Information processing device, information processing method, and program

Abstract

The present invention analyzes, on the basis of user-entered information including description (text) regarding a failure or defect of a product, the product state of the product and the importance degree, and generates presentation information for the user and a developer. A product state identification unit analyzes a text regarding a failure or defect of a product described by a user, and, for example, identifies the product state of the product that the user is using. Further, an importance degree calculation unit calculates the importance degree of the identified product state. Furthermore, a presentation information generation unit generates presentation information including the importance degree calculated by the importance degree calculation unit, the identified product state, countermeasures for the product state, and statistical data, and presents the presentation information to the user and a product developer.

Description

Information processing device, information processing method, and program

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. More specifically, the present disclosure relates to an information processing device, an information processing method, and a program that analyzes a user's explanation of a malfunction or defect of an electrical appliance such as a smartphone and generates a response to the user or a report to a developer.

[0002] Currently, various electrical appliances such as smartphones, PCs, televisions, refrigerators, washing machines, etc. are widely used by many users.

[0003] These electrical appliances can sometimes experience various breakdowns or malfunctions while in use by users. In recent years, with the spread of communication networks such as the Internet, if a breakdown or malfunction occurs in the device that the user is using, the user can send a comment such as an explanation of the malfunction to the device's retailer or manufacturer via the Internet and receive a response from the retailer or manufacturer regarding a solution to the problem.

[0004] Many electrical equipment manufacturers have systems in place to respond to user inquiries via the Internet. For example, they prepare countermeasures for common malfunctions in advance and have a system in place that allows them to immediately provide users with a response, including the optimal solution, for any malfunction reported by the user.

[0005] However, it is often difficult for the manufacturer's personnel to accurately grasp the device's condition based on user comments, which can lead to the problem of being unable to provide the user with the correct solution.

[0006] One example of a conventional technique that discloses a configuration for reducing the workload on the manufacturer side is the configuration described in Patent Document 1 (JP 2011-192059 A). Patent Document 1 discloses a system that performs morphological analysis of text that describes a malfunction of a device, extracts from the text words that match words registered in a dictionary database, and analyzes the risk and importance of the malfunction of the device based on word attention values ​​that are defined in association with the registered words.

[0007] However, this method only analyzes the risk and severity of equipment malfunctions and does not create responses to users or reports to developers. Another problem is that it cannot be used when the text describing the equipment malfunction does not contain words that match those registered in the dictionary database.

[0008] JP 2011-192059 A

[0009] The present disclosure has been made, for example, in consideration of the above-mentioned problems, and provides an information processing device, an information processing method, and a program that analyze comments, etc. sent by users and generate responses including appropriate countermeasures, etc.

[0010] Furthermore, in one embodiment of the present disclosure, comments and the like sent by users are analyzed to generate statistical information such as the type of equipment failure and time series information, and this information can be presented to developers.

[0011] A first aspect of the present disclosure resides in an information processing device having a product state identification unit that identifies a product state of a first product based on user input information including text describing the product state of the first product, an importance calculation unit that calculates an importance of the identified product state of the first product, and a presentation information generation unit that generates presentation information based on the importance.

[0012] Furthermore, a second aspect of the present disclosure is an information processing method executed in an information processing device, comprising: a product state identification step in which a product state identification unit identifies the product state of a first product based on user input information including text describing the product state of the first product; an importance calculation step in which an importance calculation unit calculates the importance of the identified product state of the first product; and a presentation information generation step in which a presentation information generation unit generates presentation information based on the importance.

[0013] Furthermore, a third aspect of the present disclosure is a program for executing information processing in an information processing device, the program executing: a product state identification step for causing a product state identification unit to identify a product state of a first product based on user input information including text describing the product state of the first product; an importance calculation step for causing an importance calculation unit to calculate the importance of the identified product state of the first product; and a presentation information generation step for causing a presentation information generation unit to generate presentation information based on the importance.

[0014] The program of the present disclosure is, for example, a program that can be provided in a computer-readable format via a storage medium or a communication medium to an information processing device or a computer system capable of executing various program codes. By providing such a program in a computer-readable format, processing according to the program is realized on the information processing device or the computer system.

[0015] Further objects, features, and advantages of the present disclosure will become apparent from the following detailed description of the embodiments of the present disclosure and the accompanying drawings. Note that in this specification, a system refers to a logical collective configuration of multiple devices, and is not limited to devices that are located within the same housing.

[0016] According to one embodiment of the present disclosure, the product status and importance of a product are analyzed based on user input information, such as a description (text) of a product failure or malfunction, and presentation information is generated for a user or developer. Specifically, for example, a product status identification unit analyzes text, etc., in which the user explains the product failure or malfunction, and identifies the product status of, for example, a product used by the user. Furthermore, an importance calculation unit calculates the importance of the identified product status. Furthermore, a presentation information generation unit generates presentation information, such as the importance calculated by the importance calculation unit, the identified product status, countermeasures for the product status, statistical data, etc., and presents the information to a user or product developer. These configurations realize a configuration in which the product status and importance of a product are analyzed based on user input information, such as a description (text) of a product failure or malfunction, and presentation information is generated for a user or developer. Note that the effects described in this specification are merely exemplary and not limiting, and additional effects may also be present.

[0017] 1 is a diagram illustrating an example of a general process that does not use an information processing device of the present disclosure. FIG. 1 is a diagram illustrating an overview of a process executed by an information processing device of the present disclosure. FIG. 2 is a block diagram illustrating an example of a configuration of an information processing device of the present disclosure. FIG. 3 is a diagram illustrating a product state analysis process executed by a product state identification unit of the information processing device of the present disclosure. FIG. 4 is a diagram illustrating a detailed configuration of a product state identification unit. FIG. 5 is a diagram illustrating a specific example of user input information input via a communication unit of the information processing device. FIG. 6 is a diagram illustrating an example of registered data in a product state information DB. FIG. 7 is a diagram illustrating an example of a data input process by a user using a UI displayed on a user terminal. FIG. 8 is a diagram illustrating an example of a data input process by a user using a UI displayed on a user terminal. FIG. 9 is a diagram illustrating an example of a data input process by a user using a UI displayed on a user terminal. FIG. 10 is a diagram illustrating an example of a data input process by a user using a UI displayed on a user terminal. FIG. 11 is a diagram illustrating a flowchart illustrating a sequence of a process executed by a product state identification unit of the information processing device of the present disclosure. FIG. 12 is a block diagram illustrating a detailed configuration example of an importance calculation unit of the information processing device of the present disclosure. FIG. 13 is a diagram illustrating a process executed by a time importance calculation unit. FIG. 14 is a diagram illustrating an example of stored data in a defect report information DB. FIG. 15 is a diagram illustrating an example of a specific calculation process of time importance. FIG. 16 is a diagram illustrating a process executed by a context importance calculation unit. FIG. 17 is a diagram illustrating a detailed configuration of a context importance calculation unit and details of the process executed. FIG. 1 is a diagram illustrating processing executed by a customer importance calculation unit. FIG. 2 is a diagram illustrating an example of data stored in a customer information DB. FIG. 3 is a diagram illustrating a detailed configuration of a customer importance calculation unit and details of the processing it executes. FIG. 4 is a diagram illustrating processing executed by a repair importance calculation unit. FIG. 5 is a diagram illustrating an example of data stored in a repair information DB. FIG. 6 is a diagram illustrating a detailed configuration of a repair importance calculation unit and details of the processing it executes. FIG. 7 is a diagram illustrating processing executed by a total importance calculation unit. FIG. 8 is a flowchart illustrating a sequence of processing executed by an importance calculation unit. FIG. 9 is a diagram illustrating a specific example of presented information (feedback information) for developers. FIG. 10 is a diagram illustrating a specific example of presented information (feedback information) for developers.1 is a diagram illustrating a specific example of developer-directed presentation information (feedback information). FIG. 1 is a diagram illustrating a specific example of developer-directed presentation information (feedback information). FIG. 2 is a diagram illustrating a specific example of developer-directed presentation information (feedback information). FIG. 3 is a diagram illustrating a specific example of developer-directed presentation information (feedback information). FIG. 4 is a diagram illustrating a specific example of developer-directed presentation information (feedback information). FIG. 5 is a diagram illustrating a specific example of user-directed presentation information (answer). FIG. 6 is a diagram illustrating a specific example of user-directed presentation information (answer). FIG. 7 is a diagram illustrating a flowchart illustrating a sequence of processing executed by an information processing device. FIG. 8 is a diagram illustrating an example of processing sequence executed by an information processing device. FIG. 9 is a diagram illustrating an example of additional registration of a new product state name in a product state information DB. FIG. 10 is a diagram illustrating an example of additional registration of defect report information corresponding to a new product state name in a defect report DB. FIG. 11 is a diagram illustrating an example of a hardware configuration of an information processing device of the present disclosure.

[0018] The information processing device, information processing method, and program of the present disclosure will be described in detail below with reference to the drawings. The description will be made according to the following items: 1. Overview of the processing performed by the information processing device of the present disclosure 2. Example configuration of the information processing device of the present disclosure 3. Detailed configuration of the product state identification unit and the processing performed 4. Detailed configuration of the importance calculation unit and the processing performed 4-1. Details of the time importance calculation processing performed by the time importance calculation unit 4-2. Details of the context importance calculation processing performed by the context importance calculation unit 4-3. Details of the customer importance calculation processing performed by the customer importance calculation unit 4-4. Details of the repair importance calculation processing performed by the repair importance calculation unit 4-5. Details of the overall importance calculation processing performed by the overall importance calculation unit 5. Sequence of processing performed by the importance calculation unit 6. Processing performed by the developer presentation information generation unit 7. Processing performed by the user presentation information generation unit 8. Processing sequence when a user requests correction of the product state analysis result 9. 10. Hardware Configuration Example of Information Processing Device of the Present Disclosure

[0019] [1. Overview of Processing Executed by Information Processing Device of the Present Disclosure] First, an overview of processing executed by an information processing device of the present disclosure will be described.

[0020] The information processing device disclosed herein analyzes descriptions of electrical appliance failures and malfunctions sent by users, generates responses including appropriate countermeasures, and generates statistical information such as the type of equipment failure and time series information, and presents this information to developers.

[0021] First, an example of a conventional system configuration that does not use the information processing device of the present disclosure and an example of the processing performed thereon will be described with reference to Fig. 1. Fig. 1 shows multiple users who use various electrical appliances such as smartphones, PCs, televisions, refrigerators, washing machines, etc., and an electrical appliance manufacturer 50 that provides these electrical appliances.

[0022] User a, 11, uses product a (smartphone) 12 manufactured by electrical equipment manufacturer 50. User b, 21, uses product b (television) 22 manufactured by electrical equipment manufacturer 50. User c, 31, uses product c (refrigerator) 32 manufactured by electrical equipment manufacturer 50.

[0023] Each user a to c inputs an explanatory statement (text) explaining the malfunction or defect of the product a to c that they use into their terminal and transmits it to the electrical equipment manufacturer 50 via a communication network such as the Internet.

[0024] User a, 11 inputs an explanation or the like explaining the malfunction or defect status of product a (smartphone) 12 used by user a, 11 into user terminal a (smartphone) 13 and transmits the user input information to an electrical equipment manufacturer 50. User b, 21 inputs an explanation or the like explaining the malfunction or defect status of product b (television) 22 used by user b, 21 into user terminal b (PC) 23 and transmits the user input information to an electrical equipment manufacturer 50. User c, 31 inputs an explanation or the like explaining the malfunction or defect status of product c (refrigerator) 32 used by user c, 31 into user terminal c (smartphone) 33 and transmits the user input information to an electrical equipment manufacturer 50. Note that users may transmit explanations (text) about malfunction or defect status not only for products used by themselves, but also for products used by family members, acquaintances, etc.

[0025] A person in charge of the electrical equipment manufacturer 50, for example, a product development person 51 shown in FIG. 1, analyzes the information 40 received from each user.

[0026] The information 40 received from each user includes descriptions of various product malfunctions and defects, such as the following: The information received from user a, 11 includes a product condition description for product a (smartphone) 12 used by user a, 11, which reads, "The battery runs out quickly..." The information received from user b, 21 includes a product condition description for product b (television) 22 used by user b, 21, which reads, "The screen flickers..." The information received from user c, 31 includes a product condition description for product c (refrigerator) 32 used by user c, 31, which reads, "It's not cooling..."

[0027] A product development manager 51 at the electrical equipment manufacturer 50 reads the product status description contained in the received information 40 from each user, analyzes the breakdown or malfunction of each product, considers the optimal countermeasure based on the analysis results, and generates a response including the analysis results to send to each user.

[0028] However, it is often difficult for the product development staff 51 to accurately analyze the status of each product based on the product status description contained in the received information 40 from each user, and in such cases, it becomes impossible to present the correct countermeasures or answers to the users.

[0029] The present disclosure solves such problems by configuring an information processing device to execute the processes executed by a product development person 51 of an electrical equipment manufacturer 50 shown in Fig. 1. That is, the information processing device executes a product state analysis process based on the description of the product state included in information 40 received from a user, a response generation process in accordance with the analysis results, and the like.

[0030] Next, an overview of the processing executed by the information processing device of the present disclosure will be described with reference to Fig. 2. Fig. 2 shows an example of a system configuration including the information processing device 100 of the present disclosure. The difference between the configuration shown in Fig. 2 and the previously described configuration shown in Fig. 1 is that the processing executed by the product development person 51 of the electrical equipment manufacturer 50 in Fig. 1 is now executed by the information processing device 100.

[0031] 2, as explained with reference to Fig. 1, each of users a, 11 to c, 31 inputs an explanatory statement (text) explaining the state of a malfunction or defect in the product a, b, c that they use into their user terminal and transmits it to the electrical equipment manufacturer 50 via a communication network such as the Internet. Note that, as explained above with reference to Fig. 1, users may transmit explanatory statements (text) about the state of a malfunction or defect not only for the product that they use themselves, but also for products used by family members, acquaintances, etc.

[0032] 2, the information processing device 100 of the electrical equipment manufacturer 50 inputs the received information 40 from each user and analyzes the received information 40. Specifically, for example, a pre-generated learning model is used to analyze the product status description and the like included in the received data, and the product status of the product used by the user, i.e., the specific state of the product failure or malfunction, is analyzed.

