Information management system, information management method, and information management device

Abstract

An information management system, an information management server, and an information management method are provided that effectively utilize business information held by each base. [Solution] In the information management system 1, the information management server 40 receives attribute data of each base 10 where a specified business is performed and multiple pieces of answer data corresponding to question data related to the specified business, stores a related answer extraction model that outputs the portion of the multiple answer data that is related to that base, receives answer data corresponding to question data related to the specified business that is common to each information management device from each information management device 30 associated with each of the multiple bases where the specified business is performed, and inputs the attribute data of the specified base and each received answer data into the related answer extraction model, thereby outputting the portion of the answer data of the multiple bases that is related to the specified base, and sends data created based on the output data to the information management device related to the specified base.

Description

[Technical Field]

[0001] The present invention relates to an information management system, an information management method, and an information management device. [Background technology]

[0002] Due to changes in social conditions and advances in information processing technology, the amount of business data that companies must manage is steadily increasing, and the number of people sharing business information is also increasing.

[0003] As a technology for sharing and managing such business information among related parties, for example, Patent Document 1 discloses a security information management system that includes an information acquisition unit that acquires account information of a company and its employees, acquires first management object information related to management objects that exist for classification purposes, and acquires second management object information related to management objects that exist in a plurality of classification items when the management objects are classified by any classification item in the management object information, and a security management unit that generates security management information that associates the account information and the first management object information with each of the plurality of classification items that make up the second management object information and registers the information in a database unit. Desired information can be searched for based on the database created in this way. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-018609 Summary of the Invention [Problem to be solved by the invention]

[0005] On the other hand, with the rapid globalization of recent years, business operations are increasingly being carried out at multiple business locations (factories, sales offices, offices, etc.), making it important to share information between these locations.

[0006] However, even for similar types of work, business policies, business know-how, and specific work content are often established separately at each location, making integrating and sharing information between locations cumbersome. Furthermore, because the amount of information to be integrated is enormous, even when one location searches for information from data at other locations, there is a risk that a large amount of unnecessary information will be mixed in the search results, resulting in increased workload. Conversely, there is also a risk of missing useful information.

[0007] The present invention has been made in consideration of the above circumstances, and its purpose is to provide an information management system, an information management method, and an information management device that can effectively utilize the business information held by each base station. [Means for solving the problem]

[0008] One aspect of the present invention for solving the above problem is an information management server that includes a storage device that stores a related answer extraction model, which is a trained model that receives attribute data of a location where a specified business is performed and a plurality of answer data corresponding to question data related to the specified business and outputs a portion of the plurality of answer data that is related to the location, and a computing device that executes an answer data receiving process that receives answer data corresponding to question data related to the specified business that is common to each information management device from each of the plurality of location where the specified business is performed, an answer data aggregation process that inputs attribute data of a specified location and each of the received answer data into the related answer extraction model and outputs a portion of the answer data of the plurality of location that is related to the specified location, and a know-how data transmission process that transmits data created based on the output data to the information management device related to the specified location.

[0009] Another aspect of the present invention for solving the above-mentioned problems is an information management system including a plurality of information management devices respectively associated with a plurality of bases where predetermined tasks are performed, and an information management server communicably connected to the plurality of information management devices, wherein each of the information management devices comprises: a storage device that stores a question-answering model, which is a trained model to which question data related to the predetermined task at the base associated with the information management device is input and to which answer data corresponding to the question data is output; and a calculation device that executes a question-answering process that inputs question data related to the predetermined task common to each of the information management devices at the bases associated with the information management device to the question-answering model, thereby outputting answer data corresponding to the question data and transmitting the output answer data to the information management server; The information management server is an information management system that includes a storage device that stores a related answer extraction model, which is a trained model that receives attribute data of a location where the specified business is performed and multiple answer data corresponding to question data related to the specified business and outputs data related to the location among the multiple answer data, and a computing device that executes an answer data receiving process that receives the output answer data from each of the information management devices, an answer data aggregation process that inputs attribute data of a specified location and each of the received answer data into the related answer extraction model, and outputs data related to the specified location among the answer data of the multiple locations, and a know-how data transmission process that transmits data created based on the output data to the information management device related to the specified location. [Effects of the Invention]

[0010] According to the present invention, it is possible to effectively utilize the business information held by each base.

