Information processing device and information processing program

Abstract

To provide an information processor capable of using a message group exchanged among plural users regarding a document file created for a matter or the matter when predicting a conclusion of propriety of signing of agreement of the matter or the like.SOLUTION: An information processor includes a memory and one or plural processors, the memory stores a message group exchanged among plural users regarding a document file created for a matter or the matter, and the processors extract information regarding an object matter from a document file or a message group stored in the memory, and predicts a conclusion regarding the object matter from the extracted information by artificial intelligence that previously learns to predict a conclusion of the matter corresponding to information within the document file or the message group for each matter by machine learning.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing device and an information processing program. [Background technology]

[0002] Patent Document 1 describes a system for supporting sales of life insurance, which includes a contact amount acquisition unit that acquires, for each prospective customer, a contact amount, which is the number of times a sales representative contacts the prospective customer; an information amount acquisition unit that acquires, for each prospective customer, an amount of information about the prospective customer collected from the prospective customer by the sales representative; and a likelihood determination unit that determines a likelihood of a contract being concluded for the prospective customer in accordance with the contact amount and the information amount. The contact amount acquisition unit acquires a first contact amount, which is the number of times the sales representative has interviewed the prospective customer, and a second contact amount, which is the number of times the sales representative has contacted the prospective customer without interviewing the prospective customer. The information processing device discloses that the probability determination unit acquires a first probability according to the first contact amount when the first contact amount is equal to or greater than a first predetermined value, determines a second probability lower than the first probability according to the amount of information when the first contact amount is less than the first predetermined value and the second contact amount is equal to or greater than a second predetermined value, and determines a third probability lower than the second probability according to the second contact amount when the first contact amount is less than the first predetermined value and the second contact amount is less than the second predetermined value.

[0003] Patent Document 2 describes an order acceptance judgment visualization device that makes it easy to objectively judge whether an order will be accepted or not based on the quality of contact between a sales source and a sales destination and the effort that the sales destination has spent on the sales source, and includes a contact point number storage means that stores contact items, which are items indicating the quality of contact, in association with evaluation points for the contact items, a labor point storage means that stores labor items, which are items indicating the content of the labor, in association with evaluation points for the labor items, a sales destination designation means for designating a sales destination, an item designation means for designating a contact item or labor item, a date and time input means for inputting the date and time when contact related to the contact item designated by the item designation means occurred or ended, or the date and time when labor related to the labor item was spent, for a sales destination designated by the sales destination designation means, and The system is equipped with an item date and time storage means which stores, for each sales destination, an item specified by an item specification means and a date and time input by a date and time input means in correspondence with each other; a sales destination selection means which selects a sales destination; a graph creation means which creates, for the sales destination selected by the sales destination selection means, a quality graph showing the change in evaluation score for contact items over time, an effort graph showing the change in evaluation score for effort items over time, and a total graph showing the change in evaluation score for contact items and effort items over time, based on the information stored in the item date and time storage means and the evaluation scores stored in the contact score storage means or the effort score storage means; and a graph display means which displays the three graphs created by the graph creation means on a single diagram with a common time axis and score axis. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5759406 [Patent Document 2] Patent No. 6224982 Summary of the Invention [Problem to be solved by the invention]

[0005] In a configuration in which a person in charge newly inputs information into predetermined items when predicting an outcome such as whether or not a case will be concluded, documents created for the case have not been utilized. Therefore, an object of the present invention is to provide an information processing device and an information processing program that can use document files created for a case or a group of messages exchanged between multiple users regarding the case when predicting an outcome such as whether or not a case will be concluded. [Means for solving the problem]

[0006] The gist of the present invention for achieving the above object resides in the following inventions. Please note that the "claims" below refer to the claims as originally filed. The invention of claim 1 is an information processing device comprising a memory and one or more processors, wherein the memory stores document files created for a case or a group of messages exchanged between a plurality of users regarding the case, and wherein the processor extracts information about a target case from the document files or message group stored in the memory, and predicts a conclusion about the target case from the extracted information using artificial intelligence that has previously learned through machine learning to predict a conclusion for the case corresponding to information in the document files or message group for each case.

[0007] The invention of claim 2 is the information processing device of claim 1, wherein the memory stores the message group, and the processor divides the message group into a series of exchanges and then extracts the information for each of the series of exchanges.

[0008] The invention of claim 3 is an information processing device as described in claim 2, in which the processor uses the artificial intelligence by associating two or more pieces of information from "when," "where," "who," "what," "why," and "how" as information extracted from the series of interactions.

[0009] The invention of claim 4 is an information processing device described in any one of claims 1 to 3, wherein the processor extracts multiple different types of information according to multiple different rules, and selects the type of information to be used in the artificial intelligence using the prediction accuracy corresponding to each extracted type of information.

[0010] The invention of claim 5 is an information processing device described in any one of claims 1 to 4, wherein the processor obtains second information related to the extracted information from an external information processing device, associates the extracted information with the second information, and uses the artificial intelligence to predict a conclusion regarding the target case.

[0011] The invention of claim 6 is an information processing device described in any one of claims 1 to 5, wherein the processor extracts the order or interval in which the extracted information is provided to the other party, associates the extracted information with the order or interval, and uses the artificial intelligence to predict a conclusion regarding the target case.

[0012] The invention of claim 7 is an information processing program for causing a computer having a memory and one or more processors, the memory storing document files created for a case or a group of messages exchanged between multiple users regarding the case, to execute a process in which the processor extracts information about a target case from the document files or group of messages stored in the memory, and predicts a conclusion about the target case from the extracted information using artificial intelligence that has previously learned through machine learning to predict a conclusion of the case corresponding to the information in the document files or group of messages for each case. Effect of the Invention

[0013] According to the information processing device of claim 1, when predicting an outcome such as whether or not a case will be concluded, a document file created for the case or a group of messages exchanged between multiple users regarding the case can be used.

[0014] According to the information processing device of claim 2, information can be extracted from a group of messages generated in a series of exchanges.

[0015] According to the information processing device of claim 3, it is possible to correlate two or more pieces of information from among "when," "where," "who," "what," "why," and "how," and make predictions.

[0016] According to the information processing device of claim 4, it is possible to select information to be used for prediction using the accuracy of prediction.

[0017] According to the information processing device of claim 5, prediction can be made by using second information related to the extracted information.

