Information processing system and information processing method

Abstract

To assist inventors in maintaining or abandoning their patents, and to assist inventors in drafting grounds for maintaining or abandoning their patents that are satisfactory to them. [Solution] An information processing system having a function to perform processing using a language model, a function to generate a summary of patent information from patent information, a function to generate questions about patents, a function to generate a patent maintenance or abandonment decision result from the summary of patent information, questions, and replies to questions, and a function to generate reasons for maintaining or abandoning patents from the summary of patent information, the patent maintenance or abandonment decision result, similar patents that have been determined to be maintained or abandoned, and the reasons for maintaining or abandoning them.

Description

Technical Field

[0001] The present invention relates to a language model, particularly an information processing system and an information processing method using a generative AI model.

[0002] Note that one aspect of the present invention is not limited to the above technical field. Examples of the technical field of one aspect of the present invention disclosed in this specification and the like include a semiconductor device, a display device, a light-emitting device, a power storage device, a storage device, an electronic device, a lighting device, an input device, an input / output device, a driving method thereof, or a manufacturing method thereof. The semiconductor device refers to all devices that can function by utilizing semiconductor characteristics.

Background Art

[0003] In recent years, the development of language models using neural networks has been actively carried out, and particularly large language models (LLMs) have attracted attention. A large language model is a natural language processing model learned using a large amount of data. For example, a dialogue model that answers user instructions can be realized by a large language model. In Non-Patent Document 1, GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) is disclosed as a large language model, and ChatGPT is disclosed as a dialogue model.

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

[0005] After an invention is filed for patent, it undergoes examination and becomes a patent. To maintain the rights thereafter, maintenance fees must be paid. During this time, technological trends may change, and a patent may become unnecessary. Therefore, even after filing a patent application, it is necessary to consider the value of the invention and determine whether obtaining and maintaining a patent is necessary. However, determining whether obtaining or maintaining a patent is necessary requires considerable effort from both the inventor and the patent engineer. Furthermore, evaluating the value of an invention and deciding whether to maintain or abandon a patent are highly complex judgments, making mechanical evaluation or judgment difficult. Even if the inventor understands the value of their invention and possesses the information necessary to decide whether to maintain or abandon the patent, making that decision remains challenging.

[0006] In view of the above-mentioned problems, the present invention aims to support inventors in the process of maintaining or abandoning their patents, and to support inventors in creating grounds for maintaining or abandoning their patents that are satisfactory to them. Here, the process of maintaining or abandoning a patent refers to determining, after filing a patent application, whether it is necessary to maintain the patent rights in consideration of the value of the invention.

[0007] Furthermore, the description of these problems does not preclude the existence of other problems. Moreover, one aspect of the present invention does not need to solve all of these problems. Other problems will naturally become apparent from the description in the specification, drawings, and claims, and it is possible to extract other problems from the description in the specification, drawings, and claims. [Means for solving the problem]

[0008] In view of the above issues, one aspect of the present invention is an information processing system having a first information processing device and a second information processing device. The first information processing device has the function of receiving a first instruction, a second instruction, a third instruction, and a fourth instruction, processing using a language model, and outputting a first response, a second response, a third response, and a fourth response. The second information processing device has the function of receiving patent information of a patent to be determined to be maintained or abandoned, creating a first instruction from the patent information, transmitting the first instruction to the first information processing device and receiving a first response including a summary of the patent information, creating a second instruction from the summary of the patent information, transmitting the second instruction to the first information processing device and receiving a second response including a question about the patent, outputting a question about the patent, receiving a first reply including an answer to the question about the patent, and creating a third instruction from the question about the patent, the first reply, and the summary of the patent information. This information processing system has the following functions: a function to send an instruction to a first information processing device and receive a third response including the result of the patent maintenance or abandonment decision; a function to acquire similar patents that have been determined to be maintained or abandoned, and the reasons for their maintenance or abandonment decision; a function to create a fourth instruction from a summary of patent information, the result of the patent maintenance or abandonment decision, similar patents that have been determined to be maintained or abandoned, and the reasons for their maintenance or abandonment decision; a function to send the fourth instruction to the first information processing device and receive a fourth response including the reasons for the patent maintenance or abandonment decision; a function to output the reasons for the patent maintenance or abandonment decision; and a function to save the reasons for the patent maintenance or abandonment decision.

