Information processing system, information processing apparatus, information processing method, and program

Abstract

To select data to be moved based on the contents of the data.SOLUTION: The information processing apparatus includes a reception unit configured to receive a selection condition of data to be moved to a second storage unit from among data stored in a first storage unit, an acquisition unit configured to input a text including contents of a plurality of data and an instruction to extract data whose content satisfies the selection condition from among the plurality of data to a pre-trained machine learning model and acquire a first output from the machine learning model, and a movement processing unit configured to move data specified based on the first output to the second storage unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] In order to increase the free space in internal (on-premise) storage at companies, etc., some data may be moved to external storage such as cloud storage. In this case, the moved data can be deleted from the internal storage, thereby increasing the free space in the storage.

[0003] For example, Patent Document 1 discloses a technique for backing up files from a local storage to a cloud storage. Summary of the Invention [Problem to be solved by the invention]

[0004] Conventionally, data to be transferred has been selected based on bibliographic information of the data, such as the last update date or the last access date.

[0005] However, this selection method does not allow for data selection based on the content of the data. Therefore, for example, it is difficult to target data related to a specific type of document for migration regardless of the timing of access. This problem is not limited to migrations to free up storage space, but is a common problem when migrating data.

[0006] The present invention has been made in view of the above points, and an object of the present invention is to make it possible to select data to be moved based on the content of the data. [Means for solving the problem]

[0007] In order to solve the above problem, the information processing device has a receiving unit that receives selection conditions for data to be moved from the data stored in a first memory unit to a second memory unit, an acquiring unit that inputs text including the contents of multiple pieces of data and instructions to extract data from the multiple pieces of data whose contents satisfy the selection conditions into a pre-trained machine learning model and acquires a first output from the machine learning model, and a moving processing unit that moves data identified based on the first output to the second memory unit. [Effects of the Invention]

[0008] It is possible to select data to be moved based on the content of the data. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating an example of a configuration of an information processing system 1 according to an embodiment of the present invention. [Figure 2] 1 is a diagram illustrating an example of a hardware configuration of an information processing device 10 according to an embodiment of the present invention. [Figure 3] 1 is a diagram illustrating an example of a functional configuration of an information processing device 10 and a selection device 20 according to an embodiment of the present invention. [Figure 4] 1 is a sequence diagram illustrating an example of a processing procedure executed in the information processing system 1. FIG. [Figure 5] FIG. 10 is a diagram showing an example of input to an input / output screen. [Figure 6] FIG. 10 is a diagram for explaining a method for selecting a priority. [Figure 7] FIG. 10 is a diagram showing an example of an output of a selection result on an input / output screen. [Figure 8] FIG. 10 is a diagram illustrating an example of a first prompt. [Figure 9] FIG. 10 is a diagram showing an example of a first output text. [Figure 10] FIG. 10 is a diagram illustrating an example of a second prompt. [Figure 11] FIG. 10 is a diagram showing an example of a second output text. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Fig. 1 is a diagram showing an example of the configuration of an information processing system 1 according to an embodiment of the present invention. As shown in Fig. 1, the information processing system 1 includes an information processing device 10, a selection device 20, and an external storage device 30. The information processing device 10 is connected to the external storage device 30 via a network such as the Internet. The information processing device 10 is also connected to the selection device 20 via a network such as a LAN (Local Area Network) or the Internet.

[0011] The information processing device 10 is placed within an internal network of an organization such as a company (hereinafter referred to as "organization X"), and is a device that stores a group of data used by organization X. In other words, the information processing device 10 is on-premise storage in organization X. For example, a computer such as a NAS (Network Attached Storage), a PC (Personal Computer), or a file server may be used as the information processing device 10.

[0012] The external storage device 30 is a device that is located outside the organization X and is capable of storing data. For example, the external storage device 30 may be a cloud storage. In this embodiment, the external storage device 30 is used as a storage destination (transfer destination) for some of the data stored in the information processing device 10 in order to increase the free space of the information processing device 10. By transferring the part of the data (hereinafter referred to as "data to be transferred") to the external storage device 30, the data can be deleted from the information processing device 10, and the free space of the information processing device 10 can be increased.