[0018] According to the information processing device of claim 6, it is possible to make a prediction using the order or interval in which the extracted information is provided to the other party.

[0019] According to the information processing program of claim 7, when predicting an outcome such as whether or not a case will be concluded, a document file created for the case or a group of messages exchanged between multiple users regarding the case can be used. [Brief description of the drawings]

[0020] [Figure 1] FIG. 2 is a conceptual module configuration diagram of a configuration example of the present embodiment. [Diagram 2] FIG. 1 is an explanatory diagram showing an example of a system configuration using the present embodiment. [Diagram 3] FIG. 2 is a detailed module configuration diagram of a configuration example of the present embodiment. [Figure 4] 4 is a flowchart showing an example of processing according to the present embodiment. [Diagram 5] 4 is a flowchart showing an example of processing according to the present embodiment. [Figure 6] 4 is a flowchart showing an example of processing according to the present embodiment. [Figure 7]4 is an explanatory diagram illustrating an example of the data structure of a document file management table; [Figure 8] FIG. 4 is an explanatory diagram illustrating an example of a data structure of a message management table. [Figure 9] 11 is an explanatory diagram illustrating an example of a data structure of an information element extraction setting management table; [Figure 10] FIG. 2 is an explanatory diagram showing a processing example according to the present embodiment. [Figure 11] 11 is an explanatory diagram illustrating an example of a data structure of a message group management table; [Figure 12] 4 is a flowchart showing an example of processing according to the present embodiment. [Figure 13] FIG. 13 is an explanatory diagram illustrating an example of the data structure of a prediction / conclusion management table. [Figure 14] 11 is an explanatory diagram illustrating an example of the data structure of a document file order management table; [Figure 15] 11A and 11B are explanatory diagrams showing examples of the order and intervals of document files provided to a partner. [Figure 16] 11 is an explanatory diagram illustrating an example of a data structure of an information element extraction setting management table; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Hereinafter, a preferred embodiment of the present invention will be described with reference to the drawings. FIG. 1 shows a conceptual module configuration diagram of an example of the configuration of this embodiment. In addition, a module generally refers to a logically separable piece of software (including a computer program as an interpretation of "software"), hardware, etc. Therefore, the module in this embodiment refers not only to a module in a computer program, but also to a module in a hardware configuration. Therefore, this embodiment also describes a computer program for functioning as those modules (for example, a program for causing a computer to execute each procedure, a program for causing a computer to function as each means, a program for causing a computer to realize each function), a system, and a method. However, for convenience of explanation, words such as "store" and "store" are used, but these words mean to store in a storage device or to control to store in a storage device when the embodiment is a computer program. In addition, a module may correspond one-to-one to a function, but in implementation, one module may be configured with one program, multiple modules may be configured with one program, or conversely, one module may be configured with multiple programs. In addition, multiple modules may be executed by one computer, or one module may be executed by multiple computers by computers in a distributed or parallel environment. In addition, one module may contain other modules. In the following, the term "connection" is used not only for physical connection but also for logical connection (e.g., data transfer, instruction, reference relationship between data, login, etc.). "Predetermined" means that it is determined before the target processing, and is used to include the meaning that it is determined according to the situation or state at that time or according to the situation or state up to that point, not only before the processing according to this embodiment starts, but also after the processing according to this embodiment starts, so long as it is before the target processing. When there are multiple "predetermined values", each may be a different value, or two or more values ​​("two or more values" includes all values, of course) may be the same. In addition, the description "If A, do B" is used to mean "determine whether A is true, and if it is determined that A is true, do B."However, this does not include cases where it is not necessary to judge whether it is A or not. In addition, when things are listed as "A, B, C", etc., this is an illustrative list unless otherwise specified, and includes cases where only one of them is selected (for example, only A). Furthermore, a system or device may be configured by connecting multiple computers, hardware, devices, etc. via a communication means such as a network ("network" includes one-to-one communication connections), and may also be realized by a single computer, hardware, device, etc. "Device" and "system" are used as synonymous terms. Needless to say, a "system" does not include anything that is merely a social "mechanism" (i.e., a social system) that is an artificial arrangement. Furthermore, for each process by each module, or for each process when multiple processes are performed within a module, the target information is read from the storage device, and after the process is performed, the processing results are written to the storage device. Therefore, the description of reading from the storage device before processing and writing to the storage device after processing may be omitted.

[0022] The information processing device 100 according to the present embodiment has a function of performing a process of predicting a conclusion such as whether or not a deal will be concluded. As shown in the example of FIG. 1, the information processing device 100 has at least a processor 105 and a memory 110, and is configured with a bus 198 for connecting them to exchange data. In addition, the information processing device 100 may have an output device 185, a reception device 190, and a communication device 195. Data is exchanged between the processor 105, the memory 110, the output device 185, the reception device 190, and the communication device 195 via the bus 198.

[0023] The block diagram shown in the example of Fig. 1 also shows an example of the hardware configuration of a computer that realizes this embodiment. The hardware configuration of the computer on which the program of this embodiment is executed is a computer as shown in Fig. 1, specifically a personal computer, a computer that can be a server, etc. As a specific example, a processor 105 is used as a processing unit, and a memory 110 is used as a storage device.

[0024] The number of processors 105 may be one or more. Examples of the processor 105 include a CPU (abbreviation of Central Processing Unit) and a microprocessor. When a plurality of processors 105 are used, the processors may be in the form of either a tightly coupled multiprocessor or a loosely coupled multiprocessor. For example, a single processor 105 may be equipped with a plurality of processor cores. Furthermore, a system may be provided in which a plurality of computers are connected by a communication path and behave virtually as if they were a single computer. As a specific example, the loosely coupled multiprocessor may be configured as a cluster system or a computer cluster. The processor 105 executes a program in the program memory 120.

[0025] The memory 110 may include, for example, semiconductor memory inside the processor 105, such as a register or cache memory, a main memory which is a primary storage device composed of RAM (abbreviation of Random Access Memory) or ROM (abbreviation of Read Only Memory), or an internal storage device such as an HDD (abbreviation of Hard Disk Drive) or SSD (abbreviation of Solid State Drive) having a function as a persistent storage device, an external storage device or auxiliary storage device such as a CD, DVD, Blu-ray (registered trademark) Disc, USB memory, or memory card, or may also include a storage device such as a server connected via a communication line. Memory 110 has a program memory 120 that mainly stores programs, and a data memory 115 that mainly stores data. Note that in addition to the programs of the modules shown in the figure, program memory 120 and data memory 115 may also store programs such as an OS for starting up the computer, and data such as parameters that change as appropriate when the modules are executed.