[0009] Preferably, in the above information processing system, the first information processing device has the function of receiving a fifth instruction, processing it using a language model, and outputting a fifth response, and the second information processing device has the function of receiving a second reply including whether or not modifications are necessary to the grounds for maintaining or abandoning the patent, creating a fifth instruction from the fourth instruction, the fourth response, and the second reply, and transmitting the fifth instruction to the first information processing device and receiving a fifth response including the modified grounds for maintaining or abandoning the patent.

[0010] Furthermore, one aspect of the present invention comprises steps 1 to 15, in the first step, obtaining patent information of a patent to be determined to be maintained or abandoned; in the second step, creating a first instruction from the patent information; in the third step, inputting the first instruction into a language model to obtain a first response including a summary of the patent information; in the fourth step, creating a second instruction from the summary of the patent information; in the fifth step, inputting the second instruction into a language model to obtain a second response including a question about the patent; in the sixth step, outputting a question about the patent; in the seventh step, obtaining a first reply including an answer to the question about the patent; in the eighth step, creating a third instruction from the question about the patent, the first reply, and the summary of the patent information; and in the ninth step... The information processing method involves inputting a third instruction into a language model to obtain a third response containing the patent maintenance or abandonment decision; in the tenth step, if the patent maintenance or abandonment decision is not possible, returning to the fourth step; if it is possible, proceeding to the eleventh step; in the eleventh step, obtaining similar patents that have been determined to be maintained or abandoned, and the reasons for their maintenance or abandonment decisions; in the twelfth step, creating a fourth instruction from the similar patents that have been determined to be maintained or abandoned, the reasons for their maintenance or abandonment decisions, and a summary of patent information; in the thirteenth step, inputting the fourth instruction into a language model to obtain a fourth response containing the reasons for patent maintenance or abandonment; in the fourteenth step, outputting the reasons for patent maintenance or abandonment; and in the fifteenth step, saving the reasons for patent maintenance or abandonment.

[0011] In the above information processing method, it is preferable that the 16th to 19th steps are included after the 14th step, in the 16th step a second response is obtained, including whether or not the grounds for maintaining or abandoning the patent need to be amended; in the 17th step, if no amendment is needed to the grounds for maintaining or abandoning the patent, the process proceeds to the 15th step; if amendment is needed, the process proceeds to the 18th step; in the 18th step a fifth instruction is created from the fourth instruction, the fourth response, and the second response; in the 19th step the fifth instruction is input into the language model to obtain the amended grounds for maintaining or abandoning the patent, and the process proceeds to the 14th step. [Effects of the Invention]

[0012] According to one aspect of the present invention, it is possible to support the process of maintaining or abandoning a patent in accordance with the inventor's intentions, and to create grounds for maintaining or abandoning a patent that are satisfactory to the inventor, without requiring the labor of a patent engineer. [Brief explanation of the drawing]

[0013] [Figure 1] Figure 1 is a schematic diagram illustrating an example of the configuration of an information processing system. [Figure 2] Figure 2 is a block diagram showing an example of the configuration of an information processing system. [Figure 3] Figure 3 is a flowchart showing an example of the processing in an information processing system. [Figure 4] Figure 4 is a flowchart showing an example of the processing in an information processing system. [Figure 5] Figure 5 is a flowchart showing an example of the processing in an information processing system. [Figure 6] Figure 6 is a flowchart showing an example of the processing in an information processing system. [Modes for carrying out the invention]

[0014] The embodiments will be described below with reference to the drawings. However, it will be readily apparent to those skilled in the art that the embodiments can be implemented in many different ways, and their form and details can be modified in various ways without departing from the spirit and scope thereof. Accordingly, the present invention shall not be construed as being limited to the contents of the following embodiments.

[0015] In the invention described below, the same reference numerals are used in common across different drawings for identical parts or parts having similar functions, and repeated explanations are omitted. Furthermore, reference numerals may be omitted when referring to similar functions.

