Information processing device, information processing method and information processing program

Abstract

To perform issue discovery work of an EC store and proposal of solution means more appropriately.SOLUTION: An information processing device comprises: an identification unit which identifies an index with issues by comparing the index with that of a competitor; a management unit which manages pairs of past issues and measures for the issues; a similarity determination unit which determines the past issues similar to the issues based on the identified index; a generation unit which generates the measures for the issues based on the identified index, from the measures for similar past issues; and a provision unit which provides the measures for the issues based on the identified index.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] A technology has been disclosed that evaluates the effectiveness and risks of business design by reflecting the business environment, which changes daily, and proposes appropriate business measures according to the situation (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-122814 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is room for improvement in the above-mentioned conventional techniques. For example, the above-mentioned conventional techniques make it difficult to identify problems in e-commerce stores and propose solutions. Therefore, there is a need for a method for more appropriately identifying problems in e-commerce stores and proposing solutions.

[0005] The present application has been made in consideration of the above, and aims to more appropriately identify problems in EC stores and propose solutions. [Means for solving the problem]

[0006] The information processing device according to the present application is characterized by comprising an identification unit that identifies problematic indicators by comparing the indicators with competitors, a management unit that manages pairs of past issues and solutions for the issues, a similarity determination unit that determines past issues that are similar to issues based on the identified indicators, a generation unit that generates solutions for issues based on the identified indicators from solutions for similar past issues, and a provision unit that provides solutions for issues based on the identified indicators. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to more appropriately identify problems in an EC store and propose solutions. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram showing an overview of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of a server device according to the embodiment. [Figure 4] FIG. 4 is a flowchart showing a processing procedure according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] [1. Overview of the information processing system] First, an overview of an information processing system according to an embodiment will be described with reference to Fig. 1. Fig. 1 is an explanatory diagram showing an overview of an information processing system according to an embodiment. As shown in Fig. 1, an information processing system 1 according to an embodiment includes a terminal device 10 and a server device 100. These various devices are connected to each other via a network N in a wired or wireless manner so as to be able to communicate with each other. This enables the terminal device 10 to cooperate with the server device 100. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

[0011] Terminal device 10 is an information processing device used by a user U. For example, terminal device 10 may be a smart device such as a smartphone or tablet terminal, a mobile phone such as a feature phone (Gala-ke or Gala-ho), a personal computer (PC), a personal digital assistant (PDA), a game console or AV device with communication functions, an information appliance or digital appliance, a car navigation system, a wearable device such as a smart watch, a head-mounted display, or smart glasses. Terminal device 10 may also be a house or building, a car, a home appliance, an electronic device, or the like that is compatible with the Internet of Things (IOT).

[0012] In this embodiment, the terminal device 10 is a smart device such as a smartphone or tablet terminal used by a user U, and is a mobile terminal device capable of communicating with any server device via a wireless communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: fifth generation mobile communication system). The terminal device 10 has a screen such as a liquid crystal display with a touch panel function, and accepts various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by the user U with a finger or a stylus. Note that an operation performed on an area of ​​the screen where content is displayed may be considered an operation on the content. The terminal device 10 may be not only a smart device, but also an information processing device such as a desktop PC (Personal Computer) or a notebook PC.

[0013] In addition, the terminal device 10 can connect to the network N via a wireless communication network such as LTE, 4G, or 5G, or via short-range wireless communication such as Bluetooth (registered trademark) or wireless LAN (Local Area Network), and communicate with the server device 100.

[0014] The server device 100 is, for example, a computer such as a PC or a blade server, or a mainframe or a workstation, etc. The server device 100 may be realized by cloud computing.

[0015] In this embodiment, the server device 100 is an information processing device that works in conjunction with the terminal device 10 of each user U and provides API (Application Programming Interface) services for various applications (hereinafter referred to as apps) and various data to the terminal device 10 of each user U, and is realized by a computer, a cloud system, etc.

[0016] The server device 100 may also be an information processing device that provides some kind of online web service to the terminal device 10 of each user U. For example, the server device 100 may provide the following web services: internet connection, search service, social networking service (SNS), electronic commerce (EC), electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route search, route guidance, line information, operation information, and weather forecast. In practice, the server device 100 may cooperate with various servers that provide the above-mentioned web services and act as an intermediary for the web services or may be responsible for processing the web services.

[0017] The server device 100 can acquire user information about the user U. For example, the server device 100 acquires, as the user information, information (attribute information) about the attributes of the user U, such as the gender, age, and residential area of ​​the user U. The server device 100 can also acquire information about the attributes of the user U, such as demographic attributes, psychographic attributes, geographic attributes, and behavioral attributes. The server device 100 may also acquire, as the user information, a segment to which the user U belongs in the marketing field or a persona (personality). The server device 100 then stores and manages the information (attribute information) about the attributes of the user U together with identification information (such as a user ID) that identifies the user U.

