Information processing method, program, and information processing system

Abstract

To provide an information processing method, a program, and an information processing system which facilitate obtaining a desired processing result.SOLUTION: The information processing method in an information processing system in which a user terminal and a server are connected to communicate with each other via a network includes: a configuration information candidate generation step for generating a candidate of configuration information constituting at least a part of processing instruction information corresponding to processing performed by the information processing system; an evaluation step for evaluating a processing result based on the processing instruction information including the candidate of the configuration information; an optimization step for performing optimization analysis of the candidate based on the evaluation; and an optimum configuration information generation step for performing at least one of selection and generation of the configuration information based on the result of the optimization analysis.SELECTED DRAWING: Figure 9

Description

[Technical field]

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

[0002] Cited Document 1 discloses an information processing method for providing a dialogue using a language model. This information processing method generates a query for a document using a language model in advance, and in response to a question input by a user, selects a document by referring to the query, and outputs an answer to the user's question. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-076413 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the case of the above-mentioned prior art, the answer may change depending on the question entered by the user. In other words, depending on how the question is asked, the user may not get the answer he or she wants, and there is room for improvement in this regard.

[0005] SUMMARY OF THE PRESENT EMBODIMENT In consideration of the above, an object of the present invention is to make it easier to obtain a desired processing result. [Means for solving the problem]

[0006] According to an information processing method of one embodiment, the information processing method is executed by an information processing device, and includes a configuration information candidate generation step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to processing performed by the information processing device, an evaluation step of evaluating a processing result based on the processing instruction information including the candidate configuration information, an optimization step of performing an optimization analysis of the candidates based on the evaluation, and an optimal configuration information generation step of selecting and / or generating the configuration information based on a result of the optimization analysis.

[0007] According to a program of one embodiment, an information processing device is caused to execute an information processing method including a configuration information candidate generation step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to processing performed by the information processing device, an evaluation step of evaluating processing results based on the processing instruction information including the candidates for configuration information, an optimization step of performing optimization analysis of the candidates based on the evaluation, and an optimal configuration information generation step of selecting and / or generating the configuration information based on the results of the optimization analysis.

[0008] According to one embodiment, an information processing system is executed by an information processing device, and includes a configuration information candidate generation step for generating candidates for configuration information that constitute at least a part of processing instruction information corresponding to processing performed by the information processing device, an evaluation step for evaluating processing results based on the processing instruction information including the candidate configuration information, an optimization step for performing optimization analysis of the candidates based on the evaluation, and an optimal configuration information generation step for selecting and / or generating the configuration information based on the results of the optimization analysis. Effect of the Invention

[0009] According to one embodiment, it is possible to easily obtain a desired processing result. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server according to an embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of a user terminal according to an embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional configuration of a server according to an embodiment. [Diagram 5] FIG. 2 is a diagram illustrating an example of a functional configuration of a user terminal according to an embodiment. [Figure 6] FIG. 1 is an explanatory diagram showing a part of an outline of an embodiment; [Figure 7] FIG. 1 is an explanatory diagram showing a part of an outline of an embodiment; [Figure 8] FIG. 1 is an explanatory diagram showing a part of an outline of an embodiment; [Figure 9] 5 is a flowchart illustrating an example of processing executed by the information processing system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] An embodiment of an information processing system according to the present invention will be described below with reference to Figures 1 to 7. In each drawing, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for the convenience of explanation and may differ from the actual ratios.

[0012] (System Overview) First, an overview of the information processing system 10 according to this embodiment will be described. The information processing system 10 according to this embodiment is a system in which, when a user U gives an instruction for a process to be performed by a server 14 as an information processing device, the system performs the process based on the instruction and outputs the processing result to the user U. Specifically, when the user U inputs a prompt as processing instruction information corresponding to the process to be performed by the server 14, the system generates a processing result corresponding to the prompt. In other words, the prompt is an instruction from the user U, and the processing result generated by the server 14 based on the prompt is presented to the user U.

[0013] The information processing system 10 presents a template of a prompt according to the content of the processing desired by the user U. As shown in FIG. 6, this template has a field for inputting a task representing the desired processing, and a field for inputting multiple conditions (A, B, and C as an example in this embodiment) for executing the task. Information regarding these conditions corresponds to the configuration information described in claim 1. When the user U selects a template and inputs the content of the processing desired for the task in natural language, the large-scale language model of the information processing system 10 generates multiple candidate information for each of the multiple conditions based on the task. As an example, the condition is related to the content of the output, such as "output in about 100 characters" or "in a formal style." The condition is not limited to this, and may be other conditions.