[0011] Configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0012] [Figure 1]1 is a diagram illustrating an example of a configuration of an information management system according to an embodiment of the present invention. [Figure 2] 2 is a diagram illustrating an example of information stored in each information management device and functional units included in each information management device. FIG. [Figure 3] 2 is a diagram illustrating an example of information stored in an information management server and functional units included in the information management server. FIG. [Figure 4] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information management device and each information processing device of an information management server. [Figure 5] FIG. 10 is a sequence diagram illustrating an example of processing performed in the information management system. DETAILED DESCRIPTION OF THE INVENTION

[0013] An embodiment of the present invention will be described in detail below with reference to the drawings. However, the present invention should not be construed as being limited to the description of the embodiment shown below. Those skilled in the art will readily understand that the specific configuration can be modified within the scope of the idea or intent of the present invention. Furthermore, in the configuration described below, the same reference numerals will be used in common between different drawings for the same parts or parts having similar functions, and duplicated explanations may be omitted.

[0014] FIG. 1 is a diagram showing an example of the configuration of an information management system 1 according to this embodiment. The information management system 1 is applied to a predetermined business (hereinafter referred to as the business in question; in this embodiment, it is assumed to be a product manufacturing business, but is not intended to be limited to this) performed at a plurality of bases 10 (for example, an area of ​​a sales office, business establishment, factory, etc., or an area managed by such an area). Each base 10 is provided with equipment 20 used for the business in question (for example, equipment for manufacturing products, a photography device for photographing the equipment or products, and a server for storing various data used in the business), and an information management device 30.

[0015] The information management system 1 also includes an information management server 40 that manages data confidentiality policies (details of which will be described later) at each base 10.

[0016] The information management device 30 manages data (hereinafter referred to as business data) related to business being performed or having been performed at the base 10. Specifically, the information management device 30 acquires data from the equipment 20 at predetermined timing (for example, at a predetermined time, at predetermined time intervals, etc.) and stores the acquired data as business data. The equipment 20 is, for example, product manufacturing equipment, sensors installed in the manufacturing equipment, or a business management system. Details of the business data will be described later.

[0017] The equipment 20 and the information management device 30 at each base 10, the information management devices 30 between the bases 10, and the information management device 30 and the information management server 40 at each base 10 are communicatively connected via a wired or wireless communication network 5 such as the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), or a dedicated line.

[0018] 2 is a diagram illustrating an example of information stored in each information management device 30 and functional units included in each information management device 30. First, each information management device 30 stores attribute data 31, a question and answer model 32, and business data 34.

[0019] The attribute data 31 is data that represents various attributes or characteristics related to the base 10 associated with the corresponding information management device 30. The attribute data 31 may include, but is not limited to, an identifier of the base 10, the name of the base, the equipment 20 owned by the base 10, the product manufactured by the equipment 20, the manufacturing process required to manufacture the product, or the manufacturing method of the product. The attribute data 31 may vary significantly depending on the base. For example, even when the same product is manufactured, the parts that make up the product and the manufacturing method used may differ depending on the base 10.

[0020] The question and answer model 32 is a trained model that receives question data about the actual business at the base 10 related to the corresponding information management device 30 and outputs answer data corresponding to the question data. In this embodiment, the question and answer model 32 is a trained model that receives question data about the situation in the actual business at the base (for example, question data asking how to resolve a problem that has occurred in the actual business at the base) and outputs data on countermeasures for the situation (for example, data on the specific content of how to resolve the problem). The question and answer model 32 may be an existing publicly available natural language processing model (such as a large language model (LLM)), or may be a newly created trained model.

[0021] In this embodiment, the question and answer model 32 receives question data in natural language, image, or video data, while receiving answer data in natural language. That is, the question and answer model 32 receives natural language data of a question about the business at the site 10, and outputs natural language data of an answer corresponding to the question data. Alternatively, the question and answer model 32 may receive data of a question about an image or video captured in the business at the site 10, and output natural language data of an answer to the question (improvements for business problems indicated by the image or video).

[0022] In this embodiment, the question and answer model 32 is a neural network having an input layer to which question data is input, one or more intermediate layers (hidden layers) that extract and output feature quantities from the question data, and an output layer that outputs answer data from the feature quantities, but is not limited to this. Examples of neural networks include a convolution neural network (CNN), a recurrent neural network (RNN), a bidirectional encoder representations from transformers (BERT), an XLNet, and a generative pre-trained transformer (GPT).

