Information processing systems, information processing methods, and programs

Abstract

To motivate people to provide information. [Solution] An information processing system comprising: a known information storage unit that stores known information and the registration time of the known information in association with each other; a provider storage unit that stores information that identifies the provider of the known information; a search unit that searches for known information relating to input data; an identification unit that identifies the provider and registration time relating to the retrieved known information by referring to the provider storage unit and the known information storage unit; and an incentive granting unit that grants an incentive to the identified provider according to the age of the registration time.

Description

Technical Field

[0004] ,

[0006] , , ,

[0005] , , , ,

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

Background Art

[0002] Techniques for enabling a machine to automatically respond to questions and requests from users have been developed and provided as automatic response services such as bots (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] Retrieval-Augmented Generation (RAG), which combines text generation processing by a large language model (LLM) with retrieval of external information to generate answers, has begun to be used, but it is necessary to enrich the information used in RAG.

[0005] The present invention has been made in view of such a background, and an object thereof is to provide a technique capable of motivating the provision of information.

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 known information storage unit that stores known information and the registration time of the known information in association with each other; a provider storage unit that stores information that identifies the provider of the known information; a search unit that searches for the known information relating to input data; an identification unit that identifies the provider and the registration time relating to the retrieved known information by referring to the provider storage unit and the known information storage unit; and an incentive granting unit that grants an incentive to the identified provider according to the age of the registration time.

[0007] Further issues and solutions disclosed in this application will be made clear in the section on embodiments of the invention and in the drawings. [Effects of the Invention]

[0008] According to the present invention, it is possible to motivate the provision of information. [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 known information storage unit 231, a provider storage unit 232, an information receiving unit 211, an NFT issuing unit 212, an input data receiving unit 213, a search unit 213, a specification unit 214, an incentive granting unit 215, and a generation unit 216.

[0016] <Storage section> The known information storage unit 231 stores various types of knowledge as known information. Known information may be, for example, PDF files, word processor files, or text files. Image data and audio data can also be used as known information. Known information may also be structured data, such as tabular data, XML data, or JSON data. Specific examples of text data include user-entered questions, text extracted from web pages, and excerpts from books and papers. Specific examples of image data include user-taken photographs, images extracted from web pages, and figures and tables included in books and papers. Specific examples of audio data include user-recorded audio, audio extracted from videos, and podcasts.

[0017] In this embodiment, the known information storage unit 231 stores known information in association with a timestamp at the time of registration of that known information. The timestamp at the time of registration may be, for example, a date and time. The timestamp at the time of registration can be a UNIX® time value or text data in ISO date format.

[0018] Furthermore, in this embodiment, the known information storage unit 231 includes a vector store that stores vector information in which all or part of the location information has been embedded, and a file system that stores the content of the known information. The known information storage unit 231 can store information that identifies the known information and vector information in which all or part of the stored data has been embedded, in association with each other. The information that identifies the known information can be a path or URL that identifies the file of the known information stored in the file system.

[0019] The provider storage unit 232 stores information for identifying the provider of the known information. The information for identifying the provider is, for example, the user ID of the user terminal 1, the identification information of the user terminal 1, or the like. In the present embodiment, the information for identifying the provider is the user ID. The user ID is, for example, a character string used when the user of the user terminal 1 logs in to this system. Alternatively, the user ID may be the email address of the user of the user terminal 1. Further, the information for identifying the provider may be the identification information of the user terminal 1. For example, the MAC address, IMEI (International Mobile Equipment Identifier), IP address, or the like of the user terminal 1 may be used. The provider storage unit 232 stores information for identifying the known information with the user ID as a key. The information for identifying the known information is, for example, a file path, a key of a database, a URL, or the like.

[0020] <Functional unit> The information reception unit 211 receives information to be registered as known information (hereinafter referred to as candidate information). The candidate information can be received, for example, from the user terminal 1. The candidate information can be arbitrary data similar to the above-described known information. For example, the candidate information can be received as a file from the user terminal 1.

[0021] If the known information identical to the received candidate information is not registered in the known information storage unit 231, the information reception unit 211 can register the candidate information as known information in association with the time stamp at the reception timing (or the current time). The information reception unit 211 can also register the vector information obtained by performing the embedding process on the candidate information in the vector store.

[0022] The NFT issuing unit 212 issues non-fungible tokens (NFTs) on a blockchain network (not shown). The NFT issuing unit 212 issues NFTs for candidate information registered as known information by the information receiving unit 211. The NFT is linked to the known information and the registration date of that known information. For example, the NFT issuing unit 212 can set information that identifies the known information and the registration date as metadata for the NFT.

