processor 33 is omitted here, as they are the same as the descriptions of the respective units in the information processing device 2.

[0022] <Display section 34> The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. The display unit 34 may be included in the housing of the user terminal 3 or may be externally attached. Specifically, the display unit 34 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them depending on the type of the user terminal 3.

[0023] <Input section 35> The input unit 35 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the processor 33 via the communication bus 30. The processor 33 can execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 35 may be included in the housing of the user terminal 3 or may be externally attached. For example, the input unit 35 may be implemented as a touch panel integrated with the display unit 34. When the input unit 35 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 35. Instead of a touch panel, the input unit 35 may be implemented as a switch button, a mouse, a QWERTY keyboard, etc. Furthermore, the input unit 35 is not limited to the above-mentioned input operations by contact, and may also be implemented as equipment that accepts audio input from a microphone, etc.

[0024] 2. Functional configuration In this section, the functional configuration will be described. Fig. 4 is a functional block diagram showing the functions of the information processing device 2. As shown in Fig. 4, the processor 23 executes various programs stored in the storage unit 22, thereby functioning as an acquisition unit 231, an identification unit 232, a notification unit 233, a processing unit 234, a calculation unit 235, a reception unit 236, and a display control unit 237. In other words, information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23.

[0025] The acquisition unit 231 is configured to acquire various information as an acquisition step. Specifically, the acquisition unit 231 is configured to acquire information via the communication unit 21 or the storage unit 22 and read the information into the working memory. Preferably, the acquisition unit 231 acquires history information IF1 related to the business history of the store as an acquisition step. Details will be described later.

[0026] The identification unit 232 is configured to identify various information as an identification step. Preferably, the identification unit 232 identifies a typical routine operation of the store based on the history information IF1 and predetermined reference information as an identification step. Details will be described later.

[0027] The notification unit 233 is configured to notify various information as a notification step. Preferably, the notification unit 233 notifies the store manager, who is the manager of the store, of confirmation information IF2 including whether or not the process corresponding to the identified routine task can be executed. Details will be described later.

[0028] The processing unit 234 is configured to execute various information processes as processing steps. Preferably, the processing is executed when the store manager approves the execution of the processing. Also preferably, as a processing step, the processing unit 234 inputs at least a portion of the history information IF1 into an artificial intelligence module, causing the artificial intelligence module to generate a sentence TX corresponding to the routine task. Details will be described later.

[0029] Here, we will provide some additional information about the artificial intelligence module. The artificial intelligence module is an AI (Artificial Intelligence) equipped with a learning model such as a language model or a recurrent neural network (RNN) or a transformer including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, GPT-4, and GPT-4o), BERT (Bidirectional Encoder Representations from Transformers), and BART (Bidirectional and Auto-regressive Transformer), and may be a generative AI or an AI agent.

[0030] A language model is an example of a learning model based on a machine learning algorithm. Specific machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence module can apply the above algorithms as appropriate.

[0031] The artificial intelligence module may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of pairs of input data for learning and output data (correct answer data). In addition, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0032] The artificial intelligence module may be a natural language model or may include a general-purpose natural language processing trained model such as a large-scale language model (LLM). An LLM is a learning model that has previously trained a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). It can perform various language processing tasks when given a task. It can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, answering questions, and generating sentences, according to given prompts. Such a general-purpose learning model may include a language model that can handle various tasks without fine-tuning, using one-shot learning or few-shot learning. Furthermore, a general-purpose learning model can also handle various tasks using zero-shot learning. The artificial intelligence used in each functional unit of the processor 23 may be a separate learning model or a common general-purpose learning model. A large-scale language model is a type of generative AI and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. Additionally, the artificial intelligence module may include any machine learning model, deep learning model, artificial intelligence model, etc. The artificial intelligence module may be constructed in a system external to the information processing system 1. Furthermore, the artificial intelligence module may be of an interactive type (which may be interpreted as a chat type or a conversation type) that alternately receives input to perform instructed output and generates and outputs information.

