JP7261095B2 - BUSINESS MATCHING SUPPORT DEVICE AND BUSINESS MATCHING SUPPORT METHOD - Google Patents

Description

The present invention relates to a business matching support device and a business matching support method.

Patent Literature 1 describes a business matching support device configured for the purpose of enabling accurate business matching. The business matching support device stores an evaluation formula that defines the strength of the business relationship between the industries from the perspective of looking at the other industry from one industry for each viewpoint between each industry, Input each type of information about other companies into the evaluation formula for each viewpoint, with the industry to which the company to be evaluated belongs to in one industry or the other, and transactions between the company to be evaluated and other companies from each perspective Calculate the strength of the relationship, specify the total value of the calculated strength of the business relationship from each viewpoint as the matching score between the company to be evaluated and other companies, and among the other companies, the matching score is equal to or higher than a predetermined standard The object is determined as a matching candidate, and information on the matching candidate is output to a predetermined device.

JP 2018-206219 A

2. Description of the Related Art Recently, for the purpose of efficient business development, etc., business matching is performed to introduce candidates for requesting companies (business partners) that can cooperate with a requesting company for problem solving. In business matching, it is important to introduce a company that is likely to conclude a contract with a requesting company.

By the way, there are various reasons why companies request matching (hereinafter referred to as "matching patterns"), such as expansion of suppliers and sales destinations, capital investment, and searching for new product development partners. Matching patterns categorize differences in factors that affect contract closure, such as "it is important to match policies in new product development." In addition, in order to improve the accuracy of matching, consideration is given to company characteristics such as owned facilities, management philosophy, and policies, such as "the same community-based policy hits it off" and "special refrigeration equipment has been successful in matching with the fishery industry." is also important.

The present invention has been made in view of such a background, and its object is to provide a business matching support device and a business matching support method capable of providing highly accurate information for business matching. .

A business matching support device for supporting business matching between companies, comprising an information processing device, a data acquisition unit for acquiring data describing information about each of a plurality of companies, and characteristics of each company from the data A company feature vector generation unit that extracts words indicating and generates a company feature vector that vectorizes the features of each company based on the frequency of appearance of the extracted words in the data; a transaction between the companies acquired from the data a transaction log classifying unit for classifying transaction logs, which are the history of, according to a matching pattern classification rule, which is a condition for classifying the transaction log, which is the history of the company, for each matching pattern, which is a pattern categorizing reasons for requesting matching by a company; generating a co-occurrence rule for each pattern, which is information obtained by extracting a co-occurrence rule, which is a combination of words co-occurring between companies that have transactions, for each matching pattern based on the log and the company feature vector; a co-occurrence rule extraction unit for each pattern; an evaluation expression generation unit for generating an evaluation expression for generating an evaluation value indicating a high rate of closing a contract between companies for each of the matching patterns; a variable determination unit that determines variables to be used in the evaluation formula by specifying the factor for each of the matching patterns; a candidate company evaluation unit that obtains an evaluation value using the evaluation formula and outputs the obtained evaluation value for each company, wherein the candidate company evaluation unit presets the magnitude of the influence on the evaluation value . Output the variable that exceeds the specified threshold.

In addition, the problems disclosed by the present application and their solutions will be clarified by the description of the mode for carrying out the invention and the drawings.

According to the present invention, highly accurate information for business matching can be provided.

1 is a diagram showing a schematic configuration of an information processing system; FIG. 1 is a block diagram showing an example of an information processing device that implements a support device or a company information providing device; FIG. It is a figure which shows the main functions with which a support apparatus is provided. 9 is a flowchart for explaining evaluation formula generation processing; It is a flowchart explaining the detail of a company characteristic matrix production|generation process. It is an example of a company feature matrix. It is an example of corporate attribute information. It is an example of transaction log information. It is an example of a matching pattern classification rule. This is an example of pattern-wise co-occurrence rules. It is an example of per-pattern evaluation formula information. 4 is a flowchart for explaining evaluation processing; It is an example of a candidate company evaluation list. 9 is a flowchart for explaining evaluation processing according to the second embodiment; This is an example of company extraction conditions.