[0033] Furthermore, the information processing device 100 considers the optimal countermeasure based on the analysis results, generates "user presentation information 61" including an answer including the consideration results, and transmits it to the user terminal of each user. The information processing device 100 also generates "developer presentation information (feedback information)" to present to the product developer 51, such as statistical information based on the analysis results, and transmits it to the terminal of the product developer 51.

[0034] In this manner, the information processing device 100 of the present disclosure analyzes user input information including a description of the product state sent by the user, and generates a response to the user and feedback information for the product development staff.

[0035] 2. Configuration Example of Information Processing Apparatus of the Present Disclosure Next, a configuration example of an information processing apparatus of the present disclosure will be described.

[0036] Fig. 3 is a block diagram showing an example configuration of the information processing device 100 of the present disclosure. As shown in Fig. 3, the information processing device 100 of the present disclosure includes a communication unit 101, a product state identification unit 102, an importance calculation unit 103, a developer-oriented presentation information generation unit 104, and a user-oriented presentation information generation unit 105. Furthermore, the information processing device 100 includes databases (DBs) such as a product state information DB 111, a repair information DB 121, a customer information DB 122, and a defect report information DB 123.

[0037] The communication unit 101 transmits and receives data to and from the user terminal 13 via a communication network such as the Internet. Although Fig. 3 shows only the user terminal 13 of the user 11 as a representative example of a communication partner of the information processing device 100, the information processing device 100 also communicates with the user terminals of many other users.

[0038] The communication unit 101 receives information including descriptions (text) of product states such as failures and defects of various products from a large number of user terminals, such as the user terminal 13, i.e., user input information 210 shown in FIG. 3, and inputs the received user input information 210 to the product state identification unit 102.

[0039] The product state specifying unit 102 executes an analysis process on the user input information 210 input via the communication unit 101, and executes an analysis process on the state of the product, for example, specific details of a malfunction or defect.

[0040] The product state identification unit 102 receives user input information 210 via the communication unit 101 and information stored in the product state information DB 111, and uses a pre-generated learning model to estimate the product state of the user's product, for example, specific details of a malfunction or defect, based on the information included in the user input information 210. In other words, it executes a process of identifying the product state of the user's product based on the user input information 210.

[0041] Product status information indicating various product failures and defects is registered in advance in the product status information DB 111. Details of the processing executed by the product status identification unit 102 and specific examples of data stored in the product status information DB 111 will be described later.

[0042] The analysis result of the product state identification unit 102, i.e., the analysis result (identification result) of the user's product state, is input to the importance calculation unit 103, the developer presentation information generation unit 104, and the user presentation information generation unit 105.

[0043] The importance calculation unit 103 inputs the analysis results of the product condition identification unit 102, i.e., the estimated results of the user's product condition (failures and defects), and determines the importance of the user's product condition (failures and defects) using the information stored in each of the databases, namely, repair information DB 121, customer information DB 122, and defect report information DB 123.

[0044] The importance calculated by the importance calculation unit 103 is based on various perspectives, such as whether the failure or malfunction requires immediate discontinuation of use of the product, whether the failure or malfunction requires immediate response, or whether similar failures or malfunctions have spread to a large number of products.

[0045] Details of the processing executed by importance calculation unit 103 and specific examples of data stored in repair information DB 121, customer information DB 122, and defect report information DB 123 will be described later.

[0046] The importance calculated by the importance calculation unit 103, that is, the importance information of the product state (failure or defect) for the user, is input to a developer presentation information generation unit 104 and a user presentation information generation unit 105.

[0047] The developer presentation information generation unit 104 generates presentation information for the product development staff 51 by using the analysis result of the product state identification unit 102, i.e., the analysis result of the user's product state, and the importance calculated by the importance calculation unit 103, i.e., importance information of the user's product state (failure or malfunction). For example, information consisting of statistical information such as the type of failure for each product type is generated as "developer presentation information (feedback information) 220" and sent to the terminal of the product development staff 51.

[0048] The process executed by the developer-oriented presentation information generation unit 104 and specific examples of the "developer-oriented presentation information 220" generated by the developer-oriented presentation information generation unit 104 will be described later.

[0049] The user-oriented presentation information generation unit 105 uses the analysis result of the product condition identification unit 102, i.e., the analysis result of the user's product condition, and the importance calculated by the importance calculation unit 103, i.e., the importance information of the user's product condition (failure or malfunction), to generate ``user-oriented presentation information 230'' that includes a response to the user, i.e., countermeasures for the failure or malfunction explained by the user, and transmits the information to each user terminal, such as the user terminal 13, via the communication unit 101.

[0050] The processing executed by the user-directed presentation information generating unit 105 and specific examples of the "user-directed presentation information 230" generated by the user-directed presentation information generating unit 105 will be described later.

[0051] 3. Detailed Configuration of Product Condition Identification Unit and Processing Executed Next, a detailed configuration of the product condition identification unit 102 of the information processing device 100 shown in FIG. 3 and processing executed by the product condition identification unit 102 will be described.

[0052] FIG. 4 is a diagram illustrating the product state analysis process executed by the product state identification unit 102. As shown in FIG.

[0053] As described above, the product state identification unit 102 receives the user input information 210 input via the communication unit 101 and the information stored in the product state information DB 111, and uses a pre-generated learning model to estimate the product state of the user's product, for example, specific details of a malfunction or defect, based on the information included in the user input information 210. In other words, it executes a process of identifying the product state of the user's product.

[0054] The analysis result of the product state identification unit 102 , that is, the identification result of the user's product state, is input to the importance calculation unit 103 , the developer presentation information generation unit 104 , and the user presentation information generation unit 105 .

[0055] The detailed configuration and processing of the product state identification unit 102 will be described with reference to Fig. 5 and subsequent figures. Fig. 5 is a diagram showing the detailed configuration of the product state identification unit 102. As shown in Fig. 5, the product state identification unit 102 includes a user input information analysis unit 301, a product state description analysis unit 302, and a learning model 303.

[0056] The user input information analysis unit 301 executes a process of checking whether the user input information 210 input via the communication unit 101 includes recorded data of the "registered product state."

[0057] Specific examples of user input information 210 input via communication unit 101 will be described with reference to Figure 6 and subsequent figures. Figure 6 is a diagram showing an example of a UI (user interface) displayed on user terminal 13. This UI is provided by electrical equipment manufacturer 50, and is used by users of electrical products manufactured by electrical equipment manufacturer 50 to report the status of a malfunction of the electrical product to electrical equipment manufacturer 50, for example.

[0058] As shown in Figure 6, the UI has the following data entry items: (a) Customer number (required) (b) Product name (required) (c) Product status description (required) (d) Registered product status (optional)

[0059] "(a) Customer number" is, for example, a number (user ID) assigned to a user by the electrical equipment manufacturer 50 when the user purchases an electrical product from the electrical equipment manufacturer 50. This item is a required item. "(b) Product name" is an input item for the product name and model number of the electrical product from the electrical equipment manufacturer 50 that the user uses. This item is also a required item.

[0060] "(c) Product Status Description" is an item for inputting a sentence (text) explaining the breakdown, malfunction, or problem of the electrical product of the electrical equipment manufacturer 50 that the user uses. This item is also a required item.

[0061] 6 shows the state in which the following description (text) has been entered: "The Internet connection is poor. It stops when playing videos. Also, the battery life is poor. Even if it's 100% charged in the morning, it's down to 50% by noon." This product condition description can be written freely by the user, and there is no set format.

[0062] "(d) Registered product status" is an item in which, if the status (failure, malfunction, etc.) of the product used by the user matches a product status registered in the product status information DB 111 in the information processing device 100 owned by the electrical equipment manufacturer 50, the matching product status is selected and input.

[0063] An example of data registered in the product status information DB 111 is shown in Fig. 7. Product status information indicating various product failures and defects is registered in advance in the product status information DB 111. For example, as shown in Fig. 7, data folders are set up for each product type, and "product status" indicating various failures and defects for each product type is registered in association with a "product status identifier."

[0064] In the example shown in Fig. 7, the following data folders are shown as data folders for each product type: Smartphone (SAAA) Refrigerator (R234) Smartphone (SAAA) Television (TV101) Note that (SAAA) etc. are product model numbers.

[0065] For example, in the data folder of a smartphone (SAAA), "product status" indicating various malfunctions and problems of the smartphone (SAAA) is registered in association with a "product status identifier." The example shown in Figure 7 shows an example in which product status information indicating various malfunctions and problems of the smartphone (SAAA), such as poor communication, poor battery, poor housing, delayed operation, cracked screen, and cracked sound, is registered.

[0066] In addition, in the data folder for the refrigerator (R234), "product status" indicating various malfunctions and problems of the refrigerator (R234) is registered in association with a "product status identifier." In the example shown in Fig. 7, product status information indicating various malfunctions and problems of the refrigerator (R234), such as poor cooling, poor ice making, and defective door, is registered.

[0067] Returning to Fig. 6, the description of the UI will continue. "(d) Registered Product Status" at the bottom of the UI is not a setting that the user can input arbitrarily, but a selectable product status is set in advance. In other words, only the product statuses registered in the product status information DB 111 described with reference to Fig. 7 are set in advance as selectable input data. If there is a status that matches the status (failure, malfunction, etc.) of the product used by the user, the user selects and inputs that product status. This item is an optional input item. Note that Fig. 6 shows a state in which "Poor communication" is selected.

[0068] An example of the data input process for this "(d) Registered Product Status" will be described with reference to Figure 8 and subsequent figures. As shown in Figure 8, when the user touches the downward-pointing triangle mark (▼) on the left edge of the "(d) Registered Product Status" input field in the UI, multiple product statuses that can be input are displayed as shown in Figure 8. These correspond to a list of product statuses that have been registered in the product status information DB 111. Note that "Other" is set as an option that can be selected when the status (failure, malfunction, etc.) of the user's product does not fall under any of the displayed selection items.

[0069] For example, as shown in Fig. 9, if the user selects "Poor communication" from the multiple options displayed, "Poor communication" is entered in the input field for "(d) Registered product status." Note that multiple different product statuses can be entered in this "(d) Registered product status."

[0070] For example, as shown in Fig. 9, after "poor communication" has been entered in the input field for "(d) registered product status," if the user wants to enter another product status, the user first touches the "add" button as shown in Fig. 10. This touch process adds an input field for "(d) registered product status," as shown in Fig. 10.

[0071] The user then touches the downward-pointing triangle (▼) at the left end of the additional input field for "(d) Registered product status," displays multiple product statuses that can be input, and selects the product status that the user wants to add. In the example shown in Figure 10, the user selects "Battery failure."

[0072] In this way, when the user selects "Battery failure", "Battery failure" is entered in the additional input field for "(d) Registered product status" as shown in FIG.

[0073] After completing these inputs, when the user touches the "send" button as shown in FIG. 11, the input data is sent to the information processing device 100 of the electrical equipment manufacturer 50.

[0074] 5 , a detailed sequence of the product state analysis process executed by the product state identification unit 102 will be described. First, the user input information 210 input via the communication unit 101 is input to the user input information analysis unit 301 of the product state identification unit 102.

[0075] The user input information analysis unit 301 checks whether or not selection data for a product status other than "Other" has been entered in the input field for "Registered Product Status" included in the user input information 210. As described with reference to FIG. 6 etc., the UI displayed on the user terminal is a UI in which the following data input fields are set: (a) Customer number (required) (b) Product name (required) (c) Product status description (required) (d) Registered product status (optional)

[0076] Of these input items (a) to (d), items (a) to (c) are required and must be entered by the user. However, input for input item (d) Registered Product Status is optional and may not be entered. In other words, if the status (failure, malfunction, etc.) of the product used by the user matches one of the product statuses registered in the product status information DB 111 and is a selectable product status displayed in the UI, the user can select and enter it. However, if there is no match, the user will either not enter it or will select "Other" and enter it.

[0077] The user input information analysis unit 301 checks whether or not selection data of a product state other than "other" has been entered in the input item of "registered product state" included in the user input information 210.

[0078] If it has been entered, it is determined that the status (failure, malfunction, etc.) of the product used by the user matches one of the product statuses registered in the product status information DB 111, and this product status is output as "product status information 211a" indicating the status (failure, malfunction, etc.) of the product used by the user. That is, the process of "process a" shown in FIG. 5 is executed.

[0079] The “product state information 211 a ” is output to the importance calculation unit 103 , the developer presentation information generation unit 104 , and the user presentation information generation unit 105 .

[0080] On the other hand, if no selection data for the product status other than "Other" is entered in the input field for "Registered Product Status" included in the user input information 210, the "User input information 210" entered via the communication unit 101 is input as is to the product status description analysis unit 302. That is, the process of "Process b" shown in FIG. 5 is executed.

[0081] In this case, the product status description analysis unit 302 analyzes the status (failure, malfunction, etc.) of the product used by the user based on the "user input information 210," and generates and outputs "product status information 211b" indicating the status (failure, malfunction, etc.) of the product used by the user.

[0082] The product condition description analysis unit 302 inputs the "product name" and "product condition description" contained in the "user input information 210" into the learning model 303, estimates the "product condition" indicating the condition (failure, malfunction, etc.) of the product used by the user, and outputs this estimation result as "product condition information 211b."

[0083] The learning model 303 is a learning model that uses, for example, a deep neural network (DNN) and analyzes a document created by a user, i.e., an "explanatory document of a product state." The learning model 303 analyzes which of the multiple product states registered in the product state information DB 111 the "explanatory document (text) of a product state" created by the user is closest to.

[0084] Specifically, the learning model 303 may be, for example, BERT (Bidirectional Encoder Representations from Transformers), which is a learning model for natural language processing.

[0085] A learning model using BERT executes, for example, the following process. First, it performs label setting processing on the constituent words of the "product status description" created by the user, calculates vectors based on the set labels, and then generates document-corresponding vectors that indicate the characteristics of the "product status description." Next, it calculates the similarity between this document-corresponding vector and each vector of the product status registered in the product status information DB 111. Cosine similarity is used to calculate the similarity between the vector that indicates the characteristics of the "product status description" and the product status registered in the product status information DB 111 that has the vector with the highest cosine similarity, and it performs processing to estimate this status as the "product status" that indicates the status (failure, defect, etc.) of the product used by the user.