[0018] The server device 100 also acquires various types of history information (log data) indicating the behavior of the user U from the terminal device 10 of the user U or from various servers based on the user ID, etc. For example, the server device 100 acquires a location history, which is a history of the user U's location and date and time, from the terminal device 10. The server device 100 also acquires a search history, which is a history of search queries entered by the user U, from a search server (search engine). The server device 100 also acquires a browsing history, which is a history of content viewed by the user U, from a content server. The server device 100 also acquires a purchase history (payment history), which is a history of the user U's product purchases and payment processes, from an e-commerce server or a payment processing server. The server device 100 may also acquire a listing history and a sales history, which are a history of the user U's listings on the marketplace, from the e-commerce server or the payment processing server. The server device 100 also acquires a posting history, which is a history of the user U's posts, from a posting server or SNS server that provides a word-of-mouth posting service. The various servers and the like described above may be the server device 100 itself. That is, the server device 100 may function as the various servers and the like described above.

[0019] Furthermore, the number of devices included in the information processing system 1 shown in Fig. 1 is not limited to that shown in the figure. For example, in Fig. 1, for the sake of simplicity, only one terminal device 10 is shown, but this is merely an example and is not limiting, and two or more devices may be included.

[0020] [2. Store Suggestion GPT] Currently, it is difficult to identify issues and propose solutions for e-commerce stores. For example, when identifying issues, sales representatives analyze YoY (Year over Year), distribution progress, category share, and trends to identify stores with potential for growth, such as target stores. However, the process of identifying issues varies depending on the individual. Furthermore, after identifying a store, when looking for ways to increase distribution to address that potential, they also use company diagnosis and distribution project reports. However, these reports are also based on key performance indicators (KPIs), so whether or not they can identify potential for growth beyond the KPIs depends on the individual's knowledge and experience, and anything other than the key KPIs is highly dependent on the individual.

[0021] In addition, with regard to analysis, after identifying potential for growth, we clarify the KPIs and elements that make up that potential, and then use BI (Business Intelligence) tools such as Micro to dig deeper into the clarified areas and make proposals, but the results of the analysis are influenced by differences in individual knowledge of BI tools.

[0022] Furthermore, when documenting proposals, there were problems such as not being able to find suitable similar past proposals, past proposals being scattered, and not knowing how to make a proposal.

[0023] Therefore, in order to reduce the man-hours required for proposal activities, from problem identification to documentation, we will automate proposal activities using GPT (Generative Pre-trained Transformer).GPT is a text generation AI (Artificial Intelligence) and a language model that can generate sentences using natural language processing.

[0024] For example, as shown in Fig. 1, the server device 100 compiles KPIs for each product category of a designated store (step S1). For example, the designated store is a store of a customer to which a sales representative makes a proposal.

[0025] Next, the server device 100 determines stores to be compared for each product category (step S2). Here, the server device 100 determines competing stores (similar stores, stores ranked before or after) as stores to be compared. Note that the server device 100 is not limited to competing stores, and may determine stores that the user wants to compare or stores with similar products as stores to be compared. The server device 100 may also determine stores to be compared using any method. Similarities in average customer spending, etc. may be taken into consideration, or stores with similar customer attributes may be used.

[0026] Next, the server device 100 generates KPI comparison information with the store to be compared (step S3). At this time, the server device 100 identifies how much each KPI is winning / losing.

[0027] Next, the server device 100 provides the KPI comparison information (step S4).

[0028] Next, the server device 100 generates a database that compiles past problems and proposed solutions (solutions to the problems) from past proposal sentences, and vectorizes the problems registered in the database (step S5).

[0029] Next, the server device 100 converts the current task based on the KPI comparison information into natural sentences, and vectorizes the task converted into natural sentences (step S6).

[0030] Next, the server device 100 finds past tasks that are similar to the current task based on the cosine similarity of the vectors of the past tasks and the current task, and generates a prompt for the action to be taken for the current task based on the current task and the past action taken as prerequisites (step S7).

[0031] Next, the server device 100 provides the proposed content, such as a measure, generated by the GPT by passing the prompt to the GPT (step S8).

[0032] Furthermore, the server device 100 may obtain feedback on whether the proposed content was successful, create a database of successful cases, and prompt the GPT to input this information for reference. The server device 100 may also create a database of how much improvement was achieved, and input this information into the GPT for reference. The server device 100 may also create a database of only moves that were evaluated as successful.

[0033] Furthermore, if there is no similarity in the database, the server device 100 may generate a prompt to consider measures for the new issue since it is a new issue (such as, since there have been no past cases, please consider broadly), or may output a message to the effect that this should be done manually. Note that when generating a prompt, the server device 100 may input information from a broad database.

[0034] For example, the server device 100 may make a general proposal, or may give priority to proposals that consider examples of stores with similar store information in past examples. Also, the server device 100 may be created for both and make separate proposals.

[0035] The server device 100 may propose both general problem solutions and store-specific problem solutions, or only one of them, based on similarities in customer attributes such as store attributes, product attributes, sales methods, and average customer spending.

[0036] The above embodiment can be applied not only to e-commerce but also to affiliated stores of specific services such as search advertising and cashless payment. In addition, the contents to be compiled into a database can be applied to any field, not just commerce.

[0037] Hereinafter, specific processing will be explained, divided into Phase 1 and Phase 2.

[0038] [2-1. Phase 1] In Phase 1, the server device 100 compares the main KPI indicators with competitors to identify problematic KPI indicators for each category.