[0023] The NFT issuing unit 212 can issue an NFT by generating metadata that includes known information and corresponding registration time information, and by attaching a predetermined electronic signature to the metadata. The electronic signature can be generated by the NFT issuing unit 212 using a private key, for example. The metadata of the NFT may include information that uniquely identifies the known information (e.g., a hash value), the registration time of the known information, and information about the provider.

[0024] The NFT issuing unit 212 can record information about the issued NFTs on a blockchain network. The blockchain network can be an existing blockchain network such as Ethereum, or a blockchain network specifically for this system may be constructed. During the NFT issuance process, the NFT issuing unit 212 can receive information (addresses) indicating the NFT owner and assign the NFT to those addresses. This makes it possible to identify the NFT owner.

[0025] The NFT issuing unit 212 can also manage the transfer of ownership of issued NFTs. Ownership transfers can be carried out, for example, by receiving the recipient's address from the current owner. The NFT issuing unit 212 can record NFT transfer records on the blockchain network.

[0026] The search unit 211 searches for known information related to the input data. The input data is, for example, a question sent from the user terminal 1. The search unit 211 can retrieve known information similar to the input data from the known information storage unit 231. Specifically, the search unit 211 calculates the similarity between the input data and each piece of known information, and can output known information with a similarity above a threshold as a search result. The similarity is calculated using, for example, the edit distance, cosine similarity, or Jacquard similarity between the input data and the known information. The edit distance is an index that represents the number of editing operations required to convert one string to the other string, the cosine similarity is an index that represents the cosine of the angle between two vectors, and the Jacquard similarity is an index that represents the value obtained by dividing the number of elements in the intersection of two sets by the number of elements in the union.

[0027] Furthermore, the search unit 211 may calculate the similarity between the input data and each known piece of information using a machine learning model. The machine learning model may be, for example, a neural network model using deep learning, which can learn how to calculate similarity from a large amount of input data and known information pairs. Examples of neural network models that can be used include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and Transformer.

[0028] In this embodiment, the search unit 211 creates vector information by embedding all or part of the input data, and searches for known information similar to the input data according to the distance between the created vector information and the vector information stored in the known information storage unit 231. Vector information is, for example, a representation of words or sentences as points in a multidimensional space, and can be generated using distributed representation learning algorithms such as word2vec or doc2vec. The search unit 211 vectorizes the input data and each piece of known information, and can determine that the closer the distance in the vector space (for example, Euclidean distance or cosine distance), the higher the similarity.

[0029] The search unit 213 searches for known information similar to the input data, and if multiple known pieces of information are found, it can determine a priority based on the age of the corresponding registration date. The search unit 213 can obtain a predetermined number of search results in order of priority. The search unit 213 may also determine the priority based on a weighted similarity score that takes into account the age of the registration date (for example, the length of time from the current time to the registration date).

[0030] The predetermined number acquired by the search unit 213 can be, for example, a pre-set fixed value. The search unit 213 may determine the predetermined number according to the number of known information retrieved. For example, the search unit 213 may determine the predetermined number as a predetermined percentage (e.g., the top 30%) of the number of known information retrieved. Alternatively, the search unit 213 may determine the predetermined number based on the priority of the retrieved known information. For example, the search unit 213 may determine the predetermined number as the number of known information whose priority is above a predetermined threshold.

[0031] Furthermore, the search unit 213 may determine a predetermined number depending on the category and type of input data. For example, the search unit 213 may determine a first predetermined number (e.g., "5") if the input data is text data, and a second predetermined number (e.g., "3") which is less than the first predetermined number if the input data is image data or audio data.

[0032] Furthermore, the search unit 213 may be configured to accept a predetermined number of inputs from the user terminal 1. For example, the search unit 213 can accept numerical inputs such as "3" or "10" as the predetermined number from the user terminal 1 and determine the input numerical value as the predetermined number.

[0033] The identification unit 214 identifies the provider and registration date of the retrieved known information. The identification unit 214 can identify the provider and registration date of the retrieved known information by referring to the provider storage unit 232 and the known information storage unit 231. Specifically, for each retrieved known piece of information, the identification unit 214 can identify the provider corresponding to the known information from the provider storage unit 232 and obtain the registration date corresponding to the known information from the known information storage unit 231.

[0034] The identification unit 214 can search the blockchain network for and identify an NFT corresponding to the retrieved known information. The identification unit 214 can identify an NFT corresponding to the known information retrieved by the search unit 213 by referring to the blockchain network. Specifically, the identification unit 214 can determine whether or not an NFT containing metadata (e.g., hash value) of the retrieved known information has already been issued, based on the information recorded on the blockchain network. If the NFT has already been issued, it can obtain the latest owner information recorded on the blockchain network.