[0086] The learning model used by the product state description analysis unit 302, i.e., the learning model 303 used to estimate the "product state" based on the "product state description" created by the user, is not limited to a model using BERT, and learning models with other configurations may be used. Various types of learning models can be used to analyze which of the multiple product states registered in the product state information DB 111 the "product state description" created by the user is closest to.

[0087] In this way, if no selection data for the product status other than "Other" is entered in the input field for "Registered product status" included in the user input information 210, the "user input information 210" entered via the communication unit 101 is input as is to the product status description analysis unit 302, and the product status description analysis unit 302 uses the learning model 303 to analyze the status (failure, malfunction, etc.) of the product used by the user, and generates and outputs "product status information 211b" indicating the status (failure, malfunction, etc.) of the product used by the user.

[0088] That is, the learning model 303 is used to analyze which of the multiple product states already registered in the product state information DB 111 the "product state description document" created by the user is closest to, and the DB-registered product state that is closest to the "product state description document" created by the user is output as "product state information 211b."

[0089] The output destinations of the "product state information 211b" are the importance calculation unit 103, the developer presentation information generation unit 104, and the user presentation information generation unit 105, just like the output destinations of the "product state information 211a".

[0090] Next, the sequence of the process executed by the product state identification unit 102 shown in FIG. 5 will be described with reference to the flowchart shown in FIG.

[0091] In addition to the flowchart shown in Fig. 12, the processing according to the flowcharts described below can be executed under the control of a control unit in accordance with a program stored in a storage unit of the information processing device 100 of the present disclosure. The control unit has a processor such as a CPU having a program execution function, and controls the processing according to the flow by program execution processing using the processor. The processing of each step of the flow shown in Fig. 12 will be described below in order.

[0092] (Step S101) First, in step S101, the product state specifying unit 102 of the information processing device 100 inputs received data (user input information) from the user terminal via the communication unit 101.

[0093] The data received from the user terminal (user input information) is input to a user input information analysis unit 301 of the product state identification unit 102 shown in FIG.

[0094] (Step S102) Next, in step S102, it is determined whether or not valid selection data other than "other" has been input in the "registered product status" item in the data received from the user terminal (user input information).

[0095] This process is executed by the user input information analysis unit 301 of the product state identification unit 102 shown in FIG.

[0096] As previously explained with reference to Fig. 5, the user input information analysis unit 301 checks whether or not selection data for a product status other than "Other" has been entered in the input field for "Registered Product Status" included in the user input information 210. As explained with reference to Fig. 6 etc., the UI displayed on the user terminal is a UI with the following data input fields set: (a) Customer number (required) (b) Product name (required) (c) Product status description (required) (d) Registered product status (optional)

[0097] Among these input items, the input item "(d) Registered Product Status" is optional and may not be entered. If the status of the product used by the user (failure, malfunction, etc.) is a selectable product status displayed in the UI, the user can select and enter it, but if there is no match, the user will either not enter it or will select "Other" and enter it.

[0098] In step S102, the user input information analysis unit 301 checks whether or not selection data of a product state other than "other" has been entered in the input item of "registered product state" included in the user input information 210.

[0099] If valid selection data other than "Other" is entered in the "Registered Product Status" field, the determination in step S102 becomes "Yes" and the process proceeds to step S103. For example, if a preset option such as "Communication failure" or "Battery failure" is entered, the determination in step S102 becomes "Yes" and the process proceeds to step S103.

[0100] On the other hand, if no valid selection data other than "Other" is input in the "Registered Product Status" field, the determination in step S102 becomes "No" and the process proceeds to step S104. For example, if "Other" is input in the "Registered Product Status" input field, or if nothing is input, the determination in step S102 becomes "No" and the process proceeds to step S104.

[0101] (Step S103) If it is determined in step S102 that valid selection data other than "Other" has been input in the "Registered Product Status" field, the process proceeds to step S103.

[0102] In step S103, the "product status" is determined based on the valid selection data recorded in the "registered product status" field. This process corresponds to (process a) described above with reference to Fig. 5. That is, it is determined that the status (failure, malfunction, etc.) of the user's product is the "product status" recorded in the "registered product status" field (i.e., any of the product statuses registered in the product status information DB 111).

[0103] In this case, the user input information analysis unit 301 of the product state identification unit 102 shown in Fig. 5 outputs this product state as "product state information 211a" indicating the state (failure, malfunction, etc.) of the product used by the user. That is, the process of "process a" shown in Fig. 5 is executed. The "product state information 211a" is output to the importance calculation unit 103, the developer-directed presentation information generation unit 104, and the user-directed presentation information generation unit 105.

[0104] (Step S104) On the other hand, in step S102, if no product status selection data other than "Other" has been entered in the input field for "Registered Product Status" included in the user input information 210, the process of step S104 is executed. For example, if "Other" has been entered in the input field for "Registered Product Status," or if nothing has been entered, the determination in step S102 is "No," and the process of step S104 is executed.

[0105] In step S104, the user's explanation and the like in the data received from the user terminal (user input information) is input into the learning model, and a process of estimating the product state is executed.

[0106] This process is executed by the product state description analysis unit 302 of the product state identification unit 102 shown in Fig. 5. That is, the process "process b" shown in Fig. 5 is executed. The user input information analysis unit 301 of the product state identification unit 102 inputs the "user input information 210" input via the communication unit 101 directly to the product state description analysis unit 302, and the product state description analysis unit 302 inputs the user description and the like in the data received from the user terminal (user input information) into a learning model to estimate the product state.

[0107] As explained above with reference to Figure 5, the product state description analysis unit 302 inputs the "product name" and "product state description" included in the "user input information 210" into the learning model 303, estimates the "product state" indicating the state (failure, malfunction, etc.) of the product used by the user, and outputs this estimation result as "product state information 211b."

[0108] The learning model 303 is a learning model that uses, for example, BERT or DNN (Deep Neural Network), and analyzes a document created by a user, i.e., an "explanatory document (text) of a product state." The learning model 303 analyzes which of the multiple product states registered in the product state information DB 111 the "explanatory document of a product state" created by the user is closest to.

[0109] In this way, in step S104, the "product state description document" created by the user and the like are input into the learning model to estimate the user's product state, and this is output as "product state information 211b" as described with reference to Fig. 5. The output destinations of the "product state information 211b" are the importance calculation unit 103, the developer-oriented presentation information generation unit 104, and the user-oriented presentation information generation unit 105, just like the output destinations of the "product state information 211a."

[0110] 4. Detailed Configuration of Importance Calculation Unit and Processing Executed Next, a detailed configuration of the importance calculation unit 103 of the information processing device 100 shown in FIG. 3 and processing executed therein will be described.

[0111] As explained above with reference to FIG. 3 , the importance calculation unit 103 inputs the analysis result of the product state identification unit 102, i.e., the estimated result of the user's product state (failure or malfunction), and determines the importance of the user's product state (failure or malfunction) by using the information stored in each of the databases, namely, the repair information DB 121, the customer information DB 122, and the malfunction report information DB 123.

[0112] The importance calculated by the importance calculation unit 103 is based on various perspectives, such as whether the failure or malfunction requires immediate discontinuation of use of the product, whether the failure or malfunction requires immediate response, or whether similar failures or malfunctions have spread to a large number of products.

[0113] Fig. 13 is a block diagram showing a detailed configuration example of the importance calculation unit 103. As shown in Fig. 13, the importance calculation unit 103 includes a time importance calculation unit 401, a context importance calculation unit 402, a customer importance calculation unit 403, a repair importance calculation unit 404, and a total importance calculation unit 405.

[0114] 13, the importance calculation unit 103 receives user input information 210 and product status information 211 from the product status identification unit 102. The user input information 210 is information received from the user terminal via the communication unit 101, and includes the following information as previously described with reference to FIG. 6 etc.: (a) Customer number (b) Product name (c) Product status description (d) Registered product status Note that (d) Registered product status may not be input.

[0115] The product status information 211 is the above-mentioned “(d) registered product status” included in the information received from the user terminal, or the product status information estimated by the product status identification unit 102 using the learning model 103, and is data indicating the status of the product being used by the user (problems such as breakdowns and malfunctions).

[0116] The importance calculation unit 103 receives user input information 210 and product status information 211 from the product status identification unit 102, and uses the information stored in the repair information DB 121, customer information DB 122, and defect report information DB 123, and the following units calculate the following importance levels: (a) the time importance calculation unit 401 calculates the time importance level, (b) the context importance calculation unit 402 calculates the context importance level, (c) the customer importance calculation unit 403 calculates the customer importance level, (d) the repair importance calculation unit 404 calculates the repair importance level, and (e) the overall importance calculation unit 405 calculates the overall importance level. The importance calculation unit 103 performs the calculation process for each of these importance levels.

[0117] Below, the details of the processing executed by each of the time importance calculation unit 401, the context importance calculation unit 402, the customer importance calculation unit 403, the repair importance calculation unit 404, and the overall importance calculation unit 405 will be explained in order.

[0118] (4-1. Details of the Calculation Process of Time Importance Executed by the Temporal Importance Calculation Unit) First, the details of the calculation process of time importance executed by the temporal importance calculation unit 401 will be described.

[0119] The processing executed by the time importance calculation unit 401 will be described with reference to Fig. 14. As shown in Fig. 14, the time importance calculation unit 401 receives the user input information 210 and the product state information 211 from the product state identification unit 102, calculates the time importance 221 by referring to the defect report information DB 123, and outputs the calculated time importance 221 to the overall importance calculation unit 405.

[0120] The time importance calculated by the time importance calculation unit 401 is an importance that is set to a higher value the higher the ranking of the number of occurrences of a product state (failure or malfunction) that matches the product state (failure or malfunction) reported by a user among all the various product states (failures or malfunctions) reported by a large number of users over a specified period for products of the same type as the product used by the user.

[0121] For example, suppose the electrical appliance used by a user is a smartphone. Suppose that various product conditions (failures and malfunctions) such as poor communication, poor battery, and poor housing have been reported by many users over a predetermined period (for example, the past year) regarding smartphones. Suppose that the number of cases reported over the past year was as follows: Number of reports regarding poor communication = 250 Number of reports regarding poor battery = 120 ... Number of reports regarding poor housing = 5 ...

[0122] Here, suppose that the product condition (failure or malfunction) reported by the user under consideration this time is “poor communication.” In the above example, “poor communication” is the largest number of product conditions (failure or malfunction) reported in a predetermined period (e.g., the past year) related to smartphones, so the time importance of the product condition (failure or malfunction) reported by the user under consideration this time = “poor communication” is calculated as high importance.

[0123] Also, for example, if the product condition (failure or malfunction) reported by the user under consideration this time is "faulty housing," in the above example, the number of reports of "faulty housing" within a predetermined period (e.g., the past year) is five, which is small. In this case, the time importance of the product condition (failure or malfunction) reported by the user = "faulty housing" is calculated as low importance.

[0124] The database that the time importance calculation unit 401 refers to when calculating the time importance is the defect report information DB 123. An example of data stored in the defect report information DB 123 is shown in FIG.

[0125] 15, the defect report information DB 123 stores the following data in association with each other: (a) date, (b) customer ID, (c) report ID, (d) report document, (e) product status identifier, and (f) product status.

[0126] "(a) Date" is the date on which a report of the product status (failure, malfunction, etc.) was received from the user (user input information to the UI shown in Figure 6). "(b) Customer ID" is the identifier of the user who sent the report of the product status (failure, malfunction, etc.). "(c) Report ID" is the identifier of each report of the product status (failure, malfunction, etc.). "(d) Report Document" is an explanatory text created by the user and included in the report of the product status (failure, malfunction, etc.). "(e) Product Status Identifier" is the identifier of each product status (failure, malfunction, etc.). "(f) Product Status" is data indicating the specific content of the product status (failure, malfunction, etc.). Note that "(f) Product Status" corresponds to user input information or the result of analysis by the product status identification unit 102.

[0127] The time importance calculation unit 401 calculates the time importance by referring to the data stored in the defect report information DB 123 that stores the data shown in Fig. 15. Specifically, the time importance is calculated based on the ranking of the number of reports of product states (failures and defects) that match the product state (failures and defects) analyzed from the user reports that are the subject of time importance calculation.

[0128] Fig. 16 is a diagram showing an example of a specific calculation process of time importance. The graph shown in Fig. 16 has the "ranking of the number of reports of each product state stored in the defect report information DB (within a specified period)" on the horizontal axis and the time importance (0 to 1.0) on the vertical axis. The time importance is set in the range of 0 to 1.0, with the closer to 0 the lower the time importance and the closer to 1.0 the higher the time importance.

[0129] The graph shown in the figure is a graph showing a function that calculates time importance (f(x)) based on the value x of the horizontal axis (x-axis) setting, "ranking of the number of reports for each product condition stored in the defect report information DB (within a specified period)." The function f(x) is the following function: f(x)=e-0.01(x-1)

[0130] The time importance calculation unit 401 calculates the time importance (0 to 1.0) based on the value x of the "ranking of the number of reports of each product condition stored in the defect report information DB (within a specified period)" according to, for example, the above function (f(x) = e-0.01(x-1)).

[0131] FIG. 16 shows an example in which the time importance f(x) = 0.91 is calculated when x = 10, i.e., when the ranking of the number of reports of each product condition stored in the defect report information DB (within a specified period) is x = 10th.

[0132] The function shown in FIG. 16 is an example, and the time importance calculation unit 401 may be configured to calculate the time importance using a function other than the function shown in FIG.

[0133] In this way, the time importance calculated by the time importance calculation unit 401 is importance information that indicates a higher value when the number of reports within a specified period (e.g., within one year) regarding the same product condition (failure or malfunction) as the product condition (failure or malfunction) reported by the user is greater compared to other product conditions.

[0134] As described with reference to FIG. 14, the time importance 221 calculated by the time importance calculation unit 401 is input to the overall importance calculation unit 405 and used in the calculation process of the overall importance.

[0135] (4-2. Details of the Context Importance Calculation Process Executed by the Context Importance Calculation Unit) Next, the details of the context importance calculation process executed by the context importance calculation unit 402 will be described.

[0136] The processing executed by the context importance calculation unit 402 will be described with reference to Fig. 17. As shown in Fig. 17, the context importance calculation unit 402 receives the user input information 210 and the product state information 211 from the product state identification unit 102, calculates the context importance 222, and outputs the calculated context importance 222 to the overall importance calculation unit 405.

