Information processing device and information processing program

Abstract

To provide an information processing device capable of generating text with a reduced risk of information leakage compared to conventional methods, and an information processing program.SOLUTION: An information processing device of an embodiment comprises a first acquisition unit, a removal unit, and a second acquisition unit. The first acquisition unit acquires first text information from first audio data. The removal unit removes elements satisfying predetermined conditions as confidential information from the first text information. The second acquisition unit inputs the first text information from which the confidential information has been removed into a large language model configured to instruct the summary of the first text information, and acquires the summary information generated by the large language model.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] An embodiment of the present invention relates to an information processing device and an information processing program. [Background technology]

[0002] In recent years, a technology has been proposed for automatically creating sentences using an AI model called a large-scale language model (LLM). A large-scale language model is an AI model in the field of natural language processing that has been pre-trained on a large-scale corpus, and when a text describing the content of a query is input together with instruction information (also called a prompt) that specifies the output format, the model is configured to generate and output a response sentence (hereinafter also called summary information) related to the content of the query in the specified format.

[0003] In the business of support centers and the like, inquiries from customers are accepted and handled over the telephone. In such business, it is expected that speech data from telephone calls will be converted into text and input into the above-mentioned large-scale language model to generate summary information about the inquiry content.

[0004] However, speech data may contain confidential information. For example, it may contain customer information about an individual customer or information about the organization (company, etc.) to which the customer belongs. In addition, it is often unclear how the text input into a large-scale language model should be handled after input. For example, it may be used for retraining.

[0005] Therefore, carelessly inputting text containing confidential information into a large-scale language model may lead to the risk of the confidential information being leaked, and there is room for further improvement from a security perspective. Summary of the Invention [Problem to be solved by the invention]

[0006] The problem to be solved by the present invention is to provide an information processing device and an information processing program that can generate text with a reduced risk of information leakage compared to conventional methods. [Means for solving the problem]

[0007] The information processing device of the embodiment includes a first acquisition unit that acquires first text information from first voice data, a removal unit that removes elements that meet predetermined conditions from the first text information as confidential information, and a second acquisition unit that inputs the first text information from which the confidential information has been removed into a large-scale language model that is functionally configured to instruct a summary of the first text information, and acquires summary information generated by the large-scale language model. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram showing a schematic configuration of an information processing system according to this embodiment. [Figure 2] FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing device according to this embodiment. [Figure 3] FIG. 3 is a block diagram showing an example of the functional configuration of the information processing device according to this embodiment. [Figure 4] FIG. 4 is a schematic diagram showing an example of checklist information according to this embodiment. [Figure 5] FIG. 5 is a schematic diagram showing an example of report information according to this embodiment. [Figure 6] FIG. 6 is a flowchart showing an example of control processing of the information processing device according to this embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of control processing of the information processing device according to this embodiment. [Figure 8] FIG. 8 is a flowchart showing an example of control processing of the information processing device according to this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of an information processing system will be described with reference to the drawings. Furthermore, the present invention is not limited to the following embodiments, and the components in the following embodiments include those that would be easily conceived by a person skilled in the art, those that are substantially the same, and those that are within the scope of what is called equivalents. Furthermore, various omissions, substitutions, modifications, and combinations of the components can be made without departing from the spirit of the following embodiments.

[0010] 1 is a schematic diagram showing a general configuration of an information processing system 10 according to an embodiment. The information processing system 10 is a system including a voice input device 1, an information processing device 2, and a display device 3.

[0011] The voice input device 1 is, for example, a telephone used by a customer or a maintenance person. The voice input device 1 acquires voice data of the customer or maintenance person and outputs the acquired voice data to the information processing device 2. For example, when a device used by the customer breaks down, the customer uses the voice input device 1 to make an inquiry to a management company that manages the broken down device, such as to request repairs for the broken down device.