[0035] The generation unit 216 generates an answer based on the retrieved known information. The generation unit 216 can generate an answer by providing a large-scale language model with a prompt that includes the retrieved known information, input data, and instructions to respond to the input data based on the known information. The generation unit 216 can provide the generated answer to the user terminal 1.

[0036] Examples of "large-scale language models" include GPT-3 (Generative Pre-trained Transformer 3), PaLM (Pathways Language Model), OPT (Open Pre-trained Transformer), Chinese-LLaMa, and Bloom. These large-scale language models have acquired advanced language understanding and language generation capabilities through pre-training using large amounts of text data. Generally, they consist of deep neural networks with hundreds of millions to hundreds of billions of parameters. Large-scale language models can predict the continuation of input text, and generate answers, summaries, and translations for input text. They also possess the ability to perform new tasks with only a small number of examples, demonstrating small-shot learning capabilities.

[0037] The incentive granting unit 215 grants incentives to the retrieved known information (i.e., known information used for generation by the generation unit 216) according to the registration date. The incentive granting unit 215 can grant a larger amount of incentive the older the registration date. The incentive granting unit 215 can grant incentives of higher rarity the older the registration date.

[0038] Furthermore, the incentive granting unit 215 can count the number of times known information has been used to generate an answer and determine the amount of the incentive based on the count result. Specifically, the incentive granting unit 215 identifies the known information used when the generation unit 216 generated the answer, and counts the number of times the identified known information has been used in the generation of past answers. The count of the number of times known information has been used can be done, for example, for each ID or identifier of the known information. The incentive granting unit 215 can store the information that identifies the known information and the number of times it has been used in association with each other in a storage unit (not shown), and can identify the known information and increase the number of times it has been used each time an answer is generated. The incentive granting unit 215 can grant an amount of incentive proportional to the number of times it has been used. Alternatively, the incentive granting unit 215 can also change the rarity of the incentive according to the number of times it has been used. For example, if it has been used many times, a high-rarity incentive can be granted, and if it has been used few times, a low-rarity incentive can be granted.

[0039] The incentive granting unit 215 grants an incentive to the owner of the NFT corresponding to the known information. The incentive granting unit 215 may also grant an incentive to the provider of the known information, either in lieu of or in addition to the NFT. The incentive granting unit 215 can grant an incentive to the owner of the NFT identified by the identification unit 214.

[0040] Incentives could include methods such as awarding a predetermined cryptocurrency or token, or awarding a predetermined number of points. The incentive awarding unit 215 can also record the awarding of incentives on the blockchain network. This makes it possible to track the history of incentive awards.

[0041] <Operation> Figure 4 is a diagram illustrating the operation of the management server 2.

[0042] When the management server 2 receives known information (S301), it registers the known information with a timestamp associated with it (S302), and issues an NFT linked to the known information and the timestamp (S303). When the management server 2 receives input data (S304), it searches for known information similar to the input data (S305), generates a response based on the retrieved known information and the input data (S306), determines the amount or type of incentive for the provider of the known information used in the generation, according to how old it was at the time of registration (S307), and grants an incentive to the owner of the NFT corresponding to the known information (S308).

[0043] As described above, the information processing system of this embodiment allows for stronger incentives to be provided the earlier information is provided. Furthermore, since the right to receive the incentive is issued as an NFT, it becomes possible to circulate that NFT in secondary markets.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] <Example 1> In the above embodiment, an example was described in which the incentive granting unit 215 grants incentives according to the age of the information at the time of registration, but it is not limited to this. The incentive granting unit 215 may also determine the amount and type of incentive by considering, in addition to the age of the information at the time of registration, the quality of the known information and user evaluations.

[0048] For example, the incentive provisioning unit 215 can calculate a score indicating the quality of the known information and determine the amount of incentive according to that score. The quality score can be calculated based on, for example, the number of characters in the known information, the types of words used, the specificity of the description, and its credibility. Alternatively, the quality score may be calculated using a machine learning model. The machine learning model can estimate the quality of unknown known information by learning from quality evaluations manually assigned to a large amount of known information.

[0049] Furthermore, the incentive granting unit 215 may determine the amount and type of incentive based on user evaluations. For example, if a user gives a high rating to an answer generated by the generation unit 216, the system may grant a larger incentive to the provider of the known information used to generate that answer. User evaluations can be obtained, for example, by presenting a UI to the user terminal 1 for inputting evaluations along with the answers, and accepting input from the user.