[0016] In the figures described herein, the size of each component, the thickness of the layers, or the area may be exaggerated for clarity. Therefore, the scale is not necessarily limited to those figures.

[0017] Furthermore, ordinal numbers such as "first," "second," etc., in this specification are added to avoid confusion of constituent elements and do not imply any numerical limitation. They do not indicate any order or rank, such as process order or layering order. Even if an ordinal number is not used for a term in this specification, an ordinal number may be used in the claims to avoid confusion of constituent elements. Even if an ordinal number is used for a term in this specification, a different ordinal number may be used in the claims. Even if an ordinal number is used for a term in this specification, the ordinal number may be omitted in the claims.

[0018] In this specification, the language model is based on a transformer architecture and has been further trained to become an interactive (also called conversational) model. A representative example of a language model is the Large-Scale Language Model (LLM). LLMs specialize in text generation, processing based on given text data, while generative AI possesses not only text generation capabilities but also image generation capabilities, processing based on image data. In other words, the Large-Scale Language Model is a type of generative AI.

[0019] (Embodiment 1) In this embodiment, a configuration example of an information processing system, which is an aspect of the present invention, will be described with reference to FIG. 1.

[0020] An information processing system according to an aspect of the present invention outputs a question about a patent by using a language model from the patent information of the patent for which maintenance or abandonment is to be determined. Further, from the patent information, the question about the patent, and the reply to the question about the patent, the language model is used to determine whether to maintain or abandon the patent. Furthermore, it is possible to output the reason for maintaining or abandoning the patent by using the language model from the similar patents for which the maintenance or abandonment determination has been made.

[0021] Hereinafter, a more specific example will be described with reference to the drawings.

[0022] <Configuration example of information processing system> As shown in FIG. 1, the information processing system of this embodiment preferably has a first information processing device 10, a second information processing device 20, and an information terminal 30. The second information processing device 20 is connected to the first information processing device 10 via a network 40. Also, the second information processing device 20 is connected to the information terminal 30 via a network 50.

[0023] Also, in the information processing device of this embodiment, the device configuration in FIG. 1 is an example, and the second information processing device 20 may have the functions of the first information processing device 10, or the functions of the second information processing device 20 may be distributed and implemented in a plurality of information processing devices.

[0024] 《Configuration example of information terminal 30》 In the example configuration of the information processing system, the information terminal 30 is operated by the user and can also be called a client computer. Figure 1 shows a desktop computer and a smartphone as examples, but a notebook computer or a tablet computer may also be used as the information terminal 30. A tablet computer may be used by connecting a casing that has an input unit (typically a keyboard). In the present invention, it is preferable that the user has a detailed understanding of the patent that they wish to decide whether to maintain or abandon, and the user may be, for example, the inventor.

[0025] 《Example of the configuration of the first information processing device 10》 Next, we will describe an example configuration of the first information processing device 10.

[0026] The first information processing device 10 can perform processing using a language model. In particular, the first information processing device 10 can perform processing using a model that utilizes a large-scale language model (such as a text generation model or a dialogue model). For example, it can perform processing using large-scale language models such as GPT-4®, Llama2, and Llama3. In this specification, the term "language model" includes large-scale language models.

[0027] The first information processing device 10 has the function of receiving instruction sentences. Furthermore, the first information processing device 10 has the function of outputting response sentences to instruction sentences using a language model, and is capable of performing various natural language processing tasks such as translation and summarization.

[0028] A provider of services using an information processing system according to one aspect of the present invention does not necessarily need to own the first information processing device 10 itself. For example, a service provider can use a portion of the services provided by another business operator as the first information processing device 10.

[0029] 《Example of the configuration of the second information processing device 20》 Next, an example configuration of the second information processing device 20 will be explained using Figure 2.

[0030] As shown in Figure 2, the second information processing device 20 includes a receiving unit 110, an output unit 120, a storage unit 130, a processing unit 140, and a transmission line 150. In Figure 2, in addition to the second information processing device 20, the first information processing device 10 and the information terminal 30 are shown, and the arrows indicate the transmission and reception of data. The receiving unit and the output unit together are sometimes called the communication unit. The communication unit enables the second information processing device 20 to send and receive data with the outside world.