[0026] The output device 185 includes, for example, a display device 187, a printing device 189, etc. The display device 187, such as a liquid crystal display, an organic EL display, a three-dimensional display, etc., displays the processing results by the processor 105, the data in the data memory 115, etc. as text, image information, etc. The printing device 189, such as a printer, a multifunction device, etc., prints the processing results by the processor 105, the data in the data memory 115, etc. In addition, the output device 185 may include a speaker, an actuator that vibrates a device, etc. The reception device 190 includes, for example, an instruction reception device 192, a document file reader 194, etc. The instruction reception device 192, which includes a keyboard, a mouse, a microphone, a camera (including a gaze detection camera, etc.), etc., receives data based on user operations (including movements, voice, gaze, etc.) on these devices. Also, there may be a device, such as a touch screen, that has the functions of both the display device 187 and the instruction receiving device 192. In that case, even if there are no physical keys, the keyboard function may be realized by drawing a keyboard (also called a software keyboard or a screen keyboard) on the touch screen by software. As a user interface, a display device 187 and an instruction receiving device 192 are mainly used. A document file reading device 194 such as a scanner or a camera reads or photographs a document and accepts the resulting image data as a document file. The communication device 195 is a communication line interface such as a network card for connecting to other devices via a communication line.

[0027] In the present embodiment, in the case of a computer program, a computer program, which is software, is loaded into the program memory 120 of the present hardware configuration, and the present embodiment is realized by the software and hardware resources working together. Note that the hardware configuration shown in FIG. 1 is one example configuration, and the present embodiment is not limited to the configuration shown in FIG. 1, and any configuration capable of executing the modules described in the present embodiment may be used. For example, a GPU (short for Graphics Processing Unit, including GPGPU (short for General-Purpose computing on Graphics Processing Units)) may be used as processor 105, or the execution of some of the modules may be configured using dedicated hardware (for example, an application-specific integrated circuit (a specific example is ASIC (short for Application Specific Integrated Circuit)) or a reconfigurable integrated circuit (a specific example is FPGA (short for Field-Programmable Gate Array))). Some of the modules may be in an external system and connected via a communication line, or multiple systems shown in FIG. 1 may be connected to each other via communication lines and operate in cooperation with each other. In particular, the system may be incorporated in a personal computer, as well as a portable information and communication device (including a mobile phone, a smartphone, a mobile device, a wearable computer, etc.), an information appliance, a robot, a copier, a fax, a scanner, a printer, a multifunction device (an image processing device having two or more functions of a scanner, a printer, a copier, a fax, etc.), etc.

[0028] The processor 105 is connected to the memory 110, the output device 185, the reception device 190, and the communication device 195 via a bus 198. The processor 105 executes processing according to a computer program that describes the execution sequence of each module, which is a program in the program memory 120. For example, upon reception of a user's operation by the instruction reception device 192, the processor 105 executes processing by a module in the program memory 120 that corresponds to the operation, and stores the processing result in the data memory 115, outputs it to the display device 187, or controls the communication device 195 to transmit it to another device.

[0029] The memory 110 includes a data memory 115 and a program memory 120 , and is connected to the processor 105 , the output device 185 , the reception device 190 , and the communication device 195 via a bus 198 . The data memory 115 includes a document file storage area 125 and a message storage area 130 . Document files created for cases are stored in the document file storage area 125. The stored document files may contain meta-information, which will be described later, in addition to the document files themselves. Here, a "case" is an issue to be dealt with, involving multiple people including the person making the proposal or application and the person who issues a decision on it. For example, a salesperson is an example of the person who issues a proposal, and a customer is an example of the person who issues a decision on it. Cases also have a final conclusion. Conclusions can include whether or not a deal will be concluded, success or failure, permission or not, pass or fail, etc. Also, an item may be understood as a group of activities that may result in the above-mentioned conclusion. For example, in communication using a collaboration tool, a group of people (also called a room) is often formed to carry out a group of activities. In the example of the explanation of this embodiment, it is assumed that some unit, such as a room in a collaboration tool, corresponds to an item.

[0030] Messages exchanged among a plurality of users regarding a case are stored in the message storage area 130. The stored messages may include meta-information, which will be described later, in addition to the messages themselves. Note that "a case is exchanged among a plurality of users" does not necessarily mean that all users involved in the case are involved, but may mean that some of the users are involved.

[0031] The "document file or message group" stored in the document file storage area 125 or the message storage area 130 is a target from which character strings are extracted by the information extraction module 135. The "document file or message group" may include meta-information added to the document file or message group in addition to character strings that are the contents of the document file and character strings that are the contents of the messages. Here, meta-information refers to information other than the contents of the document file or message group, but is necessary to configure the document file or message group. For example, meta-information of a document file includes the file name, registration date and time, creator, etc., and meta-information of a message group includes the message sending date and time, sender, recipient, number of characters in the message, contents of the document file attached to the message, meta-information of the attached document file, etc.

[0032] The program memory 120 stores an information extraction module 135 , a learning model module 140 , and a machine learning module 145 . The information extraction module 135 extracts information on a target case from a document file or a message group stored in the data memory 115. As an extraction method, for example, extraction may be performed using a predetermined rule. Also, multiple rules may be used to extract one piece of information. The information extraction module 135 may also divide the messages stored in the message storage area 130 into a series of exchanges, and then extract information for each series of exchanges. Here, a "series of exchanges" refers to an exchange of messages on a certain topic between multiple people from start to finish. For example, if there is a gap in the message exchange that is longer than a predetermined period (specifically, a period during which no messages are sent or received), the series of exchanges may be deemed to have ended. Also, the beginning and end may be determined when a predetermined keyword is found. For example, the character string "First, let's discuss ~" may be determined to be the beginning of the exchange, and the character string "We'll finish" may be determined to be the end of the exchange, and the group of messages in between may be considered a "series of exchanges."

[0033] Furthermore, the information extraction module 135 may extract information from a series of interactions, relating two or more pieces of information from among “when,” “where,” “who,” “what,” “why,” and “how,” and input the information to the learning model module 140 to make predictions. "When," "where," "who," "what," "why," and "how" are the so-called 5W1H (When, Where, Who, What, Why, How), and can be extracted using language processing such as morphological analysis. And, of course, when learning artificial intelligence, it uses training data that associates two or more pieces of information among "when," "where," "who," "what," "why," and "how."