[0012] For example, when a maintenance person contacts the company to which the maintenance person belongs about maintenance of a broken device, the maintenance person uses the voice input device 1. The voice input device 1 is connected to the information processing device 2 via a communication line such as a mobile network.

[0013] The information processing device 2 is a device used by a management company that manages equipment used by customers. The information processing device 2 is equipped with, for example, a large language model (LLM) and is configured with one or more computers. The information processing device 2 is a device that receives voice data from, for example, customers or maintenance personnel and responds to inquiries about the voice data.

[0014] The information processing device 2 is connected to the voice input device 1 via a communication line such as a mobile network, etc. The information processing device 2 is also connected to the display device 3 via a communication line such as a mobile network, etc.

[0015] The display device 3 is a device used by a management company that maintains or manages equipment used by customers. The display device 3 is composed of one or more computers. For example, the display device 3 is a device on which a maintenance person who responds to a customer's inquiry and a request to repair a broken device displays information about the device to be repaired, a manual for repairing the device, etc. The display device 3 is connected to the information processing device 2 via a communication line such as a mobile network.

[0016] Next, the hardware configuration of the information processing device 2 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the hardware configuration of the information processing device 2 according to this embodiment. As shown in Fig. 2, the information processing device 2 includes a CPU (Central Processing Unit) 21, a RAM (Random Access Memory) 22, a ROM (Read Only Memory) 23, an auxiliary storage device 24, and a communication I / F (interface) 25.

[0017] The CPU 21 is the main controller. The RAM 22 expands programs and various data. The ROM 23 stores various programs. The auxiliary storage device 24 stores various programs and data. The communication I / F 25 is an interface for data communication with the voice input device 1 and the display device 3.

[0018] The CPU 21, RAM 22, ROM 23, auxiliary storage device 24, and communication I / F 25 are connected to one another via a bus 26. The CPU 21, RAM 22, and ROM 23 constitute a control unit. That is, the control unit executes control processing of the information processing device 2, which will be described later, by the CPU 21 operating in accordance with a control program stored in the ROM 23 or auxiliary storage device 24 and loaded in the RAM 22.

[0019] The auxiliary storage device 24 is configured with a non-volatile memory such as an HDD (Hard Disc Drive) or flash memory that retains stored information even when the power is turned off. The auxiliary storage device 24 stores summary information, similarity information, checklist information, maintenance information, report and feedback, and progress management information generated by the information processing device 2. Details of the summary information, similarity information, checklist information, maintenance information, report and feedback, and progress management information will be described later.

[0020] The information processing device 2 is installed in a secure environment. A secure environment is a configuration in which the information processing device 2 is placed in a local environment for use. With this configuration, the text information input for processing a large-scale language model provided in the information processing device 2, which will be described later, includes customer information of customers, etc., and therefore the information processing device 2 can contribute to the protection of personal information by being placed in a local environment for use.

[0021] Fig. 3 is a block diagram showing an example of the functional configuration of the information processing device 2 according to this embodiment. As shown in Fig. 3, the information processing device 2 includes a first receiving unit 211, a first acquiring unit 212, a removing unit 213, a second acquiring unit 214, an extracting unit 215, a third acquiring unit 216, an output unit 217, a second receiving unit 218, a fourth acquiring unit 219, a fifth acquiring unit 220, a sixth acquiring unit 221, a seventh acquiring unit 222, and an eighth acquiring unit 223. Note that the functional configuration of the information processing device 2 is not limited to this.

[0022] The first receiving unit 211 receives the first voice data. Specifically, the first receiving unit 211 receives the first voice data from a customer output by the voice input device 1. For example, the first voice data includes the name, telephone number, email address, and trade name of the customer who made the inquiry. Furthermore, for example, the first voice data includes the content of the inquiry regarding the device used by the customer. Examples of the content of the inquiry include details regarding malfunctions, usage methods, complaints, etc. of the device used by the customer. Furthermore, the first receiving unit 211 stores the received first voice data in the auxiliary storage device 24.