[0031] [Reception Desk 110] The reception unit 110 has the function of receiving data from an external source. The reception unit 110 may, for example, use a communication port, or it may use an input device such as a personal computer equipped with communication capabilities.

[0032] For example, the data that the reception unit 110 receives from the first information processing device 10 may include, for instance, a summary of patent information output by the language model in the first information processing device 10. The reception unit 110 can also receive patent information, a first reply, and a second reply from the information terminal 30.

[0033] The receiving unit 110 can supply the received data to one or more units selected from the storage unit 130 and the processing unit 140 via the transmission line 150.

[0034] [Output section 120] The output unit 120 has the function of outputting data processed by the processing unit 140 to an external source. For example, the output unit 120 can send an instruction to the first information processing device 10. The output unit 120 can also output questions about the patent, and reasons for maintaining or abandoning the patent, etc., to the information terminal 30. The output unit 120 may be, for example, a communication port, or a device such as a personal computer equipped with communication functions.

[0035] [Storage section 130] The memory unit 130 has a memory function. The memory unit 130 is a memory area and can store programs and / or data. Typical programs include programs executed by the processing unit 140. Data includes data received by the receiving unit 110 (e.g., patent information). It also includes data generated by the language model (e.g., summaries of patent information, questions about patents), and information on patents that have been determined to be maintained or abandoned, processed by the information processing system.

[0036] The storage unit 130 may have a database. The second information processing device 20 may also have a database separate from the storage unit 130. The second information processing device 20 may have a function to retrieve data from a database located outside the storage unit 130, outside the second information processing device 20, or outside the information processing system. The second information processing device 20 may also have a function to retrieve data from both its own database and an external database.

[0037] The storage unit 130 can use either a storage device or a file server, or both. Furthermore, a database recording the paths of files stored on the file server can be used in the storage unit 130.

[0038] The storage unit 130 has at least one of volatile memory and non-volatile memory. Examples of volatile memory include DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory). Examples of non-volatile memory include ReRAM (Resistive Random Access Memory), PRAM (Phase Change Random Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresistive Random Access Memory), and flash memory. The storage unit 130 may also have at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 130 may also have a recording media drive. Examples of recording media drives include hard disk drives (HDD) and solid state drives (SSD).

[0039] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)". NOSRAM is a type of memory where the memory cell is a 2-transistor (2T) or 3-transistor (3T) gain cell, and the transistors are transistors that use metal oxide in the channel formation region (also called OS transistors). OS transistors have an extremely small current flowing between the source and drain when off, i.e., a leakage current. By utilizing the characteristic of extremely low leakage current, NOSRAM can be used as a non-volatile memory by holding charge corresponding to the data within the memory cell. In particular, NOSRAM can read the stored data without destroying it (non-destructive read), making it suitable for computational processing that involves repeating data read operations a large amount. Because the data capacity of NOSRAM can be increased by stacking it, it can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0040] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM," and refers to RAM with a 1T (transistor) 1C (capacitance) type memory cell. DOSRAM is a type of DRAM formed using OS transistors, and it is a memory that temporarily stores information sent from an external source. DOSRAM is a memory that takes advantage of the low off-current of OS transistors.

[0041] In this specification, "metal oxide" refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also called oxide semiconductors or simply OS), etc. For example, when a metal oxide is used in the semiconductor layer of a transistor, that metal oxide may be referred to as an oxide semiconductor.

[0042] The metal oxide in the channel-forming region preferably contains indium (In). When the metal oxide in the channel-forming region contains indium, the carrier mobility (electron mobility) of the OS transistor increases. For example, indium oxide can be suitably used as the metal oxide in the channel-forming region. Furthermore, the metal oxide in the channel-forming region is preferably an oxide semiconductor containing element M. Element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, multiple elements mentioned above may be combined as element M. Element M is, for example, an element with a high bond energy with oxygen. For example, an element with a higher bond energy with oxygen than indium. Furthermore, the metal oxide containing the channel-forming region is preferably a metal oxide containing zinc (Zn). Metal oxides containing zinc may be more prone to crystallization. For example, indium gallium zinc oxide (also written as IGZO) or indium tin oxide (also written as ITZO®) can be used as the metal oxide containing the channel-forming region.