[0034] In addition, the information extraction module 135 may extract multiple different types of information according to multiple different rules, and select the type of information to be used as input to the learning model module 140 using the prediction accuracy corresponding to each extracted type of information. When a final, definitive conclusion is reached for a case, the extracted information and that conclusion are stored in association with each other. For example, if there is information A that is extracted frequently when a contract conclusion is reached, and information B that is extracted frequently both when a contract conclusion is reached and when a non-contract conclusion is reached, the prediction accuracy of information A is set to be higher than that of information B. In this case, information A is selected and used for prediction by the artificial intelligence.

[0035] The information extraction module 135 may also acquire second information related to the extracted information from an external information processing device. Then, the extracted information and the second information may be associated with each other and input to the learning model module 140. Here, the "second information acquired from an external information processing device" may be, for example, information indicating the size of the customer. Information indicating the size of the customer may be, for example, the amount of capital, the number of employees, etc. In addition, the phase of the case may be used, or the number of contacts made by the person in charge with the customer may be used.

[0036] The information extraction module 135 may also extract the order or interval in which the extracted information is provided to the other party. The extracted information may then be associated with the order or interval and input to the learning model module 140. For example, when the order of information provided is set, the possibility of a deal increases when information that is generally provided at the end is provided at the beginning. Also, when the interval between information is long, the possibility of a deal tends to decrease compared to when the interval is short. For this reason, artificial intelligence is used to associate information with the order or interval. Needless to say, artificial intelligence learns using teacher data that associates information with the order or period in which that information was provided.

[0037] The learning model module 140 predicts a conclusion for a target case from the information extracted by the information extraction module 135. The learning model module 140 is a model that has learned in advance by machine learning to predict the conclusion of a case corresponding to the information in the document file or message group for each case. The "conclusion" may be a binary value such as "conclude" or "not conclude", or may be a probability of conclusion indicating the proportion of cases where a contract will be concluded. Of course, it may also be a probability of non-conclusion indicating the proportion of cases where a contract will not be concluded. Furthermore, the learning model module 140 may input the information extracted by the information extraction module 135 and the second information in association with each other, and predict a conclusion regarding the target case. Furthermore, the learning model module 140 may input the information extracted by the information extraction module 135 in association with the order or interval, and predict a conclusion for the target case.

[0038] The machine learning module 145 learns in advance by machine learning to predict the conclusion of a case corresponding to information in a document file or a group of messages for each case, and generates the learning model module 140. For example, for a past case whose conclusion has been determined, the learning model module 140 is generated by machine learning using teacher data that pairs a document file created for the case or a group of messages exchanged between multiple users regarding the case and the conclusion in the case. Machine learning is a method of automatically learning a model that classifies unknown data into several predefined categories from a set of data, and machine learning methods such as a decision tree, a Naive Bayes model, a decision list, a support vector machine, a maximum entropy method, a conditional random field, a convolutional neural network, and a recurrent neural network may be used. The learning model module 140 generated by the machine learning module 145 predicts a desired outcome from information that is a plurality of factors. Here, the desired outcome is the outcome of a case. Furthermore, the machine learning module 145 may perform machine learning to improve the prediction accuracy in comparison with the track record of the outcome of the case.

[0039] FIG. 2 is an explanatory diagram showing an example of a system configuration using this embodiment. The information processing device 100, the user terminal 210A, the user terminal 210B, the attendance management system 250, the customer information management system 260, and the sales support system 270 are connected to each other via a communication line 290. The communication line 290 may be wireless, wired, or a combination of these, and may be, for example, the Internet, an intranet, or the like as a communication infrastructure. Furthermore, the functions of the information processing device 100 may be realized as a cloud service.

[0040] For example, a sales user creates a document file to be submitted to a customer for a certain case using the user terminal 210. The user also exchanges messages with the customer, superiors, colleagues, etc., in order to close the case. For example, a collaboration tool is used to exchange messages and accumulate document files. Then, the user or the superior uses the information processing device 100 when he or she wishes to predict whether or not the case will be concluded. In a file management type collaboration tool, the target is a document file. In a chat type collaboration tool, the target is a message and a document file attached to the message. In addition to collaboration tools, a message function in a bulletin board system or SNS (short for Social Networking Service) may also be used.

[0041] The information processing device 100 extracts information from document files or message groups created for a target case according to predetermined rules, predicts whether the case can be closed using artificial intelligence that has performed machine learning, and presents the prediction result to the requester, the user, or the superior. Note that for cases that have been concluded in the past, the machine learning uses a set of information extracted according to the above-mentioned rules from the conclusions, document files, or message groups created for the case as training data. Note that the user is not required to input any new information in order to make this prediction. In other words, the prediction is made using document files created for the case and messages exchanged regarding the case, so there is no need to input any new information for the prediction.

[0042] FIG. 3 is a detailed module configuration diagram of an example of the configuration of this embodiment. The information processing device 300 includes an information extraction module 335 and a contract likelihood prediction learning model module 340 . The information extraction module 335 includes a message group creation module 302 , an information element extraction module 304 , an information element occurrence frequency calculation module 306 , an other system linkage module 308 , and an information element narrowing down module 310 . The message group creation module 302 is connected to an information element extraction module 304 , a document file DB 325 , and a message DB 330 . The information element extraction module 304 is connected to the message group creation module 302 , the information element occurrence frequency calculation module 306 , and the information element narrowing down module 310 . The information element occurrence frequency calculation module 306 is connected to the information element extraction module 304 and the contract likelihood prediction learning model module 340 . The other system linkage module 308 is connected to an information element narrowing down module 310 , a time attendance management system 250 , a customer information management system 260 , a sales support system 270 , and case success / failure information 392 . The information element narrowing down module 310 is connected to the information element extraction module 304 , the other system linkage module 308 , and the deal likelihood prediction learning model module 340 . The document file DB 325 is connected to the message group creation module 302 . The message DB 330 is connected to the message group creation module 302 . The contract likelihood prediction learning model module 340 is connected to the information element occurrence frequency calculation module 306 , the information element narrowing down module 310 , the user 390 , and the case success / failure information 392 . The attendance management system 250 , the customer information management system 260 , and the sales support system 270 are connected to an other system linkage module 308 .