[0023] The business data 34 is used as training data for the question and answer model 32. Specifically, the business data 34 includes data on each past situation in the business at the corresponding base 10 (training data for question data) and data on each countermeasure for each past situation (training data for answer data), which are acquired from the equipment 20. The business data 34 is, for example, natural language data, image data, or video data.

[0024] If the facility 20 is a facility for manufacturing products, the business data 34 is data representing the attributes of the manufacturing facility, the operation of the manufacturing facility (manufacturing method such as forging, casting, or assembly), parts used in manufacturing the product, or the manufactured product (its attributes, type, size, quality, etc.) acquired from a predetermined sensor provided in the facility 20. If the facility 20 is a photographing device, the business data 34 is data of images or videos of the manufacturing facility, products, parts, or workers photographed by the photographing device.

[0025] Furthermore, if the equipment 20 is a business management system (server), the business data 34 is data relating to the progress or process of the business in question obtained from the business management system, data on cases of defects or accidents that have occurred in the product or the product's manufacturing equipment, data on cases of complaints from customers, data on the risk of each case occurring, or data on the cause of each case or countermeasures (improvement measures).

[0026] Next, each information management device 30 includes the functional units of a learning unit 35, an inquiry unit 36, and a question and answer unit 37.

[0027] The learning unit 35 learns the question and answer model 32 using the business data 34. Since the training data for the question and answer model 32 differs for each location 10, the content of the learned question and answer model 32 also differs for each location 10.

[0028] The inquiry unit 36 ​​transmits question data (natural language data, image data, or video data) related to the present business to each of the other information management devices 30 via the information management server 40. Note that this question is common to all of the information management devices 30.

[0029] When the question answering unit 37 receives the above question data from another information management device 30, it inputs the above question data regarding the business in question at the base (hereinafter referred to as its own base) associated with the information management device 30 related to the question answering unit 37 into the question answering model 32, outputs answer data corresponding to the question data, and transmits the output answer data to the information management server 40.

[0030] 3 is a diagram illustrating an example of information stored in the information management server 40 and functional units included in the information management server 40. First, the information management server 40 stores a related answer extraction model 42 and a confidentiality determination model 43.

[0031] The related answer extraction model 42 is a trained model that receives attribute data of the home base where the business in question is performed and multiple answer data from multiple information management devices 30 corresponding to the above-mentioned question data regarding the business in question, and outputs the data portion of the multiple answer data that is related to the home base (hereinafter referred to as home base-related answer data).

[0032] In this embodiment, the related answer extraction model 42 is a neural network having an input layer to which attribute data and answer data are input, one or more intermediate layers (hidden layers) that extract and output feature quantities from the attribute data and answer data, and an output layer that outputs answer data related to the user's location from the feature quantities, but is not limited to this. Examples of neural networks include a convolution neural network (CNN), a recurrent neural network (RNN), a bidirectional encoder representations from transformers (BERT), an XLNet, and a generative pre-trained transformer (GPT).

[0033] The related answer extraction model 42 may be an existing natural language processing model (such as an LLM) or a newly created trained model. When the related answer extraction model 42 is a newly created trained model, the related answer extraction model 42 is created, for example, as follows. That is, the information management server 40 acquires the attribute data 31 or business data 34 of each base 10, and performs machine learning using the acquired attribute data 31 or business data 34, thereby creating a trained model that receives the attribute data of its own base and multiple answer data and outputs self-base related answer data that is a portion of the multiple answer data that is related to its own base.

[0034] The confidentiality determination model 43 is a trained model that receives input of local base related answer data and outputs data from the local base related answer data that should be kept confidential at a predetermined base 10. Note that the confidentiality determination model 43 may be stored in each information management device 30, but the present embodiment will be described mainly regarding the case where the information management server 30 stores the confidentiality determination model 43.

[0035] In this embodiment, the confidentiality determination model 43 is a neural network having an input layer to which the own-location-related response data is input, one or more intermediate layers (hidden layers) that extract and output feature quantities of the own-location-related response data, and an output layer that outputs data to be confidential from the feature quantities, but is not limited to this. Examples of neural networks include a convolution neural network (CNN), a recurrent neural network (RNN), a bidirectional encoder representations from transformers (BERT), an XLNet, and a generative pre-trained transformer (GPT).