[0043] The metal oxides present in the channel-forming regions are not limited to indium-containing metal oxides. For example, the metal oxides present in the channel-forming regions may be zinc-tin oxides, gallium-tin oxides, or other metal oxides that do not contain indium but contain zinc, gallium, or tin.

[0044] [Processing Unit 140] The processing unit 140 has the function of performing calculations, analyses, and other processing using data supplied from either or both of the receiving unit 110 and the storage unit 130. The processing unit 140 can supply the processed data to either or both of the storage unit 130 and the output unit 120.

[0045] The processing unit 140 may, for example, have an arithmetic circuit. The processing unit 140 may, for example, have a central processing unit (CPU). In addition, the processing unit 140 may have a GPU (Graphics Processing Unit) in addition to or instead of the CPU. Furthermore, the processing unit 140 may have an NPU (neural processing unit / neural network processing unit).

[0046] The processing unit 140 may have registers and main memory in addition to the CPU. The registers and main memory may also be provided by the CPU. The main memory is capable of sending and receiving data with a secondary cache, etc. The main memory includes at least one of volatile memory such as RAM (Random Access Memory) and non-volatile memory such as ROM (Read Only Memory). Furthermore, the main memory may include at least one of NOSRAM and DOSRAM. The main memory may include either or both OS transistors and transistors containing silicon in their channel formation region (also called Si transistors). Note that the configuration of registers and main memory can be understood by substituting CPU with GPU in this paragraph.

[0047] Examples of RAM include DRAM and SRAM. By allocating a virtual memory space to DRAM or SRAM, the processing unit 140 can use that memory space as a workspace. The operating system, application programs, program modules, program data, and lookup tables stored in the storage unit 130 are loaded into RAM immediately before execution. The processing unit 140 can access and manipulate the operating system, application programs, program modules, program data, and lookup tables via RAM.

[0048] ROM can store systems that do not require rewriting. Examples of systems that do not require rewriting include BIOS (Basic Input / Output System) and firmware. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROM include UV-EPROM (Ultra-Violet Erasable Programmable Read Only Memory), which allows data to be erased by ultraviolet irradiation, EEPROM (Electrically Erasable Programmable Read Only Memory), and flash memory.

[0049] The processing unit 140 may have a microprocessor such as a DSP (Digital Signal Processor) in addition to the CPU or GPU. Since the DSP is specialized for digital signal processing, it is preferable to include it to control peripheral circuits of the CPU or GPU. The microprocessor may be implemented using a PLD (Programmable Logic Device) operating in hardware such as an FPGA (Field Programmable Gate Array) or FPAA (Field Programmable Analog Array).

[0050] The processing unit 140 enables the second information processing device 20 to generate instruction statements from text data. Specifically, it has the function of generating a first instruction statement from patent information, a function of generating a second instruction statement from a summary of patent information, a function of generating a third instruction statement from replies to questions about patents and a summary of patent information, and a function of generating a fourth instruction statement from a summary of patent information, the result of a patent maintenance or abandonment decision, similar patents that have been determined to be maintained or abandoned, and the reasons for those maintenance or abandonment decisions.

[0051] Furthermore, the processing unit 140 provides the second information processing device 20 with the function of searching for similar patents that have been determined to be maintained or abandoned.

[0052] Furthermore, the processing unit 140 may have a function that allows the second information processing device 20 to input the fourth instruction sentence into the language model of the first information processing device, and to create a fifth instruction sentence from the output fourth response sentence and the user's reply to the reasons for maintaining or abandoning the patent.

[0053] [Transmission path 150] The transmission line 150 has the function of transmitting data. Data can be transmitted and received between the receiving unit 110, the output unit 120, the storage unit 130, and the processing unit 140 via the transmission line 150. As the transmission line 150, for example, an external bus, a LAN (Local Area Network), or the Internet, which is the basis of the World Wide Web (WWW), may be used.

