Machine learning device, information processing device, inference device, machine learning method, information processing method, and inference method

Abstract

Provided is an information processing apparatus capable of performing customer relationship management by a simple method based on easily obtainable data. 【Solution means】The information processing apparatus 2 includes an order-related data acquisition unit 203A that acquires order-related data related to an order from a customer, and a business situation acquisition unit 203B that acquires a business situation regarding the business situation of a customer by inputting situation inference model input information based on the order-related data into a situation inference model 220. The situation inference model 220 is a learned inference model obtained by machine learning of the correlation between situation inference model input information D30 based on order-related data attached to an order from a customer and the business situation regarding the business situation of a customer.

Description

Technical Field

[0001] The present invention relates to a machine learning device, an information processing device, an inference device, a machine learning method, an information processing method, and an inference method.

Background Art

[0002] In recent years, CRM (Customer Relationship Management) has attracted attention, and systems for performing CRM have been developed. For example, Patent Document 1 discloses a system that creates a coordinate space as an evaluation map based on various data related to the relationship with customers, determines virtual coordinates for temporarily arranging processing target data in the coordinate space according to the evaluation of the processing target data using the evaluation axis as an index, and performs recommendation of the processing target data based on the virtual coordinates on the evaluation map.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technology of Document 1 above, it is necessary to acquire various data related to the relationship with customers, and since analysis processing is performed using these data, there are problems in terms of difficulty in obtaining data and complexity of processing.

[0005] The present invention has been made paying attention to the above problems, and an object thereof is to provide an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method capable of performing customer relationship management by a simple method based on easily acquirable data.

Means for Solving the Problems

[0006] To achieve the above object, a machine learning device according to an aspect of the present invention includes a learning data acquisition unit that acquires a plurality of situation inference model input information based on order-related data related to an order from a customer as learning data, a machine learning unit that uses the plurality of pieces of learning data acquired by the learning data acquisition unit to cause a situation inference model to learn the correlation between the situation inference model input information and the business situation regarding the business of the customer, and a learned model storage unit that stores the situation inference model in which the machine learning unit has learned the correlation.

Advantages of the Invention

[0007] According to an information processing apparatus according to an aspect of the present invention, it is possible to determine the situation in a customer's business by utilizing data that has already been acquired when receiving an order, and it is possible to perform customer relationship management by a simple method based on easily acquirable data.

[0008] Problems, configurations, and effects other than the above will be clarified in the mode for carrying out the invention described later.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0010] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. In the following, the scope necessary for the description for achieving the object of the present invention is schematically shown, and mainly the scope necessary for the description of the corresponding part of the present invention will be described, and the parts where the description is omitted shall be based on known techniques.

[0011] FIG. 1 is an overall configuration diagram showing an example of the customer situation determination system 1 according to the embodiment. FIG. 2 is a diagram showing an example of various data related to a new order. FIG. 3 is a diagram showing an example of various data related to an existing order.

[0012] The customer situation determination system 1 is a system that receives an order from the user U and determines the business situation of the customer who placed the order. Further, the customer situation determination system 1 is a system that registers and manages various types of information for reference when determining the business situation of the customer in the database 210. Here, the business situation of the customer means whether the customer's business related to the order is as before. When the business is as before, it can be said that the business situation of the customer is normal. On the other hand, when the business is not as before, it can be said that the business situation of the customer is abnormal.

[0013] As an example, the order may be an order related to a processed product manufactured by performing one or more processing steps on a material by various processing apparatuses or manual work based on drawing information. Specifically, examples of the order include, for example, machined products by machining, buildings by construction processing, clothing products by cutting and sewing processing, etc. In the present embodiment, the case where the order is a machined product based on drawing information will be mainly described.

[0014] When determining the customer's situation, the main data input into the customer situation determination system 1 is order-related data D10 related to a new order, as shown in FIG. 2. As an example, the order-related data D10 includes order information D11, quotation information D12, performance information D13, and profit and loss information D14.

[0015] When determining the customer's situation, the main data referred to by the customer situation determination system 1 is order-related data D20 related to an existing order, as shown in FIG. 3. Similar to the above, as an example, the order-related data D20 includes order information D21, quotation information D22, performance information D23, and profit and loss information D24. These data are registered and accumulated in the database 210.