Hereinafter, embodiments will be described with reference to the drawings. In the following description, the same reference numerals may be given to the same or similar configurations, and redundant description may be omitted.

[First embodiment]
FIG. 1 shows a schematic configuration of an information processing system 1 shown as the first embodiment. The information processing system 1 includes a business matching support device (hereinafter referred to as "support device 10"), one or more Web servers 2, one or more company information servers 3, and one or more transaction information servers 4. include. All of these are information processing apparatuses (computers) and are communicably connected via a communication network 5 . The communication network 5 is a wired or wireless communication means such as the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), a leased line, a public communication network, or the like.

The Web server 2, the company information server 3, and the transaction information server 4 (hereinafter, these devices are collectively referred to as "company information providing devices") all provide various information ( company name, business type, business content, research content, owned facilities, owned assets, number of employees, partner companies, suppliers, sales destinations, transaction history, sales performance, advertising, etc.)
provide to

Based on the information collected from the company information collection device via the communication network 5, the support device 10 provides reasons why companies request matching, such as expansion of suppliers and sales destinations, capital investment, searching for partners in new product development, etc. (hereinafter referred to as "matching pattern"), provides information on the evaluation of companies (business partners) that are candidates for matching requests.

FIG. 2 is a block diagram showing an example of an information processing device that implements the support device 10 and the company information providing device. As shown in the figure, the illustrated information processing apparatus 100 includes a processor 11 , a main storage device 12 , an auxiliary storage device 13 , an input device 14 , an output device 15 and a communication device 16 . The information processing apparatus 100 may be implemented using virtual information processing resources such as a cloud server provided by a cloud system, for example. Also, the information processing apparatus 100 may be implemented as a container deployed on a container platform, for example.

The processor 11 is, for example, a CPU (Central Processing Unit), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable
Gate Array), ASIC (Application Specific Integrated Circuit), AI (Artificial Intelligence) chip, and the like.

The main storage device 12 is a device that stores programs and data, and is, for example, a ROM (Read
Only Memory), RAM (Random Access Memory), nonvolatile memory (NVRAM (Non Volatile RAM)), and the like.

The auxiliary storage device 13 is, for example, a hard disk drive, an SSD (Solid State Drive)
), optical storage devices (CD (Compact Disc), DVD (Digital Versatile Disc), etc.), storage systems, read/write devices for recording media such as IC cards, SD cards and optical recording media, cloud server storage areas, etc. Programs and data can be read into the auxiliary storage device 13 via a recording medium reading device or the communication device 16 . Programs and data stored (stored) in the auxiliary storage device 13 are read into the main storage device 12 at any time.

The input device 14 is an interface that receives input from the outside, and includes, for example, a keyboard, mouse, touch panel, card reader, pen-input tablet, voice input device, and the like.

The output device 15 is an interface for outputting various information such as processing progress and processing results. The output device 15 is, for example, a display device (liquid crystal monitor, LCD (Liquid Crystal Display), graphic card, etc.) that visualizes the above various information, a device (audio output device (speaker, etc.)) that converts the above various information into sound. , a device (printing device, etc.) that converts the above various information into characters.

For example, the information processing device 100 may be configured to input and output information with another device via the communication device 16 . The input device 14 and the output device 15 may be implemented by hardware that is communicably connected to the support device 10 and independent of the support device 10 .

The communication device 16 is a device that realizes communication with other devices. The communication device 16 is a wired or wireless communication interface that realizes communication with other devices via the communication network 5, and includes, for example, a NIC (Network Interface Card), a wireless communication module, a USB module, A serial communication module or the like.

The functions of the supporting device 10 and the corporate information providing device are realized by the processor 11 reading and executing a program stored in the main storage device 12, or by hardware (FPGA, ASIC, AI chip, etc.).