[0036] The confidentiality determination model 43 may be an existing natural language processing model (such as an LLM) or a newly created trained model. When the confidentiality determination model 43 is a newly created trained model, the confidentiality determination model 43 is created, for example, as follows. That is, the information management server 40 acquires confidentiality policy data for each location 10, which is a standard (policy) for information that should be kept confidential and that is prohibited from being provided to any location other than the location 10, as determined at each location 10. The information management server 40 performs machine learning using this confidentiality policy data to input attribute data and self-location-related answer data for each location 10, and creates a trained model that outputs data that should be kept confidential at the specified location 10 from the self-location-related answer data.

[0037] The information management server 40 also includes a response data receiving unit 45 , a response data aggregating unit 46 , a confidentiality determining unit 48 , and a know-how data transmitting unit 47 .

[0038] The response data receiving unit 45 receives response data corresponding to question data common to each information management device 30 regarding the present business from each information management device 30 associated with each of the multiple locations 10 where the present business is performed.

[0039] The response data aggregation unit 46 inputs the attribute data of its own base and each response data received from each information management device 30 into the related response extraction model 42, and outputs its own base-related response data, which is the data related to its own base among the response data of the multiple bases.

[0040] The confidentiality determination unit 48 uses a predetermined algorithm to identify data that should be kept confidential at a specified location 10 (specifically, another location 10 that provided the original response data of the know-how data) from the response data related to the location itself output by the response data aggregation unit 46, and creates data (hereinafter referred to as know-how data) by deleting or processing the identified data that should be kept confidential from the data output by the response data aggregation unit 46.

[0041] In this embodiment, the confidentiality determination unit 48 inputs the own base-related response data output by the response data aggregation unit 46 into the confidentiality determination model 43, thereby identifying data that should be kept confidential at a predetermined base 10.

[0042] The know-how data transmission unit 47 transmits data (specifically, know-how data created by the confidentiality determination unit 48) created based on the response data related to the local base output by the response data aggregation unit 46 to the information management device 30 related to the local base.

[0043] 4 is a diagram showing an example of a hardware configuration of each information processing device of the information management device 30 and the information management server 40. Each information processing device includes an arithmetic unit 51 such as a CPU (Central Processing Unit), a main memory device 52 such as a RAM (Random Access Memory) or a ROM (Read Only Memory), an auxiliary memory device 53 such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive), an input device 54 such as a keyboard, a mouse, or a touch panel, an output device 55 such as a display or a touch panel, and a communication device 56 configured by a NIC (Network Interface Card), a wireless communication module, a USB (Universal Serial Interface) module, a serial communication module, or the like.

[0044] The functions of the functional units of each information processing device described above are realized by the arithmetic unit 51 of each information processing device reading out a program from the main storage device 52 or the auxiliary storage device 53. Each program can be recorded on, for example, a portable or fixed recording medium and distributed. All or part of each program in each information processing device may be realized using virtual information processing resources provided using virtualization technology, process space separation technology, or the like, such as a virtual server provided by a cloud system. All or part of these programs may be realized by a service provided by a cloud system via an API (Application Programming Interface), for example.

[0045] Next, the processing performed by the information management system 1 will be described.

[0046] FIG. 5 is a sequence diagram showing an example of processing performed by the information management system 1. As shown in FIG.

[0047] First, the information management device 30 of each base 10 receives input of data relating to the business being carried out at that base 10 from the administrator or the like of that base 10 (s1).

[0048] For example, the information management device 30 of each base 10 accepts input of text describing the content (parts, products, equipment) of the business currently being performed or about to be performed at that base 10 (own base). Also, for example, the information management device 30 accepts designation of image or video data acquired from the equipment 20.

[0049] The information management device 30 (information management device 30 at the local base) that received the data input at s1 inputs the question data including the data input at s1 into the question and answer model 32 at the local base, thereby obtaining the corresponding answer data (local base answer data) (s3).

[0050] For example, the information management device 30 generates a prompt using RAG (Retrieval-Augmented Generation) that includes the sentence entered in s1 and a sentence asking whether there are any problems or areas for improvement in the business at the location represented by the sentence, and inputs the generated prompt into the question and answer model 32 to obtain sentence data that represents the problems and areas for improvement at the location.

[0051] Furthermore, for example, the information management device 30 generates a prompt using RAG that includes the image or video specified in s1 and a sentence asking whether there are any problems or areas for improvement in the business at the location represented by the image or video, and inputs this into the question and answer model 32 to obtain sentence data that represents the problems and areas for improvement at the location.