[0016] When determining the customer's situation, the main data output as a determination result from the customer situation determination system 1 is determination result D50 (see FIG. 6). As an example, the determination result D50 is binary data indicating whether the customer's business situation is normal or abnormal.

[0017] The order information D11 and D21 are information regarding the content of the order. As an example, it includes at least one of drawing information, order date and time, product name, dimensions, material, quantity, delivery date, and person in charge in the order, but is not limited to this example.

[0018] The drawing information is data recording the design drawing or assembly drawing of the order. The drawing information includes not only the outline of the order but also various lines such as center lines and dimension lines, as well as characters, numbers, symbols, notations, etc. (not shown) for instructing the processing process.

[0019] The drawing information may be either 2D data (such as a plan view or a sectional view) or 3D data (stereoscopic information), and may be in either vector format or raster format. The drawing information may be, for example, CAD data (an example of vector format) output by various CAD software, or image data (an example of raster format) output by reading a drawing printed on a paper medium using a scanner or the like. In the case of 3D data, it may be handled as 2D data after undergoing a conversion process to convert the 3D data into 2D data. In this embodiment, the case where the drawing information is 2D data will be mainly described.

[0020] Dimensions are those that express the outer shape of the raw material before processing or the outer shape of the order after processing using two or more variables. As dimensions, for example, dimension expressions such as three variables of width × length × thickness, three variables of outer diameter × inner diameter × length, and two variables of outer diameter × length are used, but are not limited thereto. Note that different dimension expressions can also be used according to the shape category. For example, when the shape category is "plate", a dimension expression with three variables of width × length × thickness is used, and when the shape category is "rod" or "tube", a dimension expression with three variables of outer diameter × inner diameter × length can be used.

[0021] The order date and time is the date and time when the order was received. The product name is the name of the processed product for which the order was received. The material is what indicates the material of the raw material before processing. The material may be specified by either the official name or the abbreviated name. The quantity is the number of processed products for which the order was received. The delivery date is the date by which the processed product for which the order was received is to be delivered. The person in charge is the name of the person in charge of the customer who placed the order.

[0022] The quotation information D12, D22 is information regarding the quotation, and as an example, includes at least one of the contact date and time, the quotation amount, and the response deadline, but is not limited to this example. The contact date and time is the date and time when the quotation was sent to the customer. The quotation amount is the amount of the quotation presented to the customer for the said order. The response deadline is the date when an order is to be placed after the quotation has been sent.

[0023] The performance information D13 and D23 is information regarding the performance of received or lost orders. As an example, it includes at least one of the order receipt date and time, the lost order date and time, and the delivery date and time, but is not limited to this example. The order receipt date and time is the date and time when an order contact is received from a customer. The lost order date and time is the date and time when a contact indicating that the customer will not place an order is received. The delivery date and time is the date and time when the processed products in the order are delivered.

[0024] The profit and loss information D14 and D24 is information regarding the profit and loss in the manufacture of processed products based on orders. As an example, it includes at least one of the drawing gross profit and the project gross profit, but is not limited to this example. The drawing gross profit is the gross profit of the processed products in terms of drawing units in the order. The project gross profit is the gross profit of the order in terms of project units.

[0025] As shown in FIG. 1, the customer situation determination system 1 includes an information processing device 2 and a user terminal device 3. The information processing device 2 and the user terminal device 3 are connected to a wired or wireless network 4 and are configured to be able to transmit and receive various data to and from each other. Note that the number of the information processing device 2 and the user terminal device 3 and the connection configuration of the network 4 are not limited to the example in FIG. 1 and may be changed as appropriate.

[0026] The information processing device 2 is a server-type computer or a cloud-type computer and is composed of a general-purpose or dedicated computer (see FIG. 7 described later) or the like. The information processing device 2 performs machine learning of the situation inference model 220. The information processing device 2 uses the learned situation inference model 220 to generate a determination result D50 as a result of determining the situation of a customer regarding a new order.

[0027] The user terminal device 3 is a client-type computer and is composed of a general-purpose or dedicated computer (see FIG. 7 described later) or the like. The user terminal device 3 receives various input operations via a display screen such as an application or a browser in order to input the determination of the customer situation and confirm the determination result, and outputs various information via the display screen or voice.