[0014] In the information processing system 10, the large-scale language model of the information processing system 10 generates a processing result based on a plurality of prompts including information on the generated conditions. Then, as shown in FIG. 7, the generated processing result is evaluated. In this embodiment, this evaluation is performed based on information input to a user interface (not shown) communicably connected to a user terminal 12 as an information processing device. That is, the generated processing result is compared with a processing result desired by a person such as a user U, and the evaluation result is input to the user terminal 12, whereby the evaluation is performed based on the input information. The evaluation result is linked to each prompt including information on the generated conditions. In this embodiment, the evaluation is performed based on information input to the user interface, but this is not limited to this. It is also possible to prepare predetermined evaluation criteria information in advance, compare the generated processing result with the evaluation criteria information, and automatically perform evaluation based on an index such as the degree of deviation. In addition, when evaluating, the desired processing result (in other words, teacher data) is used as the evaluation criterion, but this is not limited to this, and log information, which is information on the operation result of the user U, may be used as the evaluation criterion. In this case, by giving a high evaluation to the processing results that are close to the user U's log information, personalization that meets the user U's preferences becomes possible.

[0015] The information processing system 10 acquires the generated candidates for each condition and the evaluation results associated therewith, and performs Bayesian optimization, which is a sequential approximation optimization method in black-box optimization processing, as an optimization analysis, to estimate information about the optimal condition. Then, at least one of selection and generation is performed on the estimated optimal condition information, and the information is applied to a prompt template, and the large-scale language model of the information processing system 10 generates a processing result based on the prompt. Then, similarly to the above, the generated processing result is evaluated again, and Bayesian optimization is performed again on the evaluation result. By repeating this cycle a predetermined number of times, a prompt including information about the optimal condition is estimated (see FIG. 8). Note that in this embodiment, this cycle is repeated a predetermined number of times, but is not limited thereto, and may be repeated until a predetermined evaluation value in the evaluation reaches a predetermined threshold value or more, or until a predetermined convergence judgment condition is reached in the optimization analysis, or may be repeated based on other judgment conditions.

[0016] (System Configuration) Fig. 1 is a diagram showing an example of a configuration of an 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 user terminal 12 and a server 14, which 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 of these.

[0017] The user terminal 12 is an example of an information processing device that performs operations for inputting and displaying various information. The user terminal 12 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, a wearable device, or a combination of these.

[0018] The server 14 is an example of an information processing device that acquires information on an input sentence input from the user terminal 12, searches for alternative sentences from the web, various documents, databases, etc. based on the input sentence information, performs processing based on the alternative sentences, and outputs the results. The server 14 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, or a combination of these. The specific configuration and operation of the server 14 will be described later.

[0019] (Hardware configuration - Server) 2 is a block diagram showing a hardware configuration of the server 14. The server 14 includes a processor 20, a memory 22, a storage 24, and a communication I / F 26, which are communicatively connected to each other via a bus B.

[0020] The processor 20 controls each component of the server 14 and realizes the functions of the server 14 by expanding various programs stored in the storage 24 into the memory 22 and executing them. The programs executed by the processor 20 include, but are not limited to, an OS (Operating System) and various programs described below. The execution of these programs by the processor 20 realizes a part of the state visualization method according to this embodiment. The processor 20 is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), or a combination of these.

[0021] The memory 22 is, for example, a Read Only Memory (ROM), a Random Access Memory (RAM), or a combination thereof. The ROM is, for example, a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), or a combination thereof. The RAM is, for example, a Dynamic RAM (DRAM), a Static RAM (SRAM), a Magnetoresistive RAM (MRAM), or a combination thereof.

[0022] The storage 24 stores the OS, various programs described below, and various data. The storage 24 is, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a storage class memory (SCM), or a combination of these.

[0023] The communication I / F 26 is an interface for connecting the server 14 to external devices including the user terminal 12 and the image capturing device 16 via the network N and for controlling communication. The communication I / F 26 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.