[0054] <Example of processing in an information processing system> Figures 3, 4, and 5 are examples of flowcharts illustrating each step of an information processing system according to one aspect of the present invention.

[0055] <Step S101> In step S101, the second information processing device 20 obtains patent information from the user.

[0056] Patent information includes textual information such as the specification, claims, filing date, examination history, and legal status of the patent right of the patent to be determined to be maintained or abandoned. Alternatively, the processing unit 140 may automatically acquire patent information from the storage unit 130 by receiving an identification number such as the application number from the user.

[0057] The user input corresponding to step S101 is performed at the information terminal 30. The patent information is transmitted to the second information processing device 20 via the reception unit 110 and stored in the storage unit 130.

[0058] <Step S102> In step S102, the second information processing device 20 generates a first instruction statement from the patent information in the processing unit 140.

[0059] An instruction is an input sentence that causes a language model to perform a desired action, and the language model generates a response sentence based on the instruction. The first instruction is a string intended to cause the language model to generate a summary of patent information. The first instruction is, for example, a sentence such as "Please summarize the following patent information" and a string containing the patent information.

[0060] <Step S103> In step S103, the second information processing device 20 transmits the first instruction to the first information processing device 10 via the output unit 120. The first information processing device 10 inputs the first instruction to its language model and generates a first response containing a summary of patent information. The second information processing device 20 receives the first response via the receiving unit 110.

[0061] <Step S104> In step S104, the second information processing device 20 generates a second instruction statement from the summary of patent information in the processing unit 140.

[0062] The second instruction is a string of characters intended to cause the language model to generate questions that determine whether the user wants to maintain or abandon the patent. For example, it could be a string of characters including the sentence, "The inventor is currently struggling to decide whether to maintain or abandon the patent they have obtained. Please come up with questions that will help us understand how the inventor feels about the invention," along with a summary of the patent information.

[0063] <Step S105> In step S105, the second information processing device 20 transmits the second instruction to the first information processing device 10 via the output unit 120. The first information processing device 10 inputs the second instruction into its language model and generates a second response containing a question about the patent. The second information processing device 20 receives the second response via the receiving unit 110.

[0064] The questions regarding the patent are intended to supplement any missing information in the patent information received in step S101, such as the history of the invention.

[0065] <Step S106> In step S106, the second information processing device 20 transmits a question about the patent to the information terminal 30 via the output unit 120.

[0066] <Step S107> In step S107, the second information processing device 20 receives a first response from the information terminal 30 via the reception unit 110, which includes the user's response to a question about the patent.

[0067] <Step S108> In step S108, the second information processing device 20 generates a third instruction statement from the questions regarding the patent, the first reply, and the summary of patent information in the processing unit 140.

[0068] The third instruction is a string of characters intended to cause the language model to output a decision on whether to maintain or abandon the patent. For example, it could be a string of characters including the sentence "Based on the following patent information and the user's response, determine whether the user wants to maintain or abandon the patent," along with a question about the patent, the first response, and a summary of the patent information.

[0069] <Step S109> In step S109, the second information processing device 20 transmits the third instruction to the first information processing device 10 via the output unit 120. The first information processing device 10 inputs the third instruction to its language model and generates a third response statement including the patent maintenance or abandonment decision result. The second information processing device receives the third response statement via the reception unit 110.

[0070] The determination of whether the patent should be maintained or abandoned is, for example, one of the following strings: abandoned, maintained, or undetermined.

[0071] <Step S110> In step S110, if the determination of whether to maintain or abandon the patent obtained in step S109 is impossible, the process returns to step S104; otherwise, the process proceeds to step S111.

[0072] By repeating steps S104 through S109 and repeatedly asking the user questions about the patent, it becomes possible to extract useful information about the patent.

[0073] When repeating steps S104 to S109, it is preferable that in step S108, the third instruction statement includes a plurality of questions and answers regarding the patent obtained by repeating steps S104 to S107.

[0074] <Step S111> In step S111, the second information processing device 20, in its processing unit 140, performs a similar patent search from the storage unit 130 and obtains similar patents that have been determined to be maintained or abandoned, as well as the reasons for those maintenance or abandonment decisions.