[0013] The selection device 20 is one or more computers that support the selection of data to be moved from among the data group stored in the information processing device 10. For example, data that is not accessed frequently but that the user wants to keep or that must keep may be selected as data to be moved.

[0014] 2 is a diagram showing an example of the hardware configuration of an information processing device 10 according to an embodiment of the present invention. The information processing device 10 in FIG. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a processor 104, and an interface device 105, which are all interconnected via a bus B.

[0015] A program for realizing processing in the information processing device 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program does not necessarily have to be installed from the recording medium 101, but may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program as well as necessary files, data, etc.

[0016] When an instruction to start a program is received, the memory device 103 reads and stores the program from the auxiliary storage device 102. The processor 104 is a CPU or a GPU (Graphics Processing Unit), or a CPU and a GPU, and executes functions related to the information processing device 10 in accordance with the program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

[0017] The selection device 20 and the external storage device 30 also have the same hardware configuration as that shown in FIG.

[0018] FIG. 3 is a diagram showing an example of the functional configuration of the information processing device 10 and the selection device 20 according to the embodiment of the present invention.

[0019] 3, the selection device 20 has a machine learning model 21. The machine learning model 21 is realized by a process in which one or more programs installed in the selection device 20 cause a processor of the selection device 20 to execute the process. The machine learning model 21 is a machine learning model (language model) that has been trained to receive text as input and output text corresponding to the input text, and is realized by, for example, a neural network. For example, a large language model (LLM (Large Language Model)) such as GPT may be used as the machine learning model 21. In this embodiment, the machine learning model 21 is used to select data to be moved to the external storage device 30 from the data stored in the data storage unit 121.

[0020] On the other hand, the information processing device 10 has a reception unit 11, an acquisition unit 12, and a movement processing unit 13. Each of these units is realized by a process in which one or more programs installed in the information processing device 10 are executed by the processor 104. The information processing device 10 also uses a data storage unit 121. The data storage unit 121 can be realized using, for example, the auxiliary storage device 102, or a storage device connectable to the information processing device 10 via a network.

[0021] The data storage unit 121 stores a set of data used by the user. In this embodiment, an example will be described in which data is stored in a file, but the data storage format is not limited to a specific one.

[0022] The receiving unit 11 receives, from the user, selection conditions for data to be transferred to the external storage device 30 (second storage unit) from among a plurality of data stored in the data storage unit 121 (first storage unit).

[0023] The acquisition unit 12 inputs text including the contents of multiple data and instructions to extract data from the multiple data whose contents satisfy the selection conditions into a machine learning model 21 (a pre-trained machine learning model), and acquires output from the machine learning model 21.

[0024] The transfer processing unit 13 transfers the data identified based on the output from the machine learning model 21 to the external storage device 30.

[0025] The following describes the processing procedures executed in the information processing system 1. Fig. 4 is a sequence diagram for explaining an example of the processing procedures executed in the information processing system 1.

[0026] In step S101, the reception unit 11 receives, via an input / output screen, a selection of a folder to be searched for data to be moved (hereinafter referred to as a "target folder") or data to be candidates for data to be moved (hereinafter referred to as "candidate data"), and an input of selection conditions for selecting data to be moved, from the user. If a display device is connected to the information processing device 10, the input / output screen may be displayed on the display device, or may be displayed on a terminal (such as a PC or a smartphone) that functions as a user interface for the information processing device 10.

[0027] 5 is a diagram showing an example of input to the input / output screen 510. In FIG. 5, an input / output screen 510 includes an area 511, an area 512, an area 513, a send button 514, an OK button 515, and the like.

[0028] Area 511 is an area for receiving input of a file path of candidate data or a folder path of a target folder in step S101. Input of a file path or folder path may be realized, for example, by dragging and dropping an icon corresponding to a file or folder from a screen displaying the file system of data storage unit 121.

[0029] Area 513 is an area for receiving input of selection conditions in step S101. In this embodiment, the selection conditions include items such as target size, target type, and priority. Therefore, area 513 is configured to be able to receive input of values ​​for these items.