[0024] (Hardware configuration - User terminal) 3 is a block diagram showing a hardware configuration of the user terminal 12. The user terminal 12 includes a processor 20, a memory 22, a storage 24, a communication I / F 26, an input / output I / F 28, an output device 30, and an input device 32, which are communicatively connected to each other via a bus B. The communication I / F 26 is an interface for connecting the user terminal 12 to an external device including the server 14 via a network N and controlling communication. The communication I / F 26 is, for example, an adapter conforming to Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), Ethernet (registered trademark), or optical communication (for example, Fibre Channel), but is not limited thereto.

[0025] The input / output I / F 28 is an interface for connecting the input device 32 and the output device 30 to the user terminal 12. The input device 32 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a camera, various sensors, an operation button, or a combination of these. The output device 30 as a user interface is, for example, a display, a projector, a printer, a speaker, a vibrator, or a combination of these. In this embodiment, as an example, the output device 30 and the input device 32 are an integrally configured touch panel display.

[0026] In this embodiment, the program may be written into memory 22 or storage 24 during the manufacturing stage of server 14, or may be provided to server 14 via network N, or may be provided to server 14 via a non-transitory computer-readable recording medium such as a disk medium not shown.

[0027] (Functional configuration - Server) Next, the functional configuration of the server 14 will be described. FIG. 4 is a diagram showing an example of the functional configuration of the server 14. When executing various programs, the server 14 realizes various functions using the above hardware resources. The server 14 has a storage unit 31, a processing unit 33, and a communication unit 34 as functional configurations realized by the server 14. Each functional configuration is realized by the processor 20 reading and executing a program 36 stored in the memory 22 or the storage 24. Note that the learning model 38 stored in the storage unit 31 is a large-scale language model, as an example. This large-scale language model 38 is configured to be stored in the storage unit 31, but is not limited to this, and may be stored in an external server or the like.

[0028] (Functional configuration - User terminal) Next, the functional configuration of the user terminal 12 will be described. Fig. 5 is a diagram showing an example of the functional configuration of the user terminal 12. When executing various programs, the user terminal 12 realizes various functions using the above-mentioned hardware resources. The user terminal 12 has a storage unit 60 in which a program 36 is stored, a processing unit 62, and a communication unit 64 as the functional configuration realized by the user terminal 12. Each functional configuration is realized by the processor 20 reading and executing the program 36 stored in the memory 22 or storage 24.

[0029] FIG. 6 is a schematic diagram showing an example of a flow of a part of the initial stage of processing performed in the information processing system 10. As shown in FIG. The process executed by the information processing system 10 is as shown in Fig. 6. In this embodiment, a template of the prompt is used, but the present invention is not limited to this, and a prompt that is directly input without using a template may be used. In this embodiment, the configuration information is information related to the conditions, but the present invention is not limited to this, and other information that constitutes at least a part of another prompt may be used.

[0030] FIG. 7 is a schematic diagram showing an example of a flow of a part of the intermediate stage of the processing performed in the information processing system 10. As shown in FIG. The process executed by the information processing system 10 is as shown in Fig. 7. Note that, in this embodiment, Bayesian optimization is used as the optimization analysis, but the present invention is not limited to this, and one or more black-box optimization methods from among a direct search method represented by evolutionary computing, a sequential approximation optimization method represented by Bayesian optimization, and reinforcement learning may be used, or a combination of these may be used.

[0031] FIG. 8 is a schematic diagram showing an example of a flow of a part of a later stage of processing performed in the information processing system 10. be. The process executed by the information processing system 10 is as shown in FIG.

[0032] FIG. 9 is a diagram relating to the processing executed by the information processing system 10. As shown in FIG. The process executed by the information processing system 10 is as shown in FIG.

[0033] Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope that can achieve the object of the present invention are included in the present invention.

[0034] Also, for example, the above-mentioned series of processes can be executed by hardware or software. In other words, the functional configuration is merely an example and is not particularly limited. That is, it is sufficient that the information processing system is provided with a function capable of executing the above-mentioned series of processes as a whole, and there is no particular limit to what kind of functional block is used to realize this function. In addition, the location of the functional block is not particularly limited and may be arbitrary. For example, the functional block of the server may be transferred to a user terminal or the like. Conversely, the functional block of the user terminal may be transferred to a server or the like. In addition, one functional block may be configured by hardware alone, software alone, or a combination thereof.