[0028] (Configuration of the information processing device 2) FIG. 4 is a block diagram showing an example of the information processing apparatus 2.

[0029] The information processing apparatus 2 includes a control unit 20, a data storage unit 21, a learned model storage unit 22, a communication unit 23, an input unit 24, and an output unit 25.

[0030] The communication unit 23 is connected to an external device (for example, the user terminal device 3, etc.) via the network 4 and functions as a communication interface for transmitting and receiving various data. The input unit 24 accepts various input operations, and the output unit 25 functions as a user interface by outputting various information via a display screen or voice. Note that the input unit 24 and the output unit 25 may be omitted.

[0031] The data storage unit 21 stores a database 210 and an information processing program 211. As shown in FIG. 3, a plurality of order-related data D20 of existing orders (that is, order information D21, estimate information D22, performance information D23, and profit and loss information D24) are registered in the database 210. The specific configuration of the database 210 is not limited to the example of FIG. 3 and may be designed as appropriate.

[0032] The learned model storage unit 22 stores a learned situation inference model 220. The situation inference model 220 stored in the learned model storage unit 22 may be provided to other devices via the network 4, a recording medium, or the like. Also, the number of situation inference models 220 stored in the learned model storage unit 22 is not limited to one each. For example, a plurality of inference models with different conditions, such as machine learning methods and data differences, may be stored and made available for selective or parallel use.

[0033] In FIG. 4, the data storage unit 21 and the learned model storage unit 22 are shown as two storage units, but they may be composed of a single storage unit or three or more storage units. Further, at least one of the data storage unit 21 and the learned model storage unit 22 may be composed of a storage unit of an external computer (for example, a server-type computer or a cloud-type computer).

[0034] By executing the information processing program 211 recorded in the data storage unit 21, the control unit 20 functions as a transmission / reception control unit 200, a database management unit 201, a situation inference model learning unit 202, and a customer situation determination processing unit 203.

[0035] (Transmission / Reception Control Unit 200) The transmission / reception control unit 200 transmits and receives various data to and from an external device (for example, the user terminal device 3, etc.). The transmission / reception control unit 200 transmits, for example, display information for outputting various display screens to the user terminal device 3 to the user terminal device 3, and receives operation information for receiving an input operation performed on the display screen of the user terminal device 3 from the user terminal device 3. Then, the transmission / reception control unit 200 cooperates with the database management unit 201, the situation inference model learning unit 202, and the customer situation determination processing unit 203 to transmit display information and receive operation information.

[0036] (Database Management Unit 201) When the database management unit 201 receives order-related data D20 from the user terminal device 3 regarding an existing order, it registers the order information D21, the estimate information D22, the performance information D23, and the profit and loss information D24 included in the order-related data D20 in the database 210 in an associated manner. Further, when the determination result D50 is generated by the customer situation determination processing unit 203 (details will be described later) regarding a new order, the database management unit 201 registers the order-related data D10 in the database 210. Thereby, the number of data registered in the database 210 increases, and the processing accuracy can be improved.

[0037] In addition, various types of information registered in the database 210 may be made accessible for reference from the user terminal device 3 by the transmission / reception control unit 200. In this case, editing operations such as addition, deletion, and modification of each data may be performed on the display screen of the user terminal device 3. Furthermore, in the database 210, the information registered as the order-related data D20 is not limited to the order information D21, the estimate information D22, the performance information D23, and the profit and loss information D24, and any information can be associated as necessary.

[0038] (Situation inference model learning unit 202) FIG. 5 is a functional explanatory diagram showing an example of the situation inference model learning unit 202. The situation inference model learning unit 202 includes a learning data acquisition unit 202A and a machine learning unit 202B.

[0039] The learning data acquisition unit 202A refers to the database 210 and acquires learning data D30 composed of input data.

[0040] The input data constituting the learning data D30 is situation inference model input information based on at least one of the order information D21, the estimate information D22, the performance information D23, and the profit and loss information D24 among the order-related data D20 related to existing orders.

[0041] Note that the learning data acquisition unit 202A may acquire the learning data D30 for data that satisfies a predetermined condition among the data registered in the database 210. Also, the learning data acquisition unit 202A may acquire the learning data D30 by other methods instead of or in addition to the database 210. The learning data acquisition unit 202A may acquire the learning data D30 in cooperation with an external device connected via the network 4, for example, or may acquire the learning data D30 by accepting an input operation via the input unit 24 and the output unit 25.