[0039] For example, the server device 100 receives a designation of a store ID (seller_id) from the terminal device 10 of a salesperson who is the user U (step S11). The store corresponding to this store ID (seller_id) becomes the designated store.

[0040] Next, the server device 100 aggregates the major KPI indicators of the specified store (step S12). For example, the server device 100 aggregates the major KPI indicators of the specified store for the most recent three months for each category in the first hierarchy from Teradata (shpps_f_kpi_monthly). At this time, the server device 100 selects categories with a GMV (Gross Merchandise Value: total distribution transaction amount) share of 10% or more within the specified store from the aggregated values.

[0041] Next, the server device 100 determines the stores to be compared (step S13). For example, the server device 100 extracts the competing stores before and after each category based on rankings within the category (e.g., GMV ranking) as stores to be compared. The default number of stores to be extracted for comparison is 20 stores in total, 10 before and 10 after. When determining the stores to be compared, it is also possible to directly specify the stores to be compared by entering the store ID (seller_id) of the store to be compared.

[0042] Next, the server device 100 determines the relative merits of the designated store and the comparison store (step S14). For example, the server device 100 obtains the average of the main KPI indicators for the most recent three months for each category of the designated store and the comparison store, and determines the relative merits of the designated store based on the ratio of each indicator of the designated store to the comparison store. In this case, the server device 100 determines the relative merits of the designated store based on the following definitions: "superior to competitors: 125% or more," "slightly inferior to competitors: more than 75% to 90% or less," and "significantly inferior to competitors: 75% or less." That is, the server device 100 determines that the designated store is superior to the competitor if it is 125% or more superior to the competitor; determines that the designated store is slightly inferior to the competitor if it is more than 75% but less than 90% superior to the competitor; and determines that the designated store is significantly inferior to the competitor if it is 75% or less superior to the competitor.

[0043] Next, the server device 100 identifies KPI indices that are inferior to the comparison store (step S15). For example, the server device 100 identifies KPI indices that are inferior and KPI indices that are significantly inferior to the comparison store (competitor store) for each category. For example, the server device 100 identifies the KPI indices "Losing: Number of visitors" and "Losing: Number of new purchasers" for "Category: Women's fashion."

[0044] [2-2. Phase 2] In Phase 2, the server device 100 has the GPT extract and summarize pairs of issues and solutions (proposals) for those issues from past sales materials.

[0045] For example, the server device 100 prepares actual past sales proposal materials and extracts sentences from the sales proposal materials (step S21).

[0046] Next, the server device 100 uses GPT to extract pairs of issues and solutions for the issues from the text of the sales proposal materials, summarizes the "issues" and "solutions for the issues" and manages them as pairs (step S22). In other words, the server device 100 holds pairs of past issues and solutions.

[0047] Example: Past sales proposal materials "Proposal by Mr. / Ms. XX As we increase GMV, there is room for growth in the number of visitors. Let me suggest two actions to increase your visitors. 1. Participate in Superior Delivery, which will boost your ranking in shopping search results. 2. Setting PR option rates, which are search advertising products, to increase traffic The expected effects of each....xxxxx"

[0048] Example: Problem and move pair {Challenge: There is an issue with the number of visitors, Action: Participate in superior delivery to make it easier to boost in search results} {Issue: There is an issue with the number of visitors, Solution: Setting the PR option fee rate, which is a search advertising product, to increase traffic} ===== {Challenge: Few repeat customers, Solution: Deliver news clips to past purchasers} {Challenge: Many visitors but few orders, Solution: Participate in bonus store campaign} {Challenge: Many visitors but few orders, Solution: Improve product descriptions on product pages} …

[0049] Next, the server device 100 vectorizes the stored assignment sentences using Embedding (step S23). That is, the server device 100 generates vectors by performing semantic interpretation on the assignment portion using Embedding. Embedding is a technique for arranging natural language information such as words and sentences in a vector space that represents the meaning of the words and sentences.

[0050] For example, the server device 100 generates a vector for the following problem part: Visitor numbers are an issue: [0.2, 0.1, 0.2, 0.3, 0.4, ...] · Low repeat customers: [0.5,0.7,0.8,0.8,0.4,...] Many visitors but few customers: [0.2,0.2,0.1,0.1,0.4,...]

[0051] Next, the server device 100 converts the issues into natural sentences based on logic and vectorizes them using Embedding (step S24) based on the KPI indicators with the issues identified in Phase 1. That is, the server device 100 generates vectors that have been semantically interpreted in the same way as in step S23, treating the store issues derived from the main KPIs as sentences.

[0052] For example, the server device 100 generates a vector of the following problem. The category is women's fashion, the number of new buyers is significantly lower than competitors, and there is significant room for growth: [0.2, 0.1, 0.2, 0.3, 0.4, ...] - The category is women's fashion and the number of visitors is lower than competitors: [0.4, 0.3, 0.8, 0.3, 0.1, ...]

[0053] Next, the server device 100 determines whether the sentences (problems) have similar meanings by calculating the cosine similarity from each vector (step S25). As a result, problems with similar meanings and solutions for the problems of the main KPI can be obtained from past sales documents.

[0054] That is, the server device 100 calculates the cosine similarity between the vector generated from the main KPI issue (see step S24) and the vector generated from the issue in the sales materials (see step S23), and picks out those that are similar in meaning. This makes it possible to know what kind of proposals have been made in the past for issues similar to the main KPI issue.

