Information processing method, program, and information processing system

Abstract

To provide an information processing method, a program, and an information processing system that effectively obtain desired processing results.SOLUTION: In an information processing system including a server as an information processing device and a user terminal connected to each other so as to be able to communicate with each other via a network, an information processing method executed by the information processing device includes a processing instruction acquisition step S100 of acquiring processing instruction information giving instructions on processing, a use information acquisition step S108 of acquiring use information required for processing from an information source based on the processing instruction information, and a processing step S110 of executing processing using a trained model based on the use information.SELECTED DRAWING: Figure 4

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses an information processing apparatus that improves the prediction accuracy of a machine learning model. In this information processing apparatus, in training a reliability determination model for evaluating the reliability of correct labels used for training a machine learning model, additional information including the freshness of information is collected and used to more accurately evaluate the reliability of correct labels.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, although it is known that the processing result output by a trained learned model changes depending on the data (usage information) input to the learned model, it is required to control the usage information so that a desired processing result can be obtained based on the processing instruction information that instructs the processing.

[0005] An object of the present invention is to effectively obtain a desired processing result.

Means for Solving the Problems

[0006] According to an information processing method according to an embodiment, it is an information processing method executed by an information processing apparatus, including a processing instruction acquisition step of acquiring processing instruction information that instructs processing, a usage information acquisition step of acquiring usage information necessary for processing from an information source based on the processing instruction information, and a processing step of executing processing using a learned model based on the usage information.

[0007] According to a program according to an embodiment, an information processing apparatus is caused to execute an information processing method including: a process instruction acquisition step of acquiring process instruction information for instructing a process; a use information acquisition step of acquiring use information necessary for the process from an information source based on the process instruction information; and a process step of executing the process using a learned model based on the use information.

[0008] According to an information processing system according to an embodiment, a process instruction acquisition step of acquiring process instruction information for instructing a process, a use information acquisition step of acquiring use information necessary for the process from an information source based on the process instruction information, and a process step of executing the process using a learned model based on the use information are performed.

Advantages of the Invention

[0009] According to an embodiment, a desired processing result can be effectively obtained.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0011] (First Embodiment) Hereinafter, a first embodiment of the information processing system according to the present invention will be described with reference to FIGS. 1 to 5. In each figure, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may be different from the actual ratios.

[0012] (System Overview) First, the overview of the information processing system 10 according to the present embodiment will be described. When a prompt as processing instruction information for instructing processing is input to a learned model such as a large language model, the information processing system 10 according to the present embodiment is a system that generates a processing result corresponding to the prompt by the learned model and outputs the processing result. That is, when a prompt is input by the user U, the information processing system 10 acquires usage information necessary for processing from a predetermined information source based on the prompt, performs processing using the learned model, and generates a processing result. Details will be described later.

[0013] (System Configuration) FIG. 1 is a diagram showing an example of the configuration of the information processing system 10 according to the present embodiment. As shown in FIG. 1, the information processing system 10 according to the present embodiment includes a server 12 as an information processing device and a user terminal 14 that are communicably connected to each other via a network N. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination thereof.

[0014] The user terminal 14 is an example of an information processing device that performs operations for inputting and displaying various information by the user U. The user terminal 14 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, a wearable device, or a combination thereof.

[0015] Server 12 is an example of an information processing apparatus that acquires information input from user terminal 14, performs processing based on the information, and outputs a result. Server 12 may be a PC (Personal Computer), smartphone, tablet terminal, server device, microcomputer, or a combination thereof. The specific configuration and operation of server 12 will be described later.

[0016] (Hardware Configuration) FIG. 2 is a block diagram showing the hardware configuration of server 12. Server 12 includes a processor 120, a memory 122, a storage 124, a communication I / F 126, an input / output I / F 128, and a drive device 134, which are communicably connected to each other via bus B.

[0017] Processor 120 controls each component of server 12 and realizes the functions of server 12 by expanding and executing various programs stored in storage 124 in memory 122. The programs executed by processor 120 include, but are not limited to, an OS (Operating System) and program 220 described later. By executing these programs by processor 120, a part of the state visualization method according to the present embodiment is realized. Processor 120 is, for example, a CPU (Central Processing Unit), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit), DSP (Digital Signal Processor), or a combination thereof.