[0030] The target size is the target value of the free space to be created by the data transfer. In other words, the target size can be said to be the minimum value of the total size of the data to be transferred.

[0031] The target type is the type of data to be moved. The data type is also the type of document that the data content represents. For example, documents may be classified into categories such as evidence, contracts, and specifications, and the following types may be defined for each category:

[0032] - Types of supporting documents: quotations, purchase orders, invoices, receipts, delivery notes, etc. · Types of contracts: confidentiality agreements, outsourcing contracts, etc. -Types of specifications: system specifications, functional specifications, design specifications, etc. In Figure 5, an example is shown in which the target type options are types related to supporting documents, followed by estimates, purchase orders, invoices, etc., but this is just one example, and the categories and types that are selected as target type options may be changed as appropriate in consideration of the user's business operations, etc.

[0033] The priority is the priority (priority order) when selecting data to be moved. In Fig. 5, the priority can be selected using a drop-down list 5131. Also, a button 5132 can be used to add to the drop-down list 5131.

[0034] Figure 6 is a diagram for explaining a method for selecting a priority. Figure 6 (1) shows a state in which only one drop-down list 5131 is displayed, as shown in Figure 5. When button 5132 is pressed in this state, a new drop-down list 5131 is added, as shown in (2).

[0035] The options of the drop-down list 5131 (i.e., examples of priority options) are, for example, "Creation date and time (oldest first)", "Creation date and time (newest first)", "Last updated date (oldest first)", "Last updated date (newest first)", "Last accessed date (oldest first)", "Last accessed date (newest first)", "File size (largest first)", "File size (smallest first)", etc. By adding multiple drop-down lists 5131, it is possible to specify the priority by combining multiple options.

[0036] The selection conditions are not limited to those described above. For example, if the target type is a document that belongs to evidentiary documents, the transaction amount may be added to the selection conditions. If the target type is a document that belongs to a contract, the contract date, contract termination date, contract period, etc. may be added to the selection conditions. If the target document is a document that belongs to a specification, the version (old / new) may be added to the selection conditions.

[0037] When the user completes the input and presses the OK button 515, the receiving unit 11 transmits the input file path / folder path and the selection conditions to the acquiring unit 12 (S102).

[0038] Next, the acquisition unit 12 acquires information (hereinafter referred to as "file information") about the file related to the file path and each file stored under the folder related to the folder path (i.e., each candidate data) from the data storage unit 121 (S103, S104). The file information is information including the file name, file size, text (character string) indicating the contents of the file, the last update date, the last access date, etc. In the case of a file that stores an image, the acquisition unit 12 may acquire the text indicating the contents of the file using character recognition.

[0039] Next, the acquisition unit 12 inputs information including the file information and selection conditions of each candidate data into the machine learning model 21 (S105).

[0040] The machine learning model 21 selects data to be moved from among the candidate data by performing calculations based on pre-learned parameters on the input information (S106). Subsequently, the machine learning model 21 outputs the selection result to the acquisition unit 12 (S107). The selection result is, for example, a list of file path names of data selected by the machine learning model 21 as data to be moved (hereinafter referred to as "model selected data"). Note that the model target data has not been confirmed as data to be moved.

[0041] Next, the acquisition unit 12 transmits a list of file information corresponding to each file path name included in the selection result to the reception unit 11 as the selection result by the machine learning model 21 (S108). The reception unit 11 displays the selection result in the area 512 of the input / output screen 510 (S109).

[0042] Fig. 7 is a diagram showing an example of the output of the selection results on the input / output screen. In Fig. 7, the same parts as in Fig. 5 are given the same reference numerals. In Fig. 7, a list of file information of the model selection data is displayed in area 512.

[0043] The user refers to area 512 to check whether the selection result (list of model selection data) by the machine learning model 21 is correct, and selects the check button corresponding to the data to be confirmed as data to be moved. Figure 7 shows an example in which two of three model selection data have been selected (checked) as data to be moved.