[0050] The incentive granting unit 215 may determine the amount and type of incentive by combining multiple indicators, such as the age of the information at the time of registration, the quality of the known information, and user evaluations. For example, a score for granting incentives can be calculated by weighting and adding up multiple indicators, and the incentive can be determined according to that score.

[0051] <Modification 2> Furthermore, the search unit 213 can also filter known information based on categories of known information, provider attributes, etc., in order to select known information suitable for the input data.

[0052] For example, the known information storage unit 231 can store known information in association with its category. The category may be, for example, a field such as "sports," "politics," "economics," or "entertainment," or a type of information such as "news," "blog," "paper," or "novel." The search unit 213 can identify a category from keywords included in the input data and search for known information belonging to the identified category.

[0053] Furthermore, the provider storage unit 232 can store provider attributes in association with other data. These provider attributes may include, for example, the provider's occupation, field of expertise, affiliated organization, and residential area. The search unit 213 can extract keywords related to provider attributes included in the input data and search for known information registered by providers with attributes containing the extracted keywords.

[0054] The search unit 213 can also prioritize searching for known information registered by the same provider as the input data provider, or known information registered by a provider with the same attributes as the input data provider.

[0055] <Variation 3>

[0056] The above embodiment shows examples of providing virtual currency or points as incentives, but it is not limited to these. For example, it is also possible to create and publish rankings based on the contribution level of the providers.

[0057] Specifically, the management server 2 can collect data on each provider stored in the provider storage unit 232, such as the number of known pieces of information provided, the number of times that known piece of information was used to generate answers, and the age of the known piece of information at the time of registration, and quantify the level of contribution. The level of contribution can be calculated, for example, by the following formula (1).

[0058] Contribution = Σ(Number of times known information i is used × Number of days elapsed since registration of known information i) ... (1)

[0059] Here, Σ represents the sum of all known information provided by the provider. The number of days elapsed since the registration of known information i can be, for example, the difference between the timestamp at the time of registration of known information i and the current time, converted into days.

[0060] Management Server 2 can create a ranking of providers based on the calculated contribution score. The ranking can be a list of providers ordered from highest to lowest contribution score. Management Server 2 can publish the created ranking on a website or notify providers of the ranking information.

[0061] Furthermore, the method for calculating the contribution is not limited to the above formula (1). Weighting may be applied to the number of times known information has been used or the number of days elapsed since registration, or the quality of the known information's content and evaluations from other providers may also be taken into consideration.

[0062] <Modification 4> In this embodiment, the information receiving unit 211 may request the provider to summarize or categorize the known information when registering known information. For example, the information receiving unit 211 can send an input form to the user terminal 1 for the provider to input a summary of the candidate information received from the provider, and receive the entered summary. The summary may be, for example, a sentence that concisely explains the content of the candidate information, or keywords that represent the subject of the candidate information.

[0063] Furthermore, the information receiving unit 211 may allow the provider to select the category to which the candidate information belongs from a predefined set of categories. Categories can include, for example, "News," "Sports," "Technology," "Entertainment," "Business," "Science," and "Health." Categories may also be defined in a tree structure, for example, with the first level being a major classification, the second level a medium classification, and the third level a minor classification, with the categories becoming more detailed as the hierarchy deepens.

[0064] The information receiving unit 211 can register the summary and category obtained from the provider in the known information storage unit 231, associating them with candidate information.

[0065] When the search unit 213 searches for known information similar to the input data, it can refer to summaries and categories associated with the known information. For example, when the search unit 213 calculates the similarity between the input data and each piece of known information, it can also take into account the similarity between the input data and the summary. Specifically, the search unit 213 can calculate the final similarity by adding the cosine similarity between the input data and the summary to the cosine similarity between the input data and the text of the known information, using a predetermined weight.

[0066] Furthermore, the search unit 213 may estimate categories related to keywords contained in the input data and preferentially select known information belonging to the estimated categories. This makes it possible to efficiently search for known information that is more suitable for the input data.