[0033] The learning model included in the artificial intelligence module can undergo additional learning using techniques such as transfer learning or fine tuning. For example, the artificial intelligence module learns whether the output content has been modified by a user or the like. That is, the artificial intelligence module may perform additional learning and fine tuning based on modifications to the content output by the learning model. Also, for example, each time new data is registered, the artificial intelligence module may perform additional learning and fine tuning using the new data as new training data. This improves the accuracy of the information output from the learning model.

[0034] The learning model included in the artificial intelligence module may be a learning model (distilled model) obtained by knowledge distillation using an original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model (distilled model) are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby training the student model, which becomes the distilled model. Alternatively, the student model may be trained to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model). Compared to the original trained model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the trained model. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0035] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the learning model used in each functional unit, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the learning model used in each functional unit.

[0036] AI agents may also be called autonomous agents. An "AI agent" is a model that, when given a goal (purpose, objective, etc.) such as "teach me XX" or a task such as "output XX," breaks down the processing required to reach the goal or accomplish the task into subtasks, actions, etc., and performs tasks such as collecting and analyzing necessary data, generating and executing programs, etc. AI agents target information and instructions input by a user, autonomously select and execute tasks and actions according to the goal, and output information according to the goal, without requiring user intervention (operational input). AI agents may also autonomously learn to achieve their goals by autonomously creating and executing plans and evaluating the results. For example, an AI agent may be autonomously updated based on the results of subtask execution (e.g., collected information, information analysis results, etc.).

[0037] The calculation unit 235 is configured to execute various information processing calculations related to the information processing device 2. The type of calculation is not important.

[0038] The receiving unit 236 is configured to receive various information or inputs. Specifically, the receiving unit 236 is configured to receive information via the communication unit 21 or the storage unit 22 and to be able to read this information into the working memory.

[0039] As a display control step, the display control unit 237 executes processing for displaying various pieces of information on a display medium in a manner recognizable to a user. When the phrase "display" is used, it does not matter whether the display medium to be displayed is in a local environment or whether the processing for displaying is performed via the communication network 11. As a result of processing by the display control unit 235, various pieces of information are presented to various users operating, for example, the user terminal 3 via the display unit 34. The presented various pieces of information are visual information such as screens, images, icons, and messages. The display control unit 235 may generate the visual information itself, or may generate only rendering information for displaying the visual information on the display unit 34.

[0040] 3. Information Processing Method This section describes an information processing method executed by the information processing system 1. Note that the order of processes included in the information processing method can be changed as appropriate, multiple processes may be executed simultaneously, or some processes may be omitted.

[0041] 3.1 Overview As described above, the information processing system 1 is an information system for supporting store operations. The information processing system 1 also includes at least one processor 23, which includes the following units by reading a program. In other words, the information processing method includes the steps of the information processing system 1 described below. From another perspective, the program causes at least one computer to execute the steps of the information processing system 1 described below. Figure 5 is a flowchart showing an overview of the processing executed by the information processing system 1. Each step shown in Figure 5 will be described below.

[0042] First, the acquisition unit 231 acquires history information IF1 relating to the business history of the store (S001). The identification unit 232 identifies the typical routine tasks of the store based on the history information IF1 and predetermined reference information (S002). The notification unit 233 notifies the store manager, who is the operator of the store, of confirmation information IF2 including whether or not the process corresponding to the identified routine task can be executed (S003). The processing unit 234 executes the process when the store manager approves that the process be executed (S004). According to this embodiment, the typical business process that the store manager has manually executed each time can be automated based on the history information IF1, thereby reducing the workload of the store manager.

[0043] 3.2 Specific examples Specific examples may fall within the scope specified in the overview above. In the specific example, the following situation is assumed. First, an administrator who manages the information processing device 2 provides a service (hereinafter referred to as the service) that supports store operations to users via the Internet. The service is introduced in various stores and used by store managers and employees working at the stores. The service is a type of SaaS that uses a website (hereinafter referred to as the specific site) provided by the information processing device 2. Note that the specific site may be accessed using an Internet browser or a dedicated app.

[0044] Furthermore, in the process according to the specific example, at least one large-scale language model M (corresponding to the artificial intelligence module described above) may be used as an example of reference information. A common large-scale language model M tuned for various processes may be employed, or a different large-scale language model M may be employed by tuning it specifically for each process. The following description will be given using as an example a store where a store manager and employees work.