[0044] If the user wishes to search for other model selection data, the user can request a re-search for model selection data by changing the selection conditions, etc. in area 513 (S111). For example, the user may add the file path of the candidate data or the folder path of the target folder to area 511. The user may also select a new target type that is not currently selected. The user may also change the target size or priority. Hereinafter, the changed selection conditions will be referred to as "additional conditions." The additional conditions do not include overlapping portions with the original selection conditions. For example, the original target type is not included in the additional conditions. Furthermore, if the target size has not been changed, the target size is not included in the original additional conditions. Note that the "target size" in the following refers to the original value if not changed, and the changed value if changed.

[0045] When the changes to the selection conditions and the like are completed and the OK button 515 is pressed, the reception unit 11 transmits the added file path / folder path (if any) and the additional conditions to the acquisition unit 12 (S112). At this time, the reception unit 11 includes the value obtained by subtracting the total size of the data selected in the area 512 from the target size as the target size in the additional conditions.

[0046] In the subsequent steps S113 to S117, the same processing as in the above-described steps S105 to S109 is executed. At this time, the file information in step S113 may be the same as that in step S105. However, if a file path / folder path has been added, the same processing as in steps S103 and S104 is executed for the added file path and folder path, and the additionally acquired file information is also input to the machine learning model 21 in step S113.

[0047] When step S117 is executed again, new model selection data selected by the machine learning model 21 is added to area 512. If the user wants to add any data among the added model selection data as data to be moved, the user selects (checks) the check button corresponding to the data.

[0048] Following step S109 or S117, when the user presses the send button 514 (S121), the reception unit 11 transmits a transfer instruction including a list of file information displayed in the area 512 to the transfer processing unit 13 (S122). In response to the transfer instruction, the transfer processing unit 13 executes a transfer process for the data to be transferred corresponding to each piece of file information in the list (S123). Specifically, the transfer processing unit 13 acquires each piece of data to be transferred from the data storage unit 121 and transmits (uploads) it to the external storage device 30. The transfer processing unit 13 deletes the successfully transmitted data to be transferred from the data storage unit 121. At this time, the transfer processing unit 13 may generate link information (link file) for the data to be transferred in the storage area (e.g., folder) where the data to be transferred existed before deletion. This allows the user to easily access the data to be transferred.

[0049] The migration process here includes a process of copying the data to be migrated to the external storage device 30 and, after the copying is complete, deleting the data to be migrated from the data storage unit 121, as well as a process of simply copying the data to be migrated to the external storage device 30.

[0050] Next, the input to the machine learning model 21 in step S105 or S113 and the output from the machine learning model 21 in step S107 or S115 will be described.

[0051] Generally, instructions to an LLM are given by inputting text called a prompt. In this embodiment, the acquisition unit 12 also generates a prompt such as the following in step S105 and inputs the prompt to the machine learning model 21.

[0052] Fig. 8 is a diagram showing an example of a first prompt. Prompt p1 shown in Fig. 8 is a prompt that instructs the creation of a list of data (files) (related to the document types included in the selection conditions) that are likely to be of the type selected as the target type ("invoice" in Fig. 8) from among the candidate data. In other words, prompt p1 is a prompt for extracting candidate data that satisfies the target document among the selection conditions. In prompt p1, description d1 is the file information (file name and file contents) acquired for the candidate data in steps S103 and S104.

[0053] In response to the input of prompt p1, the machine learning model 21 outputs, for example, the following text (first output):

[0054] 9 is a diagram illustrating an example of a first output text o1, which includes a list of candidate data (files) that are likely to be invoices and is generated by the machine learning model 21 in accordance with a prompt p1.

[0055] After acquiring the output text o1, the acquisition unit 12 subsequently inputs the following prompt to the machine learning model 21:

[0056] FIG. 10 is a diagram showing an example of a second prompt. Prompt p2 shown in FIG. 10 is a prompt corresponding to the target size and priority of the selection conditions. Description d2 of prompt p2 indicates an instruction to create a list of files from the list of files shown in description d3, in order of oldest "last updated date," up to a total file size of 5 GB. Description d3 is file information for each file included in output text o1. Note that the specific values ​​such as "last updated date" and "5 GB" change depending on the priority and target size of the selection conditions.

