Information processing systems, information processing methods, and programs

Abstract

To enable the valuation of patents. [Solution] An information processing system comprising: a keyword extraction unit that extracts keywords from the claims of a patent to be verified; a search unit that searches for information about a business or product that matches the extracted keywords; an infringement determination unit that estimates the degree to which the searched information about the business or product satisfies the constituent elements of the claim; and a valuation unit that evaluates the value of the patent according to the degree.

Description

Technical Field

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

Background Art

[0002] The value of patents has been evaluated (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the market approach as described in Patent Document 1, it is difficult to collect similar cases.

[0005] The present invention has been made in view of such a background, and an object thereof is to provide a technology capable of evaluating the value of a patent.

Means for Solving the Problems

[0006] The main invention of the present invention for solving the above problems is an information processing system, comprising: a keyword extraction unit that extracts keywords from claims related to a patent to be verified; a search unit that searches for information on businesses or products that match the extracted keywords; an infringement determination unit that estimates the degree of possibility that the information on the searched business or product satisfies the constituent elements of the claims; and a value evaluation unit that evaluates the value of the patent according to the degree.

[0007] Regarding other problems disclosed in the present application and their solutions, they will be clarified by the embodiments of the invention and the drawings.

Effects of the Invention

[0008] According to the present invention, it is possible to evaluate the value of a patent. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the overall configuration of an information processing system. [Figure 2] This figure shows an example of the hardware configuration of management server 2. [Figure 3] This figure shows an example of the software configuration for management server 2. [Figure 4] This diagram illustrates the operation of management server 2. [Modes for carrying out the invention]

[0010] <System Overview> The following describes an information processing system according to one embodiment of the present invention.

[0011] Figure 1 shows an example of the overall configuration of an information processing system. The information processing system in this embodiment includes a management server 2. The management server 2 is connected to the user terminal 1 via a communication network. The communication network is, for example, the internet and is constructed using public telephone networks, mobile phone networks, wireless communication channels, Ethernet (registered trademark), etc.

[0012] User terminal 1 is a computer operated by the user. User terminal 1 can be, for example, a smartphone, a tablet computer, or a personal computer.

[0013] The management server 2 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0014] <Management Server> Figure 2 shows an example of the hardware configuration of the management server 2. Note that the illustrated configuration is just one example, and other configurations are also possible. The management server 2 includes a CPU 201, memory 202, storage device 203, communication interface 204, input device 205, and output device 206. The storage device 203 stores various data and programs, such as a hard disk drive, solid-state drive, or flash memory. The communication interface 204 is an interface for connecting to a communication network, such as an adapter for connecting to Ethernet®, a modem for connecting to a public telephone network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector or RS232C connector for serial communication. The input device 205 is for inputting data, such as a keyboard, mouse, touch panel, button, or microphone. The output device 206 is for outputting data, such as a display, printer, or speaker. Furthermore, each functional unit of the management server 2, as described later, is realized by the CPU 201 reading programs stored in the storage device 203 into memory 202 and executing them, and each storage unit of the management server 2 is realized as part of the storage area provided by memory 202 and storage device 203.

[0015] Figure 3 shows an example of the software configuration of the management server 2. The management server 2 includes a patent information acquisition unit 211, a keyword extraction unit 212, a search unit 213, an infringement determination unit 214, and a value evaluation unit 215.

[0016] The patent information acquisition unit 211 acquires information indicating the content of the target patent (hereinafter referred to as patent information). The patent information includes at least the content of the claims. The content of the claims may be, for example, text data, rich text data, HTML data, etc. The patent information may be, for example, an XML file or PDF file of the patent publication. The patent information acquisition unit 211 may accept input of patent information from the user, or it may accept input of information identifying the patent, such as the patent number, from the user, and download the patent publication of the patent identified by the accepted information from a patent information database, etc.

[0017] The keyword extraction unit 212 extracts keywords from the claims of the target patent. The keyword extraction unit 212 can generate keywords by, for example, providing a large-scale language model with a prompt that includes the text of the claims and instructions to extract keywords from the claims. The keyword extraction unit 212 can also divide the claims into morphemes by, for example, morphological analysis, and extract nouns, proper nouns, verbs, etc., from the morphemes as keywords. Note that the keywords may also be phrases (key phrases).

[0018] The search unit 213 searches for information about businesses or products that match the keywords extracted by the keyword extraction unit 212. The search unit 213 can perform a search by determining whether information about a business's business activities or information about a product matches the keywords. In this embodiment, the information about businesses or products is assumed to be web pages. For example, the search unit 213 can obtain search results for web pages related to businesses or products by sending a search request to a search engine that specifies the keywords extracted by the keyword extraction unit 212 as an AND condition or an OR condition.

[0019] In addition, the search unit 213 can index the pre-collected web pages and perform searches using the indexes. Specifically, it periodically collects web pages by a crawler program, divides the text included in the collected web pages by morphological analysis or the like, and creates indexes. Then, the search unit 213 can identify the web pages containing the keyword by comparing the keyword extracted by the keyword extraction unit 212 with the indexes. According to this method, since it is possible to perform a search using its own index without using a search engine, the freedom of search can be increased.