[0018] Memory 122 is, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), or a combination thereof. The ROM is, for example, a PROM (Programmable ROM), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), or a combination thereof. The RAM is, for example, a DRAM (Dynamic RAM), an SRAM (Static RAM), an MRAM (Magnetoresistive RAM), or a combination thereof.

[0019] Storage 124 stores the OS, various programs described later, and various data. Storage 124 is, for example, a flash memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), an SCM (Storage Class Memories), or a combination thereof.

[0020] Communication I / F 126 is an interface for connecting server 12 to external devices including user terminal 14 and imaging device 16 via network N and controlling communication. Communication I / F 126 is, for example, an adapter compliant with Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), Ethernet (registered trademark), or optical communication (e.g., Fibre Channel), but is not limited thereto.

[0021] Input / output I / F 128 is an interface for connecting input device 132 and output device 130 to server 12. Input device 132 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a camera, various sensors, operation buttons, or a combination thereof. Output device 130 is, for example, a display, a projector, a printer, a speaker, a vibrator, or a combination thereof.

[0022] The drive device 134 reads and writes data on the disk medium 136. The drive device 134 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or a combination thereof. The disk medium 109 is, for example, a CD (Compact Disc), a DVD (Digital Versatile Disc), an FD (Floppy Disk), an MO (Magneto-Optical disk), a BD (Blu-ray (registered trademark) Disc), or a combination thereof.

[0023] Note that in this embodiment, the program may be written in the memory 122 or the storage 124 at the manufacturing stage of the server 12, may be provided to the server 12 via the network N, or may be provided to the server 12 via a non-transitory computer-readable recording medium such as the disk medium 136.

[0024] Also, regarding the hardware configuration of the user terminal 14, since it is substantially the same as the hardware configuration of the server 12 described above, detailed description thereof is omitted.

[0025] (Functional Configuration) Next, the functional configuration of the server 12 will be described. FIG. 3 is a diagram showing an example of the functional configuration of the server 12. When executing various programs, the server 12 uses the above hardware resources to realize various functions. The server 12 has a communication unit 20, a storage unit 22, and a control unit 24 as functional configurations realized by the server 12. Each functional configuration is realized by the processor 120 reading and executing the program 220 stored in the memory 122 or the storage 124.

[0026] The communication unit 20 is realized by the communication I / F 126. The communication unit 20 transmits and receives information to and from the user terminal 14 via the network N. The communication unit 20 receives information input from the user terminal 14. Also, the communication unit 20 transmits information to the user terminal 14 and receives a request from the user U from the user terminal 14.

[0027] The storage unit 22 is realized by the memory 122 and the storage 124. The storage unit 22 stores a program 220, a learned model 222, a prompt 224, usage information 226, and a processing result 228.

[0028] The learned model 222 is composed of at least one learned machine learning model. This learned model 222 is, for example, a large language model, and is a model that has learned a large amount of text data from articles, books, websites, etc. on the Internet. When text data is input as a prompt, text data corresponding to the prompt is generated and output. The large language model in the learned model 222 of the present embodiment determines the direction of the output result based on the content of the prompt. Note that this output result refers to the expected output result.

[0029] Here, the directionality indicates the nature or characteristics of the output result (hereinafter simply referred to as "nature"). As an example, the learned model 222 determines the following two natures. That is, the first nature is the "strict based on the information source" nature (hereinafter simply referred to as "strict"). The output result along this nature is based on clear information extracted or derived from a specific information source. On the other hand, the second nature is the "broad and creative" nature (hereinafter simply referred to as "creativity"). The output result along this nature is not limited to a specific information source, but draws insights from a wide range of information and provides new perspectives and interpretations. The learned model 222 determines, by the determination of directionality, to what extent the "strict" and "creativity", which are opposite to each other as the nature of the output result, are. That is, when an instruction to the effect of "Please answer based on the content of the previous management meeting" is given in the prompt, the learned model 222 determines that an output result with a strict nature based on an information source such as the minutes of the previous management meeting is required, and determines the directionality of the output result as "strict". On the other hand, when an instruction to the effect of "Please answer considering recent economic and technological trends" is given in the prompt, the learned model 222 determines that an output result with a creative nature not limited to a specific information source is required, and determines the directionality of the output result as "creativity". Note that the above determinations of "strict" and "creativity" are merely examples, and it goes without saying that the directionality is appropriately determined based on the content for other prompts as well. Also, the directionality may be determined based on other natures. Furthermore, instead of only determining the presence or absence of each nature, the degree to which the nature is required may be determined numerically, such as "strictness 80, creativity 20". Moreover, the output result may be divided into a plurality of parts, and the nature may be determined for each part. As a specific example, it can be mentioned that the output result is divided into a first part that answers based on facts and a second part that conducts considerations on the previous part, and the first part is determined as "strict" and the second part is determined as "creativity".