[0075] For similar patent searches, the search criteria should include patent classifications, patent families, and remaining patent terms. Furthermore, it is preferable to increase the search count in accordance with the number of tokens that can be input into the language model.

[0076] <Step S112> In step S112, the second information processing device 20 creates a fourth instruction statement from the similar patents that the processing unit 140 has determined to maintain or abandon, and the reasons for those determinations.

[0077] The fourth instruction is a string intended to cause the language model to output reasons for maintaining or abandoning a patent. For example, it may include a sentence such as "The following are samples of similar patents that have been determined to be maintained or abandoned, and the reasons for maintaining or abandoning them. Please use these samples as a reference to create reasons for maintaining or abandoning the target patent," along with a summary of the patent information, the patent maintenance or abandonment determination result, similar patents that have been determined to be maintained or abandoned, and the reasons for maintaining or abandoning them.

[0078] Furthermore, it is preferable that the fourth instruction includes the second instruction, the second response, and the first reply. By including the second instruction, the second response, and the first reply in the fourth instruction, the language model can generate more convincing reasons for retaining or abandoning the patent for the user.

[0079] <Step S113> In step S113, the second information processing device 20 transmits the fourth instruction to the first information processing device 10 via the output unit 120. The first information processing device 10 inputs the fourth instruction to its language model and generates a fourth response statement including the reasons for maintaining or abandoning the patent. The second information processing device receives the fourth response statement via the receiving unit 110.

[0080] <Step S114> In step S114, the second information processing device 20 transmits the reasons for maintaining or abandoning the patent to the information terminal 30 via the output unit 120.

[0081] <Step S115> In step S115, the second information processing device 20 stores the patents that have been determined to be maintained or abandoned, and the reasons for maintaining or abandoning the patents, in the storage unit 130.

[0082] By using such an information processing system, it is possible to extract useful information about patents from users and then present them with a decision on whether to maintain or abandon the patent, along with the reasons for that decision, in accordance with their wishes.

[0083] <Abnormalities in the processing of information processing systems> Figure 6 shows a modified example of the processing flow of an information processing system. In Figure 6, steps S116 to S119 are added after step S114.

[0084] <Step S116> In step S116, the second information processing device 20 receives a second reply from the information terminal 30 via the receiving unit 110, which includes whether or not modifications are necessary to the grounds for maintaining or abandoning the patent.

[0085] In step S116, the second response is the user's judgment regarding the grounds for maintaining or abandoning the patent, output by the information processing system, and a string indicating the reason.

[0086] In step S116, the user's decision indicates whether or not the user is satisfied with the reasons for maintaining or abandoning the patent output by the information processing system.

[0087] <Step S117> In step S117, if the user's judgment obtained in step S116 is satisfactory, the process proceeds to step S115; otherwise, the process proceeds to step S118.

[0088] <Step S118> In step S118, the second information processing device 20 creates a fifth instruction from the fourth instruction, the fourth response, and the second reply in the processing unit 140.

[0089] The fifth instruction is a string intended to cause the language model to output reasons for retaining or abandoning the patent, which are different from those output in step S113. For example, it is a string containing the following sentences: "The following are instructions and responses for outputting reasons for retaining or abandoning the patent, regarding which the user has the following complaints. Please output new reasons for retaining or abandoning the patent," along with the fourth instruction, the fourth response, and the second reply.

[0090] <Step S119> In step S119, the second information processing device 20 transmits the fifth instruction to the first information processing device 10 via the output unit 120. The first information processing device 10 inputs the fifth instruction into its language model and generates a fifth response containing the modified reasons for retaining or abandoning the patent. The second information processing device receives the fifth response via the receiving unit 110.