[0043] The information extraction module 335 corresponds to the information extraction module 135 of the information processing device 100, the likelihood of closing prediction learning model module 340 corresponds to the learning model module 140 and machine learning module 145 of the information processing device 100, the document file DB 325 corresponds to the document file memory area 125 of the information processing device 100, and the message DB 330 corresponds to the message memory area 130 of the information processing device 100.

[0044] The case success / failure information 392 is information indicating whether or not the case has been concluded. The information processing device 300 acquires the case success / failure information 392, for example, by manual input by the user 390 or by the information element extraction module 304. The message group creation module 302 groups together a plurality of messages related to one exchange related to a case into a message group, from among the messages in the message DB 330 .

[0045] The information element extraction module 304 extracts information elements from messages and document files (including document files attached to messages) from the message DB 330 and document file DB 325. An information element is an information element extracted from a target message or document file according to predetermined rules. Here, rules are predefined for extracting information elements that may be related to the conclusion of a case. Also, according to a plurality of rules, a plurality of different types of information elements (hereinafter, information element types) are extracted. Note that a plurality of rules may be predefined for extracting information elements of one information element type. The information element narrowing module 310 narrows down the information elements to be passed to the contract likelihood prediction learning model module 340 so as to more accurately predict the contract likelihood. Note that the information element narrowing module 310 is not a required component, and the information elements extracted by the information element extraction module 304 may be passed directly to the contract likelihood prediction learning model module 340.

[0046] The information element occurrence frequency calculation module 306 calculates the occurrence frequency of the information element by using the occurrence time information of the information element and the type information of the information element. Note that the information element occurrence frequency calculation module 306 is not a required configuration, and the contract likelihood prediction learning model module 340 may perform prediction without using the occurrence frequency of the information element. The contract likelihood prediction learning model module 340 predicts the contract likelihood from the information elements extracted by the information element extraction module 304. Furthermore, the prediction may be made using the information elements narrowed down by the information element narrowing down module 310, or the occurrence frequency of the information elements calculated by the information element occurrence frequency calculation module 306. In addition, the deal likelihood prediction learning model module 340 uses the deal success / failure information 392 to perform further machine learning and improve prediction accuracy.

[0047] The document DB 325 stores document files exchanged using collaboration tools. The message DB 330 stores messages exchanged in the collaboration tool.

[0048] The other system cooperation module 308 cooperates with other systems (the attendance management system 250, the customer information management system 260, the sales support system 270) to acquire information elements. The other systems include, for example, a sales support system 270 which is a core system for recording the success or failure of cases, a attendance management system 250 which records attendance information of sales representatives, and a customer information management system 260 which manages customer information. An example of the customer information management system 260 is a CRM (short for Customer Relationship Management) system. An example of the sales support system 270 is an SFA (short for Sales Force Automation) system. The following are examples of taking into account information elements that are itemized, managed, and recorded in other systems. -Examples of newly added information elements The information element [customer size] may not be obtained from the document file or message, but may be obtained from other systems such as a CRM system. Examples of alternative information elements The information element of [Phase of the case] may be obtained from a document file or message and managed in an SFA system, and the information obtained from the SFA system may be more accurate. In this case, the information in the SFA system can be used without extracting it from the document file or message. Example of improved accuracy through addition For the information element [number of contacts with customers], by obtaining information on outings from the attendance management system 250 in addition to the content obtained from the document file or message, it is possible to identify the dates of outings and calculate the number of contacts with greater accuracy. Furthermore, even in situations where the CRM system does not record drop-in level visits, the number of contacts can be extracted with greater accuracy by using the number of contacts extracted from document files or messages.

[0049] 4 is a flowchart showing an example of processing according to this embodiment (mainly, information extraction module 135). Processing according to this flowchart is performed for the target case. In step S402, an information element extraction setting is read. For example, an information element extraction setting management table 900 is read. FIG. 9 is an explanatory diagram showing an example of the data structure of the information element extraction setting management table 900. The information element extraction setting management table 900 has an information element type column 905, a search word column 910, and an extraction rule column 915. The information element type column 905 stores the type of information element. The search word column 910 stores a search word for extracting the type of the information element. For example, the search word is a search word when searching the title of a document file or a message, or the entire text of a document file or a message. The extraction rule column 915 stores a rule for extracting the type of the information element. For example, the first line of the information element extraction setting management table 900 indicates that the information element type "visit count" has a search word of "visit" and an extraction rule of "visit count.+(￥d+)", and the second line indicates that the information element type "competitive information" has a search word of "competitive" and an extraction rule of "competitive product name [(.+)]". Note that regular expressions are used as the extraction rules. The aforementioned "visit count.+(￥d+)" means that any character is repeated one or more times after "visit count", followed by one or more numeric characters. For example, a character string such as "visit count 5" is matched, and "5" is extracted as an information element of the information element type "visit count".

[0050] In step S404, it is determined whether or not there is any unprocessed setting, and if there is, the process proceeds to step S406, otherwise the process ends (step S499). In step S406, one unprocessed setting is obtained, and the search word and extraction rule (regular expression) are read in. This corresponds to the search word column 910 and extraction rule column 915 of the information element extraction setting management table 900 described above.

[0051] In step S408, document files registered since the previous processing time are searched for using the search word, and matching document files are obtained. In step S410, it is determined whether or not there is an unprocessed document file. If there is, the process proceeds to step S412; otherwise, the process returns to step S404.

[0052] In step S412, one unprocessed document file is taken out, and the extraction rules are applied to extract information elements. In step S414, the target case and information elements are temporarily stored for use in later processing, and the process returns to step S410. In other words, the extracted information elements are stored for each case. The stored information elements are used to predict whether the case will be concluded.

[0053] In addition, although the flowchart shown in the example of Fig. 4 shows an example of a process for extracting information elements from a document file, an example of a process for extracting information elements from a message can be performed in the same way. In other words, it is sufficient to read "document file" in the flowchart shown in the example of Fig. 4 as "message".

[0054] FIG. 5 is a flowchart showing an example of processing according to this embodiment (mainly, the machine learning module 145). In step S502, the success / failure information of the case is read in. That is, for cases whose past success / failure has been confirmed, the success / failure information is read in. In step S504, the success / failure information of the case and the corresponding information elements of the case are input and learning is performed. In other words, learning is performed using the pair of the success / failure information of the case and the corresponding information elements of the case as teacher data. Of course, the information elements can be extracted for the target case according to the flowchart shown in the example of FIG.