[0045] It is preferable that the attendance records and perks (described in detail later) of employees working at the store are managed by the information processing system 1. Specifically, the storage unit 22 of the information processing device 2 stores a database DB that stores attendance records, perks granted status, performance data, etc.

[0046] 6 is an activity diagram showing a specific example of processing executed by the information processing system 1. Below, an explanation will be given along with each activity shown in FIG.

[0047] First, the process from when the acquisition unit 231 acquires history information IF1 to when the processing unit 234 executes processing, i.e., the process related to activities A101 to A112, will be described. First, as an acquisition step, the acquisition unit 231 acquires history information IF1, which is various histories related to store operations stored in the storage unit 22 (activity A101). The history information IF1 may include, for example, shift information IF11, performance information IF12, request information IF13, and sales promotion information IF14, but is not limited to these. For example, the history information IF1 may further include chat histories between the store manager and employees, chat histories between the store manager and customers, etc. In one embodiment, as an example, the description will be given assuming that shift information IF11 and chat histories between the store manager and employees are acquired from the history information IF1.

[0048] Next, the calculation unit 235 analyzes the acquired shift information IF11 (activity A102). Specifically, the calculation unit 235 inputs the shift information IF11 into a large-scale language model M tuned for analysis, and outputs the analysis results to the large-scale language model M. The shift information includes information about employee work shifts at the store. Specifically, for example, the shift information may include an employee ID, a responsibility classification, a shift time frame, a shift confirmation status, the employee's desired shift, comments for adjusting the shift, and the number of working hours. Next, based on the analysis of the shift information IF11, the identification unit 232 identifies employee vacancy dates and candidate employees who can fill the vacancies (activity A103). Hereinafter, candidate employees who can fill the vacancies may be simply referred to as "candidates." As a result, the identification unit 232 identifies the shift request as a routine task as an identification step (activity A104).

[0049] In other words, the identification unit 232 inputs the history information IF1 into a predetermined large-scale language model M (an example of reference information) to identify the shift request as a routine task.

[0050] Next, the notification unit 233 sends a notification including the specific status of the routine task and whether or not the shift request can be automated to the user terminal 3 (manager terminal) via the communication unit 21 and the communication network 11 (activity A105). That is, the display control unit 237 displays a notification screen 6 (see FIG. 8) on the display unit 34 in a manner that can be viewed by the store manager. Details of the notification screen 6 will be described later.

[0051] Next, the store manager inputs an input regarding consent to the automation of the shift request via the input unit 35 of the user terminal 3 (store manager terminal) (activity A106). The input regarding consent to the automation is sent to the communication unit 21 via the communication unit 31 and the communication network 11. If the store manager does not consent to the automation, the calculation unit 235 ends the processing. If the store manager consents to the automation, the processing proceeds to activity A108 (activity A107).

[0052] Next, the processing unit 234 inputs the information on the vacant date and the candidate identified in activity A103 into the large-scale language model M tuned for shift adjustment (activity A108). In addition to the information on the vacant date and the candidate, the processing unit 234 may input, for example, a predetermined prompt into the large-scale language model M. As a result, the processing unit 234 causes the large-scale language model M to generate a sentence TX urging the candidate to come to work (activity A109).

[0053] In this way, the history information IF1, including the shift information IF11, includes the history of the work the store manager has performed in running the store. By having the large-scale language model M analyze the history information IF1, including this history, routine work can be identified. Routine work can be identified based on whether the history information IF1 indicates that the work has been performed repeatedly (e.g., periodically or periodically) in the past. In addition to shift adjustment, other tasks, such as the store manager's request for reorganizing shelves every Wednesday and the history of performance reports submitted at the end of each month, can also be extracted as typical work patterns. In other words, the processing unit 234 inputs at least a portion of the history information IF1 into the large-scale language model M as a processing step, causing the large-scale language model M to generate text TX corresponding to routine work (e.g., shift adjustment). According to this embodiment, text TX corresponding to routine work can be automatically generated by the large-scale language model M, allowing the store manager to accurately and quickly create text related to the work, regardless of the store manager's expressiveness or writing ability.