[0023] The first acquisition unit 212 acquires first text information. Specifically, the first acquisition unit 212 acquires the first text information from the first voice data received by the first reception unit 211. The first acquisition unit 212 converts the first voice data into text by performing voice recognition processing and natural language processing (NLP) on the first voice data using a known method, and acquires the converted first text information. In addition, the first acquisition unit 212 stores the acquired first text information in the auxiliary storage device 24.

[0024] The removal unit 213 removes, from the text information, an element that satisfies a predetermined condition as secret information. Specifically, the removal unit 213 removes, from the first text information acquired by the first acquisition unit 212, the secret information that is an element that satisfies the predetermined condition.

[0025] The elements that meet the predetermined conditions are elements related to confidential information. These elements are predetermined as information that should be kept confidential. For example, the confidential information includes at least customer information about the individual customer. Specifically, the confidential information includes, as customer information, elements that indicate, for example, the name, telephone number, email address, and trade name of the company to which the customer belongs of the customer who made the inquiry. Furthermore, the removal unit 213 stores the first text information from which the confidential information has been removed in the auxiliary storage device 24.

[0026] The second acquisition unit 214 acquires summary information. Specifically, the second acquisition unit 214 inputs the first text information, from which the hidden information has been removed by the removal unit 213, to a large-scale language model that is functionally configured to instruct summarization of the first text information, and acquires the summary information generated by the large-scale language model.

[0027] For example, the second acquisition unit 214 inputs the first text information and instruction information (also called a prompt) instructing the large-scale language model to summarize the first text information using a known method, thereby causing the large-scale language model to generate summary information that summarizes the first text information, and acquires the summary information generated by the large-scale language model. The summary information includes the case number of the summary information, the creation date and time of the summary information, and the query requirement included in the first text information.

[0028] The second acquisition unit 214 generates a first prompt that, for example, describes instructions to assign a case number, add a creation date and time, assign an inquiry title corresponding to the inquiry requirements, extract inquiry content such as concerns, and itemize the inquiry, in order to manage inquiries from multiple customers. Note that the first prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the second acquisition unit 214. The second acquisition unit 214 stores the acquired summary information in the auxiliary storage device 24.

[0029] The extraction unit 215 extracts similar information. Specifically, the extraction unit 215 extracts similar information that is similar to the summary information acquired by the second acquisition unit 214 from an auxiliary storage device different from the auxiliary storage device 24. The similar information is information that is similar to the content of an inquiry from a customer, and is information extracted by searching for information that includes content similar to, for example, the details of a malfunction of a device used by a customer, the method of using the device, the details of the malfunction, or the details of a complaint about the device. The extraction unit 215 also stores the extracted similar information in the auxiliary storage device 24.

[0030] The third acquisition unit 216 acquires checklist information. Specifically, the third acquisition unit 216 acquires checklist information corresponding to the summary information acquired by the second acquisition unit 214 and the similarity information extracted by the extraction unit 215. The third acquisition unit 216 inputs the summary information, the similarity information, and instruction information instructing the large-scale language model to combine the summary information and the similarity information using a known method, thereby causing the large-scale language model to generate checklist information combining the summary information and the similarity information, and acquires the checklist information generated by the large-scale language model. The checklist information is a checklist that lists the contents of the summary information and the similarity information in itemized form.

[0031] The third acquisition unit 216 generates a second prompt that, for example, lists the similar information extracted by the extraction unit 215 below the summary information acquired by the second acquisition unit 214, generates check items, adds a check box to the first sentence of the list, and if there is an overlapping case in which the requirements of the summary information and the requirements of the similar information overlap, lists the remaining requirements of the similar information excluding the overlapping requirements.

[0032] The second prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the third acquisition unit 216. The third acquisition unit 216 may combine summary information and similarity information for the checklist information without using a large-scale language model, and acquire the combined information as the checklist information. The third acquisition unit 216 stores the acquired checklist information in the auxiliary storage device 24.