[0030] In addition, the pre-trained model 222 determines candidates for the usage information required for processing based on the prompt. Specifically, the pre-trained model 222 evaluates the characteristics of the information required for the processing performed based on the prompt (such as whether the information comes from general common sense or specialized knowledge), and when it is determined that such characteristics need to be obtained from an external information source or the like, it searches for the information source and determines the information required for the processing as candidates for the usage information. Note that the information source may be the storage unit 22 in which various types of information are stored, or an external information source such as books or information on the Internet. Also, the usage information is various types of information including the text information stored in these information sources, and the details will be described later.

[0031] Furthermore, the pre-trained model 222 generates at least a part of the index information of the candidate usage information. At least a part of this index information is, as an example, the freshness information of the information, and this freshness information changes according to the content of the usage information and the content of the processing. That is, the freshness information, in other words, is "the value of the information on the time axis", and is roughly divided into a pattern in which the value decreases with the passage of time (hereinafter simply referred to as the "decrease pattern"), a pattern in which the value remains constant with respect to the passage of time (hereinafter simply referred to as the "constant pattern"), and a pattern in which the value increases with the passage of time (hereinafter simply referred to as the "increase pattern"). Each pattern will be described below. Note that the "value of the information" referred to here represents how much the information contributes to the processing result desired by the user U, and when the value of the information is high, it highly contributes to the output of the desired processing result.

[0032] There are two types of downward patterns: a pattern in which the value decreases at a roughly constant rate (see Fig. 5(A)) and a pattern in which the value decreases rapidly (see Fig. 5(B)). Information on the pattern in which the value decreases at a roughly constant rate specifically corresponds to general news information, product information for which new models are regularly released, result information of events, etc. These types of information have a time limit in which their value gradually decreases over time. Also, information on the pattern in which the value decreases rapidly specifically corresponds to stock information, weather forecasts, news information related to events with drastic changes in situations such as accidents and disasters, etc.

[0033] Information on the constant pattern (see Fig. 5(C)) specifically corresponds to information related to historical facts and scientific principles. These types of information have relatively little change in value over time.

[0034] There are two types of upward patterns: a pattern in which the value increases at a roughly constant rate (see Fig. 5(D)) and a pattern in which the value increases rapidly (see Fig. 5(E)). Information on the pattern in which the value increases at a roughly constant rate specifically includes information such as historical data, classical literature, information on products produced in limited quantities or antique books, etc. Although these may not be initially recognized as having much value, their importance and value are re-recognized over time and the value increases. Also, information on the pattern in which the value increases rapidly specifically includes information on past artworks and collectibles, information on predictive analysis and forecasts, information on specific technologies and theories, information on vintage products, etc. Although these are not initially given much attention, they gain rapid value due to events such as the death of the author or past predictions coming true later. Note that the specific information for each pattern is not limited to the above.

[0035] In addition, the above three patterns are just examples, and other patterns may be included, such as patterns in which the value fluctuates periodically, such as information regarding periodic events. Further, patterns combining the above-described patterns may be included. That is, examples include information whose value increases and then becomes constant or decreases after a predetermined timing, information whose value was constant and then increases or decreases after a predetermined timing, and information whose value decreases and then becomes constant or increases after a predetermined timing. In other words, the learned model 222 can also be expressed as "evaluating usage information whose value changes according to the acquired prompt using an index called freshness information".

[0036] The prompt 224 is information indicating the prompt input by the user U. The prompt 224 is in natural language and, as an example, is stored associated with the account information of the user U.

[0037] The usage information 226 is usage information necessary in the process. This usage information 226 is information acquired from information sources such as books, the Internet, and the storage unit 22 as described above, and includes text information, image information, and the like. Note that the usage information 226 includes unstructured data and structured data. Here, "unstructured data" refers to data that is stored without being structured in a predefined manner. On the other hand, "structured data" refers to data that exists in fixed fields in files or records. "Structured data" includes "semi-structured data". The usage information 226 can be stored in a data lake (not shown) in the storage unit 22, and can be acquired using the index information of the usage information 226 described later from the data lake.