[0055] Next, the server device 100 passes the issues and past actions to the GPT as premise information, and generates actions (proposals) for the issues (step S26). That is, the server device 100 generates proposals in the GPT using information such as what proposals sales have made in the past for issues similar to the issue of the main KPI.

[0056] For example, the server device 100 passes the following prompt to the GPT: Example: Prompt " You are an e-commerce consultant who supports stores that operate on e-commerce sites. When faced with a problem in running a store, we refer to past solutions to similar problems, Please consider the proposal on how to solve the problem. *Please prioritize proposals that are in line with past actions, rather than delusions. - assignment "In the women's fashion category, the number of visitors is lower than competitors." - Past actions taken on similar issues (priority) Participate in premium delivery (priority) to be more likely to be boosted in search results Setting PR option rates, which are search advertising products, to increase traffic "

[0057] Note that the server device 100 may create new data to be used as past proposals when a new problem that has never been encountered before is encountered. For example, the server device 100 may set a threshold for cosine similarity, and when a problem below the threshold (no similar problem) is encountered, the server device 100 may prompt the GPT to start from scratch and create data to be used as past proposals. Furthermore, the sales representative may review the response from the GPT, and if it looks good, the response may be added to the data to be used as past proposals.

[0058] At this time, the server device 100 may provide a solution (proposal) for the problem to the terminal device 10 of the sales representative who will be the user U. Then, the sales representative who will be the user U proposes the solution (proposal) for the problem to the designated store. Note that the server device 100 may also provide the solution (proposal) for the problem directly to the designated store.

[0059] [3. Example of terminal device configuration] Next, the configuration of the terminal device 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example configuration of the terminal device 10. As shown in Fig. 2, the terminal device 10 includes a communication unit 11, a display unit 12, an input unit 13, a positioning unit 14, a sensor unit 20, a control unit 30 (controller), and a storage unit 40.

[0060] (Communications Department 11) The communication unit 11 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the server device 100 via the network N. For example, the communication unit 11 is realized by a NIC (Network Interface Card), an antenna, etc.

[0061] (Display section 12) Display unit 12 is a display device that displays various information such as position information. For example, display unit 12 is a liquid crystal display (LCD) or an organic electro-luminescent display (OLED). Display unit 12 is also a touch panel display, but is not limited to this.

[0062] (Input section 13) The input unit 13 is an input device that accepts various operations from the user U. For example, the input unit 13 has buttons for inputting characters, numbers, etc. The input unit 13 may be an input / output port (I / O port), a USB (Universal Serial Bus) port, etc. If the display unit 12 is a touch panel display, a part of the display unit 12 functions as the input unit 13. The input unit 13 may be a microphone that accepts voice input from the user U. The microphone may be wireless.

[0063] (Positioning unit 14) The positioning unit 14 receives signals (radio waves) transmitted from satellites of a GPS (Global Positioning System), and acquires position information (e.g., latitude and longitude) indicating the current position of the terminal device 10, which is the device itself, based on the received signals. That is, the positioning unit 14 positions the position of the terminal device 10. Note that GPS is merely an example of a GNSS (Global Navigation Satellite System).

[0064] The positioning unit 14 can also measure the position using various methods other than GPS. For example, the positioning unit 14 may measure the position by using various communication functions of the terminal device 10 as an auxiliary positioning means for position correction, etc., as described below.

[0065] (Wi-Fi positioning) For example, the positioning unit 14 uses a Wi-Fi (registered trademark) communication function of the terminal device 10 or a communication network provided by each communication company to measure the position of the terminal device 10. Specifically, the positioning unit 14 performs Wi-Fi communication or the like and measures the distance to a nearby base station or access point, thereby measuring the position of the terminal device 10.

[0066] (Beacon positioning) The positioning unit 14 may also measure the position by using a Bluetooth (registered trademark) function of the terminal device 10. For example, the positioning unit 14 measures the position of the terminal device 10 by connecting to a beacon transmitter connected by the Bluetooth (registered trademark) function.

[0067] (geomagnetic positioning) The positioning unit 14 also measures the position of the terminal device 10 based on a geomagnetic pattern of a structure that has been measured in advance and a geomagnetic sensor that the terminal device 10 has.

[0068] (RFID positioning) Furthermore, for example, if the terminal device 10 has a function of an RFID (Radio Frequency Identification) tag equivalent to a contactless IC card used at station ticket gates, in stores, etc., or has a function of reading an RFID tag, the location where the terminal device 10 was used is recorded together with information on the payment or the like made by the terminal device 10. The positioning unit 14 may obtain such information to determine the location of the terminal device 10. Alternatively, the location may be determined by an optical sensor, an infrared sensor, or the like provided in the terminal device 10.

[0069] The positioning unit 14 may measure the position of the terminal device 10 using one or a combination of the above-mentioned positioning means, as needed.

[0070] (Sensor unit 20) The sensor unit 20 includes various sensors mounted on or connected to the terminal device 10. The connection may be wired or wireless. For example, the sensors may be detection devices other than the terminal device 10, such as wearable devices or wireless devices. In the example shown in FIG. 2 , the sensor unit 20 includes an acceleration sensor 21, a gyro sensor 22, a barometric pressure sensor 23, a temperature sensor 24, a sound sensor 25, a light sensor 26, a magnetic sensor 27, and an image sensor (camera) 28.