[0033] The output unit 217 outputs the checklist information. Specifically, the output unit 217 outputs the checklist information acquired by the third acquisition unit 216 to the display device 3. Here, the checklist information output by the output unit 217 will be described with reference to Fig. 4. Fig. 4 is a schematic diagram showing an example of checklist information according to this embodiment.

[0034] Figure 4 shows checklist information 41. The checklist information 41 includes the case number, creation date, inquiry title, and checkboxes, along with the inquiry requirements listed in itemized form and similar requirements listed in itemized form with checkboxes. This allows maintenance personnel who maintain equipment used by customers to improve work efficiency by checking the checklist information 41.

[0035] 3, the second receiving unit 218 receives the second voice data. Specifically, the second receiving unit 218 receives the second voice data from the maintenance staff output by the voice input device 1. For example, the second voice data includes the name of the customer who attended the maintenance, the trade name of the company to which the customer belongs, the name of the maintenance staff corresponding to the case in the checklist information 41, the case number, a reading of the check items, the details of the maintenance corresponding to the check items, the results of the maintenance, etc.

[0036] The fourth acquisition unit 219 acquires second text information. Specifically, the fourth acquisition unit 219 acquires second text information corresponding to the second voice data received by the second reception unit 218. The fourth acquisition unit 219 converts the second voice data into text by performing voice recognition processing or natural language processing on the second voice data using a known method, and acquires the second text information converted into text.

[0037] The fifth acquisition unit 220 acquires second summary information. Specifically, the fifth acquisition unit 220 acquires second summary information (hereinafter also referred to as report information) indicating a summary of the checklist information 41 acquired by the third acquisition unit 216 and the second text information acquired by the fourth acquisition unit 219. The fifth acquisition unit 220 inputs the checklist information 41, the second text information, and instruction information instructing the large-scale language model to summarize the checklist information 41 and the second text information using a known method, thereby causing the large-scale language model to generate second summary information indicating a summary of the checklist information 41 and the second text information, and acquires the second summary information generated by the large-scale language model.

[0038] The fifth obtaining unit 220 generates a third prompt that, for example, states that the maintenance response from the maintenance person is to match the case number listed in the checklist information 41, to add the creation date and time, to add check results for check items corresponding to the inquiry requirements and similar requirements, and not to include confidential information. The confidential information in the third prompt includes customer information, such as the name of the customer who attended the maintenance and the trade name of the company to which the customer belongs.

[0039] The third prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the fifth acquisition unit 220. The fifth acquisition unit 220 may combine the checklist information 41 and the second text information and acquire the combined information as the second summary information without using a large-scale language model. The fifth acquisition unit 220 stores the acquired summary information in the auxiliary storage device 24.

[0040] Here, the report information will be described with reference to FIG. 5. FIG. 5 is a schematic diagram showing an example of report information according to this embodiment. In addition to the contents described in FIG. 4, the report information 51 shown in FIG. 5 further shows the check results of the check items corresponding to the inquiry requirements and similarity requirements. As a result, the fifth acquisition unit 220 acquires the report information 51 from the second voice data related to the maintenance response of the maintenance technician, thereby reducing the effort required for the maintenance technician to create a report and improving the work efficiency of the maintenance technician. Furthermore, the fifth acquisition unit 220 stores the acquired report information 51 in the auxiliary storage device 24.

[0041] 3, the sixth acquisition unit 221 acquires first progress management information. Specifically, the sixth acquisition unit 221 acquires first progress management information for managing the progress of a checklist based on the first text information acquired by the first acquisition unit 212 and checklist information. The sixth acquisition unit 221 inputs the first text information and instruction information that instructs progress management of the first text information into a large-scale language model using a known method, thereby causing the large-scale language model to generate first progress management information corresponding to the first text information, and acquires the first progress management information generated by the large-scale language model.