For example, an operating system, a device driver, a file system, a DBMS (DataBase Management System), etc. may be installed in the support device 10 and the corporate information providing device.

FIG. 3 shows main functions of the support device 10. As shown in FIG. As shown in the figure, the support device 10 includes a storage unit 110, a data acquisition unit 111, a company feature vector generation unit 112, a transaction log classification unit 113, a pattern co-occurrence rule extraction unit 114, a variable determination unit 115, an evaluation formula It has the functions of a generation unit 116 and a candidate company evaluation unit 117 . These functions are realized by the processor 11 reading out and executing programs stored in the main storage device 12 or by hardware (FPGA, ASIC, AI chip, etc.) included in the support device 10 .

The storage unit 110 stores company text information 151, company attribute information 152, transaction log information 153, matching pattern classification rules 154, company feature matrix 155, pattern-based co-occurrence rules 156, pattern-based evaluation formula information 157, and candidate company evaluation list. 158 is stored. The storage unit 110 stores such information (data) as, for example, a database table provided by a DBMS and a file provided by a file system.

The company text information 151 is information acquired from the company information providing device, and includes text data describing information about the company.

The company attribute information 152 is information acquired from the company information providing device, and information related to company attributes such as company name, industry, location, number of employees, etc. (hereinafter referred to as "company attribute information") is managed. be.

The transaction log information 153 is information acquired from the company information providing device, and manages information relating to the history of transactions conducted between companies (hereinafter referred to as “log information”).

The matching pattern classification rule 154 includes information on conditions (rules) for determining which matching pattern the transaction log managed by the transaction log information 153 corresponds to (hereinafter referred to as "matching pattern classification rule"). ) is managed. The matching pattern classification rule 154 is, for example, information acquired by an operation input from the user via the input device 14 .

The company feature matrix 155 is information generated by the support device 10 and includes information regarding scores for various features of each company. In this embodiment, the score is a value calculated using TF-IDF, but the form of the score is not necessarily limited.

The co-occurrence rule for each pattern 156 is information generated by the support device 10, and is information obtained by extracting a co-occurrence rule that is a combination of words co-occurring between companies that have transactions for each matching pattern (hereinafter referred to as (referred to as "per-pattern co-occurrence rules"). The per-pattern co-occurrence rule is information that indicates what kind of characteristics are often traded between companies with respect to each matching pattern.

The pattern-by-pattern evaluation formula information 157 is information generated by the support device 10, and manages information relating to an evaluation formula for generating an evaluation value representing an evaluation of the high contract rate between companies for each matching pattern.

The candidate company evaluation list 158 includes information indicating the evaluation value of the contract rate, the matching pattern, and the co-occurrence rule that affects the evaluation value, etc., for companies that are candidates for matching request destinations. The candidate company evaluation list 158 is generated by the support device 10 .

Among the functions shown in FIG. 3 , the data acquisition unit 111 acquires text data describing information about a company from the company information providing device via the communication network 5 . The data acquisition unit 111 acquires information at any time from the company information providing device via the communication network 5 by, for example, crawling or scraping.

The company feature vector generation unit 112 extracts words that indicate the features of each company from the text data acquired from the company information providing device, and vectorizes the features of each company based on the frequency of appearance of the extracted words in the text data. In this example, a company feature vector vectorized by TF-IDF) is generated, and a company feature matrix 155, which is a determinant in which the company feature vectors of each company are aggregated, is generated.

The transaction log classification unit 113 classifies the log information included in the transaction log information 153 according to the matching pattern according to the matching pattern classification rule 154 .

The pattern-based co-occurrence rule extraction unit 114 generates pattern-based co-occurrence rules based on the transaction logs classified for each matching pattern and the company feature vector (company feature matrix 155).

The variable determination unit 115 determines variables to be used in the evaluation formula by identifying factors affecting the presence/absence of transactions for each matching pattern.