[0137] The context importance calculated by the context importance calculation unit 402 is an importance that is set to a higher value as the assertiveness of the description of the product state included in the report from the user, i.e., the user input information 210 input from the product state identification unit 102, increases. The context importance calculated by the context importance calculation unit 402 is set in the range of 0 to 1.0, with the context importance being lower the closer to 0, and higher the context importance being closer to 1.0.

[0138] Specifically, if the description of the product condition created by the user contains many words that express, for example, scolding or anger toward the product, it is determined to be highly assertive, and the context importance is set to a high value (close to 1.0).

[0139] The detailed configuration of the context importance calculation unit 402 and the details of the processing executed by the context importance calculation unit 402 will be described with reference to Fig. 18. As shown in Fig. 18, the context importance calculation unit 402 includes a data extraction unit 421 and a learning model 422.

[0140] The data extraction unit 421 extracts data to be input to the learning model 422 from the user input information 210 input from the product state identification unit 102 and the product state information 211. Specifically, the data includes product type information, product state information, and product state description, and these data are input to the learning model 422.

[0141] The learning model 422 outputs the context importance 222 based on these input data. The learning model 422 is a learning model generated in advance by a learning process using a large number of different sample data, specifically sentences describing the product state. For example, if the product state description contains many words expressing criticism or anger toward the product, the learning model 422 outputs a high value of the context importance, and if it contains many understated expressions, the learning model 422 outputs a low value of the context importance.

[0142] The learning model 422 is a learning model that uses, for example, a DNN (Deep Neural Network), and is a learning model that analyzes a document created by a user, that is, a "document explaining the product state."

[0143] Specifically, it is possible to use a learning model that uses BERT (Bidirectional Encoder Representations from Transformers), which is a natural language processing learning model used in the product state identification unit 102 described above with reference to FIG. 5 .

[0144] However, the learning model 422 used in the context importance calculation unit 402 is not limited to a model using BERT, and learning models with other configurations may be used. Various types of learning models can be used, which analyze the "explanation document of the product state" created by the user and output a higher value of context importance as the "explanation document of the product state" becomes more assertive.

[0145] In this way, the context importance calculated by the context importance calculation unit 402 is importance information that indicates a higher value as the assertiveness of the "explanation document of the product state" created by the user becomes higher.

[0146] As described with reference to FIG. 17, the context importance 222 calculated by the context importance calculation unit 402 is input to the overall importance calculation unit 405 and used in the calculation process of the overall importance.

[0147] (4-3. Details of the Customer Importance Calculation Process Executed by the Customer Importance Calculation Unit) Next, the details of the customer importance calculation process executed by the customer importance calculation unit 403 will be described.

[0148] The processing executed by the customer importance calculation unit 403 will be described with reference to Fig. 19. As shown in Fig. 19, the customer importance calculation unit 403 receives the user input information 210 and the product state information 211 from the product state identification unit 102, calculates the customer importance 223 by referring to the customer information DB 122, and outputs the calculated customer importance 223 to the overall importance calculation unit 405.

[0149] The customer importance calculated by the customer importance calculation unit 403 is an importance that is set to a higher value the more types of products that the user (customer) who generated the user input information 210 input from the product status identification unit 102 has purchased within a specified period (e.g., five years) that are highly similar to the product for which the user is reporting the product status (failure, malfunction, etc.).

[0150] For example, suppose the product for which a user (customer) reported a product condition (such as a malfunction or defect) is a smartphone. The more products (such as smartphones, PCs, tablet devices, etc.) similar to the smartphone that the user has purchased over a predetermined period (such as the past three years), the higher the customer importance is calculated to be.

[0151] On the other hand, the fewer the number of products (e.g., smartphones, PCs, tablet devices, etc.) similar to the smartphone that this user has purchased over a predetermined period (e.g., the past three years), the lower the customer importance is calculated to be. Note that the customer importance is set in the range of 0 to 1.0, with the closer to 0 the lower the customer importance and the closer to 1.0 the higher the customer importance.

[0152] The database that the customer importance calculation unit 403 refers to when calculating the customer importance is the customer information DB 122. An example of data stored in the customer information DB 122 is shown in FIG.

[0153] As shown in Fig. 20, the customer information DB 122 stores the following data in association with each other: (a) customer ID, (b) product purchase history information, (b1) product identifier, (b2) product type, and (b3) purchase date.

[0154] "(a) Customer ID" is the identifier of the user (customer) who sent the report on the product status (failure, malfunction, etc.). "(b) Product purchase history information" records (b1) product identifier, (b2) product type, and (b3) purchase date. "(b1) Product identifier" is the identifier of the product purchased by the user (customer). "(b2) Product type" is the type of product purchased by the user (customer). "(b3) Purchase date" is the date on which the user (customer) purchased the product.

[0155] The customer importance calculation unit 403 calculates the customer importance by referring to the data stored in the customer information DB 122, which stores the data shown in Fig. 20. Specifically, the number of products purchased over a predetermined period (e.g., the past three years) of a type (category) highly similar to the product for which the user (customer) whose product condition (failure, defect, etc.) is reported by the user (customer) for whom the customer importance is to be calculated is analyzed, and the greater the number of purchases, the higher the calculated customer importance.

[0156] The detailed configuration of the customer importance calculation unit 403 and the details of the processing executed by the customer importance calculation unit 403 will be described with reference to Fig. 21. As shown in Fig. 20, the customer importance calculation unit 403 has a data extraction unit 431, learning models 432-1 to 432-N, and a customer importance calculation unit 433.

[0157] The data extraction unit 431 extracts data to be input to the learning models 432-1 to 432-N from the user input information 210 input from the product state identification unit 102 and the product state information 211. Specifically, the data extracted are the customer ID, product type, product state information, and product state description, and are input to the learning models 432-1 to 432-N.

[0158] Each of learning models 432-1 to 432-N receives the data (customer ID, product type, product status information, and product status description) extracted by data extraction unit 431 and outputs the product importance for each product type. The product importance calculated by each of learning models 432-1 to 432-N is a value ranging from 0 to 1.0, with the closer to "0" the lower the product importance and the closer to "1.0" the higher the product importance.

[0159] Each of the learning models 432-1 to 432-N is a learning model that outputs a product importance corresponding to a different type of product 1 to N. The higher the similarity between the product and the product whose condition (failure, defect, etc.) reported by the user (customer) and the greater the number of product purchases within a predetermined period, the higher the product importance value that is output.

[0160] Each of learning models 432-1 to 432-N calculates and outputs product importance corresponding to a different product type (product types 1 to N). For example, learning model 432-1 calculates and outputs product importance corresponding to product type 1 (= smartphone). Learning model 432-2 calculates and outputs product importance corresponding to product type 2 (= PC). Learning model 432-3 calculates and outputs product importance corresponding to product type 3 (= refrigerator). ... In this way, each of learning models 432-1 to 432-N calculates and outputs product importance corresponding to a different product type (product types 1 to N).

[0161] For example, if the product for which a user (customer) reported a product condition (failure, malfunction, etc.) is a smartphone, the output value (smartphone-compatible product importance) of learning model 432-1, which calculates the product importance corresponding to product type 1 (= smartphone), will be higher the more smartphones purchased within a specified period. Similarly, the output value (smartphone-compatible product importance) of learning model 432-2, which calculates the product importance corresponding to product type 2 (= PC), will be higher the more PCs purchased within a specified period. This is because learning model 432-1 and learning model 432-2 are learning models that each calculate product importance for products (smartphone, PC) similar to the product (smartphone) for which a user (customer) reported a product condition (failure, malfunction, etc.).

[0162] On the other hand, the output value (smartphone-compatible product importance) of learning model 432-3, which calculates the product importance corresponding to product type 3 (=refrigerator), is low even if the number of refrigerator purchases within a specified period is large. This is because learning model 432-3 is a learning model that calculates the product importance corresponding to a product (refrigerator) that is not similar to the product (smartphone) for which the user (customer) reported the product condition (breakdown, malfunction, etc.).

[0163] In this way, each of learning models 432-1 to 432-N calculates and outputs the similarity between the product and the product whose product condition (failure, defect, etc.) was reported by the user (customer) being analyzed, and the product importance according to the number of product purchases over a specified period (e.g., the past three years), for each corresponding individual product type 1 to N.

[0164] Specifically, these learning models 432-1 to 432-N are learning models using, for example, a deep neural network (DNN). For example, it is possible to use a learning model using bidirectional encoder representations from transformers (BERT), which is a natural language processing learning model used in the product state identification unit 102 described above with reference to FIG.

[0165] However, the learning models 432-1 to 432-N used in the customer importance calculation unit 403 are not limited to models using BERT, and learning models having other configurations may also be used.

[0166] Learning models 432-1 to 432-N can be of various types, each configured to calculate and output the similarity between the product and the product whose condition (failure, defect, etc.) has been reported by the user (customer) being analyzed, and the product importance based on the number of product purchases over a specified period (e.g., the past three years), for each corresponding individual product type 1 to N.

[0167] The product importance (product 1 importance to product N importance) corresponding to the product type (product type 1 to N) calculated by each of the learning models 432 - 1 to 432 -N is input to the customer importance calculation unit 433 .

[0168] The customer importance calculation unit 433 calculates the customer importance using the product importance (product 1 importance to product N importance) corresponding to the product type (product type 1 to N) calculated by each of the learning models 432-1 to 432-N. Specifically, the customer importance is calculated according to the following calculation formula:

[0169] Customer importance = (Product 1 importance + Product 2 importance + ... + Product N importance) / N

[0170] In this way, the customer importance is calculated by analyzing the products purchased by the user (customer) whose customer importance is to be calculated over a predetermined period (e.g., the past three years). That is, the customer importance calculation unit 403 calculates a customer importance (0 to 1.0) that becomes higher the more products similar to the product whose product condition (failure, defect, etc.) the user (customer) whose customer importance is to be calculated has purchased over a predetermined period (e.g., the past three years).

[0171] As described with reference to FIG. 19, the customer importance 223 calculated by the customer importance calculation unit 403 is input to the overall importance calculation unit 405 and used in the calculation process of the overall importance.

[0172] (4-4. Details of the Repair Importance Calculation Process Executed by the Repair Importance Calculation Unit) Next, the repair importance calculation process executed by the repair importance calculation unit 404 will be described in detail.

[0173] The processing executed by the repair importance calculation unit 404 will be described with reference to Fig. 22. As shown in Fig. 22, the repair importance calculation unit 404 receives the user input information 210 and the product state information 211 from the product state identification unit 102, calculates the repair importance 224 by referring to the repair information DB 121, and outputs the calculated repair importance 224 to the overall importance calculation unit 405.

[0174] The repair importance calculated by the repair importance calculation unit 404 is set to a higher value the higher the percentage of repairs performed for the same product state (failure or malfunction) as reported by the user. The repair importance calculated by the repair importance calculation unit 404 is set in the range of 0 to 1.0, with the closer to 0 the lower the repair importance and the closer to 1.0 the higher the repair importance.

[0175] For example, if the product used by a user is a smartphone and the product condition (failure or malfunction) reported by the user is a defective battery, for smartphones of the same type as the smartphone used by this user, the higher the ratio of the number of repairs (repairs) to the number of reports of battery defects received over a predetermined period in the past (e.g., the past year), the higher the calculated repair importance (a value closer to 1.0).

[0176] On the other hand, for example, if the product condition (failure or malfunction) reported by a user is a communication failure, and for smartphones of the same type as the smartphone used by this user, the lower the ratio of the number of repair responses (number of repairs) to the number of reports of communication failures received over a specified period in the past (for example, the past year), the lower the value (closer to 0.0) of repair importance will be calculated.

[0177] The database that the repair importance calculation unit 404 refers to when calculating the repair importance is the repair information DB 121. An example of data stored in the repair information DB 121 is shown in FIG.

[0178] 23, the repair information DB 121 stores the following data in association with each other: (a) date, (b) customer ID, (c) report ID, (d) report document, (e) product status identifier, (f) product status, (g) repair reception ID, and (h) repair content.

[0179] "(a) Date" is the date on which a report of the product status (failure, malfunction, etc.) was received from the user (user input information to the UI shown in Figure 6). "(b) Customer ID" is the identifier of the user who sent the report of the product status (failure, malfunction, etc.). "(c) Report ID" is the identifier of each report of the product status (failure, malfunction, etc.). "(d) Report Document" is an explanatory text created by the user and included in the report of the product status (failure, malfunction, etc.). "(e) Product Status Identifier" is the identifier of each product status (failure, malfunction, etc.). "(f) Product Status" is data indicating the specific content of the product status (failure, malfunction, etc.), and is user input information or the product status analyzed by the product status identification unit 102.

[0180] "(g) Repair reception ID" is an ID that is set when repairs are made to the product condition (failure, malfunction, etc.) reported by the user. It is not set if no repairs are made. "(h) Repair details" records the specific repair details when repairs are made to the product condition (failure, malfunction, etc.) reported by the user. It is not recorded if no repairs are made.

[0181] The repair importance calculation unit 404 calculates the repair importance by referring to the data stored in the repair information DB 121 that stores the data shown in Fig. 23. Specifically, the higher the percentage of repairs performed for the same product state (failure or malfunction) as reported by the user, the higher the repair importance calculated.

[0182] The detailed configuration of the repair importance calculation unit 404 and the details of the processing executed by the repair importance calculation unit 404 will be described with reference to Fig. 24. As shown in Fig. 24, the repair importance calculation unit 404 has a data extraction unit 441 and a repair importance calculation unit 442.

[0183] The data extraction unit 441 extracts data to be input to the repair importance calculation unit 442 from the user input information 210 input from the product state identification unit 102 and the product state information 211. Specifically, the data extraction unit 441 extracts product type information, product state information, and product state description, and inputs these data to the repair importance calculation unit 442.

[0184] The repair importance calculation unit 442 outputs the repair importance 224 based on these input data and the data stored in the repair information DB 121 described above with reference to Fig. 23. The repair importance calculation unit 442 calculates the percentage (repair percentage) of repairs performed for product conditions identical to the product condition (failure or malfunction) reported by the user, and calculates a repair importance (0 to 1.0) according to the calculated repair percentage.