[0071] The above-described sensors 21 to 28 are merely examples and are not intended to be limiting. That is, the sensor unit 20 may be configured to include some of the sensors 21 to 28, or may include other sensors such as a humidity sensor in addition to or instead of the sensors 21 to 28.

[0072] The acceleration sensor 21 is, for example, a three-axis acceleration sensor, and detects physical movements of the terminal device 10, such as the direction of movement, speed, and acceleration of the terminal device 10. The gyro sensor 22 detects physical movements of the terminal device 10, such as tilt in three axial directions, based on the angular velocity of the terminal device 10. The air pressure sensor 23 detects, for example, the air pressure around the terminal device 10.

[0073] Since the terminal device 10 includes the acceleration sensor 21, the gyro sensor 22, the atmospheric pressure sensor 23, etc., it is possible to measure the position of the terminal device 10 using a technique such as Pedestrian Dead-Reckoning (PDR) that uses these sensors 21 to 23. This makes it possible to obtain indoor position information that is difficult to obtain using a positioning system such as GPS.

[0074] For example, the number of steps, walking speed, and distance walked can be calculated using a pedometer that uses the acceleration sensor 21. In addition, the direction of travel, line of sight, and body tilt of the user U can be determined using the gyro sensor 22. In addition, the altitude and floor on which the terminal device 10 of the user U is located can be determined from the air pressure detected by the air pressure sensor 23.

[0075] The temperature sensor 24 detects, for example, the temperature around the terminal device 10. The sound sensor 25 detects, for example, the sound around the terminal device 10. The light sensor 26 detects the illuminance around the terminal device 10. The magnetic sensor 27 detects, for example, the geomagnetism around the terminal device 10. The image sensor 28 captures an image around the terminal device 10.

[0076] The above-mentioned air pressure sensor 23, temperature sensor 24, sound sensor 25, light sensor 26, and image sensor 28 can detect the air pressure, temperature, sound, and illuminance, respectively, and capture images of the surroundings, thereby detecting the environment and situation around the terminal device 10. Furthermore, the accuracy of the location information of the terminal device 10 can be improved based on the environment and situation around the terminal device 10.

[0077] (control unit 30) The control unit 30 includes, for example, a microcomputer having a CPU (Central Processing Unit), ROM (Read Only Memory), RAM, input / output ports, etc., and various other circuits. The control unit 30 may also be configured with hardware such as an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 30 includes a transmitting unit 31, a receiving unit 32, and a processing unit 33.

[0078] (Transmitter 31) The transmission unit 31 can transmit, for example, various information input by the user U using the input unit 13, various information detected by each sensor 21 to 28 mounted on or connected to the terminal device 10, and location information of the terminal device 10 measured by the positioning unit 14 to the server device 100 via the communication unit 11.

[0079] (Receiving unit 32) The receiving unit 32 can receive various types of information provided by the server device 100 and requests for various types of information from the server device 100 via the communication unit 11.

[0080] (Processing unit 33) The processing unit 33 controls the entire terminal device 10, including the display unit 12. For example, the processing unit 33 can output various information transmitted by the transmitting unit 31 and various information received from the server device 100 by the receiving unit 32 to the display unit 12 for display.

[0081] (Storage unit 40) The storage unit 40 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), an optical disk, etc. The storage unit 40 stores various programs, various data, etc.

[0082] [4. Server device configuration example] Next, the configuration of the server device 100 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the server device 100 according to the embodiment. As shown in Fig. 3, the server device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0083] (Communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC), etc. The communication unit 110 is connected to a network N by wire or wirelessly.

[0084] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as an HDD, an SSD, or an optical disk. The storage unit 120 may store attribute information and history information (log data) of the user U along with identification information (such as a user ID) indicating the user U. The storage unit 120 may also store tally results, past sales materials, and the like.

[0085] (control unit 130) The control unit 130 is a controller, and is realized by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like, executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the server device 100 using a storage area such as a RAM as a working area. In the example shown in FIG. 3, the control unit 130 has an acquisition unit 131, a problem discovery unit 132, and a proposal generation unit 133.

[0086] (Acquisition part 131) The acquisition unit 131 acquires a search query input by a user U. For example, when the user U inputs a search query into a search engine or the like to perform a keyword search, the acquisition unit 131 acquires the search query via the communication unit 110. That is, the acquisition unit 131 acquires, via the communication unit 110, the keywords input by the user U into the search box of a search engine, website, or app.

[0087] Furthermore, the acquisition unit 131 acquires user information about the user U via the communication unit 110. For example, the acquisition unit 131 acquires identification information (such as a user ID) indicating the user U, location information of the user U, attribute information of the user U, etc. from the terminal device 10 of the user U. Furthermore, the acquisition unit 131 may acquire the identification information indicating the user U, attribute information of the user U, etc. when the user U is registered. Then, the acquisition unit 131 stores the user information in the storage unit 120.