[0067] <Disclosure Items> Furthermore, this disclosure also includes the following configurations. [Item 1] A known information storage unit that stores known information and the registration time of said known information in association with each other, A provider storage unit that stores information identifying the provider of the aforementioned known information, A search unit that searches for the aforementioned known information regarding the input data, A specification unit that identifies the provider and registration time related to the retrieved known information by referring to the provider storage unit and the known information storage unit, An incentive granting unit provides incentives to the identified provider according to the age of the registration at the time of registration, An information processing system characterized by comprising the following features. [Item 2] The information processing system described in item 1, The system includes a generation unit that provides a prompt to a large-scale language model containing the retrieved known information and the input data to generate a response, and provides the generated response. An information processing system characterized by the following. [Item 3] The information processing system described in item 2, The incentive granting unit determines the incentive according to the number of times the known information was used to generate the answer and the registration date. An information processing system characterized by the following. [Item 4] The information processing system described in item 1, The search unit searches for known information similar to the input data, and if multiple pieces of known information are found, it determines a priority according to the age at the time of registration and retrieves a predetermined number of them in order of priority. An information processing system characterized by the following. [Item 5] The information processing system described in item 1, The incentive granting unit grants a larger amount of the incentive the older the registration date. An information processing system characterized by the following. [Item 6] The information processing system described in item 1, The incentive granting unit grants incentives of higher rarity the older the registration date. An information processing system characterized by the following. [Item 7] The information processing system described in item 1, A non-fungible token is issued to the provider, with the aforementioned known information and registration time set. The specified unit obtains the non-fungible tone corresponding to the retrieved known information, The incentive granting unit grants the incentive to the owner of the non-fungible token. An information processing system characterized by the following. [Item 8] A step of storing known information and the registration time of said known information in a known information storage unit in association with each other, The steps include storing information identifying the provider of the known information in the provider storage unit, A step of searching for the aforementioned known information regarding the input data, The steps include: identifying the provider and registration time of the retrieved known information by referring to the provider storage unit and the known information storage unit; The steps include providing an incentive to the identified provider according to the age of the registration at the time of registration, An information processing method characterized by a computer executing the following. [Item 9] A step of storing known information and the registration time of said known information in a known information storage unit in association with each other, The steps include storing information identifying the provider of the known information in the provider storage unit, A step of searching for the aforementioned known information regarding the input data, The steps include: identifying the provider and registration time of the retrieved known information by referring to the provider storage unit and the known information storage unit; The steps include providing an incentive to the identified provider according to the age of the registration at the time of registration, A program that causes a computer to execute something. [Explanation of Symbols]

[0068] 1 User terminal 2 Management Server

Claims

1. A known information storage unit that stores known information and the registration time of said known information in association with each other, A provider storage unit that stores information identifying the provider of the aforementioned known information, A search unit that searches for the aforementioned known information regarding the input data, A specification unit that identifies the provider and registration time related to the retrieved known information by referring to the provider storage unit and the known information storage unit, An incentive granting unit provides incentives to the identified provider according to the age of the registration at the time of registration, An information processing system characterized by comprising the following features.

2. The information processing system according to claim 1, The system includes a generation unit that provides a prompt to a large-scale language model containing the retrieved known information and the input data to generate a response, and provides the generated response. An information processing system characterized by the following.

3. The information processing system according to claim 2, The incentive granting unit determines the incentive according to the number of times the known information was used to generate the answer and the registration date. An information processing system characterized by the following.

4. The information processing system according to claim 1, The search unit searches for known information similar to the input data, and if multiple pieces of known information are found, it determines a priority according to the age at the time of registration and retrieves a predetermined number of them in order of priority. An information processing system characterized by the following.

5. The information processing system according to claim 1, The incentive granting unit grants a larger amount of the incentive the older the registration date. An information processing system characterized by the following.

6. The information processing system according to claim 1, The incentive granting unit grants incentives of higher rarity the older the registration date. An information processing system characterized by the following.

7. The information processing system according to claim 1, A non-fungible token is issued to the provider, with the aforementioned known information and registration time set. The specified unit obtains the non-fungible tone corresponding to the retrieved known information, The incentive granting unit grants the incentive to the owner of the non-fungible token. An information processing system characterized by the following.

8. A step of storing known information and the registration time of said known information in a known information storage unit in association with each other, The steps include storing information identifying the provider of the known information in the provider storage unit, A step of searching for the aforementioned known information regarding the input data, The steps include: identifying the provider and registration time of the retrieved known information by referring to the provider storage unit and the known information storage unit; The steps include providing an incentive to the identified provider according to the age of the registration at the time of registration, An information processing method characterized by a computer executing the following.

9. A step of storing known information and the registration time of said known information in a known information storage unit in association with each other, The steps include storing information identifying the provider of the known information in the provider storage unit, A step of searching for the aforementioned known information regarding the input data, The steps include: identifying the provider and registration time of the retrieved known information by referring to the provider storage unit and the known information storage unit; The steps include providing an incentive to the identified provider according to the age of the registration at the time of registration, A program that causes a computer to execute something.

Images