[0185] Specifically, the repair importance calculation unit 442 calculates the repair importance according to the following repair importance calculation formula: Repair importance=(number of repairs handled / number of reports)

[0186] The "number of reports" refers to the number of reports about the same product condition (failure or malfunction) as reported by the user. The "number of repairs handled" refers to the number of repairs carried out among the number of reports. The numbers of reports and repairs handled are obtained and used within a predetermined period, such as the past year.

[0187] The repair importance calculated by the repair importance calculation unit 404 according to the above repair importance calculation formula is a value in the range of 0 to 1.0, with the closer to 0 the lower the repair importance and the closer to 1.0 the higher the repair importance.

[0188] In this way, the repair importance calculated by the repair importance calculation unit 404 is importance information that indicates a higher value the more repairs are performed relative to the number of reports of the same product condition (failure or malfunction) reported by the user.

[0189] As described with reference to FIG. 22, the repair importance 224 calculated by the repair importance calculation unit 404 is input to the overall importance calculation unit 405 and used in the calculation process of the overall importance.

[0190] (4-5. Details of the overall importance calculation process executed by the overall importance calculation unit) Next, the overall importance calculation process executed by the overall importance calculation unit 405 will be described in detail.

[0191] The processing executed by the overall importance calculation unit 403 will be described with reference to Fig. 25. As shown in Fig. 25, the overall importance calculation unit 403 receives four types of importance information calculated by the following four different importance calculation units: (a) time importance calculated by the time importance calculation unit 401; (b) context importance calculated by the context importance calculation unit 402; (c) customer importance calculated by the customer importance calculation unit 403; and (d) repair importance calculated by the repair importance calculation unit 404.

[0192] The overall importance calculation unit 403 receives the four types of importance information calculated by the four different importance calculation units and calculates the overall importance using these four types of importance information. The overall importance calculated by the overall importance calculation unit 403 is a value in the range of 0 to 1.0.

[0193] The overall importance calculation unit 403 calculates the overall importance according to the following calculation formula, for example: Overall importance=(time importance+context importance+customer importance+repair importance) / 4

[0194] The above formula calculates the overall importance as the average value of the time importance, the context importance, the customer importance, and the repair importance.

[0195] Instead of using the above formula, the total importance may be calculated by multiplying each of the four levels of importance by a weighting coefficient a to d (where a+b+c+d=1) that corresponds to each level of importance, and adding the resulting values ​​together: Total importance = (a x time importance) + (b x context importance) + (c x customer importance) + (d x repair importance).

[0196] As shown in FIG. 25 , the overall importance calculated by the overall importance calculation unit 403 is input to the developer presentation information generation unit 104 and the user presentation information generation unit 105 together with the four different types of importance information used to calculate the overall importance.

[0197] That is, the following five different pieces of importance information are input to the developer presentation information generation unit 104 and the user presentation information generation unit 105: (a) time importance calculated by the time importance calculation unit 401, (b) context importance calculated by the context importance calculation unit 402, (c) customer importance calculated by the customer importance calculation unit 403, (d) repair importance calculated by the repair importance calculation unit 404, and (e) overall importance calculated by the overall importance calculation unit 405.

[0198] 5. Processing Sequence Executed by Importance Calculation Unit Next, a processing sequence executed by the importance calculation unit 103 will be described.

[0199] The sequence of the process executed by the importance calculation unit 103 shown in FIG. 13 or 25 will be described with reference to the flowchart shown in FIG.

[0200] The processing according to the flowchart shown in Fig. 26 can be executed under the control of a control unit in accordance with a program stored in a storage unit of the information processing device 100 of the present disclosure. The control unit has a processor such as a CPU having a program execution function, and controls the processing according to the flow by program execution processing using the processor. The processing of each step of the flow shown in Fig. 26 will be described below in order.

[0201] (Step S201) First, in step S201, the necessity calculation unit 103 of the information processing device 100 inputs the received data (user input information) from the user terminal via the product state identification unit 102 and the product state information that is the analysis result of the product state identification unit 102.

[0202] As described with reference to FIG. 6 etc., the data received from the user terminal (user input information) is data entered by the user for the following data input items: (a) Customer number (required) (b) Product name (required) (c) Product status description (required) (d) Registered product status (optional)

[0203] (Step S202) Next, in step S202, the time importance calculation unit 401 calculates the time importance.

[0204] The time importance calculation process executed by the time importance calculation unit 401 is the process previously described with reference to Fig. 14 to Fig. 16. As previously described with reference to Fig. 14, the time importance calculation unit 401 receives the user input information 210 and the product state information 211 from the product state identification unit 102, and calculates the time importance 221 by referring to the defect report information DB 123.

[0205] The time importance calculated by the time importance calculation unit 401 is set to a higher value the higher the ranking of the number of occurrences of a product state (failure or malfunction) that matches the product state (failure or malfunction) reported by a user among all the various product states (failures or malfunctions) reported by a large number of users over a predetermined period for products of the same type as the product used by the user. Note that the time importance calculated by the time importance calculation unit 401 is set in the range of 0 to 1.0, with the closer to 0 the lower the time importance and the closer to 1.0 the higher the time importance.

[0206] (Step S203) Next, in step S203, the context importance calculation unit 402 calculates the context importance.

[0207] The context importance calculation process executed by the context importance calculation unit 402 is the process previously described with reference to FIGS.

[0208] 18 , the context importance calculation unit 402 has a data extraction unit 421 and a learning model 422. The data extraction unit 421 extracts product type information, product state information, and product state description from the user input information 210 and product state information 211 input from the product state identification unit 102, and inputs these data to the learning model 422. The learning model 422 outputs the context importance 222 based on this input data.

[0209] The context importance calculated by the context importance calculation unit 402 is importance information that indicates a higher value the more assertive the "product condition description" created by the user. For example, if the product condition description created by the user contains many expressions expressing scolding or anger toward the product, a high value of context importance is output, and if it contains many understated expressions, a low value of context importance is output.

[0210] The context importance calculated by the context importance calculation unit 402 is set in the range of 0 to 1.0, with the closer to 0 the context importance is, the lower the context importance is, and the closer to 1.0 the context importance is, the higher the context importance is.

[0211] (Step S204) Next, in step S204, the customer importance calculation unit 403 calculates the customer importance.

[0212] The customer importance calculation process executed by the customer importance calculation unit 403 is the process previously described with reference to FIGS.

[0213] As previously explained with reference to FIG. 21 , the customer importance calculation unit 403 has a data extraction unit 431, learning models 432-1 to 432-N, and a customer importance calculation unit 433. The data extraction unit 431 extracts the customer ID, product type information, product status information, and product status description from the user input information 210 input from the product status identification unit 102 and the product status information 211, and inputs these data into the learning models 432-1 to 432-N.

[0214] Each of learning models 432-1 to 432-N inputs the data extracted by data extraction unit 431 and outputs the product importance for each product type. Each of learning models 432-1 to 432-N calculates and outputs the similarity between the product and the product whose product condition (failure, defect, etc.) was reported by the user (customer) being analyzed and the product importance according to the number of product purchases over a predetermined period (e.g., the past three years) for each corresponding individual product type 1 to N.

[0215] The product importance (product 1 importance to product N importance) corresponding to the product type (product type 1 to N) calculated by each of the learning models 432 - 1 to 432 -N is input to the customer importance calculation unit 433 .

[0216] The customer importance calculation unit 433 calculates the customer importance using the product importance (product 1 importance to product N importance) corresponding to the product type (product type 1 to N) calculated by each of the learning models 432-1 to 432-N, according to the following calculation formula: Customer importance = (product 1 importance + product 2 importance + ... + product N importance) / N

[0217] In this way, the customer importance is calculated by analyzing the products purchased by the user (customer) whose customer importance is to be calculated over a predetermined period (e.g., the past three years). That is, the customer importance calculation unit 403 calculates a customer importance (0 to 1.0) that becomes higher the more products similar to the product whose product condition (failure, defect, etc.) the user (customer) whose customer importance is to be calculated has purchased over a predetermined period (e.g., the past three years).

[0218] (Step S205) Next, in step S205, the repair importance calculation unit 404 calculates the repair importance.

[0219] The repair importance calculation process executed by the repair importance calculation unit 404 is the process previously described with reference to FIGS.

[0220] As previously described with reference to FIG. 22 , the repair importance calculation unit 404 inputs the user input information 210 and the product state information 211 from the product state identification unit 102, and calculates the repair importance 224 by referring to the repair information DB 121.

[0221] The repair importance calculated by the repair importance calculation unit 404 is set to a higher value the higher the percentage of repairs performed for the same product state (failure or malfunction) as reported by the user. The repair importance calculated by the repair importance calculation unit 404 is set in the range of 0 to 1.0, with the closer to 0 the lower the repair importance and the closer to 1.0 the higher the repair importance.

[0222] 24 , the repair importance calculation unit 404 has a data extraction unit 441 and a repair importance calculation unit 442. The data extraction unit 441 extracts data to be input to the repair importance calculation unit 442 from the user input information 210 input from the product state identification unit 102 and the product state information 211. Specifically, the data extraction unit 441 extracts product type information, product state information, and product state description, and inputs these data to the repair importance calculation unit 442.

[0223] The repair importance calculation unit 442 outputs the repair importance 224 based on these input data and the data stored in the repair information DB 121 described above with reference to Fig. 23. The repair importance calculation unit 442 calculates the percentage (repair percentage) of repairs performed for product conditions identical to the product condition (failure or malfunction) reported by the user, and calculates a repair importance (0 to 1.0) according to the calculated repair percentage.

[0224] Specifically, the repair importance calculation unit 442 calculates the repair importance according to the following repair importance calculation formula: Repair importance=(number of repairs handled / number of reports)

[0225] (Step S206) Next, in step S206, the overall importance calculation unit 405 calculates the overall importance.

[0226] The overall importance calculation process executed by the overall importance calculation unit 405 is the process described above with reference to FIG.

[0227] As described above, the overall importance calculation unit 403 calculates the overall importance according to the following calculation formula, for example: Overall importance=(time importance+context importance+customer importance+repair importance) / 4

[0228] Alternatively, instead of using the above formula, the total importance may be calculated by multiplying each of the four levels of importance by a weighting coefficient a to d (where a+b+c+d=1) corresponding to each level of importance, and adding the resulting values ​​together: Total importance = (a x time importance) + (b x context importance) + (c x customer importance) + (d x repair importance).

[0229] (Step S207) Finally, in step S207, the importance calculation unit 103 calculates the following five types of importance information calculated in steps S202 to S206, namely: (a) time importance calculated by the time importance calculation unit 401; (b) context importance calculated by the context importance calculation unit 402; (c) customer importance calculated by the customer importance calculation unit 403; (d) repair importance calculated by the repair importance calculation unit 404; and (e) overall importance calculated by the overall importance calculation unit 405.

[0230] These five pieces of importance information are output to the developer presentation information generation unit 104 and the user presentation information generation unit 105 .

[0231] 6. Processing Executed by the Developer-Directed Presentation Information Generator Next, processing executed by the developer-directed presentation information generator will be described.

[0232] 3 receives the user input information 210 via the product state identification unit 102, and also receives the product state information analyzed by the product state identification unit 102. Furthermore, the developer presentation information generation unit 104 receives the importance information calculated by the importance calculation unit 103, i.e., the following importance information: (a) time importance calculated by the time importance calculation unit 401; (b) context importance calculated by the context importance calculation unit 402; (c) customer importance calculated by the customer importance calculation unit 403; (d) repair importance calculated by the repair importance calculation unit 404; and (e) overall importance calculated by the overall importance calculation unit 405.

[0233] Based on this input information, the developer presentation information generation unit 104 generates presentation information for the product development staff 51. For example, information consisting of statistical information such as the types of failures by product type is generated as "developer presentation information (feedback information) 220" shown in FIG. 3 and is sent to the developer terminal 52, which is the terminal of the product development staff 51.

[0234] 27 and subsequent figures, a specific example of the "developer presentation information (feedback information) 220" generated by the developer presentation information generation unit 104 and transmitted to and displayed on the developer terminal 52 of the product developer 51 will be described.

[0235] 27 is a diagram showing an example of display data on the developer terminal 52 of the product developer 51, which is an example of display data generated in response to one piece of user input information 210. This display data is generated by the developer presentation information generation unit 104, and is transmitted to and displayed on the developer terminal 52 of the product developer 51.

[0236] The display data shown in Fig. 27 is composed of the following data: (a) Customer number (b) Product name (c) Product status description (d) Product status (e) Importance analysis results

[0237] "(a) Customer number" is the identifier of the user who sent the report on the product status (failure, malfunction, etc.). "(b) Product name" is the type and model number of the product used by the user who reported the product status (failure, malfunction, etc.).

[0238] "(c) Product Status Description" is a description of the product status (failure, malfunction, etc.) created by the user and included in the user input information 210. "(d) Product Status" is data indicating the specific details of the product status (failure, malfunction, etc.), and is the user input information or the product status analyzed by the product status identification unit 102. Along with this "(d) Product Status", the overall importance calculated by the importance calculation unit 103 is displayed. "(e) Importance Analysis Result" is importance information calculated by the importance calculation unit 103, and includes time importance, customer importance, context importance, and repair importance.

[0239] In the example shown in FIG. 27, two types of product status are output as "(d) Product status", namely, 1. Communication failure 2. Battery life These two types of product status are output, and the display data includes the overall importance, time importance, customer importance, context importance, and repair importance for each of these two types of product status.

[0240] The product development staff 51 can check the specific product status (failure, malfunction, etc.) that occurred in the product (smartphone SAAA) by looking at this display data. Furthermore, by referring to the values ​​of overall importance, time importance, customer importance, context importance, and repair importance, it is possible to check the frequency of occurrence, urgency, repair response status, etc. of the product status (failure, malfunction, etc.) reported by the user.

[0241] 27 is an example of display data generated in response to one user report, i.e., user input information 210, but the developer presentation information generation unit 104 also executes processing to generate list data of user reports from a predetermined period in the past (e.g., one year), as well as various analytical data and statistical information, and transmit and display them to the developer terminal 52. Examples of this display data will be described with reference to Figure 28 onwards.

[0242] FIG. 28 shows an example of a list of a large number of user reports about a certain product (e.g., a smartphone) displayed on the developer terminal 52.