[0054] Returning to the explanation of the processing, the notification unit 233 transmits a notification including a text TX urging the employee to come to work to the user terminal 3 (employee terminal) via the communication unit 21 and the communication network 11. When the user terminal 3 (employee terminal) receives the notification including the text TX urging the employee to come to work, the notification including the text TX urging the employee to come to work is displayed on the display unit 34 (activity A110). Specifically, for example, the notification including the text TX urging the employee to come to work may be displayed in a chat format as shown on the shift adjustment screen 5 (see FIG. 7). Details of the shift adjustment screen 5 will be described later.

[0055] Next, the candidate inputs a response to the text TX urging the candidate to come to work via the input unit 35 of the user terminal 3 (employee terminal) (activity A111). The response input is transmitted to the communication unit 21 via the communication unit 31 and the communication network 11.

[0056] Next, when the reception unit 236 receives the candidate's response input, the processing unit 234 adjusts the shift based on the response (activity A112). The response input may be, for example, a text response via a chat tool. More specifically, the processing unit 234 inputs the response input into a large-scale language model M tuned for shift adjustments and extracts information from the response input necessary to make adjustments to fill vacant days in the shift. Based on the extracted information, the processing unit 234 executes an update process for the shift information IF11. If the candidate's response input does not contain sufficient information to update the shift information IF11, the processing unit 234 may further generate a sentence TX for additional confirmation in the large-scale language model M. In such a case, the notification unit 233 sends a notification including the sentence TX for additional confirmation to the user terminal 3 (employee terminal) via the communication unit 21 and the communication network 11.

[0057] If the processing of activities A108 to A112 does not complete filling of vacant days, the processing of activities A108 to A112 continues. A case in which filling of vacant days is not completed occurs when a candidate's response alone is not enough to completely fill the vacant hours. More specifically, this can occur when a candidate declines to work despite a notification containing a sentence TX urging them to work, or when a candidate's scheduled work days alone still leave vacant hours. In other words, the history information IF1 includes shift information IF11 related to employee work shifts at the store. Routine tasks include work related to work shift management. As a processing step, the processing unit 234 inputs the shift information IF11 into the large-scale language model M, causing the large-scale language model M to generate a sentence TX requesting at least one employee to adjust their work shift. This embodiment can support the adjustment of employee work shifts using the large-scale language model M, reducing the burden on store managers and enabling rapid staffing.

[0058] After the shift adjustment is completed, the candidate will come to work according to the adjusted shift. The reception unit 236 accepts the employee's work to fill the vacant day (activity A113). In response to the acceptance of the employee's work, the calculation unit 235 updates the database DB in which the attendance history stored in the memory unit 22 is stored. At this time, it is preferable that the system be set so that a special benefit is granted if the work style satisfies predetermined conditions. In such a case, the identification unit 232 identifies the granting of a special benefit as a routine task as an identification step (activity A114).

[0059] Next, the process from the notification unit 233 sending a notification including the routine task identification status and whether or not it can be automated until the processing unit 234 grants a reward, i.e., the process related to activities A115 to A118, will be described. In one embodiment, as an example of a routine task in which a store manager grants rewards to store employees, a case will be described in which a task of granting rewards to employees who fill in for vacant staff is identified as a routine task. Of course, this is not limited to this. In addition, rewards may include in-house points, gift certificates, discount coupons, electronic money, additional compensation, badges / titles, additional employee benefits, etc.

[0060] The notification unit 233 sends a notification including the specific status of the routine task and whether or not the shift request can be automated to the user terminal 3 (manager terminal) via the communication unit 21 and the communication network 11 (activity A115). That is, the display control unit 237 displays a notification screen 6 (see FIG. 8) on the display unit 34 in a manner that can be viewed by the store manager. Details of the notification screen 6 will be described later.

[0061] Next, the store manager inputs an input regarding consent to the automation of the work of granting benefits to employees who fill in on vacant days via the input unit 35 of the user terminal 3 (activity A116). The input regarding consent to the automation is sent to the communication unit 21 via the communication unit 31 and the communication network 11. If the store manager does not consent to the automation, the calculation unit 235 ends the processing. If the store manager consents to the automation of shift requests, the processing proceeds to activity A118 (activity A117).