[0052] Furthermore, the information management device 30 at the own base acquires the attribute data 31 of the own base (s4).

[0053] Furthermore, the information management device 30 at the local base transmits the question data generated in s1 to the information management server 40 (s5). The information management server 40 stores the fact that the information management device 30 at the local base has been designated. In s5, the information management device 30 at the local base may specifically designate an information management device 30 at another base (a base 10 other than the local base) as the destination of the question data.

[0054] The information management server 40 transmits the question data received from the information management device 30 at its own location to the information management devices 30 at the other locations (s7).

[0055] Upon receiving the inquiry data, the information management device 30 at each of the other locations executes the following process (s9-s13).

[0056] That is, similar to s3, the information management device 30 at the other location inputs the received question data into the question and answer model 32 at the other location to obtain corresponding answer data (data representing the problems and areas for improvement at its own location) (s9).

[0057] Furthermore, the information management device 30 at the other base acquires the attribute data 31 of the other base (s11).

[0058] Then, the information management device 30 at the other base transmits the response data and attribute data 31 acquired in s9 and s11 to the information management server 40 together with an identifier indicating the other base (s13).

[0059] Meanwhile, the information management device 30 at the own base also transmits the attribute data 31 of the own base acquired in s4 to the information management server 40 (s14).

[0060] The information management server 40 uses the related answer extraction model 42 to extract answer data related to its own base (useful to its own base) from the answer data of other bases based on the question data and attribute data 31 of its own base received from the information management device 30 of its own base, and the attribute data 31 and answer data of other bases received from the information management device 30 of the other bases, and aggregates the answer data, thereby outputting answer data related to its own base (s15).

[0061] For example, the information management server 40 generates a prompt in natural language that instructs the server 40 to extract answer data from other locations that is useful or relevant to the server 40 based on the attribute data of the server 40 and each other location, and inputs the generated prompt into the related answer extraction model 42.

[0062] Next, the information management server 40 identifies data relating to information that should be kept secret at other bases from among the response data collected in s15, that is, the self-base-related response data (s17).

[0063] For example, the information management server 40 refers to a predetermined database to identify information data that should be kept secret at each of the other locations and that is included in the home-location-related response data. Alternatively, for example, the information management server 40 transmits the home-location-related response data to the information management devices 30 at each of the other locations. The information management devices 30 at each of the other locations refer to a predetermined database to identify information data that should be kept secret at each of the other locations and that is included in the home-location-related response data, and transmit the identified data to the information management server 40.

[0064] Furthermore, the information management server 40 or the information management device 30 at each other base may specify the data of information that should be kept secret at each other base, which is included in the home base related answer data, by inputting a prompt that instructs the confidentiality determination model 43 to specify a portion of the home base related answer data that should be kept secret. Alternatively, the information management server 40 or the information management device 30 at each other base may display a screen for accepting designation of information that should be kept secret, and accept the input of designation from an administrator or the like.

[0065] Next, the information management server 40 creates know-how data by deleting the data related to the information to be kept secret, identified in s16, from the response data related to its own base output in s15 or by performing a predetermined masking process (s19).

[0066] Then, the information management server 40 transmits the know-how data created in s17 to the information management device 30 at the own location (s21). The information management device 30 at the own location displays the received know-how data and the contents of the response data of the own location acquired in s3 on the screen (s23).

[0067] The information management device 30 of the home base may limit the other bases that are the target of the home base-related answer data to those similar to the home base. For example, the information management device 30 of the home base identifies other bases whose attribute data is similar to that of the home base and transmits the identified other bases to the information management server 40. The information management server 40 generates a prompt instructing the output of home base-related answer data using the answer data of the other bases and inputs the generated prompt into the related answer extraction model 42. Here, the method of identifying other bases whose attribute data is similar to that of the home base may use, for example, a predetermined model (such as a trained model or database that outputs other bases whose attribute data is similar to that of the home base when attribute data of the home base is input), or the information management device 30 of the home base may display a screen for selecting other bases whose attribute data 31 are similar to that of the home base and receive input of the selection of the other base from an administrator of the home base, etc.