[0088] Furthermore, the acquisition unit 131 acquires various types of history information (log data) indicating the behavior of the user U via the communication unit 110. For example, the acquisition unit 131 acquires various types of history information indicating the behavior of the user U from the terminal device 10 of the user U or from various servers based on the user ID or the like. Then, the acquisition unit 131 stores the various types of history information in the storage unit 120.

[0089] The acquisition unit 131 also receives a designation of a store ID (seller_id) from the terminal device 10 of the sales representative, who is the user U, via the communication unit 110. The acquisition unit 131 also acquires past sales materials from the terminal device 10 of the sales representative or another server device 100 via the communication unit 110.

[0090] (Problem Discovery Section 132) The problem discovering unit 132 includes an index collecting unit 132A, a conflict determining unit 132B, a superiority / inferiority determining unit 132C, and an identifying unit 132D.

[0091] (Index counting unit 132A) The indicator aggregation unit 132A aggregates the indicators of the designated store for a predetermined period by category. For example, the indicator aggregation unit 132A aggregates the main KPI indicators of the designated store for the most recent three months by category. The indicator aggregation unit 132A may store the aggregation results in the storage unit 120.

[0092] (Conflict determination unit 132B) The conflict determination unit 132B determines competing stores to be compared with the designated store for each category. For example, the conflict determination unit 132B extracts competing stores to be compared with the designated store from the ranking for each category.

[0093] (Superiority judgment part 132C) The superiority / inferiority determination unit 132C determines the superiority / inferiority between the designated store and competing stores for each index. Specifically, the superiority / inferiority determination unit 132C obtains the average index of the designated store and competing stores for each category within a predetermined period, and determines the superiority / inferiority based on the ratio of the designated store to competing stores for each index.

[0094] For example, the superiority / inferiority determination unit 132C determines that the specified store is superior to the competing store if it is 125% or more superior to the competing store, determines that the specified store is slightly inferior to the competing store if it is more than 75% but less than 90% superior to the competing store, and determines that the specified store is significantly inferior to the competing store if it is 75% or less superior to the competing store.

[0095] (Specific part 132D) The identifying unit 132D identifies problematic metrics by comparing the metrics with the competition. For example, the identifying unit 132D identifies metrics in which the specified store is losing out to competing stores.

[0096] (Proposal generation unit 133) The proposal generating unit 133 includes a managing unit 133A, a converting unit 133B, a similarity determining unit 133C, a generating unit 133D, and a providing unit 133E.

[0097] (Management Department 133A) The management unit 133A manages pairs of past issues and actions for those issues. For example, the management unit 133A uses GPT to extract pairs of past issues and actions for those issues from text in past proposal materials (sales proposal materials, etc.), summarizes the past issues and actions, and manages them as pairs. At this time, the management unit 133A may refer to past proposal materials stored in the storage unit 120, and store in the storage unit 120 pairs of past issues and actions to be managed.

[0098] (Conversion unit 133B) The conversion unit 133B vectorizes each of the assignments based on the identified indexes and the past assignments. For example, the conversion unit 133B vectorizes the sentences of the past assignments, and also converts the assignments based on the identified indexes into natural sentences on a logic basis and vectorizes them.

[0099] (Similarity determination unit 133C) The similarity determination unit 133C determines past assignments that are similar to the assignment based on the identified index. For example, the similarity determination unit 133C determines past assignments that are similar to the assignment based on the identified index by calculating cosine similarity from the vector of the assignment based on the identified index and the vector of the past assignment. At this time, the similarity determination unit 133C determines whether sentences have similar meanings by calculating cosine similarity from each vector.

[0100] (Generation part 133D) The generation unit 133D generates a solution for the assignment based on the identified indicators from the solutions for similar past assignments. For example, the generation unit 133D passes the assignment based on the identified indicators and the solutions for similar past assignments to GPT as preconditions, thereby generating a solution for the assignment based on the identified indicators using GPT.

[0101] (Provider 133E) The providing unit 133E provides a solution to the problem based on the identified index. For example, the providing unit 133E provides the solution to the problem based on the identified index to the terminal device 10 of the sales representative via the communication unit 110.

[0102] [5. Processing Procedure] Next, a processing procedure by the server device 100 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the processing procedure according to the embodiment. Note that the processing procedure shown below is repeatedly executed by the control unit 130 of the server device 100.

[0103] For example, as shown in FIG. 4, the index tallying unit 132A of the server device 100 tally up the indexes of the designated store within a predetermined period for each category (step S101).

[0104] Next, the conflict determination unit 132B of the server device 100 determines a conflicting store to be compared with the designated store for each category (step S102).

[0105] Next, the superiority / inferiority determination unit 132C of the server device 100 obtains the average index of the designated store and competing stores for each category within a specified period, and determines the superiority / inferiority of the designated store based on the ratio of each index to the competing stores (step S103).

[0106] Next, the identifying unit 132D of the server device 100 compares the metrics with the competition, and identifies the metrics in which the specified store is losing to the competing store as problematic metrics (step S104).

[0107] Next, the management unit 133A of the server device 100 uses GPT to extract pairs of past issues and actions for those issues from the text of past proposal materials, summarizes the past issues and actions, and manages them as pairs (step S105).