[0091] After completing step S119, the process proceeds to step S114. Subsequently, steps S116 through S119 are repeated until the user is satisfied with the reasons for maintaining or abandoning the patent output by the information processing system in step S117. This allows the user to examine the reasons for maintaining or abandoning the patent until they are satisfied. [Explanation of Symbols]

[0092] 10 Information Processing Devices 20 Information Processing Devices 30 Information terminals 40 Networks 50 Networks 110 Reception Department 120 Output section 130 Storage section 140 Processing Unit 150 transmission lines

Claims

1. It comprises a first information processing device and a second information processing device, The first information processing device has the function of receiving a first instruction, a second instruction, a third instruction, and a fourth instruction, processing them using a language model, and outputting a first response, a second response, a third response, and a fourth response. The aforementioned second information processing device is A function to receive patent information for patents to be determined to maintain or abandon, A function to generate the first instruction statement from the aforementioned patent information, A function to transmit the first instruction statement to the first information processing device and to receive the first response statement including a summary of patent information, A function to generate the second instruction statement from the summary of the aforementioned patent information, A function to transmit the second instruction to the first information processing device and to receive the second response containing a question about the patent, A function to output questions regarding the aforementioned patent, A function to receive a first reply, including a response to a question regarding the aforementioned patent, A function to generate the third instruction statement from the questions regarding the aforementioned patent, the first reply, and the summary of the aforementioned patent information, A function to transmit the third instruction to the first information processing device and to receive the third response including the result of the patent maintenance or abandonment determination, A function to obtain similar patents that have been determined to be maintained or abandoned, and the reasons for those determinations. A function to generate the fourth instruction statement from the summary of the aforementioned patent information, the result of the determination to maintain or abandon the aforementioned patent, the similar patents that have been determined to maintain or abandon, and the reasons for the determination to maintain or abandon them, A function of transmitting the fourth instruction statement to the first information processing device and receiving the fourth response statement including the grounds for maintaining or abandoning the patent, A function to output the reasons for maintaining or abandoning the aforementioned patent, An information processing system having a function for saving the reasons for maintaining or abandoning the aforementioned patent.

2. In claim 1, The first information processing device has the function of receiving a fifth instruction sentence, performing processing using the language model, and outputting a fifth response sentence. The second information processing device has a function to receive a second reply including whether or not modifications are necessary to the grounds for maintaining or abandoning the patent, A function to create the fifth instruction sentence from the fourth instruction sentence, the fourth response sentence, and the second reply sentence, An information processing system having a function of transmitting the fifth instruction statement to the first information processing device and receiving the fifth response statement including the modified reasons for retaining or abandoning the patent.

3. The process comprises steps 1 through 15, In the first step described above, patent information of the patent to be determined to be maintained or abandoned is obtained, In the second step described above, a first instruction statement is created from the patent information, In the third step, the first instruction is input to the language model to obtain a first response including a summary of patent information. In the fourth step described above, a second instruction statement is created from the summary of the patent information, In the fifth step, the second instruction is input to the language model to obtain a second response including a question about the patent. In the sixth step, the questions regarding the patent are output, In the seventh step, a first reply is obtained, which includes answers to questions regarding the patent. In the eighth step, a third instruction is prepared from the questions regarding the patent, the first reply, and the summary of the patent information. In the ninth step, the third instruction is input to the language model to obtain a third response including a determination result of whether to maintain or abandon the patent. In step 10, if it is not possible to determine whether to maintain or abandon the patent, the process returns to step 4; if it is possible to determine, the process proceeds to step 11. In the 11th step, obtain similar patents that have been determined to be maintained or abandoned, and the reasons for those determinations. In the 12th step, a fourth instruction statement is prepared from the similar patents that have been determined to be maintained or abandoned, the reasons for their maintenance or abandonment, and the summary of the patent information. In the 13th step, the fourth instruction sentence is input to the language model to obtain a fourth response sentence including the reason for maintaining or abandoning, In the 14th step, the reason for maintenance or abandonment is output, An information processing method for storing the reasons for maintenance or abandonment in the 15th step.

4. In claim 3, The process is followed by steps 16 through 19, In the sixteenth step, obtain a second response including whether or not the grounds for retention or abandonment need to be modified. In step 17, if there is no need to modify the reason for maintenance or abandonment, proceed to step 15; if there is a need for modification, proceed to step 18. In step 18 above, a fifth instruction is created from the fourth instruction, the fourth response, and the second reply. An information processing method that, in step 19, inputs the fifth instruction statement into the language model, obtains the modified reasons for retaining or abandoning the patent, and proceeds to step 14.

Images