[0068] As described above, the information management server 40 of this embodiment receives answer data corresponding to question data related to the present business that is common to each information management device 30 from each information management device 30 associated with each of the multiple bases 10 where the present business is performed. Then, the information management server 40 inputs the attribute data of its own base and each of the received answer data into the related answer extraction model 42, thereby outputting data related to its own base among the answer data of the multiple bases 10 (self-base related answer data), and transmits know-how data created based on the self-base related answer data to the information management device 30 related to its own base.

[0069] In other words, the information management server 40 of this embodiment aggregates response data from each base 10 (other bases) into data related to its own base, outputs response data related to its own base, and can provide know-how data based on this to its own base.

[0070] In this way, the information management server 40 of this embodiment can effectively utilize the business information held by each base 10. In other words, even if the business information held by each base 10 is not centrally managed, each base 10 can obtain appropriate business information (business know-how, etc.) of other bases related to that base 10, and can find defects and areas for improvement in the business that are difficult to find by manual work alone at the base itself.

[0071] For example, an automobile parts manufacturer produces the same parts under different conditions (climate, processing machines, source of raw materials, and human skills) at factories around the world. Even in cases where the same quality issue occurs, such as a hole appearing during product processing, the cause will differ depending on the manufacturing method (forging, casting, injection molding, etc.). Even when the preconditions differ between a factory and other factories, the information management server 40 can collect such information and compare it with the conditions of the factory, narrowing down the vast amount of data from numerous factories and business locations to the data necessary for the factory, thereby providing the most appropriate answer for the factory.

[0072] In addition, the information management server 40 of this embodiment outputs answer data related to its own base by inputting attribute data in natural language of its own base and each answer data in natural language received from the information management device 30 of each other base into the related answer extraction model 42.

[0073] By using such a trained model based on natural language, it is possible to accurately extract response data from other locations related to the user's own location.

[0074] In addition, the information management server 40 of this embodiment outputs answer data related to its own base by inputting data on at least one of the equipment owned by its own base, the products manufactured by the equipment, or the manufacturing methods of the products, and each answer data in natural language received from the information management device 30 of each other base into the related answer extraction model 42.

[0075] This allows each base 10 to accurately extract response data from other bases related to the base itself in accordance with the content of the business in question at that base.

[0076] In addition, the information management server 40 of this embodiment identifies data from the response data related to its own base that should be kept confidential at other bases using a predetermined algorithm, creates know-how data by deleting or modifying the identified data that should be kept confidential from the response data related to its own base, and transmits the created know-how data to the information management device 30 related to its own base.

[0077] This makes it possible to prevent other bases from providing their own base with information that should not be provided to the base (confidential data, etc.), which prevents each base 10 from avoiding providing information to other bases 10 because it has information that should be kept confidential, and enables active sharing and utilization of business information within appropriate limits.

[0078] Specifically, the information management server 40 of this embodiment inputs the own base-related response data into the confidentiality determination model 43, thereby identifying data that should be kept confidential at the own base.

[0079] This makes it possible to accurately identify confidential data for each of the other bases.

[0080] For example, in a company's own factories, contracts with client companies may restrict the sharing of certain information (e.g., information on processing accuracy) between factories, even within the same company. In such cases, information that could potentially contain such information could not be shared between factories. However, if the confidentiality judgment model 43 or similar device determines whether or not information can be shared, humans need only check the judgment results of the confidentiality judgment model 43, allowing each factory to share information more widely and appropriately. In particular, when multiple companies (factories) collaborate to manufacture products, restrictions on information sharing become stricter. For example, a parts manufacturer that has been contracted to perform work will not disclose information such as quality or the operating status of the production line to the finished product manufacturer that requested the work. For this reason, if a parts manufacturer's production line is idle, even if the parts supplier wants to increase finished product inventory now, their needs will not be aligned unless both parties have a forum for discussion. Even in such cases, by having the information management server 40 process confidential information using the confidentiality determination model 43 or the like, it becomes possible to share information when an agreement is reached between the ordering party and the parts manufacturer, thereby making it possible to take advantage of business opportunities that would have been missed in the past.

[0081] Furthermore, in the information management system 1 of this embodiment, each information management device 30 inputs question data related to the present business, which is common to each information management device at the base 10 associated with that information management device 30, into the question and answer model 32, thereby outputting answer data corresponding to the question data, and transmitting the output answer data to the information management server 40. Then, the information management server 40 receives the answer data from each information management device 30, and creates know-how data as described above based on the received answer data.