[0108] Next, the conversion unit 133B of the server device 100 vectorizes the sentences of the past assignments, and also converts the assignments based on the indicators identified in step S104 above into natural sentences on a logic basis and vectorizes them (step S106).

[0109] Next, the similarity determination unit 133C of the server device 100 calculates the cosine similarity between the vector of the task based on the identified index and the vector of the past task, thereby determining sentences that are similar in meaning and determining past tasks that are similar to the task based on the identified index (step S107).

[0110] Next, the generation unit 133D of the server device 100 generates solutions for the tasks based on the identified indicators using GPT by passing the tasks based on the identified indicators and solutions for similar past tasks to GPT as prerequisites (step S108).

[0111] Next, the providing unit 133E of the server device 100 provides the solution to the problem based on the identified index to the terminal device 10 of the sales representative via the communication unit 110 (step S109).

[0112] [6. Modifications] The terminal device 10 and the server device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, modifications of the embodiment will be described below.

[0113] In the above embodiment, some or all of the processing executed by the server device 100 may actually be executed by the terminal device 10 (or an application running on the terminal). For example, the processing may be completed in a stand-alone manner (by the terminal device 10 alone). In this case, the terminal device 10 is assumed to have the functions of the server device 100 in the above embodiment. Furthermore, in the above embodiment, the terminal device 10 is linked to the server device 100, and therefore, from the perspective of the user U, it appears that the processing of the server device 100 is also being executed by the terminal device 10. In other words, from another perspective, the terminal device 10 can also be said to be equipped with the server device 100.

[0114] In addition, in the above embodiment, each store, which is a customer, rather than a sales representative, may input a store ID specifying their own store as the designated store, thereby enabling the discovery of issues and suggestions for solutions to those issues to be received.

[0115] In the above embodiment, the server device 100 may be configured to accept input of various information from a sales representative or the like in an interactive format using GPT. For example, all of the processing of the server device 100 may be completed using GPT.

[0116] Furthermore, in the above embodiment, the GPT is merely an example of a large language model (LLM), and in practice, other language models may be used.

[0117] In addition, in the above embodiment, when determining a store to be compared, the server device 100 may use a model constructed by machine learning to determine a store to be compared to the designated store. For example, the server device 100 may construct a model by machine learning that inputs a category and an index and outputs a store to be compared, and may input the product categories of the designated store and KPI indexes for each product category into this model to determine a store to be compared to the designated store.

[0118] [7. Effects] As described above, the information processing device (terminal device 10 and server device 100) according to the present application is characterized by comprising an identification unit 132D that identifies indicators that have challenges by comparing indicators with competitors, a management unit 133A that manages pairs of past assignments and actions for those assignments, a similarity determination unit 133C that determines past assignments that are similar to assignments based on the identified indicators, a generation unit 133D that generates actions for assignments based on the identified indicators from actions for similar past assignments, and a provision unit 133E that provides actions for assignments based on the identified indicators.

[0119] The information processing device according to the present application further includes a conversion unit 133B that vectorizes the assignment based on the identified index and the past assignment. The similarity determination unit 133C determines past assignments that are similar to the assignment based on the identified index by calculating cosine similarity between the vector of the assignment based on the identified index and the vector of the past assignment.

[0120] The conversion unit 133B vectorizes the sentences of past assignments, and also converts assignments based on the identified indicators into natural sentences on a logic basis and vectorizes them. The similarity determination unit 133C calculates cosine similarity from each vector to determine whether sentences have similar meanings.

[0121] The generation unit 133D generates a solution for the task based on the identified indicators using GPT by passing the task based on the identified indicators and the solution for a similar past task to GPT as preconditions.

[0122] The information processing device according to the present application further includes an index aggregation unit 132A that aggregates indexes of the designated store within a predetermined period for each category, a competition determination unit 132B that determines a competing store to be compared with the designated store for each category, and a superiority / inferiority determination unit 132C that determines the superiority / inferiority between the designated store and a competing store for each index. The identification unit 132D identifies the indexes in which the designated store is inferior to the competing store.

[0123] The superiority / inferiority determining unit 132C obtains the average of the indexes of the designated store and competing stores for each category within a predetermined period, and determines the superiority / inferiority of the designated store based on the ratio of each index to the competing stores.

[0124] The superiority / inferiority determination unit 132C determines that the specified store is superior to the competing store if its performance is 125% or more of the competing store, determines that the specified store is slightly inferior to the competing store if its performance is more than 75% but not more than 90% of the competing store, and determines that the specified store is significantly inferior to the competing store if its performance is 75% or less of the competing store.

[0125] The management unit 133A uses GPT to extract pairs of past issues and actions for those issues from the text of past proposal materials, summarizes the past issues and actions, and manages them as pairs.

[0126] By performing any one or a combination of the above-described processes, the information processing device according to the present application can more appropriately perform tasks such as problem detection for EC stores and proposing solutions.

[0127] [8. Hardware Configuration] The terminal device 10 and the server device 100 according to the above-described embodiments are realized by a computer 1000 having a configuration as shown in Fig. 5, for example. The following description will be given taking the server device 100 as an example. Fig. 5 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output I / F (Interface) 1060, an input I / F 1070, and a network I / F 1080 are connected via a bus 1090.