[0042] Further, the learning data acquisition unit 202A may extract feature quantities from the order-related data D20 and acquire the situation inference model input information as learning data D30. The feature quantities are defined by, for example, data in a vector format represented by a fixed-length numerical array. The feature quantities are not limited to the vector format and may be defined in other data formats. By doing so, unnecessary noise can be removed from the learning data in subsequent machine learning processes, and the learning efficiency can be improved.

[0043] Further, the learning data acquisition unit 202A may take into account information regarding the time series of the order-related data D20 and acquire the situation inference model input information as learning data D30. By doing so, the correlation between the situation inference model input information and the business situation regarding the customer's business can be learned taking into account the time series.

[0044] The machine learning unit 202B performs machine learning to cause the situation inference model 220 to learn the correlation between the input data and the situation in the customer's business using a plurality of sets of learning data D30 acquired by the learning data acquisition unit 202A. As an example, the machine learning unit 202B performs unsupervised learning using an autoencoder. The learning data D30 is data used as training data in unsupervised learning. The machine learning unit 202B includes an encoder that encodes a plurality of learning data D30 to generate compressed data, and a decoder that restores the compressed data to generate reconstructed data. The learned situation inference model 220 is stored in the learned model storage unit 22.

[0045] Note that the timing at which the machine learning unit 202B performs the machine learning of the situation inference model learning unit 202 may be when the number of newly registered data in the database 210 exceeds a predetermined number, when an instruction from the user U or a customer situation determination is received, or is not limited thereto.

[0046] (Customer Situation Determination Step) FIG. 6 is a functional explanatory diagram showing an example of the customer situation determination processing unit 203. The customer situation determination processing step includes an order-related data acquisition unit 203A, a business situation acquisition unit 203B, and a business situation determination unit 203C.

[0047] The order-related data acquisition unit 203A acquires order-related data D10 related to a new order. As an example, for determining the customer situation, the user U transmits the order-related data D10 from the user terminal device 3. The order-related data acquisition unit 203A acquires the order-related data D10 from the transmission / reception control unit 200 that has received the order-related data D10.

[0048] The business situation acquisition unit 203B inputs situation inference model input information based on the order-related data D10 related to a new order into the situation inference model 220 learned by the situation inference model learning unit 202, thereby acquiring the business situation D40 for the order-related data D10.

[0049] As the situation inference model 220, a model that has been machine-learned by the situation inference model learning unit 202 and stored in the learned model storage unit 22 is used. That is, the situation inference model 220 is a learned model in which machine learning of the correlation between situation inference model input information based on order-related data D20 related to existing orders and the business situation regarding the business situation of the customer has been performed.

[0050] Also, the business situation acquisition unit 203B performs preprocessing on the order-related data D10 in accordance with the definition of the input data in the situation inference model 220 and inputs it into the situation inference model 220, thereby acquiring the business situation D40 for the order-related data D10. The preprocessing may be a process of extracting feature amounts from the order-related data D10.

[0051] The business situation determination unit 203C outputs a determination result D50 of the customer's business situation based on the business situation D40. As an example, the business situation determination unit 203C may output binary data representing either normal or abnormal as the determination result D50. Specifically, for example, the business situation D40 is output as a numerical value within a predetermined normalized range (e.g., 0 to 1). The business situation determination unit 203C compares the business situation D40 with a predetermined threshold value (e.g., 0.5). If the business situation D40 is less than the threshold value, the determination result D50 is output as "abnormal", and if the business situation D40 is greater than or equal to the threshold value, the determination result D50 may be output as "normal".

[0052] (Hardware configuration of each device) FIG. 7 is a hardware configuration diagram showing an example of a computer 900. The information processing device 2 and the user terminal device 3 in the customer situation determination system 1 are configured by a general-purpose or dedicated computer 900.

[0053] As shown in FIG. 7, the main components of the computer 900 include a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be appropriately omitted according to the application for which the computer 900 is used.