[0038] The processing result 228 is information indicating the result of executing processing using the usage information based on the prompt. The processing result 228 is various information including text information and image information, and is stored associated with the prompt and the usage information.

[0039] The control unit 24 is realized by the processor 120 reading and executing the program 220 from the memory 122 (see FIG. 2) and collaborating with other hardware configurations. The control unit 24 includes an information acquisition unit 242, an information processing unit 244, and an output unit 246.

[0040] The information acquisition unit 242 acquires various information necessary for the processing in the information processing unit 244. Specifically, it acquires a prompt 224 for instructing processing and usage information 226 including unstructured data necessary for the processing. In addition, the information acquisition unit 242 acquires index information of the usage information 226 (details will be described later). The information acquired may be information stored in the storage unit 22 or information acquired from an external data source or the like.

[0041] The information processing unit 244 determines the direction of the output result based on the content of the prompt, acquires and generates index information of the usage information 226, determines the degree of coincidence between the direction of the output result and the usage information, and executes processing based on the prompt. The determination of the direction of the output result is made using the learned model 222 for the nature of the output result assumed corresponding to the prompt input by the user U as described above.

[0042] The information processing unit 244 generates freshness information among the index information of the usage information 226 using the learned model 222 as described above. In addition, the information processing unit 244 can also be used for metadata and log data as index information of the usage information acquired by the information acquisition unit 242. Metadata is information that describes characteristics and attributes of data such as the content, source, creator, timestamp, etc. of the usage information 226. Log data is information recorded along with the time when a certain operation such as recording or accessing the usage information 226 is performed, the executor who performed it, request and response information, error information, etc. These metadata and log data are made available by being associated with the usage information 226 in advance. The information processing unit 244 performs a coincidence determination between the usage information and the direction of the output result using at least one of the freshness information, metadata, and log data that are index information (details will be described later).

[0043] The information processing unit 244 determines the degree of match between the direction of the output result and the usage information 226. That is, for the direction, it determines from the index information of the usage information 226 whether the candidate of the usage information 226 matches the process based on the prompt and the degree of match. As a specific example, when the direction is determined to be "strict", the degree of match of the usage information 226 is determined using the index information from viewpoints such as whether the candidate of the usage information 226 is accurate, complete, up-to-date, highly reliable, clear, traceable, consistent, etc.

[0044] That is, for example, whether it is accurate is determined based on criteria such as whether the update date and time of the usage information 226 is the most recent from the metadata, whether the recording of the date and time is accurate, whether the registrant is a highly reliable person or organization, whether the metadata conforms to a predefined format or standard, whether error messages or abnormal patterns are searched from the log data and there are no signs indicating system abnormalities, whether the factors causing the increase or decrease pattern are traced from the freshness information and there is no contradiction with the content in the case of an increase or decrease pattern, etc.

[0045] Whether it is complete is determined based on criteria such as whether all the necessary metadata elements are present, whether all the log data to be collected is present, whether important elements or bits for capturing the overall picture of the information value variation such as the specific time period when the value increase or decrease occurred from the freshness information and the situation in which it occurred are included, etc.

[0046] Whether it is up-to-date is determined based on criteria such as whether the metadata reflects the latest information, whether the log data is real-time or the latest data, whether the freshness information reflects the latest information value variation, whether the information value is above a predetermined value, etc.

[0047] Whether it is highly reliable is determined based on criteria such as the reliability of the data source and the evaluation result of the metadata generation process from the metadata, whether the log data is collected by a highly reliable means and there is no risk of forgery, and whether the freshness information has little variation in information value in any pattern.

[0048] Whether it is clear is determined based on criteria such as whether the metadata is defined according to clear explanations and conventions, whether the log data is recorded in a consistent format and can be clearly interpreted, and whether the factors causing the information value to decrease, remain constant, or increase can be clearly interpreted from the freshness information.

[0049] Whether it is traceable is determined based on criteria such as whether the data source is specified from the metadata and it is possible to inquire about the data source, whether each log entry in the log data is traceable over time (whether time information is included), and whether the variation in each information value from the freshness information is traceable over time, that is, whether the point in time when the variation occurred is specified.