[0055] FIG. 6 is a flowchart showing an example of processing according to this embodiment (mainly, the learning model module 140). In step S602, the success / failure information of the case is read. In step S604, the information elements of the case that do not correspond to the success / failure information of the case are input to predict the likelihood of the case being concluded. Here, "cases that do not correspond to the success / failure information of the case" refer to cases whose success / failure has not been determined. The process of step S602 may be set to "accept a case for which the outcome is to be predicted," and the process of step S604 may be set to "input information elements of the case and predict the likelihood of closing the case." In step S606, a list of cases and the likelihood of closing is output.

[0056] The target document file is managed, for example, by a document file management table 700. FIG. 7 is an explanatory diagram showing an example of the data structure of the document file management table 700. The document file management table 700 has a document file ID column 705, a document file name column 710, a message ID column 715, and a content column 720. In this embodiment, the document file ID column 705 stores information for uniquely identifying a document file (specifically, a document file ID: an abbreviation for IDentification). The document file name column 710 stores the name of the document file. In this embodiment, the message ID column 715 stores information for uniquely identifying a message (specifically, a message ID). For example, it stores the message ID to which the document file was attached. The content column 720 stores the content of the document file. For example, the first line of document file management table 700 indicates that the document file ID "document file a" has a document file name "schedule proposal", a message ID "100", and content "The schedule for patent review in fiscal year 2012 is...", while the second line indicates that the document ID "document file b" has a document file name "questionnaire", a message ID "100", and content "Question 1...". Both document file a and document file b are document files that were attached to message ID: 100. In this document file management table 700, it is possible to extract which case the document file corresponds to by referring to the value "100" in the message ID column 715 and referring to the case ID column 825 of the row in the message management table 800 where the value in the message ID column 805 is "100." Also, a case ID column may be provided in the document file management table 700 so that each document file can be associated with a case.

[0057] The target messages are managed, for example, by a message management table 800. FIG. 8 is an explanatory diagram showing an example of the data structure of the message management table 800. The message management table 800 has a message ID column 805, a message column 810, a poster column 815, a creation date column 820, and a case ID column 825. The message ID column 805 stores the message ID. The message column 810 stores the content of the message. The poster column 815 stores the poster of the message. The creation date column 820 stores the creation date of the message (which may include the hour and minute, etc.). In this embodiment, the case ID column 825 stores information for uniquely identifying a case (specifically, a case ID). For example, the first row of message management table 800, message ID "100", indicates that the message is "I explained the proposal to Mr. XX. On the spot...", the poster is "User A", the creation date is "2019 / 10 / 10", and the case ID is "Case A", and the second row, message ID "101", indicates that the message is "Regarding the question that was supposed to be taken home, we have confirmed...", the poster is "User B", the creation date is "2019 / 11 / 20", and the case ID is "Case A".

[0058] 10 is an explanatory diagram showing an example of processing according to this embodiment. For example, in a communication tool of a collaboration tool, a display like a message display screen 1000 is performed for the exchange of messages regarding one particular case. The message display screen 1000 displays a title column 1005, a poster column 1010, a date and time column 1015, and an attached document file column 1020. The title column 1005 displays the title of the message, the poster column 1010 displays the poster of the message, the date and time column 1015 displays the date and time of posting, and the attached document file column 1020 displays information indicating whether or not an attached document file is present. For example, the first line of the message display screen 1000 has the title "Customer visit: Report on 10 / 1.", which indicates that the poster is "A", the date and time is "2020 / 10 / 1 15:00", and there is no attached file. The second line has the title "Materials introduced to the customer (attached file)," which indicates that the poster is "A", the date and time is "2020 / 10 / 1 15:02", and there is an attached file. The third line has the title "Received.", which indicates that the poster is "B", the date and time is "2020 / 10 / 1 16:00", and there is no attached file. The fourth line has the title "Comment.", which indicates that the poster is "B", the date and time is "2020 / 10 / 1 The fifth line has the title "Proposal created. (Attachment)" which indicates that the poster is "A", the date and time is "2020 / 10 / 2 10:00", and an attached file is "Yes", the sixth line has the title "Reference material. (Attachment)" which indicates that the poster is "C", the date and time is "2020 / 10 / 2 10:30", and an attached file is "Yes", and the seventh line has the title "Corrections made. (Attachment)" which indicates that the poster is "A", the date and time is "2020 / 10 / 2 11:15", and an attached file is "Yes".

[0059] 10, these messages are divided into a series of exchanges. The results of this division are managed, for example, in a message group management table 1100. 11 is an explanatory diagram showing an example of the data structure of a message group management table 1100. The message group management table 1100 has a group ID column 1105a and a group ID column 1105b. Each group ID column 1105 has a message ID column 1110 and an attached document file column 1115. Message group 1 contains messages 1 to 4, and message 2 has an attached document file. Message group 2 includes messages 5 to 7, and messages 5, 6, and 7 each include an attached document file. Note that message n corresponds to a line on the message display screen 1000 shown in the example of FIG.

[0060] In this example, multiple messages posted in relation to a single item are divided into message group 1 and message group 2 according to the posting date and time of the messages. For example, in a chat-type collaboration tool, a series of exchanges on one topic may take place. The series of exchanges may consist of a number of messages and document files attached to the messages. In this example, consecutively posted messages are determined to belong to the same topic, and if a message is posted within a predetermined time from the previous message, the two messages are determined to belong to the same group, and the messages are grouped. In the example of FIG. 11, the predetermined time is set to one hour, and grouping is performed. Specifically, messages 1 to 4 were posted within one hour each, and messages 5 to 7 were also posted within one hour each, and there is an interval longer than one hour between messages 4 and 5, so grouping is performed as shown in the example of FIG. 11. By doing this, for example, if a message such as "Customer visit: Report from 10 / 1" or "Materials introduced to the customer (attached file)" is posted, even if the visit date and time is not written in the attached file of the case study introduction material, it is possible to extract that the materials were developed during the visit on 10 / 1 from the immediately preceding message belonging to the same group. In other words, if an information element cannot be extracted from a document file using the information element extraction setting management table 900, the information element may be extracted from a series of messages (one of the grouped messages) in the exchange that includes a message corresponding to that document file.