[0054] The processor 912 is composed of one or more arithmetic processing units (such as a CPU (Central Processing Unit), MPU (Micro-processing unit), DSP (digital signal processor), GPU (Graphics Processing Unit), etc.) and operates as a control unit that overall controls the computer 900. The memory 914 stores various data and programs 930 and is composed of, for example, a volatile memory (such as DRAM, SRAM, etc.) that functions as a main memory and a non-volatile memory (ROM), flash memory, etc.

[0055] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, a microphone, etc., and functions as an input unit. The output device 917 is composed of, for example, a sound (voice) output device, a vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, an electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be integrally configured like a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD, etc., and functions as a storage unit. The storage device 920 stores various data necessary for the execution of the operating system and the program 930.

[0056] The communication I / F unit 922 is connected to a network 940 (which may be the same as the network 4 in FIG. 1) such as the Internet or an intranet, either wired or wirelessly, and functions as a communication unit that transmits and receives data to and from other computers according to a predetermined communication standard. The external device I / F unit 924 is connected to an external device 950 such as a camera, a printer, a scanner, a reader / writer, etc., either wired or wirelessly, and functions as a communication unit that transmits and receives data to and from the external device 950 according to a predetermined communication standard. The I / O device I / F unit 926 is connected to an I / O device 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data such as detection signals from sensors and control signals to actuators to and from the I / O device 960. The media input / output unit 928 is composed of, for example, a drive device such as a DVD drive and a CD drive, and reads and writes data to and from a media (non-volatile storage medium) 970 such as a DVD and a CD.

[0057] In the computer 900 having the above configuration, the processor 912 calls and executes the program 930 stored in the storage device 920 in the memory 914, and controls each part of the computer 900 via the bus 910. Note that the program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded in the medium 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by downloading via the network 940 through the communication I / F unit 922. Further, the computer 900 may implement various functions realized when the processor 912 executes the program 930 by hardware such as an FPGA or an ASIC.

[0058] The computer 900 is composed of, for example, a stationary computer or a portable computer, and is an electronic device in any form. The computer 900 may be a client-type computer, a server-type computer, a cloud-type computer, or an embedded computer called, for example, a control panel, a controller (including a microcomputer, a programmable logic controller, a sequencer), etc.

[0059] (Operation of the information processing apparatus 2) FIG. 8 is a flowchart showing an example of the operation (information processing method) of the information processing apparatus 2. Note that a series of information processing methods by the information processing apparatus 2 shown in FIG. 8 will be described starting from the learning process of the situation inference model 220 that is performed in advance before the information processing apparatus 2 receives a determination of the customer situation regarding a new order from the user terminal device 3 operated by the user U. Also, it is described that a plurality of order-related data D20 are registered in the database 210 by the database management unit 201 regarding a plurality of existing orders.

[0060] First, in step S100 (learning data acquisition step), the learning data acquisition unit 202A of the situation inference model learning unit 202 acquires a plurality of sets of learning data D30 based on the order-related data D20 related to existing orders. The order-related data D20 includes at least one of order information D21, quotation information D22, performance information D23, and profit and loss information D24.

[0061] In step S110 (machine learning step), the machine learning unit 202B of the situation inference model learning process executes machine learning of the situation inference model 220 using a plurality of sets of learning data D30.

[0062] In step S120 (order-related data acquisition step), the order-related data acquisition unit 203A of the customer situation determination processing unit 203 acquires order-related data D10 related to a new order. The order-related data D10 includes at least one of order information D11, quotation information D12, performance information D13, and profit and loss information D14.

[0063] In step S130 (business situation acquisition step), the business situation acquisition unit 203B of the customer situation determination processing unit 203 inputs situation inference model input information based on the new order-related data D10 into the learned situation inference model 220, and acquires the business situation D40 for the order-related data D10.

[0064] In step S140 (business situation determination step), the business situation determination unit 203C of the customer situation determination processing unit 203 determines the business situation based on the acquired business situation D40. As an example, the business situation determination unit 203C outputs binary data representing either normal or abnormal as the determination result of the customer's business situation.

[0065] In step S150 (business situation output step), the transmission and reception control unit 200 outputs the determination result D50 of the business situation for the new order to the user terminal device 3.