[0062] Next, the processing unit 234 grants a perk to the employee who filled in for the vacant day (activity A118). Specifically, the processing unit 234 updates the database DB that stores the grant status of the perk. Furthermore, the notification unit 233 sends a notification including the updated grant status of the perk to the user terminal 3 (employee terminal) via the communication unit 21 and the communication network 11. The perk may be granted to an employee who meets a predetermined condition. For example, the perk may be granted to an employee who meets a condition such as coming to work to fill a vacant day, coming to help at another store, continuously achieving no lateness or absence, contributing to training new employees, obtaining skill certification, or achieving a store goal. In other words, the routine work includes a task performed by the store manager (an example of a store operator) to grant a perk (e.g., additional compensation) to an employee of the store. As a processing step, the processing unit 234 grants a perk to an employee who meets the condition. According to this embodiment, it is possible to automate the process of awarding rewards to store employees for their contributions, thereby improving the motivation of store employees and maintaining and strengthening the engagement of the entire store.

[0063] The above is the flow of information processing according to the specific example.

[0064] 4. Related technical matters The following describes in detail technical matters related to the above-mentioned information processing method.

[0065] (Shift adjustment screen 5) 7 shows an example of the shift adjustment screen 5 displayed on the display unit 34 of the user terminal 3. The shift adjustment screen 5 includes sentences 51-55.

[0066] Sentences 51 to 53 are an example of a dialogue between a sentence TX urging attendance included in a notification sent to the user terminal 3 (employee terminal) and a reply message MS to the sentence TX urging attendance entered by the candidate. Sentence 51 is an example of a sentence TX urging attendance generated in activity A109. Sentence 51 contains an example of a sentence TX urging employee A to come to work "July 1st, 13:00-17:00." Sentence 52 is an example of a candidate's reply message MS entered in activity A111. Sentence 52 contains a message MS indicating that employee A declines to come to work in response to the sentence TX urging employee A to come to work. In this case, filling the vacant day is not completed, so the processing of activities 108 to A112 is executed again. Sentence 53 is an example of a reply to the reply message MS entered by the candidate, generated in the large-scale language model M.

[0067] Sentences 54-55 are an example of a dialogue that occurs when the processing of activities A108-A112 is executed again and as a result, all candidates are unable to complete filling the vacant days. In such a case, the vacant days, the candidates, and the candidates' responses can be input into the large-scale language model M to generate a sentence TX urging an employee who has once refused to come to work to come to work again. Sentence 54 is an example of a sentence TX urging an employee who has once refused to come to work, which is included in a notification sent to the user terminal 3 (employee terminal). Sentence 54 is an example of a message MS in response to a sentence TX urging an employee who has once refused to come to work to come to work again, entered by a candidate who has once refused to come to work.

[0068] (Notification screen 6) 8 shows an example of a notification screen 6 displayed on the display unit 34 of the user terminal 3 (manager terminal). The notification screen 6 includes an area 61, a check box 62, a button 63, and a button 64.

[0069] Area 61 is an area where the specific status of the routine task, whether automation is possible, and a check box 62 are displayed. Area 61 displays text information such as "Shift request has been identified as a routine task" as an example of a notification of the specific status of the routine task. Also, area 61 displays text information such as "Do you want to automate the shift request?" as an example of a notification of whether automation is possible.

[0070] Check box 62 is a check box that accepts a selection of whether or not to notify again of the specified status of the routine task and whether or not it can be automated after the display of notification screen 6. If check box 62 is selected by the store manager via the input unit 35 of the user terminal 3 (store manager terminal), the notification unit 233 will not again send a notification including the specified status of the routine task and whether or not it can be automated, which has been notified once. On the other hand, if check box 62 is not selected by the store manager via the input unit 35 of the user terminal 3 (store manager terminal), the notification unit 233 will send a notification including the specified status of the routine task and whether or not it can be automated each time a routine task is identified.

[0071] Button 63 is a button for not automating routine tasks. When button 63 is pressed, the automation is not approved by the store manager, and the calculation unit 235 ends the processing. Button 64 is a button for automating routine tasks. When button 63 is pressed, the automation is approved by the store manager, and the calculation unit 235 continues the processing.