[0050] Whether there is consistency is determined based on criteria such as whether there is consistency among the metadata, whether they comply with the defined rules and standards, whether the log data is generated in a consistent format and pattern from the log data, and whether the variation in information value is consistent from the freshness information. Note that the above determination criteria are just examples, and it may be determined by other determination criteria.

[0051] When the degree of coincidence between the direction of the output result and the usage information 226 is equal to or greater than a predetermined value, the information processing unit 244 performs processing corresponding to the prompt based on the usage information using the learned model 222. On the other hand, when the degree of coincidence between the direction of the output result and the usage information 226 is less than the predetermined value, the information processing unit 244 searches for the usage information 226 again and acquires candidates for the usage information 226 as search results via the information acquisition unit 242.

[0052] The output unit 246 controls to output the processing result of the information processing unit 244 to the user terminal 14.

[0053] (Processing executed by the information processing system 10) Next, the operation of the information processing system 10 will be described. FIG. 4 is a flowchart showing an example of the processing flow by the information processing system 10. The processor 120 reads the program 220 stored in the storage 124, expands it in the memory 122, and executes it, thereby performing the processing. Although not shown, when the processor 120 receives the operation end information of the information processing system 10 or the operation end information from the user terminal 14 in the ongoing determination processing (these are simply referred to as "end operations"), the processor 120 ends the processing based on the program 220 being processed.

[0054] The processor 120 determines whether a prompt input from the user U or the like can be obtained (step S100). If the prompt has not been input or cannot be obtained such as during input (step S100: NO), the processor 120 repeats the processing of step S100. On the other hand, when the prompt is obtained (step S100: YES), the processor 120 determines the direction of the result to be output based on the content of the prompt (step S102). Note that step S100 described above corresponds to the "processing instruction acquisition step" recited in claim 1.

[0055] Processor 120 determines candidates for usage information required in prompt-based processing and acquires index information of the usage information that is the candidate (step S104). Then, processor 120 determines whether there is usage information that matches the directionality determined in step S102 from the acquired index information (step S106). If there is no usage information that matches the directionality (step S106: NO), processor 120 re-determines candidates for usage information required in prompt-based processing excluding the usage information (step S107) and transfers the process to step S104. On the other hand, if there is usage information that matches the directionality (step S106: YES), processor 120 acquires the usage information (step S108) and performs information processing using the usage information based on the prompt (step S110). Then, processor 120 outputs the processing result (step S112) and ends the process. This output includes display on the display of user terminal 14, execution of processing on external tools, sensors, data sources, etc. Note that step S108 described above corresponds to the "usage information acquisition step" recited in claim 1, and step S110 corresponds to the "processing step" recited in claim 1.

[0056] (Operation and Effect of the First Embodiment) According to the information processing system 10 according to this embodiment, an instruction acquisition step for acquiring a prompt (processing instruction information) for instructing processing, a usage information acquisition step for acquiring usage information 226 required for processing from an information source based on the processing instruction information, and a processing step for executing processing corresponding to the prompt 224 using the learned model 222 based on the usage information 226 are executed. Thereby, since processing using the usage information 226 based on the prompt 224 is executed, a desired processing result can be effectively obtained.

[0057] In addition, since the information processing system 10 acquires the usage information 226 based on the output direction determined from the prompt 224 in the usage information acquisition step, it can execute the process corresponding to the prompt 224 based on the appropriate usage information 226. As a result, a desired processing result can be obtained more effectively.

[0058] Furthermore, since the information processing system 10 utilizes the metadata of the usage information 226 when acquiring the usage information 226 in the usage information acquisition step, it can efficiently and appropriately select the usage information 226. As a result, a desired processing result can be obtained even more effectively.

[0059] Moreover, since the information processing system 10 utilizes the log data related to the usage information 226 when acquiring the usage information 226 in the usage information acquisition step, it can select the usage information 226 based on an objective record. As a result, a desired processing result can be obtained even more effectively.

[0060] In addition, since the information processing system 10 inputs the information of the information source into the learned model 222 that has been learned to output the index information of the information when the information is input in the usage information acquisition step, and utilizes the index information output from the learned model 222 when acquiring the usage information 226, it can appropriately select the usage information 226 even for data without metadata or log data. As a result, a desired processing result can be obtained even more effectively.