The evaluation formula generation unit 116 generates an evaluation formula using the determined variables, and generates evaluation formula information 157 for each pattern.

The candidate company evaluation unit 117 accepts from the user the information of the company requesting matching and the designation of the matching pattern, and the evaluation value of each company that is the candidate of the request destination obtained by using the evaluation formula corresponding to the matching pattern. , and information listing the co-occurrence rules that greatly affected the obtained evaluation value, a candidate company evaluation list 158 is generated.

Next, processing performed by the support device 10 will be described. The main processes performed by the support device 10 are a process of generating an evaluation formula for each matching pattern (hereinafter referred to as "evaluation formula generation process S400"), and a process of generating a matching request received from a user using the evaluation formula. The process is roughly divided into the process of evaluating each company (evaluating suitability as a matching destination) (hereinafter referred to as "evaluation process S1000"). For example, these may be executed as independent processes at independent timings, or may be executed as a series of processes.

FIG. 4 is a flowchart for explaining the evaluation formula generation processing S400. The support device 10 generates pattern-by-pattern evaluation formula information 157 by executing the processing with the company text information 151 , the company attribute information 152 , the transaction log information 153 , and the matching pattern classification rule 154 as inputs. Note that the data acquisition unit 111 acquires, for example, text data describing information about a company from a company information providing device at predetermined intervals, and the difference between the previous acquisition of the text data and the current acquisition of the text data is set in advance. The process is executed when the threshold is exceeded.

First, the support device 10 generates a company feature matrix 155 based on the company text information 151 (S411). Hereinafter, this process will be referred to as "company feature matrix generation process S411".

FIG. 5 is a flowchart for explaining the details of the company feature matrix generation processing S411.

First, the company feature vector generation unit 112 performs morphological analysis on the text data included in the company text information 151, and extracts words of a predetermined part of speech such as nouns and verbs from the resulting morphemes (S511).

Subsequently, the company feature vector generation unit 112 obtains the appearance frequency of each word extracted in S511, and selects words whose appearance frequency is equal to or higher than a predetermined threshold (S512).

The subsequent processing of S513 to S514 is loop processing that is repeatedly performed for each company included in the company text information 151. FIG.

In S513, the company feature vector generation unit 112 obtains the TF-IDF value of the word selected in S512 for the selected company.

Subsequently, the company feature vector generation unit 112 arranges and vectorizes the TF-IDF values obtained in S513 (S514).

After the above loop processing is completed, the company characteristic vector generation unit 112 generates the company characteristic matrix 155 by aggregating the vectors of each company obtained in S514 (hereinafter referred to as "company characteristic vectors"). Generate (S515).

From the above, the company feature matrix 155 is generated. The company feature matrix 155 expresses the features of each company as the score (TF-IDF value) obtained in S513 for the word selected in S512.

In S511, words are extracted based on the part of speech, and in S512, words are selected based on the appearance frequency. For example, words that match words registered in a separately created word dictionary may be extracted. Also, for example, words may be selected according to their TF-IDF value or other criteria.

An example of the company feature matrix 155 is shown in FIG. Each record corresponds to each company specified by the company ID 611, which is an identifier of the company. In the figure, words 612 such as "community-based", "export", "quick freezing", "slicer", "mandarin orange", and "jam" arranged in columns are words obtained from the company text information 151. be. The numerical value set in each column specified by row and column is the TF-IDF value of each word of the company.

Among the exemplified words, "community-based" and "export" are words related to corporate policy, "quick freezing" and "slicer" are words related to the company's equipment and technology, and "orange" and "Jam" is a word related to the company's products and raw materials. In this way, the characteristics of each company are represented by the TF-IDF values of words based on such diverse viewpoints. For example, a plurality of words having a relationship such as synonyms may be treated as one feature.

Returning to FIG. 4, the support device 10 then classifies the transaction log information 153 for each matching pattern based on the company attribute information 152, the matching pattern classification rule 154, and the company feature matrix 155 (S412).