[0072] (Report screen 7) 9 shows an example of the report screen 7 displayed on the user terminal 3. The report screen 7 includes an area 71, a button 72, and a button 73.

[0073] Area 71 depicts a performance report generated by a large-scale language model M tuned for report creation. The calculation unit 235 sequentially updates a database DB in which data related to performance is stored. The calculation unit 235 may extract performance data required for creating the performance report from the database DB in bulk for each specified period. In such a case, the identification unit 232 identifies the task of creating a store performance report as a routine task. Note that the data related to performance may include total sales amount, average customer spending, new / repeater customer ratio, customer satisfaction, number of complaints, etc.

[0074] Similar to activities A108 and A109, the processing unit 234 inputs performance data into the large-scale language model M, causing the large-scale language model M to generate a performance report. In other words, the history information IF1 includes performance information IF12 related to the store's performance. The routine tasks include the task of creating a report related to the store's performance. As a processing step, the processing unit 234 inputs the performance information IF12 into the large-scale language model M, causing the large-scale language model M to generate a report. According to this embodiment, the task of reporting on store performance can be automated using the large-scale language model M, reducing the time and effort required to create reports and also standardizing the content of the reports.

[0075] Button 72 is a button for editing the report. Pressing button 72 may, for example, transition to a screen (not shown) on which the generated performance report can be edited. Button 73 is a button for sending the performance report. Pressing button 73 may, for example, transition to a screen (not shown) on which the performance report can be sent by email.

[0076] (Customer response screen 8) 10 shows an example of the customer response screen 8 displayed on the user terminal 3. The customer response screen 8 includes sentences 81-83.

[0077] Sentence 81 is an example of a message MS of a request to the store input by a customer. Sentence 82 is an example of a sentence TX in response to the request, generated by the large-scale language model M. Sentence 83 is an example of a message MS of a reply from the customer to the sentence TX, received by the user terminal 3. As shown in FIG. 10, the display unit 34 may display the message MS of the request received from the customer and the sentence TX in response from the large-scale language model M in a chat format. Sentences 81 to 83 are examples of information included in request information IF13 regarding a request from a customer to the store. Furthermore, as described above, history information IF1 includes request information IF13.

[0078] Even in this case, the identification unit 232 identifies the customer service task as a routine task, similar to activity A104. Next, similar to activities A108 and A109, the processing unit 234 inputs the request information IF13 into the large-scale language model M, thereby causing the large-scale language model M to generate a response sentence TX to the request. In other words, the history information IF1 includes request information IF13 related to a request from a customer to the store. Routine tasks include customer service tasks. As a processing step, the processing unit 234 inputs the request information IF13 into the large-scale language model M, thereby causing the large-scale language model M to generate a response sentence TX corresponding to the request. According to this aspect, a response sentence to a customer request can be automatically generated, enabling timely and accurate customer service that store managers often overlook.

[0079] (Promotional screen 9) 11 shows an example of a sales promotion screen 9 displayed on the user terminal 3. The sales promotion screen 9 includes sentences 91-93.

[0080] Sentence 91 is an example of a promotional communication to a customer, generated by the large-scale language model M. Sentence 92 is an example of a response message MS to the promotional communication input by the customer. Sentence 93 is an example of a reply message TX to the response message MS, generated by the large-scale language model M. As shown in FIG. 11, the display unit 34 may display the message MS received from the customer and the message TX from the large-scale language model M in a chat format. Sentences 81 to 83 are examples of information included in request information IF13 related to requests from customers to the store. As mentioned above, history information IF1 includes request information IF13.

[0081] Even in this case, the identification unit 232 identifies the customer service task of contacting customers regarding sales promotion activities as a routine task, similar to activity A104. Next, the processing unit 234 inputs the sales promotion information IF14 into the large-scale language model M, similar to activities A108 and A109, to generate a communication sentence TX in the large-scale language model M. In other words, the history information IF1 includes the sales promotion information IF14 related to sales promotion activities for customers. Routine tasks include tasks of contacting customers regarding sales promotion activities. As a processing step, the processing unit 234 inputs the sales promotion information IF14 into the large-scale language model M, to generate a communication sentence TX in the large-scale language model M. According to this embodiment, periodic communications based on past sales promotion history can be automatically generated, thereby realizing continuous approaches to customers while reducing the burden on the store operator.