[0061] (Second Embodiment) Next, with reference to FIGS. 6 and 7, the information processing system 40 according to the second embodiment of the present invention will be described. The information processing system 40 according to the second embodiment has the same basic configuration as that of the first embodiment, and is characterized in that it executes a storage step of storing the processing result, and an output of the stored processing result when the relevance between the stored processing result and the new prompt 224 is equal to or greater than a predetermined standard. Note that the same components as those in the first embodiment are denoted by the same reference numerals and their description is omitted.

[0062] (Functional configuration) The functional configuration of the server 50 as an information processing device in the information processing system 40 will be described. FIG. 6 is a diagram showing an example of the functional configuration of the server 50. When executing various programs, the server 50 uses the same hardware resources as the server 12 in the first embodiment to realize various functions. The server 50 has a communication unit 20, a storage unit 60, and a control unit 70 as the functional configuration realized by the server 50. Each functional configuration is realized by the processor 120 reading and executing the program 600 stored in the memory 122 or the storage 124.

[0063] The control unit 70 is realized by the processor 120 reading and executing the program 600 from the memory 122 (see FIG. 2) and cooperating with other hardware configurations. The control unit 70 includes an information acquisition unit 242, an information processing unit 700, and an output unit 246.

[0064] Similar to the information processing unit 244 in the first embodiment, the information processing unit 700 determines the direction of the output result based on the content of the prompt, acquires and generates the index information of the usage information 226, determines the degree of coincidence between the direction of the output result and the usage information, and executes the processing based on the prompt. In addition, the information processing unit 700 associates the processing result corresponding to the prompt 224 with the usage information 226 when there is the prompt 224 and the usage information 226, and stores it in the storage unit 60.

[0065] Furthermore, when the information processing unit 244 acquires a new prompt 224, if the relevance between the prompt 224 and the processing result stored in the storage unit 60 is equal to or higher than a predetermined criterion, the information processing unit 244 outputs the processing result. This predetermined criterion is, as an example, a criterion for determining that the new prompt 224 is similar to the prompt 224 associated with the processing result stored in the storage unit 60. Specifically, the new prompt 224 and the prompt 224 associated with the processing result stored in the storage unit 60 are vector-converted and set to values such as cosine similarity or Euclidean distance. Here, being equal to or higher than the predetermined criterion indicates a higher similarity. Note that the predetermined criterion may be not only the one described above but also other criteria such as word-based similarity or meaning-based similarity. Also, the predetermined criterion may be used not only for comparison between the new prompt 224 and the prompt 224 associated with the processing result stored in the storage unit 60 but also for similarity determination in comparison between the new prompt 224 and the processing result itself stored in the storage unit 60. Furthermore, the predetermined criterion may be used not only for determining similarity but also for determining connection, commonality, influence relationship, etc., or other things.

[0066] (Processing performed by the information processing system 40) Next, the operation of the information processing system 40 will be described. FIG. 7 is a flowchart showing an example of the processing flow by the information processing system 40. The processor 120 reads out the program 600 stored in the storage 124, expands it in the memory 122, and executes it, thereby performing the processing. For the same processing as in the first embodiment, the same reference numerals are given and the description thereof is omitted.

[0067] After the process of step S100, the processor 120 determines the relevance between the acquired prompt 224 and the prompt 224 associated with the processing result stored in the storage unit 60 (step S200), and determines whether the determined relevance is equal to or higher than a predetermined criterion (step S202). If it is not equal to or higher than the predetermined criterion (step S202: NO), the processor 120 transfers the process to step S102. On the other hand, if it is equal to or higher than the predetermined criterion (step S202: YES), the processor 120 acquires the processing result corresponding to the prompt 224 associated with the processing result stored in the storage unit 60 (step S204), and transfers the process to step S112.

[0068] After the process of step S110, the processor 120 associates the processing result, the corresponding prompt 224, and the usage information 226 if there is any usage information 226 with each other and stores them in the storage unit 60 (step S206), and transfers the process to step S112. Note that the process of step S206 corresponds to the "storage step" described in claim 6.

[0069] (Operational effects of the second embodiment) Also in the information processing system 40 according to the present embodiment, except for performing a storage step of storing a processing result and an output of the stored processing result when the relevance between the stored processing result and the new prompt 224 is equal to or higher than a predetermined criterion, the configuration is the same as that of the first embodiment. Therefore, the same operational effects as those of the first embodiment can be obtained. Further, the information processing system 40 has a storage step of storing the processing result in the processing step in the storage unit 60 of the server 50, and outputs the processing result when the relevance between the new prompt 224 acquired in the processing instruction acquisition step and the processing result stored in the storage unit 60 is equal to or higher than a predetermined criterion. Therefore, when a new prompt 224 related to the prompt 224 processed in the past is input, execution of processing using the learned model 222 can be avoided. Thereby, stabilization of the processing result and reduction of the processing cost caused by using the learned model 222 can be achieved.