[0020] In addition, the search unit 213 can also acquire web pages in advance by a crawler or the like, vectorize all or part of the acquired web pages by embedding processing, and store the vectors in a vector storage unit in association with the web pages. In this case, the search unit 213 can identify the web page corresponding to the keyword according to the distance between the vector obtained by embedding the keyword extracted by the keyword extraction unit 212 and the vectors stored in the vector storage unit.

[0021] The search unit 213 can detect the business name and product name from the searched web pages. The search unit 213 may generate the business name and product name by giving a prompt including the content of the searched web page and an instruction to extract what is considered to be the business name and / or product name to a large language model.

[0022] The keyword extraction process by the keyword extraction unit 212 and the search process for businesses or products by the search unit 213 may be repeated multiple times until an end instruction is received from the user.

[0023] The infringement determination unit 214 determines whether the information relating to the searched business or product (for example, the content of a web page) satisfies the constituent elements described in the claim. The infringement determination unit 214 can determine whether the constituent elements are satisfied by providing a prompt to a large-scale language model that includes information relating to the business or product, the claim, and an instruction to determine whether the information satisfies the constituent elements.

[0024] Furthermore, the infringement determination unit 214 can pre-decompose the constituent elements of a claim into rules and determine whether the information relating to the business or product satisfies those rules. Specifically, it decomposes the constituent elements of a claim into keywords and phrases, and creates rules that express combinations of these keywords and phrases using AND and OR conditions. The infringement determination unit 215 then performs natural language processing on the information relating to the business or product to extract keywords and phrases, and determines whether the extracted keywords and phrases satisfy the rules. This method allows for infringement determination based on rules that regularly express the constituent elements of a claim, without using a large-scale language model.

[0025] The infringement determination unit 215 may also determine the degree to which the searched information relating to a business or product (for example, the content of a web page) is likely to satisfy the constituent elements described in the claim. In this case as well, the infringement determination unit 215 can use a large-scale language model to estimate the degree to which the constituent elements are satisfied by providing the large-scale language model with a prompt that includes information relating to a business or product, the claim, and an inquiry about the degree to which the information is likely to satisfy the constituent elements.

[0026] Furthermore, even when using the aforementioned rules, the infringement determination unit 215 can determine the degree to which the elements of the infringement are likely to be met based on the extent to which the information relating to the business or product satisfies the rules. For example, the higher the proportion of keywords and phrases constituting the rules that are included in the information relating to the business or product, the higher the likelihood that the elements of the infringement are met.

[0027] The valuation unit 215 evaluates the value of the patent according to the number of businesses or products determined to satisfy the constituent elements, or the aggregate value (e.g., total value, maximum value, etc.) of the degree of likelihood that the estimated businesses or products satisfy the constituent elements. The valuation unit 215 can, for example, determine the evaluation value such that the larger the number of businesses or products determined to satisfy the constituent elements, the higher the evaluation value. The valuation unit 215 can, for example, determine the evaluation value such that the larger the aggregate value of the degree of likelihood that the constituent elements are satisfied, the higher the evaluation value.

[0028] The valuation unit 215 may evaluate the value of a patent based on the sales of businesses or products that are determined to satisfy the constituent elements, or businesses or products whose likelihood of satisfying the constituent elements is above a predetermined value. In this case, the valuation unit 215 can search for the sales of businesses or products using a web search. The valuation unit 215 may also provide a large-scale language model with a prompt including the designation of a business or product and a query about the sales of said business or product, to estimate the sales of the business or product. The valuation unit 215 may also query the user for the sales of a business or product and accept input from the user for the amount of sales (or an estimated value thereof). The valuation unit 215 may use as an evaluation value an amount obtained by multiplying the aggregated sales (e.g., total) of businesses or products that are determined to satisfy the constituent elements by a predetermined license fee rate (e.g., a fixed value such as 3%, or a different rate depending on the business field to which the business or product belongs), or a rank corresponding to this amount. Furthermore, the valuation unit 215 can evaluate the aggregate sales (e.g., total) of businesses or products that have been determined to have a probability of satisfying the constituent elements of a patent to a predetermined value or higher, by multiplying the probability (e.g., expressed as a percentage) by the license fee rate (e.g., a fixed value such as 3%, or a different rate depending on the business field to which the business or product belongs), or by using a rank corresponding to this expected value as an evaluation value. In addition, if the sales are for one year, the valuation unit 215 can multiply by the number of years of the patent term. Furthermore, if the valuation unit 215 has obtained sales for multiple years in the past, and the sales are showing an increasing or decreasing trend, it can predict sales for the number of years of the patent term according to that trend and sum the prediction results.

[0029] <Operation> Figure 4 is a diagram illustrating the operation of the management server 2.