[0243] 28, various display data selection icons that can be selected by the product developer 51 are displayed in the upper section of the display unit of the developer terminal 52. That is, (1) Report list (2) New status (3) Time importance (4) Context importance (5) Customer importance (6) Repair importance These display data selection icons are displayed, and the user can select (touch) any icon from these display data selection icons to switch between various display data.

[0244] 28 shows an example of report list data that is displayed when the product developer 51 selects "report list." The "report list" display data is display data that shows a list of user reports (user input information) that have been received up to now.

[0245] The display data of the "report list" shown in Fig. 28 is composed of the corresponding data for each of the following data: (a) Date (b) Report ID (c) Report document (d) Product status identifier (e) Product status (f) Product type (g) Customer ID

[0246] "(a) Date" is the date on which a report of the product status (failure, malfunction, etc.) was received from the user (user input information to the UI shown in Figure 6). "(b) Report ID" is an identifier for each report of the product status (failure, malfunction, etc.). "(c) Report Document" is an explanatory text created by the user and included in the report of the product status (failure, malfunction, etc.). "(d) Product Status Identifier" is an identifier for each product status (failure, malfunction, etc.).

[0247] "(e) Product status" is data indicating the specific details of the product status (failure, malfunction, etc.), and is user-input information or the product status analyzed by the product status identification unit 102. "(f) Product type" is the type of product for which the product status (failure, malfunction, etc.) was reported. "(g) Customer ID" is the identifier of the user who sent the report of the product status (failure, malfunction, etc.).

[0248] The display data of the "report list" shown in FIG. 28 can be freely changed in the period of data to be displayed by the product development person 51 through scrolling.

[0249] By looking at the display data consisting of this report list, the product development staff 51 can check the specific product status (failures, malfunctions, etc.) occurring in the product (smartphone), and can also analyze failure trends and consider countermeasures.

[0250] 29 is the data that is displayed when the product developer 51 selects "new state." The "new state" display data is display data that shows a list of user reports (user input information) in which the product state (failure, defect, etc.) analyzed based on the user reports (user input information) is a product state that is not registered in the product state information DB 111.

[0251] When displaying this "new status" display data, the product developer 51 must specify the product to be displayed. The example shown in FIG. 29 is an example of display data when product type = smartphone and product identifier = SAAA are specified. That is, the "new status" display data shown in FIG. 29 shows a list of user reports (user input information) for a specific product with product type = smartphone and product identifier = SAAA, in which the product status (failure, malfunction, etc.) of the user report (user input information) is a product status that is not registered in the product status information DB 111.

[0252] The period of the displayed data can also be freely changed by the product development person 51 through scrolling.

[0253] As described above, the "new state" refers to a product state that is not registered in the product state information DB 111. As previously described with reference to Fig. 7, data folders are set for each product type in the product state information DB 111, and "product states" indicating various malfunctions and defects are registered for each product type in association with "product state identifiers."

[0254] The product statuses registered in the product status information DB 111 are set as product statuses that can be selected and input into one item "(d) Registered product status)" of the UI described above with reference to FIG. 6, that is, the UI that is used by the user to notify the electrical equipment manufacturer 50 of the situation when a malfunction occurs in the electrical equipment.

[0255] However, the product states (failures, defects, etc.) that occur in products used by users are not limited to the product states registered in the product state information DB 111, and it is not uncommon for product states (failures, defects, etc.) that are not registered in the product state information DB 111 to occur.

[0256] The display data shown in Figure 29 is an example of display data that selects reports of product conditions (failures, defects, etc.) that are not registered in the product condition information DB111 from user reports about a certain product (e.g., a smartphone), and displays new conditions analyzed from these reports as list data.

[0257] As described above, the product condition analysis process based on the user report (user input information 210) is executed by the product condition identification unit 102, and the product condition identification unit 102 also determines whether the product is in a new state. The display data shown in Fig. 29 displays only the states that the product condition identification unit 102 has determined to be in a new state as a single column of data.

[0258] The display data of the new state shown in Fig. 29 is made up of the corresponding data for each of the following data: (a) Date (b) Report ID (c) Report document (d) Product status (e) Customer ID

[0259] "(a) Date" is the date on which a report of the product status (failure, malfunction, etc.) was received from the user (user input information to the UI shown in FIG. 6). "(b) Report ID" is an identifier for each report of the product status (failure, malfunction, etc.). "(c) Report Document" is an explanatory text created by the user and included in the report of the product status (failure, malfunction, etc.).

[0260] "(d) Product status" is data indicating the specific details of the product status (failure, malfunction, etc.), and is a product status (failure, malfunction, etc.) that is not registered in the product status information DB 111, i.e., a new product status. It is the product status analyzed by the product status identification unit 102. "(e) Customer ID" is the identifier of the user who sent the report of the product status (failure, malfunction, etc.).

[0261] By looking at the display data consisting of this report list, the product development staff 51 can confirm any new product conditions (failures, malfunctions, etc.) that have been confirmed to have occurred in the product (smartphone SAAA), and can consider countermeasures for the new product conditions (failures, malfunctions, etc.).

[0262] Next, examples of display data showing the following importance levels calculated by the importance level calculation unit 103 will be described with reference to Figures 30 to 33: (a) Time importance level calculated by the time importance level calculation unit 401 (b) Context importance level calculated by the context importance level calculation unit 402 (c) Customer importance level calculated by the customer importance level calculation unit 403 (d) Repair importance level calculated by the repair importance level calculation unit 404

[0263] First, an example of display data of time importance calculated by the time importance calculation unit 401 will be described with reference to Fig. 30. The display data shown in Fig. 30 is displayed when the product developer 51 selects "time importance" from a plurality of display data selection icons shown in the upper section of the display unit.

[0264] When displaying this "time importance" display data, the product developer 51 needs to specify the product to be displayed and the product status. The example shown in Fig. 30 is an example of display data when product type = smartphone, product identifier = SAAA, and product status = communication failure are specified.

[0265] That is, the display data of "time importance" shown in Figure 30 is: Product type = smartphone, Product identifier = SAAA, Product status = poor communication. This is display data that shows the "time importance" for this specific product and this specific product status.

[0266] The display data for "time importance" shown in FIG. 30 is display data configured as a graph with time (date) on the horizontal axis and time importance (up to 1.0) on the vertical axis.

[0267] 14 to 16, the time importance calculated by the time importance calculation unit 401 is a value (0 to 1.0) that is set according to the ranking of the number of occurrences of a specific product state (communication failure in the example of FIG. 30) among all product states (failures and malfunctions) reported within a predetermined period for products of the same type as the product used by the user. The higher the ranking, the higher the value (closer to 1.0) that is set.

[0268] The graph shown as the display data for "time importance" in Figure 30 is a graph that shows the time progression of the ranking of the number of reports judged as "product condition = poor communication" among the number of reports of all product conditions (failures, malfunctions, etc.) included in user reports for the smartphone SAAA during a pre-specified period (e.g., the past year).

[0269] The example shown in Figure 30 is a graph showing the time progression of "time importance" from January 1, 2022 to December 1, 2022, and is a mountain-shaped graph with a peak (high time importance (close to 1.0)) from August to September 2022.

[0270] This shows that reports of communication problems related to SAAA smartphones increased compared to other problem reports from January to around September 2022, and then gradually decreased. This corresponds to data showing a trend such as, for example, a product or software update being implemented around September 2022 to resolve communication problems, resulting in a decrease in the rate of failures.

[0271] The product development person 51 can check the necessity of taking measures for various product states (failures, defects, etc.) by displaying the "time importance" display data as shown in Fig. 30 on the terminal. In addition, the effectiveness of the measures taken for various defects can also be checked.

[0272] Next, an example of display data of the context importance calculated by the context importance calculation unit 402 will be described with reference to Fig. 31. The display data shown in Fig. 31 is displayed when the product developer 51 selects "context importance" from the multiple display data selection icons shown in the upper section of the display unit.

[0273] When displaying this "context importance" display data, the product developer 51 also needs to specify the product to be displayed and the product status. The example shown in Fig. 31 is an example of display data when product type = smartphone, product identifier = SAAA, and product status = communication failure are specified.

[0274] That is, the display data of "context importance" shown in Figure 31 is: Product type = smartphone, Product identifier = SAAA, Product status = poor communication. This is display data that shows the "context importance" for this specific product and the specific product status.

[0275] As previously described with reference to Figures 17 and 18, the context importance calculated by the context importance calculation unit 402 is importance information that indicates a higher value the more assertive the "product condition description" created by the user. For example, if the product condition description created by the user contains many expressions expressing scolding or anger toward the product, the context importance will be a high value, and if it contains many understated expressions, the context importance will be a low value. The context importance calculated by the context importance calculation unit 402 is set in the range of 0 to 1.0, with the closer to 0 the context importance is, the lower the context importance is, and the closer to 1.0 the context importance is, the higher the context importance is.

[0276] The display data for "Context Importance" shown in Fig. 31 is made up of the corresponding data for each of the following data: (a) Date (b) Report ID (c) Context Importance (d) Report Document (e) Customer ID

[0277] "(a) Date" is the date on which a report of the product status (failure, malfunction, etc.) was received from the user (user input information to the UI shown in FIG. 6). "(b) Report ID" is an identifier for each report of the product status (failure, malfunction, etc.). "(c) Context Importance" is the value of the context importance calculated by the context importance calculation unit 402, and the more assertive the "explanation document of the product status" created by the user, the higher the value.

[0278] "(d) Report document" is a description created by the user and included in the report of the product status (failure, malfunction, etc.). "(e) Customer ID" is the identifier of the user who sent the report of the product status (failure, malfunction, etc.).

[0279] The period of the displayed data can also be freely changed by the product development person 51 through scrolling.

[0280] The product development person 51 can easily understand the degree of assertion of the user, for example, the degree of anger, by looking at the value of the context importance included in the display data of this "context importance."

[0281] Next, an example of display data of the customer importance calculated by the customer importance calculation unit 403 will be described with reference to Fig. 32. The display data shown in Fig. 32 is displayed when the product development person 51 selects "customer importance" from a plurality of display data selection icons shown in the upper part of the display unit.

[0282] When displaying this "customer importance" display data, the product developer 51 also needs to specify the product to be displayed and the product status. The example shown in Fig. 32 is an example of display data when product type = smartphone, product identifier = SAAA, and product status = communication failure are specified.

[0283] That is, the display data of "customer importance" shown in Figure 32 is: Product type = smartphone, Product identifier = SAAA, Product status = poor communication. This is display data that shows the "customer importance" for this specific product and the specific product status.

[0284] 19 to 21, the customer importance calculated by the customer importance calculation unit 403 is calculated by analyzing products purchased over a predetermined period (e.g., the past three years) by the user (customer) whose customer importance is to be calculated. That is, the customer importance calculation unit 403 calculates a customer importance (0 to 1.0) that increases the more products similar to the product whose product condition (failure, defect, etc.) the user (customer) whose customer importance is to be calculated has purchased over a predetermined period (e.g., the past three years).

[0285] The display data for "Customer Importance" shown in Fig. 32 is made up of the corresponding data for each of the following data: (a) Date (b) Report ID (c) Customer Importance (d) Report Document (e) Customer ID (f) Interested Product Group

[0286] "(a) Date" is the date on which a report of the product status (failure, malfunction, etc.) was received from the user (user input information to the UI shown in FIG. 6). "(b) Report ID" is an identifier for each report of the product status (failure, malfunction, etc.). "(c) Customer Importance" is the value of customer importance calculated by the customer importance calculation unit 403, and the more products similar to the product for which the user (customer) reported the product status (failure, malfunction, etc.) over a specified period (e.g., the past three years), the higher the value.

[0287] "(d) Report document" is an explanatory text written by the user and included in the report of the product status (failure, malfunction, etc.). "(e) Customer ID" is the identifier of the user who sent the report of the product status (failure, malfunction, etc.). "(f) Interested product group" indicates the types of products that the user who reported the product status (failure, malfunction, etc.) is presumed to be interested in, based on an analysis of the user's past product purchase history.

[0288] The period of the displayed data can also be freely changed by the product development person 51 through scrolling.

[0289] This "customer importance" display data allows the product development staff 51 to check the level of interest each user (customer) has in a product (e.g., a smartphone), the types of products each user (customer) is purchasing, and so on.

[0290] Next, an example of display data of the repair importance calculated by the repair importance calculation unit 404 will be described with reference to Fig. 33. The display data shown in Fig. 33 is displayed when the product developer 51 selects "repair importance" from the plurality of display data selection icons shown in the upper section of the display unit.

[0291] When displaying this "repair importance" display data, the product developer 51 must specify the product to be displayed and the product status. The example shown in Fig. 33 is an example of display data when product type = smartphone, product identifier = SAAA, and product status = communication failure are specified.

[0292] That is, the display data for "repair importance" shown in Figure 33 is: Product type = smartphone, Product identifier = SAAA, Product condition = poor communication. This is display data that indicates the "repair importance" for this specific product and the specific product condition.

[0293] The display data for "repair importance" shown in FIG. 33 is display data configured as a graph with time (date) on the horizontal axis and repair importance (up to 1.0) on the vertical axis.

[0294] As explained above with reference to Figures 22 to 24, the repair importance calculated by the repair importance calculation unit 404 is an importance that is set to a higher value the higher the percentage of repairs performed for the same product state (failure or malfunction) as reported by the user. The repair importance calculated by the repair importance calculation unit 404 is set in the range of 0 to 1.0, with the closer to 0 the lower the repair importance and the closer to 1.0 the higher the repair importance. Specifically, the repair importance is calculated according to the following repair importance calculation formula: Repair importance = (number of repairs performed / number of reports)

[0295] The graph shown as the display data for "repair importance" in Figure 33 is a graph that shows the time trend of the percentage of cases in which repairs were carried out out of the number of reports in which the "product condition = communication failure" was determined in user reports for the smartphone SAAA over a pre-specified period (for example, the past one year).

[0296] The example shown in Figure 33 is a graph showing the time progression of "repair importance" from January 1, 2022 to December 1, 2022, and the graph shows a gradual decrease in repair importance over time from January 2022.

[0297] This indicates that repair requests for communication problems related to SAAA smartphones have been gradually decreasing since January 2022. This corresponds to data showing a trend where, for example, repairs were required to resolve communication problems when the product was first released, but the need for repairs has decreased due to subsequent product and software updates.