[0066] As described above, according to the information processing apparatus 2 and the information processing method according to the present embodiment, learning of the situation inference model 220 is performed using the learning data D30 based on the existing order-related data D20, and the order-related data D10 related to the new order is input to the situation inference model 220, whereby the situation of the customer is determined. Therefore, the correlation between the order-related data and the situation in the customer's business can be learned by the situation inference model 220, and the situation of the customer based on the new order-related data can be determined. In this way, by utilizing the data related to the orders already acquired, the situation in the customer's business can be determined, and customer relationship management can be performed by a simple method.

[0067] (Other embodiments) The present invention is not limited to the above-described embodiments, and various modifications can be made and implemented without departing from the gist of the present invention. And all of them are included in the technical idea of the present invention.

[0068] In the above embodiment, the information processing apparatus 2 has been described as being configured by a single apparatus, but it may be configured by a plurality of apparatuses. For example, by distributing each part 202 to 203 included in the information processing apparatus 2 to a plurality of apparatuses, it may be configured by a machine learning apparatus including the situation inference model learning unit 202 and performing the situation inference model learning process, and an information processing apparatus including the customer situation determination unit 203 and performing the customer situation determination process. At that time, each part (each process) included in each of the above apparatuses may also be realized by a program (information processing program or machine learning program) executable by the computer 900.

[0069] Each of the above apparatuses can be configured as follows, for example. Note that since the configuration and operation of each part in each apparatus and various data handled by each apparatus are the same as those in the above embodiment, detailed description thereof is omitted.

[0070] A machine learning device that performs a situation inference model learning process includes a learning data acquisition unit 202A that acquires a plurality of sets of learning data D30 composed of input data, and a machine learning unit 202B that uses the plurality of sets of learning data D30 acquired by the learning data acquisition unit 202A to learn a correlation between the input data and a business situation regarding the business situation of a customer in a situation inference model 220, and a learned model storage unit 22 that stores the situation inference model 220 in which the correlation has been learned by the machine learning unit 202B. The input data is situation inference model input information based on order-related data D20 related to existing orders (that is, at least one of order information D21, estimate information D22, performance information D23, and profit and loss information D24).

[0071] An information processing device that performs a customer situation determination process includes an order-related data acquisition unit 203A that acquires order-related data D10 related to a new order, and a business situation acquisition unit 203B that inputs situation inference model input information based on the order-related data D10 (that is, at least one of order information D11, estimate information D12, performance information D13, and profit and loss information D14) acquired by the order-related data acquisition unit 203A into the situation inference model 220 to acquire the business situation of the customer, and a business situation determination unit 203C that outputs a determination result D50 of the business situation of the customer based on the acquired business situation. The business situation determination unit 203C may output the determination result D50 in a format other than the above-described binary data as the determination result.

[0072] Note that the transmission / reception control unit 200 and the database management unit 201 may be provided in each of the above devices. Further, the database 210 only needs to be configured to be accessible from each of the above devices, and may be stored in the storage unit of any one of the devices, or may be stored in the storage unit of an external computer. Furthermore, some of the above devices may be realized by the user terminal device 3.

[0073] (Inference Device, Inference Method, and Inference Program) The present invention can be provided not only in the form of the information processing apparatus 2 (information processing method or information processing program) according to the above-described embodiment, but also in the form of an inference apparatus (inference method or inference program) used for inferring a customer's business situation. In that case, the inference apparatus (inference method or inference program) may include a memory and a processor, and the processor among them can execute a series of processes. The series of processes includes an information acquisition process (information acquisition step) of acquiring new order-related data D10, and an inference step of inferring the customer's business situation when the new order-related data D10 is acquired by the information acquisition process.

[0074] By providing it in the form of an inference apparatus (inference method or inference program), it can be more easily applied to various apparatuses compared to the case of implementing an information processing apparatus. When the inference apparatus (inference method or inference program) infers the customer's business situation, it is naturally understandable to those skilled in the art that the inference method implemented by the information generation unit may be applied using the learned inference model generated by the machine learning apparatus and the machine learning method according to the above-described embodiment.