[0070] In the above-described first and second embodiments, at least one of metadata, log data, and freshness information is used as the index information of the usage information 226. However, the present invention is not limited to this, and other data such as annotation data may be used as the index information. Further, although the learned model 222 is configured to generate the freshness information of the usage information 226 from the content of the usage information 226, regarding the generation of this freshness information, not only the content of the usage information 226 but also information such as metadata and log data may be used to generate the freshness information. Further, the learned model 222 may generate information for determination as necessary information in processing, such as not only the freshness information but also a summary of the content of the usage information 226, as the index information. Then, the information processing systems 10 and 40 may be configured to determine these pieces of information by at least one of a rule-based method and the learned model 222 and acquire the usage information 226 necessary for processing from the information source.

[0071] Furthermore, regarding the freshness information of the usage information 226, it is information generated by the learned model 222 that performs processing based on a prompt. However, it is not limited to this, and the index information including the freshness information may be configured to be generated by a learned model different from the learned model 222 that performs processing based on a prompt. In the case of this configuration, since a learned model optimized for generating the index information can be used, the acquisition of the usage information 226 can be performed with higher accuracy. Note that the learned model that outputs the freshness information is, as an example, a model obtained by performing machine learning using a data set using at least one of time-stamped information, production source information, update frequency information, user reaction information, and topic field property information. Here, the time-stamped information is information to which a time stamp indicating when the target information was generated is added, and it enables direct evaluation of the freshness of the information. The production source information is information indicating where the target information came from. As an example, newspaper articles have the highest freshness on the day of publication, and the freshness decreases over time. However, historical data and cultural data increase in information value over time, and it enables evaluation of the freshness of the information. The update frequency information is information indicating how frequently the target information is updated. As an example, information with a high update frequency has a high information value, and it enables evaluation of the freshness of the information. The user reaction information is, as an example, information indicating how the user reacted to the target information, such as the number of clicks, display time, share count, and comments. Information with a large amount of reaction information has a high information value, and it enables evaluation of the freshness of the information. The topic field property information takes into account the background of each field, such as in the field of science and technology, information is updated every time new research or publications are made, while in fields such as literature and history, information is not updated as frequently, and it enables evaluation of the freshness of the information.

[0072] Furthermore, in the process performed by the processor 120 in step S106 in the above-described first and second embodiments, although it is configured to determine the presence or absence of usage information that matches the directionality determined in step S102 from the acquired index information, it is not limited thereto. It may be configured to calculate the degree of match with the directionality in the acquired index information and acquire the usage information corresponding to the index information in descending order of this degree of match for use in the process, or a combination of the determination based on this degree of match and the determination of the presence or absence of the above-described usage information may be used.

[0073] (Modification Example 1) Furthermore, when the above-described information processing system is grasped from a different perspective, the problem (objective) to be solved by the information processing system according to the present embodiment can also be grasped as "aiming to reduce the cost of processing".

[0074] When the problem is grasped as described above, the invention as a means for solving the problem is as follows, for example. "An information processing method executed by an information processing apparatus, a process instruction acquisition step of acquiring process instruction information for instructing a process, a process step of executing a process corresponding to the process instruction information using a learned model based on the process instruction information, a storage step of storing the process result in the process step in a storage unit of the information processing apparatus, outputting the process result when the relevance between the process instruction information and the process result stored in the storage unit is equal to or greater than a predetermined standard when new process instruction information is acquired in the process instruction acquisition step, information processing method."

[0075] According to the above configuration, there is a storage step of storing the processing result in the storage unit of the information processing apparatus in the processing step, and when new processing instruction information (i.e., a prompt) is acquired in the processing instruction acquisition step, the processing result is output when the relevance between the processing instruction information and the processing result stored in the storage unit is equal to or greater than a predetermined standard. Therefore, when new processing instruction information related to the processing instruction information processed in the past is input, execution of processing using the learned model can be avoided. As a result, stabilization of the processing result and reduction of the processing cost caused by using the learned model can be achieved.

[0076] <Supplementary Note> This embodiment includes the following disclosures.