[0082] [others] The information processing system 1 according to the above embodiment may be configured as follows.

[0083] At least one of the devices included in the information processing system 1 may be installed outside Japan. For example, the information processing device 2 or the server may be installed outside Japan, and the user terminal 3 may be installed inside Japan. Similarly, a store manager and employees may access the information processing device 2 installed inside Japan from outside Japan using their own user terminal 3. According to such an embodiment, a more convenient experience can be provided to users through various management modes.

[0084] In one embodiment, the acquisition unit 231, the identification unit 232, the notification unit 233, the processing unit 234, the calculation unit 235, the reception unit 236, and the display control unit 237 are described as functional units implemented by the processor 23 of the information processing device 2, but at least some of these may be implemented as functional units implemented by another server. Alternatively, they may be implemented as functional units implemented by the processor 33 of the user terminal 3. Furthermore, the various pieces of information described in the above example may be stored not only in the storage unit 22 of the information processing device 2, but also in a distributed manner in other external devices.

[0085] Furthermore, it may be provided in the following aspects.

[0086] (1) An information system for supporting store operations, comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: an acquisition step acquiring historical information relating to the store's business history; an identification step identifying the store's standard routine tasks based on the historical information and predetermined reference information; a notification step notifying a store operator, who is the operator of the store, of confirmation information including whether or not processing corresponding to the identified routine tasks can be performed; and a processing step executing the processing if the store operator approves the processing.

[0087] According to this embodiment, routine business processes that have been manually performed by store managers each time can be automated based on historical information, thereby reducing the workload of store managers.

[0088] (2) In the information processing system described in (1) above, the reference information is a large-scale language model, and in the processing step, at least a portion of the history information is input into the large-scale language model, thereby causing the large-scale language model to generate sentences corresponding to the routine tasks.

[0089] According to this embodiment, sentences corresponding to routine business operations can be automatically generated using a large-scale language model, and business-related sentences can be created accurately and quickly without relying on the expressiveness or writing ability of the store manager.

[0090] (3) In the information processing system described in (2) above, the historical information includes shift information regarding work shifts of employees at the store, the routine tasks include tasks related to managing the work shifts, and in the processing step, the shift information is input into the large-scale language model, causing the large-scale language model to generate a sentence requesting at least one of the employees to adjust the work shift.

[0091] According to this embodiment, the adjustment work related to employee work shifts can be supported by a large-scale language model, reducing the burden of adjustment work on the store manager and enabling rapid personnel deployment.

[0092] (4) In the information processing system described in (2) or (3) above, the historical information includes performance information regarding the store's performance, the routine work includes the work of creating a report regarding the store's performance, and in the processing step, the performance information is input into the large-scale language model, causing the large-scale language model to generate the report.

[0093] According to this embodiment, the reporting process regarding store performance can be automated using a large-scale language model, reducing the time and effort required to create reports and also standardizing the content of the reports.

[0094] (5) In the information processing system described in any one of (2) to (4) above, the history information includes request information regarding requests from customers to the store, the routine work includes customer service work, and in the processing step, the request information is input into the large-scale language model, causing the large-scale language model to generate a response sentence corresponding to the request.

[0095] According to this embodiment, a response to a customer request can be automatically generated, enabling timely and accurate customer service that store managers tend to overlook.

[0096] (6) In the information processing system described in any one of (2) to (5) above, the history information includes sales promotion information related to sales promotion activities for customers, the routine work includes work of contacting the customers regarding the sales promotion activities, and in the processing step, the sales promotion information is input into the large-scale language model, causing the large-scale language model to generate the contact text.

[0097] According to this embodiment, it is possible to automatically generate regular contact based on past sales promotion history, thereby realizing continuous approaches to customers while reducing the burden on store managers.

[0098] (7) In the information processing system described in any one of (1) to (6) above, the routine work includes the work of the store manager granting benefits to employees of the store, and in the processing step, the system grants the benefits to the employees who meet the conditions.