Explanation of Reference Numerals

[0075] 1... Customer situation determination system, 2... Information processing apparatus, 3... User terminal apparatus, 4... Network, 20... Control unit, 21... Data storage unit, 22... Model storage unit, 23... Communication unit, 24... Input unit, 25... Output unit, 200... Transmission / reception control unit, 201... Database management unit, 202... Situation inference model learning unit, 202A... Learning data acquisition unit, 202B... Machine learning unit, 203... Customer situation determination processing unit, 203A... Order-related data acquisition unit, 203B... Business situation acquisition unit, 203C... Business situation determination unit, 210... Database, 211... Information processing program, 220... Situation inference model

Claims

1. a learning data acquisition unit that acquires, as learning data, a plurality of pieces of situation inference model input information based on order-related data including at least one of order information included in an order from a customer, quotation information related to a quotation for the order, performance information related to the acceptance of the order, and profit and loss information related to a case related to the order; a machine learning unit that uses the plurality of learning data acquired by the learning data acquisition unit to make a situation inference model learn a correlation between the situation inference model input information and a business situation related to the business situation of the customer through machine learning; A machine learning device comprising: a learned model memory unit that stores the situation inference model in which the correlation has been learned by the machine learning unit.

2. The machine learning unit is an encoder for encoding a plurality of the learning data to generate compressed data; The machine learning device according to claim 1 , further comprising: a decoder that decompresses the compressed data to generate reconstructed data.

3. The machine learning device according to claim 1 , wherein the learning data acquisition unit extracts features from the order-related data and acquires the situation inference model input information as the learning data.

4. The machine learning device according to claim 1 , wherein the learning data acquisition unit acquires the situation inference model input information as the learning data by taking into account information regarding a time series of the order-related data.

5. an order-related data acquiring unit that acquires order-related data including at least one of order information included in an order from a customer, quotation information related to a quotation for the order, performance information related to the acceptance of the order, and profit and loss information related to a case related to the order; a business status acquisition unit that acquires a business status related to a business status of the customer by inputting situation inference model input information based on the order-related data into a situation inference model, The situational inference model is An information processing device that is a trained model that has been trained by machine learning to learn the correlation between situational inference model input information based on the order-related data and a business situation related to the business situation of the customer.

6. The information processing device according to claim 5 , further comprising a business status determination unit that outputs binary data representing either normal or abnormal as a determination result of the customer's business status based on the business status acquired by the business status acquisition unit.

7. An inference device comprising a memory and a processor, The processor, an input information acquisition process for acquiring situation inference model input information based on order-related data including at least one of order information included in an order from a customer, quotation information related to a quotation for the order, performance information related to the acceptance of the order, and profit and loss information related to the profit and loss of a case related to the order; When the situational inference model input information is acquired by the input information acquisition process, an inference process is executed to infer the business situation of the customer based on the correlation between the situational inference model input information learned by machine learning and a business situation related to the business situation of the customer.

8. A computer comprising: a learning data acquisition step of acquiring, as learning data, a plurality of pieces of situation inference model input information based on order-related data including at least one of order information included in an order from a customer, quotation information related to a quotation for the order, performance information related to the acceptance of the order, and profit and loss information related to a case related to the order; a machine learning process of making a situation inference model learn a correlation between the situation inference model input information and a business situation related to the business situation of the customer by machine learning using the plurality of learning data acquired by the learning data acquisition process; A machine learning method comprising: a learned model storage step of storing the situation inference model in which the correlation has been learned by the machine learning step.

9. A computer comprising: an order-related data acquisition step of acquiring order-related data including at least one of order information included in an order from a customer, quotation information related to a quotation for the order, performance information related to the acceptance of the order, and profit and loss information related to a case related to the order; a business status acquisition step of acquiring a business status related to a business status of the customer by inputting situation inference model input information based on the order-related data into a situation inference model; The situational inference model is An information processing method, comprising: a trained model that learns the correlation between situational inference model input information based on the order-related data and a business situation related to the business situation of the customer through machine learning.

10. An inference method executed by an inference device having a memory and a processor, comprising: The processor, an input information acquisition process for acquiring situation inference model input information including at least one of order information included in an order from a customer, quotation information regarding a quotation for the order, performance information regarding the receipt of the order, and profit and loss information regarding the profit and loss of a case related to the order; When the situational inference model input information is acquired by the input information acquisition process, an inference process is executed to infer the business situation of the customer based on the correlation between the situational inference model input information learned by machine learning and a business situation related to the business situation of the customer.

Images