[0042] Here, the first progress management information is, for example, a Gantt chart with a time axis on the horizontal axis and columns for recording maintenance check items on the vertical axis. The first progress management information is, for example, information for managing the progress of maintenance responses in response to customer inquiries.

[0043] The sixth acquisition unit 221 generates a fourth prompt that, for example, includes a customer inquiry such as adding a case number, adding the creation date and time, and adding content for progress management.

[0044] The fourth prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the sixth acquisition unit 221. The sixth acquisition unit 221 may combine the first text information with a Gantt chart graph and acquire the combined information as the first progress management information without using a large-scale language model for the first progress management information. The sixth acquisition unit 221 stores the acquired first progress management information in the auxiliary storage device 24.

[0045] The seventh acquisition unit 222 acquires second progress management information. Specifically, the seventh acquisition unit 222 acquires second progress management information that corresponds to the first progress management information acquired by the sixth acquisition unit 221. In other words, the seventh acquisition unit 222 acquires the first progress management information and second progress management information that manages the progress of the checklist based on the checklist information 41.

[0046] The seventh acquisition unit 222 inputs the first progress management information, checklist information 41, and instruction information that instructs the progress management of the first progress management information and the checklist information 41 into a large-scale language model using a known method, thereby causing the large-scale language model to generate second progress management information corresponding to the second progress management information, and acquires the second progress management information generated by the large-scale language model.

[0047] Here, the second progress management information is, for example, a Gantt chart with a time axis on the horizontal axis and columns for recording maintenance check items on the vertical axis. The second progress management information is, for example, information that manages the progress of maintenance responses in response to customer inquiries. The second progress management information is information in which the contents of checklist information 41 are reflected in the first progress management information.

[0048] The seventh acquisition unit 222 generates a fifth prompt that, for example, indicates that the check items included in the checklist information 41 acquired by the third acquisition unit 216 should be added to the column for recording maintenance check items of the Gantt chart of the first progress management information.

[0049] The fifth prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the seventh acquisition unit 222. The seventh acquisition unit 222 may combine the first progress management information and the checklist information 41 and acquire the combined information as the second progress management information without using a large-scale language model for the second progress management information. The seventh acquisition unit 222 stores the acquired second progress management information in the auxiliary storage device 24.

[0050] The eighth acquisition unit 223 acquires the third progress management information. Specifically, the eighth acquisition unit 223 acquires the third progress management information corresponding to the second progress management information acquired by the seventh acquisition unit 222. In other words, the eighth acquisition unit 223 acquires the third progress management information that manages the progress of the checklist based on the second progress management information and the second summary information acquired by the fifth acquisition unit 220.

[0051] The eighth acquisition unit 223 inputs the second progress management information, the second summary information, and instruction information that instructs the progress management of the second progress management information and the second summary information into a large-scale language model using a known method, thereby causing the large-scale language model to generate second progress management information corresponding to the third progress management information, and acquires the third progress management information generated by the large-scale language model.

[0052] Here, the third progress management information is, for example, a Gantt chart with a time axis on the horizontal axis and columns for recording maintenance check items on the vertical axis. The third progress management information is, for example, information that manages the progress of maintenance responses in response to customer inquiries. The third progress management information is information in which the contents of the second summary information are reflected in the second progress management information.

[0053] The eighth acquisition unit 223 generates a sixth prompt that, for example, states that the maintenance response date and time described in the second summary information acquired by the fifth acquisition unit 220, which corresponds to the time axis of the maintenance check item in the Gantt chart of the second progress management information, should be added, and that the maintenance response date and time described in the second text information acquired by the fourth acquisition unit 219 should be added.

[0054] The sixth prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the eighth acquisition unit 223. The eighth acquisition unit 223 may combine the second progress management information and the second summary information and acquire the combined information as the third progress management information without using a large-scale language model for the third progress management information. The eighth acquisition unit 223 stores the acquired third progress management information in the auxiliary storage device 24.