[0082] In this way, by providing each base 10 with the question and answer model 32, each base 10 can obtain answer data based on its own business know-how.

[0083] In the information management system 1 of this embodiment, the question and answer model 32 is a model in which question data written in a natural language relating to the business in question is input, and answer data written in a natural language corresponding to the question data is output.

[0084] In this way, since the question and answer model 32 uses natural language data as input and output data, the administrator or the like can ask appropriate questions and obtain useful answers corresponding to those questions.

[0085] In addition, in the information management system 1 of this embodiment, the question and answer model 32 is a model in which question data asking about images or videos acquired in the business in question is input, and answer data in natural language corresponding to the question is output.

[0086] In this way, the question and answer model 32 uses image or video data of the business in question as input data and natural language data as output data, so that the situation of the business in question can be accurately reflected in the question, and appropriate answers corresponding to the question can be obtained.

[0087] In the past, information sharing between bases 10 involved people from other factories or business locations visiting other factories to observe the site and identify areas for improvement in production. Therefore, even remote monitoring using cameras was not always possible to ensure that problems were not overlooked. This applies not only to productivity improvement but also to safety patrols. Potential dangers occur even when monitoring is not in progress. Furthermore, in overseas factories where employee turnover is high, it is difficult to consistently provide thorough safety training. However, the configuration of the question-and-answer model 32 described above allows each base 10 to effectively monitor from the perspectives of product productivity and safety.

[0088] Specifically, the information management device 30 of each base 10 in this embodiment generates a question and answer model 32 in which question data regarding the situation in the present business at the base 10 is input and data on the response measures for the situation is output, based on data representing each past situation in the present business at the base 10 and data on each response measure for each of the past situations.

[0089] In this way, the question and answer model 32 is trained using past business data related to each base 10, so that each base 10 can generate a question and answer model 32 whose content is in line with its business performance.

[0090] The present invention is not limited to the above-described embodiments, and can be implemented using any components within the scope of the present invention. The above-described embodiments and modifications are merely examples, and the present invention is not limited to these contents as long as the characteristics of the invention are not impaired. Furthermore, although various embodiments and modifications have been described above, the present invention is not limited to these contents. Other embodiments conceivable within the scope of the technical idea of ​​the present invention are also included within the scope of the present invention.

[0091] For example, part of the hardware provided in each device in each embodiment may be provided in another device.

[0092] Furthermore, each program of each device may be provided in another device, a program may consist of multiple programs, or multiple programs may be integrated into one program.

[0093] Furthermore, each information management device 30 may input all or any part of natural language data, video data, and image data into the question and answer model 32 to obtain various types of answer data.

[0094] Furthermore, the confidentiality determination model 43 in this embodiment is a model that identifies confidential parts from the response data related to the own base, but the confidentiality determination model 43 may not only identify confidential parts but also delete or process the confidential parts from the response data related to the own base.

[0095] Furthermore, the question and answer model 32, the related answer extraction model 42, and the confidentiality determination model 43 described in this embodiment may be other types of models such as databases instead of trained models. [Explanation of symbols]

[0096] 30 Information management device, 40 Information management server, 35 Learning unit, 36 Inquiry unit, 37 Question and answer unit, 45 Answer data receiving unit, 46 Answer data aggregating unit, 47 Know-how data transmitting unit, 48 Confidentiality determining unit

Claims

1. a storage device that stores a related answer extraction model, which is a trained model that receives attribute data of a base where a predetermined task is performed and a plurality of pieces of answer data corresponding to question data related to the predetermined task, and outputs a portion of the plurality of answer data that is related to the base; and an answer data receiving process for receiving answer data corresponding to question data common to each of the information management devices regarding the predetermined business from each of the information management devices associated with each of the plurality of bases where the predetermined business is performed; a response data aggregation process for inputting attribute data of a designated location and each of the received response data into the related response extraction model, and outputting data related to the designated location among the response data of the plurality of locations; a computing device that executes a know-how data transmission process of transmitting data created based on the output data to the information management device related to the specified base; An information management server comprising:

2. the storage device stores a related answer extraction model that receives attribute data of a base where a predetermined business is performed and a plurality of pieces of answer data in natural language corresponding to question data in natural language related to the predetermined business, and outputs natural language data of a portion of the plurality of answer data that is related to the base; In the response data aggregation process, the computing device inputs attribute data in the natural language of the designated location and each of the received natural language response data into the related response extraction model, thereby outputting data of a portion related to the designated location among the natural language response data of the plurality of locations. The information management server according to claim 1 .