[0061] FIG. 12 is a flowchart showing an example of processing according to this embodiment. In step S1202, the messages are divided into groups. In step S1204, linguistic processing is performed on the messages in the group to extract information elements of the 5W1H. Note that it is not necessary to use all of the 5W1H, and it is sufficient to extract two or more of them.

[0062] In step S1206, the data is input to the contract likelihood prediction learning model module 340. At that time, the data is input to the contract likelihood prediction learning model module 340 in association with the 5W1H extracted in step S1204. In step S1208, prediction is performed by the contract likelihood prediction learning model module 340. In step S1210, the prediction result is output.

[0063] Similarly, in machine learning, after the processes from step S1202 to step S1206 are performed, machine learning is performed using training data that pairs the information elements of 5W1H with a conclusion.

[0064] An example will be described in which the prediction accuracy corresponding to the extracted information elements is used to select information elements to be input to the learning model module 140. An example of the narrowing down process by the information element narrowing down module 310 is shown. 13 is an explanatory diagram showing an example of the data structure of a prediction / conclusion management table 1300. The prediction / conclusion management table 1300 has an input information element column 1305, a prediction result column 1310, and a conclusion column 1315. The input information element column 1305 stores information elements input to the learning model module 140. The prediction result column 1310 stores the prediction result by the learning model module 140 in that case. The conclusion column 1315 stores the actual conclusion of the case. For example, the first line of the prediction / conclusion management table 1300 indicates that the prediction result of the input information elements "information elements A, C, D, E" is "concluded" and the conclusion is "concluded", the second line indicates that the prediction result of the input information elements "information elements A, F, G, H" is "concluded" and the conclusion is "concluded", the third line indicates that the prediction result of the input information elements "information elements B, C, G, H" is "concluded" and the conclusion is "not concluded", and the fourth line indicates that the prediction result of the input information elements "information elements B, F, D, E" is "concluded" and the conclusion is "not concluded". Note that information elements with different alphabets are information elements of different information element types.

[0065] Cases where the prediction result by the learning model module 140 differs from the actual conclusion (for example, the prediction result is a contract but the conclusion is not a contract, or conversely, the prediction result is not a contract but the conclusion is a contract) are collected, and among the information elements used for prediction in those cases, information elements that are commonly used are not used. In the example of Figure 13, information element B used commonly in the third and fourth lines corresponds to this, and the information element type corresponding to information element B is not used for prediction from the next time onwards. Note that an "information element" is, for example, the value "5 (times)" in the "number of contacts with customers", and the narrowing down here does not mean that the value is not used (5 is not used), but that the "number of contacts with customers" itself is not used because it does not contribute to success or failure. In addition, when the prediction result by the learning model module 140 matches the actual conclusion (for example, when the prediction result is a contract and the conclusion is also a contract, or conversely, when the prediction result is a non-contract and the conclusion is also a non-contract), among the information elements used in the predictions in those cases, the information element type corresponding to the information element used in common is not deleted. In the example of FIG. 13, the information element A used in common in the first and second lines corresponds to this, and the information element A is not deleted from the next prediction onwards. In other words, even if an information element is to be deleted when the prediction result by the learning model module 140 differs from the actual conclusion, if it is an information element that is commonly used when the prediction result by the learning model module 140 matches the actual conclusion, it is not to be deleted.

[0066] Next, an example of extracting the order or interval at which extracted information elements are provided to the other party will be described. For example, if the interval between providing document files becomes long due to a slow response from a customer, it is predicted that the customer has low interest in the product. Also, if an estimate is submitted early, it is predicted that the customer has high interest in the product. 14 is an explanatory diagram showing an example of the data structure of a document file order management table 1400. The document file order management table 1400 has a document file ID column 1405, a group ID column 1410, an intra-group order column 1415, a preceding interval column 1420, and a following interval column 1425. The document file ID column 1405 stores a document file ID. The group ID column 1410 stores a group ID. The intra-group order column 1415 stores an intra-group order. The preceding interval column 1420 stores a preceding interval. The following interval column 1425 stores a following interval. The document file order management table 1400 indicates, after messages are grouped, the order in which document files attached to messages in the group were generated, and the intervals between the document files that were generated before and after the messages in the group. For example, as shown in the example of FIG. 15, the first row of document file order management table 1400 indicates that document file ID "00100" (document file 1520) belongs to group ID "00070," is the "5th" document file in the group, the interval between the preceding document file 1510 (previous interval 1515) is "3 days," and the interval between the subsequent document file 1530 (next interval 1525) is "10 days." Then, the extracted information is associated with the order or interval and input to the learning model module 140 to make a prediction. Of course, in machine learning, similarly, the order or interval within a group of information elements can be extracted, associated with each other to create training data, and machine learning can be performed. Although a document file is exemplified, the order or interval in which messages are provided to the recipient within a group may be used.