[0055] The eighth acquisition unit 223 acquires the third progress management information, which is the updated second progress management information, so that customers other than the maintenance person can check the latest maintenance status without waiting for the maintenance person to update the progress management information. This allows the company that manages the equipment to further strengthen its support system for the equipment.

[0056] Next, the control processing of the information processing device 2 will be described with reference to Fig. 6 to Fig. 8. Fig. 6 to Fig. 8 are flowcharts showing an example of the control processing of the information processing device 2 according to this embodiment.

[0057] 6, the first receiving unit 211 receives first voice data from the customer output by the voice input device 1 (step S61). Subsequently, the first acquiring unit 212 acquires first text information from the first voice data received by the first receiving unit 211 (step S62).

[0058] Next, the removal unit 213 removes confidential information, which is an element that satisfies a predetermined condition, from the first text information acquired by the first acquisition unit 212 (step S63). Next, the second acquisition unit 214 inputs the first text information, from which the confidential information has been removed by the removal unit 213, to a large-scale language model that is functionally configured to instruct summarization of the first text information, and acquires summary information generated by the large-scale language model (step S64).

[0059] Next, the extraction unit 215 extracts similar information that is similar to the summary information acquired by the second acquisition unit 214 from an auxiliary storage device different from the auxiliary storage device 24 (step S65). Next, the third acquisition unit 216 acquires checklist information 41 that corresponds to the summary information acquired by the second acquisition unit 214 and the similar information extracted by the extraction unit 215 (step S66).

[0060] Next, the output unit 217 outputs the checklist information 41 acquired by the third acquisition unit 216 to the display device 3 (step S67). When this process ends, the process of the information processing device 2 ends. This allows the maintenance person to perform work based on the checklist information 41.

[0061] 7, the second receiving unit 218 receives second voice data from the maintenance technician output by the voice input device 1 (step S71). Subsequently, the fourth acquiring unit 219 acquires second text information corresponding to the second voice data received by the second receiving unit 218 (step S72).

[0062] Next, the fifth acquisition unit 220 acquires report information 51 indicating a summary of the checklist information 41 acquired by the third acquisition unit 216 and the second text information acquired by the fourth acquisition unit 219 (step S73). Next, the fifth acquisition unit 220 stores the acquired summary information in the auxiliary storage device 24 (step S74). When this process ends, the processing of the information processing device 2 ends. This allows the maintenance staff to reduce the effort required to create a report, thereby improving work efficiency.

[0063] 8, the sixth acquisition unit 221 acquires first progress management information for managing the progress of a checklist based on the first text information acquired by the first acquisition unit 212 and the checklist (step S81). Subsequently, the seventh acquisition unit 222 acquires second progress management information corresponding to the first progress management information acquired by the sixth acquisition unit 221 (step S82).

[0064] Next, the eighth acquisition unit 223 acquires third progress management information corresponding to the second progress management information acquired by the seventh acquisition unit 222 (step S83). Next, the eighth acquisition unit 223 stores the acquired third progress management information in the auxiliary storage device 24 (step S84). When this process ends, the process of the information processing device 2 ends.

[0065] This allows maintenance personnel to reduce the time and effort required for progress management, improving work efficiency. In addition, customers other than maintenance personnel can also check the progress management, allowing the company that manages the equipment to further strengthen its equipment support system.

[0066] As described above, the information processing device 2 of this embodiment acquires first text information corresponding to voice data, performs natural language processing on the text information, and generates summary information corresponding to the text information that does not include confidential information.

[0067] As a result, the summary information generated by the information processing device 2 does not include confidential information, and therefore it is possible to generate text with a reduced risk of information leakage.