[0128] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The arithmetic device 1030 is realized by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

[0129] The primary storage device 1040 is a memory device such as a RAM (Random Access Memory) that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. The secondary storage device 1050 may be an internal storage device or an external storage device. The secondary storage device 1050 may also be a removable storage medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), a NAS (Network Attached Storage), a file server, or the like.

[0130] The output I / F 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a display, a projector, a printer, etc., and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input I / F 1070 is an interface for receiving information from various input devices 1020, such as a mouse, a keyboard, a keypad, a button, a scanner, etc., and is realized by a USB, etc.

[0131] Furthermore, the output I / F 1060 and the input I / F 1070 may be wirelessly connected to the output device 1010 and the input device 1020, respectively. That is, the output device 1010 and the input device 1020 may be wireless devices.

[0132] The output device 1010 and the input device 1020 may be integrated into one device, such as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated into one device as an input / output I / F.

[0133] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0134] The network I / F 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0135] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output I / F 1060 and the input I / F 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0136] For example, when the computer 1000 functions as the server device 100, the arithmetic unit 1030 of the computer 1000 executes a program loaded onto the primary storage device 1040 to realize the functions of the control unit 130. The arithmetic unit 1030 of the computer 1000 may also load a program acquired from another device via the network I / F 1080 onto the primary storage device 1040 and execute the loaded program. The arithmetic unit 1030 of the computer 1000 may also cooperate with the other device via the network I / F 1080 to call and use the functions and data of a program from another program of the other device.

[0137] [9. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Furthermore, the above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the scope of so-called equivalents. Furthermore, the above-described components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0138] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0139] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0140] For example, the above-mentioned server device 100 may be realized by multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0141] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0142] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0143] 1. Information Processing Systems 10 Terminal Equipment 100 Server device 110 Communications Department 120 Storage section 130 Control Unit 131 Acquisition Department 132 Problem Discovery Department 132A Index Collection Section 132B Competition Decision Unit 132C Superiority Judgment Department 132D Specific part 133 Proposal generation section 133A Management Department 133B conversion unit 133C Similarity determination section 133D generator 133E Providing Department

Claims

1. an identification unit that identifies problematic indicators by comparing the indicators with competitors; A management department that manages pairs of past issues and solutions for those issues; a similarity determination unit that determines past assignments that are similar to the assignment based on the identified index; a generation unit that generates a solution for the problem based on the identified indicators from solutions for similar past problems; a provision department that provides solutions to issues based on identified indicators; An information processing device comprising:

2. A conversion unit is further provided for vectorizing the identified index-based issues and the past issues, The similarity determination unit determines past assignments that are similar to the assignment based on the identified index by calculating a cosine similarity between a vector of the assignment based on the identified index and a vector of the past assignment.

2. The information processing apparatus according to claim 1, wherein:

3. The conversion unit vectorizes the sentences of past assignments, and converts assignments based on the identified indicators into natural sentences on a logic basis and vectorizes them; The similarity determination unit determines whether the sentences are similar in meaning by calculating a cosine similarity from each vector.

3. The information processing apparatus according to claim 2, wherein:

4. The generation unit generates a solution for the problem based on the identified indicator using the GPT by passing the problem based on the identified indicator and a solution for a similar past problem to the GPT as a precondition.

2. The information processing apparatus according to claim 1, wherein:

5. an index aggregation unit that aggregates indexes of a designated store for a predetermined period by category; a conflict determination unit that determines a conflict store to be compared with the designated store for each category; a superiority / inferiority determination unit that determines the superiority / inferiority between the designated store and the competing store for each index; Furthermore, The identification unit identifies an index by which the designated store is losing to the competing store.

2. The information processing apparatus according to claim 1, wherein:

6. The superiority / inferiority determination unit obtains an average of indices of the designated store and the competing store for each category within a predetermined period, and determines superiority / inferiority based on the ratio of the designated store to the competing store for each index.

6. The information processing apparatus according to claim 5,

7. The superiority / inferiority determination unit determines that the designated store is superior to the competing store if its performance is 125% or more compared to the competing store, determines that the designated store is slightly inferior to the competing store if its performance is more than 75% but not more than 90% compared to the competing store, and determines that the designated store is significantly inferior to the competing store if its performance is 75% or less compared to the competing store.

7. The information processing apparatus according to claim 6,

8. The management department uses GPT to extract pairs of past issues and measures for those issues from the text of past proposal materials, summarizes the past issues and the measures, and manages them as pairs.

2. The information processing apparatus according to claim 1, wherein:

9. An information processing method executed by an information processing device, An identification step of identifying problematic indicators by comparing the indicators with competitors; A management process for managing pairs of past issues and actions for those issues; a determination step of determining past issues similar to the issue based on the identified indicators; a generation step of generating a solution to the problem based on the identified indicators from solutions to similar past problems; a providing step of providing solutions to the issues based on the identified indicators; An information processing method comprising:

10. An identification step to identify problematic metrics by comparing them with competitors; A management procedure for managing pairs of past issues and actions for those issues; a determination procedure for determining past issues similar to the identified issue based on the indicators; a generation procedure for generating solutions to the problem based on the identified indicators from solutions to similar past problems; A delivery procedure that provides solutions to the issues based on the identified indicators; An information processing program characterized by causing a computer to execute the above.

Images