[0057] In response to the input of prompt p2, the machine learning model 21 outputs, for example, the following text (second output):

[0058] 11 is a diagram showing an example of the second output text, which shows output text o2 including a list of model selection data generated by the machine learning model 21 in accordance with prompt p2.

[0059] The acquisition unit 12 sets an example of data identified based on the output text o2 as model selection data (machine learning model 21).

[0060] That is, this list is displayed in the area 512 of the input / output screen 510 (FIG. 7) in step S109 as candidate data (model selection data) that meets the selection conditions.

[0061] In the above example, a prompt is input twice and an output is made from the machine learning model 21 in response to each prompt. S105 to S107 in FIG. 4 correspond to these two inputs and outputs.

[0062] However, since the processing in response to the instructions of prompt p2 can be realized by sorting the files based on their last update date and comparing the total file size with the target size, the acquisition unit 12 may execute the processing on a rule-based basis without executing prompt p2 on the machine learning model 21.

[0063] As described above, according to this embodiment, text including the contents of multiple data stored in the data storage unit 121 and instructions to extract data from the multiple data whose contents satisfy selection conditions input by the user is input into the pre-trained machine learning model 21, and data identified based on the output from the machine learning model 21 is moved to the external storage device 30, thereby making it possible to select the data to be moved based on the contents of the data.

[0064] As a result, for example, when it is desired to transfer only data that is not accessed frequently but needs to be saved and therefore occupies storage capacity (for example, supporting documents, contracts, etc.), conventionally, a user would have had to select the data based on its contents, but by leaving such selection to the machine learning model 21, it is possible to reduce the workload on the user. In this case, by providing a GUI (input / output screen 510) for inputting selection conditions, it is possible to reduce the variation in input by users, and the machine learning model 21 can generate prompts that are less likely to be misunderstood.

[0065] Note that the devices in this embodiment represent only one of multiple computing environments. In one embodiment, information processing apparatus 10 includes multiple computing devices, such as a server cluster. The multiple computing devices are configured to communicate with each other via any type of communication link, including a network, shared memory, etc., and perform the processes disclosed herein. Similarly, selection apparatus 20 may include multiple computing devices configured to communicate with each other.

[0066] Furthermore, the information processing device 10 is not limited to an image forming device as long as it is a device having an information processing function. The information processing device 10 may be, for example, a PJ (Projector), an IWB (Interactive White Board: a white board with an electronic blackboard function capable of mutual communication), an output device such as digital signage, a HUD (Head Up Display) device, industrial machinery, an imaging device, a sound collection device, medical equipment, a network home appliance, a notebook PC (Personal Computer), a mobile phone, a smartphone, a tablet terminal, a game console, a PDA (Personal Digital Assistant), a digital camera, a wearable PC, a desktop PC, or the like.

[0067] Furthermore, in this embodiment, machine learning refers to a technology for enabling a computer to acquire human-like learning capabilities, in which the computer autonomously generates algorithms necessary for judgments such as data classification from learning data that is previously acquired, and applies these to new data to make predictions. The learning method for machine learning may be any of supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning, or may be a combination of these learning methods; any learning method for machine learning is acceptable.

[0068] Each function of the present embodiment can be realized by one or more processing circuits. Here, the term "processing circuit" in this specification includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, as well as devices such as an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), and a conventional circuit module designed to execute each function described above.

[0069] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and variations are possible within the scope of the gist of the present invention as described in the claims.

[0070] For example, aspects of the present invention are as follows.

[0071] <1> a receiving unit that receives a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition unit that inputs text including the contents of a plurality of pieces of data and an instruction to extract data from the plurality of pieces of data whose contents satisfy the selection condition into a pre-trained machine learning model and acquires a first output from the machine learning model; a transfer processing unit that transfers data identified based on the first output to the second storage unit; An information processing device comprising:

[0072] <2> the receiving unit receives an additional selection condition for data to be moved after the first output is acquired; the acquisition unit inputs text including contents of a plurality of pieces of data and an instruction to extract data that satisfies the additional selection condition from the plurality of pieces of data to the machine learning model, and acquires a second output from the machine learning model; the movement processing unit moves data identified based on the first output and the second output to the second storage unit. Characterized by <1> The information processing device described.