Specifically, the transaction log classification unit 113 determines a matching pattern for each transaction log of the transaction log information 153 based on the company attribute information 152 and the company characteristic matrix 155 according to the contents of the matching pattern classification rule 154. , to classify the transaction logs for each matching pattern.

An example of the company attribute information 152 is shown in FIG. The illustrated company attribute information 152 is composed of a plurality of records having items such as record #1520, company name 1521, type of industry 1522, location 1523, number of employees 1524, and the like. Each record corresponds to one company.

A record identifier (record number) is set in the record #1520. A company ID is set in the company name 1521 . Information indicating the type of business of the company is set in the type of business 1522 . Information indicating the location of the company is set in the location 1523 . The number of employees 1524 is set with information indicating the number of employees of the company.

An example of the transaction log information 153 is shown in FIG. The illustrated transaction log information 153 is composed of a plurality of records having items of record ID 1530 , transaction date 1531 , selling company name 1532 , selling category 1533 , buying company name 1534 , and buying category 1535 . Each record corresponds to one transaction log.

A record identifier (record number) is set in the record #1530. The transaction date 1531 is set with the date on which the transaction of the transaction log was made. The selling company name 1532 is set with the company ID of the selling company. Information indicating the type of business of the selling company is set in the sales type 1533 . The company ID of the buying company is set in the buying company name 1534 . Information indicating the type of business of the buying company is set in the buying type 1535 .

An example of the matching pattern classification rule 154 is shown in FIG. The matching pattern classification rule 154 manages classification rules for each matching pattern. The illustrated matching pattern classification rule 154 includes matching pattern 1541, transaction tendency condition 1542, corporate attribute condition 1543 (selling side, buying side), text condition 1544 (selling side, buying side), and pattern application priority 1545. It consists of multiple records that have One record corresponds to one matching pattern.

Information indicating a matching pattern is set in the matching pattern 1541 . In the transaction trend conditions 1542, conditions (conditions for transaction intervals, conditions for transaction frequency, conditions for selling companies, conditions for buying companies) for matching the matching pattern are set. be. In the corporate attribute condition 1543, conditions (conditions for selling companies, conditions for buying companies) regarding corporate attributes for matching the matching pattern are set. In the text information condition 1544, conditions (conditions for the selling side company, conditions for the buying side company) for the company feature matrix 155 (company feature vector) for matching the matching pattern are set.

The pattern application priority 1545 is set with information (in this example, "high", "medium", "low") indicating the adoption priority when a certain transaction log corresponds to multiple matching patterns. For example, if a transaction log corresponds to multiple matching patterns, the transaction log is classified as a matching pattern with a higher priority. Incidentally, when the priority of each of the plurality of matching patterns is the same, the transaction log is classified into the plurality of matching patterns.

For example, the conditions for a record whose matching pattern 1541 in FIG. It holds if

Also, for example, the upper condition of the record whose matching pattern 1541 is “capital investment” in FIG. It is established when the side company exceeds "0.5" and the buying side company does not exceed "0.5". In addition, the conditions at the bottom of the above record are that the industry of the selling company is "manufacturing" or "wholesale", the industry of the buying company is "other than wholesale", and the word "machinery" of the selling company is TF- This condition is satisfied when the IDF value exceeds "0.5".

As an example of processing in S412 of FIG. 4, a case where the matching pattern classification rule 154 shown in FIG. 9 is applied to the company attribute information 152 of FIG. 7 and the transaction log information 153 of FIG. 8 is shown.

First, for example, if we focus on the transaction log whose record #1530 in the transaction log information 153 of FIG. In the transaction log where #1530 is "#1003", transactions have occurred between the same companies, and the matching pattern 1541 in FIG. The conditions of "same side company" and "same buying side company" are satisfied. Therefore, the transaction log whose record #1530 is "#1005" is classified as "continuous transaction".