[0298] The product development person 51 can check the time transition of repair responses for various product states (failures, defects, etc.) by displaying the "repair importance" display data as shown in Fig. 33 on the terminal. In addition, the effectiveness of the measures taken for various defects can also be confirmed.

[0299] 7. Processing Executed by User-Directed Presentation Information Generator Next, processing executed by the user-directed presentation information generator will be described.

[0300] 3 receives the user input information 210 via the product state identification unit 102, and also receives the product state information analyzed by the product state identification unit 102. Furthermore, the user presentation information generation unit 105 receives the importance information calculated by the importance calculation unit 103, i.e., the following items of importance information: (a) time importance calculated by the time importance calculation unit 401; (b) context importance calculated by the context importance calculation unit 402; (c) customer importance calculated by the customer importance calculation unit 403; (d) repair importance calculated by the repair importance calculation unit 404; and (e) overall importance calculated by the overall importance calculation unit 405.

[0301] The user-oriented presentation information generation unit 105 generates presentation information for the user (customer) who is the user of the product based on the input information. For example, the unit generates information that serves as a response to the user, including an analysis result of the product status (failure, defect, etc.) of the product used by the user and countermeasures, i.e., "user-oriented presentation information (response) 230" shown in Fig. 3, and transmits it to the user's user terminal.

[0302] Specific examples of the "user-directed presentation information (answer) 230" generated by the user-directed presentation information generating unit 105 and transmitted to and displayed on the user terminal of the user will be described with reference to FIG. 34 and subsequent figures.

[0303] 34 is a diagram showing an example of display data on the user terminal 13 of the user 11, which is an example of display data generated as a response to a user report (user input information 210) on a certain product that the user 11 generated and transmitted to the electrical equipment manufacturer 50. This display data is generated by the user-directed presentation information generation unit 105 and transmitted to the user terminal 13 of the user 11 for display.

[0304] The display data shown in Fig. 34 is composed of the following data: (a) Customer number (b) Product name (c) Product status description (customer comments) (d) Product status (analysis results)

[0305] "(a) Customer number" is the identifier of the user who sent the report on the product status (failure, malfunction, etc.). "(b) Product name" is the type and model number of the product used by the user who reported the product status (failure, malfunction, etc.).

[0306] "(c) Product status description (customer comments)" is a description of the product status (failure, malfunction, etc.) created by the user and included in the user input information 210. "(d) Product status (analysis result)" is data indicating the specific content of the product status (failure, malfunction, etc.), and is the product status analyzed by the product status identification unit 102 of the information processing device 100 of the electrical equipment manufacturer 50.

[0307] 34, two types of product status (analysis results) are displayed as "(d) Product status (analysis results)": A. Battery failure B. Communication failure These two types of product status (analysis results) are estimated results of the product status estimated by the product status identification unit 102 of the information processing device 100 of the electrical equipment manufacturer 50 from the user's hoarse voice description of the product status.

[0308] If the user 11 determines that the item displayed as "(d) Product Status (Analysis Result)" is incorrect, he or she can touch the "Correction" icon shown in the figure and resend the data. The processing sequence when this product status correction process and resend process are executed will be described in detail later.

[0309] On the other hand, if the user 11 determines that the item displayed as "(d) Product Status (Analysis Result)" is correct, the user touches the display area of ​​the product status information (A. Battery failure or B. Communication failure) displayed in "(d) Product Status (Analysis Result)." Each of these product status information display areas has embedded therein link data (URL) to pages that introduce countermeasures for the respective product status and similar cases.

[0310] For example, as shown in Figure 35, when a user touches the display area for "A. Battery failure" displayed as "(d) Product status (analysis results)," a page is displayed that introduces countermeasures for "A. Battery failure" and similar cases according to the link data (URL) embedded in this display area.

[0311] Specifically, for example, data such as that shown in Figure 36 is displayed on the user terminal 13. The display data shown in Figure 36 is a page that introduces countermeasures for "A. Battery failure" and similar cases, and also displays link data (URL) for displaying a manual that discloses the countermeasures in detail. As shown in Figure 36, when the user clicks on this link data (URL) for displaying the manual, the manual disclosing the countermeasures for "A. Battery failure" can be displayed.

[0312] 8. Processing Sequence When a User Requests Correction to the Analysis Result of the Product Status Next, a processing sequence when a user requests correction to the analysis result of the product status will be described.

[0313] As explained with reference to Figure 34, the data generated by the user presentation information generation unit 105 of the information processing device 100 on the electrical equipment manufacturer 50 side, sent to the user terminal, and displayed includes "(d) Product status (analysis result)."

[0314] The data displayed in this "(d) Product Status (Analysis Results)" is data indicating the specific details of the product status (failure, malfunction, etc.), and is the product status analyzed by the product status identification unit 102 of the information processing device 100 of the electrical equipment manufacturer 50.

[0315] However, there may be cases where the user 11 determines that the product status analyzed by the product status identification unit 102 is different from the product status of the product owned by the user 11. In this case, if the user 11 determines that the item displayed as "(d) Product Status (Analysis Result)" is incorrect, the user 11 touches the "Correction" icon shown in the figure and resends the result.

[0316] When such processing is executed, the processing sequence executed by the information processing device 100 of the electrical equipment manufacturer 50 will be described with reference to the flowcharts shown in Figures 37 and 38. The processing of each step of the flowcharts shown in Figures 37 and 38 will be described in order below.

[0317] (Step S301) First, in step S301, the information processing device 100 of the electrical device manufacturer 50 transmits the analysis result of the product state to the user terminal and displays it.

[0318] The data displayed on the user terminal by this transmission process is the display data previously described with reference to Fig. 34, and is composed of the following data: (a) Customer number (b) Product name (c) Product status description (customer comments) (d) Product status (analysis results)

[0319] Among these, “(d) Product status (analysis results)” is data indicating the specific details of the product status (failure, malfunction, etc.), and is the product status analyzed by the product status identification unit 102 of the information processing device 100 of the electrical equipment manufacturer 50.

[0320] (Step S302) The process of step S302 is a judgment process step by the user. In step S302, the user judges whether or not the "(d) Product Status (Analysis Result)" displayed on the user terminal is correct.

[0321] If it is determined to be correct, as explained above with reference to FIGS. 35 and 36, the process executes a process for displaying countermeasures in response to a user operation, and then ends the process.

[0322] On the other hand, if the user determines that the "(d) Product Status (Analysis Result)" displayed on the user terminal is incorrect, the determination in step S302 becomes No, and the process proceeds to step S303.

[0323] (Step S303) If the user determines that the "(d) Product status (analysis result)" displayed on the user terminal in step S302 is incorrect, in step S303, new data, i.e., a new product status description or a registered product status, is input into the user terminal and transmitted to the information processing device 100 of the electrical equipment manufacturer 50.

[0324] When the user touches the "Correction" icon associated with the "(d) Product Status (Analysis Result)" item in the display data displayed on the user terminal described with reference to Figure 34, the UI described earlier with reference to Figure 6, i.e., the input screen for user input information, is redisplayed, and the user can input new data into this UI and send it.

[0325] (Step S304) The process of step S304 is a process of the information processing device 100 on the side of the electric device manufacturer 50. The information processing device 100 on the side of the electric device manufacturer 50 receives the data that the user re-input into the user terminal in step S304, that is, the user input information.

[0326] (Step S305) Next, in step S305, the information processing device 100 on the electrical equipment manufacturer 50 side determines whether valid data other than “Other” has been entered in the input field for “Registered Product Status” included in the received user input information.

[0327] As explained above with reference to Figure 6, in the "registered product status" field, it is possible to select and input only the product status registered in the product status information DB 111 in the information processing device 100 owned by the electrical equipment manufacturer 50, or "other."

[0328] If valid data other than "Other" is entered in the "Registered Product Status" input field, the determination in step S305 is Yes, and the process proceeds to step S306. On the other hand, if valid data other than "Other" is not entered in the "Registered Product Status" input field, the determination in step S305 is No, and the process proceeds to step S321.

[0329] (Step S306) If it is determined in step S305 that valid data other than "Other" has been entered in the input field for "Registered Product Status" in the user input information received from the user terminal, the process of step S306 is executed.

[0330] In this case, in step S306, the product state identification unit 102 of the information processing device 100 executes a product state analysis process.

[0331] The product state analysis process by the product state identification unit 102 of the information processing device 100 is the process previously described with reference to Figures 5 to 12. In this case, valid data other than "Other" has been entered in the input field for "Registered Product State" in the user-input information, so this input data is determined to be the correct product state.

[0332] (Step S307) Next, the user-oriented presentation information generation unit 105 of the information processing device 100 generates user-oriented presentation information (presentation information having the data structure shown in FIG. 34 ) in which the product status obtained in step S306 is recorded as a new product status (analysis result), and transmits the generated information to the user terminal.

[0333] After this process, in step S302, the user again determines whether the new product state (analysis result) is correct.

[0334] On the other hand, if it is determined in step S305 that no valid data other than "Other" has been entered in the "Registered Product Status" input field in the user input information received from the user terminal, the determination in step S305 is No, and the process proceeds to step S321.

[0335] (Step S321) If it is determined in step S305 that no valid data other than "Other" has been entered in the "Registered Product Status" input field in the user input information received from the user terminal, the product status identification unit 102 of the information processing device 100 executes a product status analysis process in step S321 based on the product status description created by the user.

[0336] This process is executed by the product state description analysis unit 302 of the product state identification unit 102 described above with reference to Figure 5, and is a process that uses the learning model 303 to estimate the product state using the user's description.

[0337] (Step S322) The product state description analysis unit 302 of the product state identification unit 102 first determines whether or not a word indicating a new product state that was not detected in the user description in the previously received user input information has been detected in the user description in the newly received user input information from the user terminal.

[0338] If the newly received user description from the user terminal does not contain any words indicating a new product state that were not detected in the previously received user description, the determination in step S322 is No, and in this case, processing in step S331 is executed.

[0339] On the other hand, if a word indicating a new product state that was not detected in the previously received user description is detected in the newly received user description from the user terminal, the determination in step S322 is Yes, and in this case, processing from step S341 onwards is executed.

[0340] (Step S331) In step S322, if the newly received user description from the user terminal does not contain any words indicating a new product state that were not detected in the previously received user description, the process of step S331 is executed.

[0341] In this case, in step S331, the information processing device 100 requests the user terminal to create and transmit a new product state description including words indicating the new product state.

[0342] After this request processing, the processing from step S303 onward is executed again. That is, new user input information including a new product state description including words indicating the new product state is received from the user terminal, and the product state analysis processing is executed again using this new user input information.

[0343] (Step S341) On the other hand, in step S322, if a word indicating a new product state that was not detected in the previously received user description is detected in the newly received user description from the user terminal, the process of step S341 is executed.

[0344] In this case, in step S341, the product state identification unit 102 of the information processing device 100 executes a product state analysis process using new words in the user description newly received from the user terminal, and estimates a new product state that has not been registered in the product state information DB 111.

[0345] (Step S342) Next, in step S342, the product state identification unit 102 of the information processing device 100 defines a product state name indicating a new product state corresponding to the product state estimated in step S341 based on the word indicating the new product state detected from the product state description, and adds and registers the name to the product state information DB 111.

[0346] 39, an example of additional registration of a new product status name in the product status information DB 111 will be described. For example, as shown in Fig. 39, a new product status name (screen flashing) and its product status identifier (a015) are registered in the product status information DB 111.

[0347] (Step S343) Next, in step S343, the information processing apparatus 100 additionally registers, in the defect report DB 123, the defect report information corresponding to the new product state name additionally registered in the product state information DB 111 in step S342.

[0348] 40 , an example of additional registration of defect report information corresponding to a new product state name in the defect report DB 123 will be described. For example, as shown in FIG. 40 , defect report information corresponding to a new product state name (screen flashing) is registered in the defect report DB 123.

[0349] (Step S344) Next, in step S344, the user-oriented presentation information generation unit 105 of the information processing device 100 generates user-oriented presentation information (presentation information having the data structure shown in FIG. 34 ) recorded by the product state identification unit 102 in step S341 as the new product state (analysis result) estimated using the new word, and transmits the generated information to the user terminal.

[0350] After this process, in step S302, the user again determines whether the new product state (analysis result) is correct.

[0351] By repeating this process, even if the user 11 determines that the product state analyzed by the product state identification unit 102 is different from the product state of the user 11's product, a product state estimation process based on new words contained in a new product state description created by the user is executed, and a product state estimation process that satisfies the user is performed.

[0352] [9. Hardware Configuration Example of Information Processing Device of the Present Disclosure] Next, a hardware configuration example of the information processing device of the present disclosure will be described with reference to Fig. 41. The hardware configuration example shown in Fig. 41 is a hardware configuration example of an information processing device 100 on the side of an electrical device manufacturer 50, a user terminal used by a user, and a developer terminal 53 used by a product developer 51.

[0353] Each element of the hardware configuration shown in Fig. 41 will be described below. A CPU (Central Processing Unit) 501 functions as a data processing unit that executes various processes in accordance with programs stored in a ROM (Read Only Memory) 502 or a storage unit 508. For example, it executes processes in accordance with the sequences described in the above-mentioned embodiments. A RAM (Random Access Memory) 503 stores programs and data executed by the CPU 501. The CPU 501, ROM 502, and RAM 503 are interconnected by a bus 504.

[0354] The CPU 501 is connected to an input / output interface 505 via a bus 504, and the input / output interface 505 is connected to an input unit 506 consisting of various sensors, a camera, a switch, a keyboard, a mouse, a microphone, etc., and an output unit 507 consisting of a display, a speaker, etc.

[0355] The storage unit 508 connected to the input / output interface 505 is composed of, for example, a USB memory, an SD card, a hard disk, etc., and stores various data and programs executed by the CPU 501. The communication unit 509 functions as a transmission / reception unit for data communication via a network such as the Internet or a local area network, and communicates with external devices.

[0356] A drive 510 connected to the input / output interface 505 drives a removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory such as a memory card, and executes recording or reading of data.

[0357] [10. Summary of the Configuration of the Present Disclosure] The embodiments of the present disclosure have been described above in detail with reference to specific examples. However, it is obvious that a person skilled in the art can modify or substitute the embodiments without departing from the gist of the present disclosure. In other words, the present invention has been disclosed in the form of an example and should not be interpreted as being limited. To determine the gist of the present disclosure, the claims should be taken into consideration.