[0030] The management server 2 receives the designation of the target patent (S301), obtains the claims of the target patent (S302), extracts keywords included in the claims (S303), performs a web search using the extracted keywords (S304), and outputs the search results (S305). The management server 2 inquires whether the user is satisfied with the search results. If the user is not satisfied (S307: NO), the process from step S302 is repeated. If the user is satisfied (S306: YES), the management server 2 determines the degree of likelihood that each web page in the search results satisfies the claims (S307), obtains the sales of businesses or products related to the web page (S308), and evaluates the value of the patent by summing the expected values ​​obtained by multiplying the sales by the degree of likelihood (S309).

[0031] As described above, the information processing system of this embodiment can be used to evaluate the value of a patent.

[0032] Although these embodiments have been described above, they are intended to facilitate understanding of the present invention and are not intended to limit its interpretation. The present invention can be modified and improved without departing from its spirit, and equivalents thereof are also included.

[0033] For example, the processing performed by each functional unit of the management server 2 described above may be executed by any of the functional units. Furthermore, different functional units may be added to perform some of the processing performed by each of the functional units described above. Also, the functional units of the management server 2 may be distributed across multiple computers.

[0034] Furthermore, the information stored in each memory unit of the management server 2 may be stored in any of the memory units. That is, the information stored in the multiple memory units mentioned above may be stored in a single memory unit, or a portion of the information stored in one memory unit may be stored in another memory unit.

[0035] <Disclosure Items> Furthermore, this disclosure also includes the following configurations. [Item 1] A keyword extraction unit that extracts keywords from the claims of the patent to be verified, A search unit that searches for information about businesses or products that match the extracted keywords, An infringement determination unit that estimates the degree to which the searched information relating to the business operator or the product satisfies the constituent elements of the claim, A valuation unit that evaluates the value of the patent according to the aforementioned degree, An information processing system characterized by comprising the following features. [Item 2] The information processing system described in item 1, The infringement determination unit generates the degree by providing a large-scale language model with prompts that include information about the business or product, the claims, and a question about the likelihood that the business or product satisfies the claims. An information processing system characterized by the following. [Item 3] The information processing system described in item 1, The search unit provides the keywords to a search engine to search for information about the business or the product. An information processing system characterized by the following. [Item 4] The information processing system described in item 1, The process of extracting keywords by the keyword extraction unit and searching for businesses or products by the search unit is repeated multiple times until a termination instruction is received from the user. An information processing system characterized by the following. [Item 5] The information processing system described in item 1, The valuation unit acquires the sales of the business operator or the product, and evaluates the value of the patent according to the sales and the degree. An information processing system characterized by the following. [Item 6] The steps include: extracting keywords from the claims of the patent to be examined, The steps include: searching for information about businesses or products that match the extracted keywords; A step of estimating the degree to which the searched information relating to the business operator or the product satisfies the constituent elements of the claim, A step of evaluating the value of the patent according to the aforementioned degree, An information processing method characterized by a computer executing the following. [Item 7] The steps include: extracting keywords from the claims of the patent to be examined, The steps include: searching for information about businesses or products that match the extracted keywords; A step of estimating the degree to which the searched information relating to the business operator or the product satisfies the constituent elements of the claim, A step of evaluating the value of the patent according to the aforementioned degree, A program that causes a computer to execute something. [Explanation of Symbols]

[0036] 1 User terminal 2 Management Server

Claims

1. A keyword extraction unit that extracts keywords from the claims of the patent to be verified, A search unit that searches for information about businesses or products that match the extracted keywords, An infringement determination unit that estimates the degree to which the searched information relating to the business operator or the product satisfies the constituent elements of the claim, A valuation unit that evaluates the value of the patent according to the aforementioned degree, An information processing system characterized by comprising the following features.

2. The information processing system according to claim 1, The infringement determination unit generates the degree by providing a large-scale language model with prompts that include information about the business or product, the claims, and a question about the likelihood that the business or product satisfies the claims. An information processing system characterized by the following.

3. The information processing system according to claim 1, The search unit provides the keywords to a search engine to search for information about the business or the product. An information processing system characterized by the following.

4. The information processing system according to claim 1, The process of extracting keywords by the keyword extraction unit and searching for businesses or products by the search unit is repeated multiple times until a termination instruction is received from the user. An information processing system characterized by the following.

5. The information processing system according to claim 1, The valuation unit acquires the sales of the business operator or the product, and evaluates the value of the patent according to the sales and the degree. An information processing system characterized by the following.

6. The steps include: extracting keywords from the claims of the patent to be examined, The steps include: searching for information about businesses or products that match the extracted keywords; A step of estimating the degree to which the searched information relating to the business operator or the product satisfies the constituent elements of the claim, A step of evaluating the value of the patent according to the aforementioned degree, An information processing method characterized by a computer executing the following.

7. The steps include: extracting keywords from the claims of the patent to be examined, The steps include: searching for information about businesses or products that match the extracted keywords; A step of estimating the degree to which the searched information relating to the business operator or the product satisfies the constituent elements of the claim, A step of evaluating the value of the patent according to the aforementioned degree, A program that causes a computer to execute something.

Images