[0099] According to this embodiment, it is possible to automate the process of awarding rewards to store employees for their contributions, thereby improving the motivation of store employees and maintaining and strengthening the engagement of the entire store.

[0100] (8) An information processing method, comprising the steps of the information processing system according to any one of (1) to (7) above.

[0101] According to this aspect, the technology according to one embodiment can be provided as a method.

[0102] (9) An information processing program that causes at least one computer to execute each step of the information processing system according to any one of (1) to (7) above.

[0103] According to this aspect, the technology according to one embodiment can be provided as a program. Of course, this is not the case.

[0104] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0105] 1: Information processing system 11: Communication Network 2: Information processing equipment 20: Communication bus 21: Communications Department 22: Storage section 23: Processor 231: Acquisition Department 232: Specific part 233: Notification Department 234: Processing section 235: Arithmetic section 236: Reception 237: Display control section 3: User terminal 30: Communication bus 31: Communications Department 32: Storage section 33: Processor 34:Display section 35: Input section 5: Shift adjustment screen 51: Sentence 52: Sentence 53: Sentence 6: Notification screen 61 :Area 62: Checkbox 63: Button 64: Button 7:Report screen 71 :Area 72: Button 73: Button 8: Customer response screen 81: Sentence 82: Sentence 83: Sentence 9: Promotional screen 91: Sentence 92: Sentence 93: Sentence IF1: History information IF11: Shift information IF12: Performance Information IF13: Request Information IF14: Promotional Information IF2: Confirmation information M: Large-scale language model MS: Message TX:Text

Claims

1. An information processing system for supporting store operations, At least one processor is provided, the processor being configured to execute the following steps by reading a program: In the acquisition step, history information regarding a work history in a real space performed by a store manager who is a manager of the store or an employee of the store is acquired; In the identification step, a prompt including the history information and an instruction to identify a typical routine task in the real space of the store using the history information as an input is input to a large-scale language model, and the large-scale language model is caused to identify the routine task; In the notification step, confirmation information for confirming whether or not to permit execution of the process corresponding to the specified routine task is notified to a store manager who is a manager of the store; In the processing step, the system executes the processing when permission to execute the processing is received from the store manager in response to the notified confirmation information.

2. 2. The information processing system according to claim 1, In the processing step, a prompt including at least a portion of the historical information and an instruction to generate a sentence corresponding to the routine task using at least a portion of the historical information as input is input to the large-scale language model, and the sentence is generated by the large-scale language model.

3. 3. The information processing system according to claim 2, The history information includes shift information regarding the employee's work shifts, The routine work includes work related to managing the work shift, In the processing step, a prompt including the shift information and an instruction to generate a sentence using the shift information as input to request at least one employee to adjust the work shift is input to the large-scale language model, and the sentence is generated by the large-scale language model.

4. 3. The information processing system according to claim 2, The history information includes performance information regarding the performance of the store, The routine tasks include preparing reports on the store's performance; In the processing step, the system causes the large-scale language model to generate the report by inputting a prompt to the large-scale language model, the prompt including the performance information and an instruction to generate the report using the performance information as input.

5. 3. The information processing system according to claim 2, The history information includes request information regarding requests from customers to the store, the routine work includes a service work of serving the customer, In the processing step, a prompt including the request information and an instruction to generate a response sentence corresponding to the request using the request information as input is input to the large-scale language model, and the sentence is generated by the large-scale language model.

6. 3. The information processing system according to claim 2, The history information includes sales promotion information regarding sales promotion activities for customers, the routine tasks include a task of contacting the customer regarding the sales promotion activity; The processing step includes inputting a prompt including the promotional information and instructions for generating the communication sentence using the promotional information as input to the large-scale language model, and causing the large-scale language model to generate the sentence.

7. 2. The information processing system according to claim 1, The routine work includes a work in which the store manager grants a benefit to the employee who satisfies a predetermined condition, In a second identification step, the employee who satisfies the condition is identified from the history information; In the processing step, the system executes a process of granting the benefit to the employee.

8. An information processing method, comprising: A method in which a processor executes each step of the information processing system according to any one of claims 1 to 7.

9. An information processing program, A program causing at least one computer to execute each step of the information processing system according to any one of claims 1 to 7.

Images