[0073] <3> The selection conditions include a document type; the text includes an instruction to extract data relating to the document type included in the selection conditions from the plurality of data; Characterized by <1> or <2> The information processing device described.

[0074] <4> An information processing system including an information processing device and a selection device, The information processing device includes: a receiving unit that receives a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition unit that inputs text including the contents of a plurality of pieces of data and an instruction to extract data whose contents satisfy the selection condition from the plurality of pieces of data into a pre-trained machine learning model included in the selection device, and acquires a first output from the machine learning model; a transfer processing unit that transfers data identified based on the first output to the second storage unit; An information processing system comprising:

[0075] <5> a receiving step of receiving a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition step of inputting text including the contents of a plurality of pieces of data and instructions to extract data from the plurality of pieces of data whose contents satisfy the selection condition into a pre-trained machine learning model, and acquiring a first output from the machine learning model; a transfer processing procedure for transferring data identified based on the first output to the second storage unit; An information processing method characterized by being executed by a computer.

[0076] <6> a receiving step of receiving a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition step of inputting text including the contents of a plurality of pieces of data and instructions to extract data from the plurality of pieces of data whose contents satisfy the selection condition into a pre-trained machine learning model, and acquiring a first output from the machine learning model; a transfer processing procedure for transferring data identified based on the first output to the second storage unit; A program that causes a computer to execute the following. [Explanation of symbols]

[0077] 10. Information processing equipment 11 Reception 12 Acquisition Department 13. Movement Processing Section 20 Selection device 21 Machine Learning Models 30 External storage device 100 Drive device 101 Recording media 102 Auxiliary storage device 103 Memory Device 104 processors 105 Interface Device 121 Data storage unit B Bus [Prior art documents] [Patent documents]

[0078] [Patent Document 1] Japanese Patent Application Publication No. 2021-149773

Claims

1. a receiving unit that receives a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition unit that inputs text including the contents of a plurality of pieces of data and an instruction to extract data from the plurality of pieces of data whose contents satisfy the selection condition into a pre-trained machine learning model and acquires a first output from the machine learning model; a transfer processing unit that transfers data identified based on the first output to the second storage unit; An information processing device comprising:

2. the receiving unit receives an additional selection condition for data to be moved after the first output is acquired; the acquisition unit inputs text including contents of a plurality of pieces of data and an instruction to extract data that satisfies the additional selection condition from the plurality of pieces of data to the machine learning model, and acquires a second output from the machine learning model; the movement processing unit moves data identified based on the first output and the second output to the second storage unit.

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

3. The selection conditions include a document type; the text includes an instruction to extract data relating to the document type included in the selection conditions from the plurality of data; 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. An information processing system including an information processing device and a selection device, The information processing device includes: a receiving unit that receives a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition unit that inputs text including the contents of a plurality of pieces of data and an instruction to extract data whose contents satisfy the selection condition from the plurality of pieces of data into a pre-trained machine learning model included in the selection device, and acquires a first output from the machine learning model; a transfer processing unit that transfers data identified based on the first output to the second storage unit; An information processing system comprising:

5. a receiving step of receiving a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition step of inputting text including the contents of a plurality of pieces of data and instructions to extract data from the plurality of pieces of data whose contents satisfy the selection condition into a pre-trained machine learning model, and acquiring a first output from the machine learning model; a transfer processing procedure for transferring data identified based on the first output to the second storage unit; An information processing method characterized by being executed by a computer.

6. a receiving step of receiving a selection condition for data to be transferred to the second storage unit from among the data stored in the first storage unit; an acquisition step of inputting text including the contents of a plurality of pieces of data and instructions to extract data from the plurality of pieces of data whose contents satisfy the selection condition into a pre-trained machine learning model, and acquiring a first output from the machine learning model; a transfer processing procedure for transferring data identified based on the first output to the second storage unit; A program that causes a computer to execute the following.

Images