3. the storage device stores a related answer extraction model, which is a trained model into which at least one of data on equipment owned by a base where the predetermined work is performed, a product manufactured by the equipment, or a manufacturing method of the product, and a plurality of answer data corresponding to question data related to the predetermined work, is input, and which outputs data on a portion of the plurality of answer data related to the base; In the response data aggregation process, the computing device inputs at least one of data on equipment owned by the specified base, data on products manufactured by the equipment, and data on manufacturing methods of the products, and each of the received response data into the related response extraction model, thereby outputting data on a portion of the plurality of response data that is related to the base. The information management server according to claim 1 .

4. The computing device identifying data to be kept secret at a predetermined location from the output data using a predetermined algorithm, and executing a confidentiality determination process for deleting or processing the identified data to be kept secret from the output data; In the know-how data transmission process, the created data is transmitted to an information management device related to the specified base. The information management server according to claim 1 .

5. the storage device stores a confidentiality determination model, which is a trained model into which the output data is input and from which data that should be confidential at the predetermined location is output, the computing device, in the confidentiality determination process, inputs the output data into the confidentiality determination model, thereby identifying data that should be confidential at the predetermined location. The information management server according to claim 4.

6. An information management system including a plurality of information management devices respectively associated with a plurality of bases where predetermined tasks are performed, and an information management server communicably connected to the plurality of information management devices, Each of the information management devices is a storage device that stores a question-answering model, which is a trained model that receives question data related to the predetermined business at the base associated with the information management device and outputs answer data corresponding to the question data; and a computing device that executes a question and answer process by inputting question data related to the predetermined business common to each of the information management devices at the bases associated with the information management devices into the question and answer model, outputting answer data corresponding to the question data, and transmitting the output answer data to the information management server; The information management server a storage device that stores a related answer extraction model, which is a trained model that receives attribute data of a base where the predetermined business is performed and a plurality of pieces of answer data corresponding to question data related to the predetermined business and outputs a portion of the plurality of answer data that is related to the base; and a response data receiving process for receiving the output response data from each of the information management devices; a response data aggregation process for inputting attribute data of a designated location and each of the received response data into the related response extraction model, and outputting data related to the designated location among the response data of the plurality of locations; a computing device that executes a know-how data transmission process that transmits data created based on the output data to the information management device related to the specified base, Information management system.

7. a storage device of each of the information management devices stores a question and answer model in which question data in a natural language relating to the predetermined business is input and answer data in a natural language corresponding to the question data is output; a storage device of each of the information management devices, in the question and answering process, inputting question data in a natural language at a location associated with the information management device into the question and answering model, and outputting answer data in a natural language corresponding to the question data; The information management system according to claim 6 .

8. a storage device of each of the information management devices stores a question-answering model to which question data about an image or video acquired in the predetermined task is input and which outputs answer data in a natural language corresponding to the question; In the question and answering process, the storage device of each of the information management devices inputs question data of a question about an image or video acquired in the predetermined task at the base associated with the information management device into the question and answer model, and outputs answer data in natural language corresponding to the question data. The information management system according to claim 6 .

9. a storage device of each of the information management devices stores data representing past situations in the predetermined business at the base associated with the information management device, and data on countermeasures for each of the past situations; the computing device of each of the information management devices executes a learning process to generate a question-answering model, in which question data relating to a situation in the predetermined business at the base associated with the information management device is input based on the stored data, and data on a countermeasure for the situation is output. The information management system according to claim 6 .

10. An information management method using an information management server including a storage device that stores a related answer extraction model, which is a trained model that receives attribute data of a base where a predetermined task is performed and a plurality of answer data corresponding to question data related to the predetermined task, and outputs data related to the base among the plurality of answer data, and a computing device, The computing device an answer data receiving process for receiving answer data corresponding to question data common to each of the information management devices regarding the predetermined business from each of the information management devices associated with each of the plurality of bases where the predetermined business is performed; a response data aggregation process for inputting attribute data of a designated location and each of the received response data into the related response extraction model, and outputting data related to the designated location among the response data of the plurality of locations; and executing a know-how data transmission process for transmitting data created based on the output data to the information management device related to the specified base. Information management method.

Images