[0358] The technology disclosed in this specification can be configured as follows: (1) An information processing device having a product state identification unit that identifies a product state of a first product based on user input information including text describing the product state of the first product, an importance calculation unit that calculates an importance of the identified product state of the first product, and a presentation information generation unit that generates presentation information based on the importance.

[0359] (2) The information processing device described in (1), wherein, when the user input information includes selection information from an option that matches a registered product state registered in a product state information database, the product state identification unit determines that the registered product state corresponding to the selection information is the product state of the first product, and when the user input information does not include selection information from an option that matches the registered product state, estimates the product state of the first product using a learning model that uses the text as input information.

[0360] (3) The information processing device according to (2), wherein the learning model is a learning model that calculates a similarity between the text and the registered product state to estimate the product state of the first product.

[0361] (4) The information processing device according to any one of (1) to (3), wherein the importance calculation unit has a time importance calculation unit, and the time importance calculation unit calculates a higher value of time importance for a product state identified by the product state identification unit with a larger number of registered pieces of information indicating the product state.

[0362] (5) The information processing device according to any one of (1) to (4), wherein the importance calculation unit includes a context importance calculation unit that analyzes assertiveness of the text and calculates a higher value of context importance as the assertiveness increases.

[0363] (6) The information processing device according to (5), wherein the context importance calculation unit is configured to execute the calculation process of the context importance using a learning model, and the learning model is a learning model that outputs a high value of context importance when the text contains many words expressing criticism or anger toward the product, and outputs a low value of context importance when the text contains many understated expressions.

[0364] (7) The information processing device according to any one of (1) to (6), wherein the importance calculation unit has a customer importance calculation unit, and the customer importance calculation unit calculates a higher value of customer importance for products that are previously purchased by a purchaser of the first product and that have a high degree of similarity to the first product.

[0365] (8) The customer importance calculation unit is configured to execute the calculation process of the customer importance using a learning model, the learning model is a learning model that calculates product importance per product type, and calculates the customer importance by executing an arithmetic process using multiple product importance per product type output from the learning model. (7) Information processing device described.

[0366] (9) The information processing device according to any one of (1) to (8), wherein the importance calculation unit has a repair importance calculation unit, and the repair importance calculation unit refers to information indicating the product state identified by the product state identification unit and information indicating the corresponding repair response status, and calculates a repair importance value that is higher the higher the repair execution rate for product states that are the same as the product state of the first product.

[0367] (10) The information processing device described in any one of (1) to (9), wherein the importance calculation unit has a plurality of importance calculation units that calculate importance based on different indices, a time importance calculation unit that calculates time importance, a context importance calculation unit that calculates context importance, a customer importance calculation unit that calculates customer importance, and a repair importance calculation unit that calculates repair importance.

[0368] (11) The information processing device according to (10), wherein the importance calculation unit further includes a total importance calculation unit, and the total importance calculation unit calculates the total importance by performing an arithmetic process on the time importance calculated by the time importance calculation unit, the context importance calculated by the context importance calculation unit, the customer importance calculated by the customer importance calculation unit, and the repair importance calculated by the repair importance calculation unit.

[0369] (12) The information processing device according to any one of (1) to (11), wherein the presentation information generation unit includes a developer presentation information generation unit that generates presentation information for a product developer by using at least one of the analysis results of the product state identification unit and the importance calculated by the importance calculation unit.

[0370] (13) The information processing device described in (12) is configured such that the developer presentation information generation unit generates a graph showing the time progression of the time importance calculated by the importance calculation unit as presentation information for the product developer, and the time importance is an importance that has a higher value as the number of user reports by product state regarding the same product as the first product increases.

[0371] (14) The information processing device according to (12) or (13), wherein the developer presentation information generation unit is configured to generate presentation information including a context importance value calculated by the importance calculation unit as presentation information for the product developer, and the context importance is an importance value that increases as the assertiveness of the text increases.

[0372] (15) The developer presentation information generation unit is configured to generate presentation information indicating the value of customer importance calculated by the importance calculation unit as presentation information for the product developer, and the customer importance is an importance level that becomes higher the more products of a type that is highly similar to the first product that the customer has purchased in the past. The information processing device described in any of (12) to (14).

[0373] (16) The developer presentation information generation unit is configured to generate a graph showing the time progression of the repair importance calculated by the importance calculation unit as presentation information for the product developer, and the repair importance is an importance that has a higher value as the repair execution rate for product states that are the same as the product state of the first product is higher. (12) An information processing device described in any one of (15) to (15).

[0374] (17) The information processing device described in any one of (12) to (16), wherein the developer presentation information generation unit generates presentation data that can output a display data selection icon to the product developer's terminal to selectively display any one of the importance information calculated by the importance calculation unit, including time importance, context importance, customer importance, and repair importance, as presentation information for the product developer.

[0375] (18) The presentation information generation unit includes a user-oriented presentation information generation unit that generates presentation information for the user who sent the user input information by using at least one of data on the product state identification result based on the analysis of the product state identification unit or the importance calculated by the importance calculation unit, and the user-oriented presentation information generation unit executes a process of generating presentation information including data indicating the product state of the identified first product and countermeasures for the product state or link information for a page disclosing the countermeasures, and transmitting the presentation information to a user terminal used by the user.

[0376] (19) An information processing method executed in an information processing device, comprising: a product state identification step in which a product state identification unit identifies a product state of a first product based on user input information including text describing the product state of the first product; an importance calculation step in which an importance calculation unit calculates the importance of the identified product state of the first product; and a presentation information generation step in which a presentation information generation unit generates presentation information based on the importance.

[0377] (20) A program for executing information processing in an information processing device, the program executing: a product state identification step for causing a product state identification unit to identify a product state of a first product based on user input information including text describing the product state of the first product; an importance calculation step for causing an importance calculation unit to calculate the importance of the identified product state of the first product; and a presentation information generation step for causing a presentation information generation unit to generate presentation information based on the importance.

[0378] Furthermore, the series of processes described in this specification can be executed by hardware, software, or a combination of both. When executing processes by software, a program recording the processing sequence can be installed and executed in the memory of a computer incorporated in dedicated hardware, or the program can be installed and executed on a general-purpose computer capable of executing various processes. For example, the program can be pre-recorded on a recording medium. In addition to installing the program from the recording medium to the computer, the program can also be received via a network such as a LAN (Local Area Network) or the Internet and installed on a recording medium such as an internal hard disk.

[0379] The various processes described in this specification may not only be executed in chronological order as described, but may also be executed in parallel or individually depending on the processing capabilities of the devices executing the processes or as needed. Furthermore, in this specification, a system refers to a logical collective configuration of multiple devices, and is not limited to devices that are all located in the same housing.

[0380] As described above, according to one embodiment of the present disclosure, the product status and importance of a product are analyzed based on user input information including, for example, an explanation (text) about a product failure or malfunction, and presentation information for a user or developer is generated. Specifically, for example, a product status identification unit analyzes text or the like in which a user explains a product failure or malfunction, and identifies, for example, the product status of a product used by the user. Furthermore, an importance calculation unit calculates the importance of the identified product status. Furthermore, a presentation information generation unit generates presentation information including, for example, the importance calculated by the importance calculation unit, the identified product status, countermeasures for the product status, statistical data, and the like, and presents the information to a user or product developer. These configurations realize a configuration in which the product status and importance of a product are analyzed based on user input information including, for example, an explanation (text) about a product failure or malfunction, and presentation information for a user or developer is generated.

[0381] 11, 21, 31 User 12, 22, 32 Product 13, 23, 33 User terminal 40 Received information 50 Electrical equipment manufacturer 100 Information processing device 101 Communication unit 102 Product state identification unit 103 Importance calculation unit 104 Developer-oriented presentation information generation unit 105 User-oriented presentation information generation unit 111 Product state information DB 121 Repair information DB 122 Customer information DB 123 Defect report information DB 210 User-input information 211 Product state information 212 Importance information 220 Developer-oriented presentation information (feedback information) 221 Time importance 222 Context importance 223 Customer importance 224 Repair importance 230 User-oriented presentation information (answer) 301 User-input information analysis unit 302 Product state description analysis unit 303 Learning model 401 Time importance calculation unit 402 Context importance calculation unit 403 Customer importance calculation unit 404 Repair importance calculation unit 405 Overall importance calculation unit 421 Data extraction unit 422 Learning model 431 Data extraction unit 432 Learning model 433 Customer importance calculation unit 441 Data extraction unit 442 Repair importance calculation unit 501 CPU 502 ROM 503 RAM 504 Bus 505 Input / output interface 506 Input unit 507 Output unit 508 Storage unit 509 Communication unit 510 Drive 511 Removable media

Claims

1. An information processing device having a product state identification unit that identifies a product state of a first product based on user input information including text describing the product state of the first product, an importance calculation unit that calculates the importance of the identified product state of the first product, and a presentation information generation unit that generates presentation information based on the importance.

2. The information processing device of claim 1, wherein the product state identification unit determines that the registered product state corresponding to the selection information is the product state of the first product when the user input information contains selection information from options that match a registered product state registered in a product state information database, and estimates the product state of the first product using a learning model that uses the text as input information when the user input information does not contain selection information from options that match the registered product state.

3. The information processing device according to claim 2, wherein the learning model is a learning model that estimates the product state of the first product by calculating a similarity between the text and the registered product state.

4. The information processing device according to claim 1, wherein the importance calculation unit has a time importance calculation unit, and the time importance calculation unit calculates a higher value of time importance for a product state having a greater number of registered pieces of information indicating the product state identified by the product state identification unit.

5. The information processing device according to claim 1, wherein the importance calculation unit has a context importance calculation unit that analyzes the assertiveness of the text and calculates a higher value of context importance for a higher assertiveness.

6. The information processing device according to claim 5, wherein the context importance calculation unit is configured to execute the context importance calculation process by utilizing a learning model, and the learning model is a learning model that outputs a high value of context importance when the text contains a lot of words expressing criticism or anger toward the product, and outputs a low value of context importance when the text contains a lot of understated expressions.

7. The information processing device according to claim 1, wherein the importance calculation unit has a customer importance calculation unit, and the customer importance calculation unit calculates a higher value of customer importance for a greater number of types of products that are similar to the first product and that have been previously purchased by a purchaser of the first product.

8. The information processing device according to claim 7, wherein the customer importance calculation unit is configured to execute the calculation process of the customer importance using a learning model, the learning model being a learning model that calculates product importance per product type, and the information processing device calculates the customer importance by executing a calculation process using multiple product importance per product type output from the learning model.

9. The information processing device according to claim 1, wherein the importance calculation unit has a repair importance calculation unit, and the repair importance calculation unit calculates a higher repair importance value by referring to information indicating the product state identified by the product state identification unit and information indicating the corresponding repair response status, the higher the repair execution rate for product states that are the same as the product state of the first product.

10. The information processing device according to claim 1, wherein the importance calculation unit has a plurality of importance calculation units each calculating importance based on a different index, a time importance calculation unit calculating time importance, a context importance calculation unit calculating context importance, a customer importance calculation unit calculating customer importance, and a repair importance calculation unit calculating repair importance.

11. The information processing device according to claim 10, wherein the importance calculation unit further includes an overall importance calculation unit, which calculates overall importance by performing arithmetic processing on the time importance calculated by the time importance calculation unit, the context importance calculated by the context importance calculation unit, the customer importance calculated by the customer importance calculation unit, and the repair importance calculated by the repair importance calculation unit.

12. The information processing device according to claim 1, wherein the presentation information generation unit includes a developer-oriented presentation information generation unit that generates presentation information for product developers using at least one of the analysis results of the product state identification unit and the importance calculated by the importance calculation unit.

13. The information processing device according to claim 12, wherein the developer presentation information generation unit is configured to generate a graph showing the time progression of the time importance calculated by the importance calculation unit as presentation information for the product developer, and the time importance is an importance that has a higher value the greater the number of user reports by product status regarding the same product as the first product.

14. The information processing device according to claim 12, wherein the developer presentation information generation unit is configured to generate presentation information including a context importance value calculated by the importance calculation unit as presentation information for the product developer, and the context importance is an importance value that increases as the assertiveness of the text increases.

15. The information processing device according to claim 12, wherein the developer presentation information generation unit is configured to generate presentation information indicating the customer importance value calculated by the importance calculation unit as presentation information for the product developer, and the customer importance is an importance value that is higher the more products of a type that is highly similar to the first product that have been purchased in the past.

16. The information processing device according to claim 12, wherein the developer presentation information generation unit is configured to generate a graph showing the time progression of the repair importance calculated by the importance calculation unit as presentation information for the product developer, and the repair importance is an importance that has a higher value as the repair execution rate for product states that are the same as the product state of the first product is higher.

17. An information processing device as described in claim 12, wherein the developer presentation information generation unit generates presentation data that can output a display data selection icon to a terminal of the product developer as presentation information for the product developer, for selectively displaying any one of the importance information calculated by the importance calculation unit, namely, time importance, context importance, customer importance, and repair importance.

18. The information processing device according to claim 1, wherein the presentation information generation unit includes a user-oriented presentation information generation unit that generates presentation information for the user who sent the user input information by using at least one of data on the product status identification result based on the analysis of the product status identification unit or the importance calculated by the importance calculation unit, and the user-oriented presentation information generation unit executes a process of generating presentation information including data indicating the product status of the identified first product and countermeasures for the product status or link information of a page disclosing the countermeasures, and transmitting the presentation information to a user terminal used by the user.

19. An information processing method executed in an information processing device, comprising: a product state identification step in which a product state identification unit identifies a product state of a first product based on user input information including text describing the product state of the first product; an importance calculation step in which an importance calculation unit calculates the importance of the identified product state of the first product; and a presentation information generation step in which a presentation information generation unit generates presentation information based on the importance.

20. A program for executing information processing in an information processing device, the program executing: a product state identification step for causing a product state identification unit to identify a product state of a first product based on user input information including text explaining the product state of the first product; an importance calculation step for causing an importance calculation unit to calculate the importance of the identified product state of the first product; and a presentation information generation step for causing a presentation information generation unit to generate presentation information based on the importance.

Images