[0067] Instead of the information element extraction setting management table 900, an information element extraction setting management table 1600 may be used. 16 is an explanatory diagram showing an example of the data structure of an information element extraction setting management table 1600. The information element extraction setting management table 1600 has an information element type column 1605, an extraction source column 1610, and an extraction rule column 1615. The information element type column 1605 stores information element types. The extraction source column 1610 stores extraction sources. The extraction rule column 1615 stores extraction rules. The first line of the information element extraction setting management table 1600 has the information element type "number of contacts with customers" and the extraction source "daily report file." The extraction rule is "extract the number of visits or visit dates by matching with a regular expression. For example, there is the following regular expression. · Number of visits this week: (￥d+) times, · Number of visits this month: (￥d+) times, -Visit date: ￥d+ / ￥d+". The second line has the information element type as "Type of information provided during the visit" and the extraction source as "Proposal and case study provided to the customer." The extraction rule is, "Extract [Proposal], [Case Study Development], etc. as information types. The type of information provided is determined by regular expression matching of the file name. For example, there is the following regular expression. ·.*Proposal, ·.*Case Studies In addition, the date of visit is obtained from the message with the file attachment and the messages before and after it." The third line has the information element type "amount of information provided during the visit" and the extraction source "proposals and case studies provided to the customer." The extraction rule is: "The amount of information is calculated based on the number of pages. -The amount of information is calculated based on the number of sentences included. In addition, the date of visit is obtained from the message with the file attachment and the messages before and after it." The fourth line has the information element type as "information type obtained from customer" and the extraction source as "message, meeting memo, daily report file". The extraction rule is "Extract information types such as questions from customers and issues customers are facing. Create a dictionary of phrases like the ones below and determine the information type by matching with the phrases. Customer questions -> questions from customers, Issues heard -> issues customers are facing. In this way, information elements are extracted from before and after the matching phrases." The fifth line states that the information element type is "amount of information obtained from the customer," the extraction source is "message, meeting notes, daily report file," and the extraction rule is "calculate the amount of information based on the number of sentences it contains." The sixth line has "Sales Phase" as the information element type, "Message, Minutes, Daily Report File" as the extraction source, and the extraction rule as follows: "Sales activities have phases depending on the progress of the project. For example, it goes through stages such as [inquiry], [visit], [proposal], [quote], and [contract]. Depending on the progress of the project, the information exchanged in reports and communications also differs. Therefore, for example, a dictionary of phrases that are frequently used in the [inquiry] phase (inquiry, product information response, etc.) can be created, and if many of these words are included, it can be determined that it is in the [inquiry] phase." The seventh line has the information element type as "job title of the person in charge at the contacted company," the extraction source as "message, minutes, daily report file," and the extraction rule as "extract job titles by matching with words that represent job titles." For example, the following character string is extracted: ·Chief, Managing Director, -President." The 8th line has the information element type as "competitive information", the extraction source as "memorandum, attachments", and the extraction rule as "Extract information on other companies and similar products obtained from customers. For example, A dictionary of competing company names; A dictionary of competing product names; "We create a dictionary of phrases that refer to competing products, such as [competitor], [other company], and [.+ company under consideration], and extract competitive information by matching words."

[0068] The program described above may be provided by storing it in a recording medium, or the program may be provided via a communication means. In that case, for example, the program described above may be regarded as an invention of "a computer-readable recording medium on which a program is recorded." "Computer-readable recording medium on which a program is recorded" refers to a computer-readable recording medium on which a program is recorded, which is used for installing, executing, distributing, etc. a program. Examples of recording media include digital versatile discs (DVDs) such as "DVD-R, DVD-RW, DVD-RAM, etc." which are standards established by the DVD Forum, and "DVD+R, DVD+RW, etc." which are standards established for DVD+RW, compact discs (CDs) such as read-only memories (CD-ROMs), CD recordables (CD-Rs), CD rewritables (CD-RWs), Blu-ray (registered trademark) Discs, magneto-optical discs (MOs), flexible disks (FDs), magnetic tapes, hard disks, read-only memories (ROMs), electrically erasable and rewritable read-only memories (EEPROMs, registered trademarks), flash memories, random access memories (RAMs), and SD (short for Secure Digital) memory cards. The whole or a part of the program may be recorded on the recording medium and stored or distributed, etc. Also, the program may be transmitted by communication using a transmission medium such as a wired network used in a local area network (LAN), metropolitan area network (MAN), wide area network (WAN), the Internet, an intranet, an extranet, etc., a wireless communication network, or a combination of these, or may be transmitted on a carrier wave. Furthermore, the program may be a part or the whole of another program, or may be recorded on a recording medium together with a separate program, or may be divided and recorded on a plurality of recording media, or may be recorded in any manner that allows restoration, such as compression or encryption. [Explanation of symbols]

[0069] 100...Information processing device 105…Processor 110…Memory 115…Data memory 120…Program memory 125...Document file storage area 130: Message storage area 135…Information extraction module 140…Learning model module 145…Machine learning module 185...Output device 187…Display device 189...Printing device 190...Reception device 192...Instruction reception device 194...Document file reader 195...Communication equipment 198…Bus 210...User terminal 250...Attendance management system 260…Customer Information Management System 270…Sales Support System 290…Communication lines 300...Information processing device 302...Message group creation module 304... Information element extraction module 306... Information element occurrence frequency calculation module 308…Other system linkage module 310... Information element refinement module 325...Document file database 330...Message DB 335…Information Extraction Module 340…Probability of closing prediction learning model module 390...User 392… Case success / failure information

Claims

1. A memory and one or more processors, The memory stores a document file created for a case or a group of messages exchanged between a plurality of users regarding the case, The processor, Extracting information on a subject matter from a document file or a message group stored in said memory; By using artificial intelligence that has learned through machine learning to predict the outcome of a case based on the information in the document file or message group for each case, predicting an outcome for the subject matter from the extracted information; The plurality of users includes at least sales representatives and customers; The conclusion includes at least whether or not the contract can be concluded, In the machine learning, when there is first information extracted when a conclusion of a contract is reached and second information extracted when both a conclusion of a contract and a conclusion of a contract are reached, machine learning is performed so that the first information is extracted with a higher prediction accuracy than the second information. Information processing device.

2. the memory stores the message group; The processor, Dividing the message group into a series of exchanges and then extracting the information for each of the series of exchanges. The information processing device according to claim 1 .

3. The processor, The information extracted from the series of interactions is related to two or more pieces of information among "when," "where," "who," "what," "why," and "how," and the artificial intelligence after learning is used. The information processing device according to claim 2 .

4. The processor, Extracting multiple different types of information according to multiple different rules; Selecting a type of information to be used in the artificial intelligence after the learning using the prediction accuracy corresponding to each type of extracted information. The information processing device according to claim 1 .

5. The processor, acquiring second information related to the extracted information from an external information processing device; Associating the extracted information with the second information, and predicting a conclusion regarding the target case using the artificial intelligence after the learning. The information processing device according to claim 1 .

6. The processor, Extracting the order or interval in which the extracted information was provided to the other party; Associating the extracted information with the order or interval, and using the learned artificial intelligence to predict an outcome for the target case. The information processing device according to claim 1 .

7. A computer having a memory and one or more processors, the memory comprising: storing document files created for a case or messages exchanged between a plurality of users regarding the case; The processor, Extracting information on a subject matter from a document file or a message group stored in said memory; By using artificial intelligence that has learned through machine learning to predict the outcome of a case based on the information in the document file or message group for each case, predicting an outcome for the subject matter from the extracted information; The plurality of users includes at least sales representatives and customers; The conclusion includes at least whether or not the contract can be concluded, In the machine learning, when there is first information extracted when a conclusion of a contract is reached and second information extracted when both a conclusion of a contract and a conclusion of a contract are reached, machine learning is performed so that the first information is extracted with a higher prediction accuracy than the second information. An information processing program for executing processing.

Images