[0077] (Supplementary Note 1) An information processing method executed by an information processing apparatus, a processing instruction acquisition step of acquiring processing instruction information for instructing processing, a use information acquisition step of acquiring use information necessary for processing from an information source based on the processing instruction information, a processing step of executing processing corresponding to the processing instruction information using a learned model based on the use information, An information processing method including the above.

[0078] (Supplementary Note 2) In the use information acquisition step, the use information is acquired based on the output direction determined from the processing instruction information, The information processing method according to Supplementary Note 1.

[0079] (Supplementary Note 3) In the use information acquisition step, metadata of the use information is used when acquiring the use information, The information processing method according to Supplementary Note 1.

[0080] (Supplementary Note 4) In the use information acquisition step, log data related to the use information is used when acquiring the use information, The information processing method described in Supplementary Note 1.

[0081] (Supplementary Note 5) In the usage information acquisition step, the information of the information source is input into a learned model that has been learned to output index information of the information when the information is input, and the index information output from the learned model is used when acquiring the usage information. The information processing method described in Supplementary Note 1.

[0082] (Supplementary Note 6) It has a storage step of storing the processing result in the storage unit of the information processing apparatus, When new processing instruction information is acquired in the processing instruction acquisition step, the processing result is output when the relevance between the processing instruction information and the processing result stored in the storage unit is equal to or greater than a predetermined standard. The information processing method described in Supplementary Note 1.

[0083] (Supplementary Note 7) In an information processing apparatus, A processing instruction acquisition step of acquiring processing instruction information for instructing processing, A usage information acquisition step of acquiring usage information necessary for processing from an information source based on the processing instruction information, A processing step of executing processing using a learned model based on the usage information, A program for executing an information processing method including the above.

[0084] (Supplementary Note 8) An information processing system executed by an information processing apparatus, A processing instruction acquisition step of acquiring processing instruction information for instructing processing, A usage information acquisition step of acquiring usage information necessary for processing from an information source based on the processing instruction information, A processing step of executing processing using a learned model based on the usage information, An information processing system that performs the above.

[0085] The embodiments disclosed this time should be considered as illustrative in all respects and not restrictive. The scope of the present invention is shown not by the above description but by the claims, and it is intended that all modifications within the meaning and scope equivalent to the claims are included. Further, the present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

Explanation of Signs

[0086] 10 Information processing system 12 Server (information processing device) 22 Storage unit 50 Server (information processing device) 60 Storage unit 220 Program 222 Learned model 224 Prompt (processing instruction information) 226 Usage information 224 Policy information 500 Information processing system 600 Program

Claims

1. An information processing method executed by an information processing device, a processing instruction acquisition step of acquiring processing instruction information instructing a processing; a usage information acquisition step of acquiring usage information required for processing from an information source based on the processing instruction information; A processing step of executing a process corresponding to the processing instruction information by using a trained model based on the usage information; An information processing method comprising:

2. In the usage information acquisition step, the usage information is acquired based on an output direction determined from the processing instruction information. The information processing method according to claim 1 .

3. In the usage information acquisition step, metadata of the usage information is used when acquiring the usage information. The information processing method according to claim 1 .

4. In the usage information acquisition step, log data related to the usage information is used when acquiring the usage information. The information processing method according to claim 1 .

5. In the usage information acquisition step, information of the information source is input to a trained model that has been trained to output index information of the information when the information is input, and the index information output from the trained model is used when acquiring the usage information. The information processing method according to claim 1 .

6. a storage step of storing a processing result in the processing step in a storage unit of the information processing device; When new processing instruction information is acquired in the processing instruction acquisition step, if a correlation between the new processing instruction information and the processing result stored in the storage unit is equal to or greater than a predetermined criterion, the processing result is output. The information processing method according to claim 1 .

7. In the information processing device, a processing instruction acquisition step of acquiring processing instruction information instructing a processing; a usage information acquisition step of acquiring usage information required for processing from an information source based on the processing instruction information; A processing step of executing a process using a trained model based on the usage information; A program for executing an information processing method including the steps of:

8. An information processing system executed by an information processing device, a processing instruction acquisition step of acquiring processing instruction information instructing a processing; a usage information acquisition step of acquiring usage information required for processing from an information source based on the processing instruction information; A processing step of executing a process using a trained model based on the usage information; An information processing system that performs the above.

Images