[0068] The above-described embodiment can be modified as needed by partially changing the configuration or functions of each of the above-described devices. Therefore, several modifications of the above-described embodiment will be described below as other embodiments. The following mainly focuses on differences from the above-described embodiment, and detailed descriptions of commonalities with the content already described will be omitted. The modifications described below may be implemented individually or in appropriate combination.

[0069] (First Modification) The information processing device 2 stores the voice data in the auxiliary storage device 24, but may delete the voice data at any timing. For example, the information processing device 2 may delete the voice data when the text information is generated or when the third progress management information is generated. This allows the information processing device 2 to contribute to the protection of personal information.

[0070] (Second Modification) In the above-described embodiment, the information processing device 2 equipped with a large-scale language model is configured to be deployed and used in a local environment, but this is not limiting, and the information processing device 2 equipped with a large-scale language model may also be configured to be deployed and used in a highly secure cloud environment. A highly secure cloud environment is a cloud environment that is not disclosed on the Internet and is connected to an in-house server environment via a highly confidential communication line.

[0071] The program executed by the information processing device 2 of the embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the program executed by the information processing device 2 of the embodiment and the modified example may be provided or distributed via a network such as the Internet.

[0072] The programs executed by each device in the above-described embodiments are provided in a state where they are pre-installed in a ROM, an auxiliary storage device, etc. The programs executed by each device in the above-described embodiments may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a DVD (Digital Versatile Disk).

[0073] Furthermore, the programs executed by each device of the above-described embodiments may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.Furthermore, the programs executed by each device of the above-described embodiments may be provided or distributed via a network such as the Internet.

[0074] Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments and their modifications can be embodied in various other forms, and various omissions, substitutions, changes, and combinations can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0075] 1. Voice input device 2. Information processing equipment 3 Display device 211 First Receiving Unit 212 First acquisition part 213 Removal section 214 Second Acquisition Department 215 Extraction part 216 Third Acquisition Department 217 Output section 218 Second Receiving Unit 219 4th Acquisition Department 220 Fifth Acquisition Division 221 6th Acquisition Department 222 7th Acquisition Department 223 8th Acquisition Department [Prior art documents] [Patent documents]

[0076] [Patent Document 1] Japanese Patent Publication No. 2022-87521

Claims

1. a first acquisition unit that acquires first text information from the first voice data; a removal unit that removes, as secret information, elements that meet a predetermined condition from the first text information; a second acquisition unit that inputs the first text information from which the secret information has been removed into a large-scale language model that is configured to instruct a summary of the first text information, and acquires summary information generated by the large-scale language model; An information processing device comprising:

2. The confidential information includes at least customer information, The customer information includes the customer's name, telephone number, email address, and the name of the company to which the customer belongs, The summary information includes a case number of the summary information, a creation date and time of the summary information, and an inquiry requirement included in the first text information. The information processing device according to claim 1 .

3. an extraction unit that extracts similar information that is similar to the summary information, The similarity information includes information that is similar to the details of the malfunction of the equipment used by the customer, the method of using the equipment, and the details of the malfunction or the details of the equipment complaint. The information processing device according to claim 2 .

4. a third acquisition unit that acquires checklist information corresponding to the summary information and the similarity information, the checklist information is a checklist that lists the contents of the summary information and the similar information in itemized form; The information processing device according to claim 3 .

5. a fourth acquisition unit that acquires second text information from the second voice data; a fifth acquisition unit that acquires second summary information indicating a summary of the checklist information and the second text information, The information processing device according to claim 4 .

6. a sixth acquisition unit that acquires progress management information that manages progress of the checklist based on the first text information and the checklist information; The information processing device according to claim 4 .

7. The computer of the information processing device, a first acquisition unit that acquires first text information from the first voice data; a removal unit that removes, as secret information, elements that meet a predetermined condition from the first text information; a second acquisition unit that inputs the first text information from which the secret information has been removed into a large-scale language model that is configured to instruct a summary of the first text information, and acquires summary information generated by the large-scale language model; An information processing program that makes it function as such.

Images