[0035] For example, when a series of processes is executed by software, a program constituting the software is installed in a computer or the like from a network or a recording medium. The computer may be a computer incorporated in dedicated hardware. The computer may also be a computer capable of executing various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.

[0036] Furthermore, for example, a recording medium containing such a program may not only be constituted by a removable medium (not shown) that is distributed separately from the device main body in order to provide the program to the user, but may also be constituted by a recording medium that is provided to the user in a state in which it is pre-installed in the device main body.

[0037] In this specification, the steps of describing a program to be recorded on a recording medium include not only processes that are performed chronologically according to the order, but also processes that are not necessarily performed chronologically but are executed in parallel or individually. In addition, in this specification, the term "system" refers to an overall device that is composed of a plurality of devices, a plurality of means, etc.

[0038] In other words, the program to which the present invention is applied is sufficient as long as it has the following configuration, and can take various forms. That is, the program to which the present invention is applied is installed in an information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of generating the configuration information based on a result of the optimization analysis; Execute a process including:

[0039] This makes it possible to obtain a prompt that will result in an optimal processing result, making it easier to obtain a desired processing result.

[0040] <Additional Notes> The present embodiment includes the following disclosure.

[0041] (Appendix 1) An information processing method executed by an information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of at least one of selecting and generating the configuration information based on a result of the optimization analysis; An information processing method comprising:

[0042] (Appendix 2) The processing instruction information is a template prepared in advance. 2. An information processing method as described in Appendix 1.

[0043] (Appendix 3) In the evaluation step, the evaluation of the processing result is performed based on a comparison between the processing result based on the processing instruction information including the candidates of the configuration information and a desired processing result. 2. An information processing method as described in Appendix 1.

[0044] (Appendix 4) In the evaluation step, the evaluation of the processing result is performed based on a comparison between the processing result based on the processing instruction information including the candidates of the configuration information and information related to a user's operation result. 2. An information processing method as described in Appendix 1.

[0045] (Appendix 5) In the evaluation step, the evaluation of the processing result is performed based on information inputted through a user interface communicably connected to the information processing device. 2. An information processing method as described in Appendix 1.

[0046] (Appendix 6) The optimization analysis uses one or more black-box optimization techniques including a direct search method, a sequential approximation optimization method, and a reinforcement learning method. 2. An information processing method as described in Appendix 1.

[0047] (Appendix 7) In the information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of generating the configuration information based on a result of the optimization analysis; A program for executing an information processing method including the steps of:

[0048] (Appendix 8) An information processing system executed by an information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of generating the configuration information based on a result of the optimization analysis; An information processing system that performs the above. [Explanation of symbols]

[0049] 10 Information Processing Systems 12 User terminal (information processing device) 14 Servers (information processing devices)

Claims

1. An information processing method executed by an information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of at least one of selecting and generating the configuration information based on a result of the optimization analysis; An information processing method comprising:

2. The processing instruction information is a template prepared in advance. The information processing method according to claim 1 .

3. In the evaluation step, the evaluation of the processing result is performed based on a comparison between the processing result based on the processing instruction information including the candidates of the configuration information and a desired processing result. The information processing method according to claim 1 .

4. In the evaluation step, the evaluation of the processing result is performed based on a comparison between the processing result based on the processing instruction information including the candidates of the configuration information and information related to a user's operation result. The information processing method according to claim 1 .

5. In the evaluation step, the evaluation of the processing result is performed based on information inputted through a user interface communicably connected to the information processing device. The information processing method according to claim 1 .

6. The optimization analysis uses one or more black-box optimization techniques among a direct search method, a sequential approximation optimization method, and a reinforcement learning method. The information processing method according to claim 1 .

7. In the information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of generating the configuration information based on a result of the optimization analysis; A program for executing an information processing method including the steps of:

8. An information processing system executed by an information processing device, a configuration information candidate generating step of generating candidates for configuration information constituting at least a part of processing instruction information corresponding to a process performed by the information processing device; an evaluation step of evaluating a processing result based on the processing instruction information including the candidates of the configuration information; an optimization step of performing an optimization analysis of the candidates based on the evaluation; an optimal configuration information generating step of generating the configuration information based on a result of the optimization analysis; An information processing system that performs the above.

Images