The transaction log whose record #1530 is "#1004" in the transaction log information 153 of FIG. The industry is the same "restaurant". Such a transaction log in which the selling side is "Company A" and the buying side's industry is "Restaurant" has occurred more than five times since transaction date 1531 "19/03/14" with record #1530 being "#1004". If it exists, the transaction log whose record #1530 is "#1004" satisfies the condition of "sales destination expansion" of the matching pattern 1541 of FIG. Therefore, the transaction log whose record #1530 is "#1004" must be one year from the transaction date 1531 "19/03/14" unless it corresponds to the "continuous transaction" whose pattern application priority 1544 is "high". If there is no transaction between "Company A" and "Company S" after the previous "18/03/14", it is classified as "sales destination expansion". If there is a transaction between "Company A" and "Company S" after "18/03/14" one year before the transaction date 1531 "19/03/14", the record #1530 is changed to "# 1004” satisfies the condition of “continuous transaction” and is classified as “continuous transaction”.

Returning to FIG. 4, in S421 in the loop processing, based on the transaction log classified by matching pattern in S412 and the company feature matrix 155 obtained by the company feature vector generation unit 112 in S411, co-occurrence rules for each pattern are calculated. The extraction unit 114 generates a co-occurrence rule 156 for each pattern.

FIG. 10 shows an example of the co-occurrence rule 156 for each pattern. The per-pattern co-occurrence rule 156 includes one or more tables for each matching pattern (hereinafter referred to as "co-occurrence rule table 1560").

As shown in the figure, the co-occurrence rule table 1560 is composed of one or more records having items of record # 1561 , co-occurrence rule 1562 , and correlation coefficient 1563 . A record identifier (record ID) is set in the record #1561.

The co-occurrence rule 1562 is set with a feature (word) whose score is higher than a preset value, with correlation coefficients of a plurality of features (words) in the company feature matrix 155 being scored. The score (correlation coefficient) is set in the correlation coefficient 1563 . Note that the method of extracting the content of the co-occurrence rule 1562 is not necessarily limited. For example, a score obtained by another method may be used. For example, after binarizing each component of the company feature matrix 155 according to some criteria, correlation pattern mining or the like is performed to extract the contents of the co-occurrence rule 1562. You may Also, in the pattern-based co-occurrence rule 156 illustrated as an example, the number of sell-side and buy-side elements does not necessarily have to be one each.

Returning to FIG. 4, in subsequent S422, the company feature matrix 155 obtained by the company feature vector generation unit 112 of S411, the transaction log for each matching pattern obtained by the transaction log classification unit 113 of S412, the company attribute information 152, and Using the pattern-based co-occurrence rule 156 generated in S421 as an input, the variable determination unit 115 determines a variable that affects the presence or absence of a transaction for each matching pattern. In this example, the variable determination unit 115 determines the above variables according to the "information amount criterion", and determines the product, sum, etc. of the values in the enterprise feature matrix 155 of the features in the pattern-by-pattern co-occurrence rule 156 as variables.

For example, when the matching pattern of the co-occurrence rule 156 for each pattern in FIG. Determined as a variable by multiplying the value of the column of "community-based" of the selling company in the company feature matrix 155 shown in Fig. 6 and the value of the column of "community-based" of the buying company of the company feature matrix 155 shown in Fig. 6. do.

In this example, the variables are determined based on the "information amount criteria", but the variables may be determined by other methods such as "selection based on goodness of fit when predicting the presence or absence of transactions". In addition, variables based on each component of the row representing the selling side company or the buying side company of the company feature matrix 155 and the industry 1522 and the location 1523 of the company attribute information 152 may be used as candidates.

Returning to FIG. 4, in S423, the evaluation formula generation unit 116 generates an evaluation formula for each pattern based on the variables selected by the variable determination unit 115 in S422 and the transaction logs for each pattern obtained by the transaction log classification unit 113 in S412. Generate information 157 .

In this example, the evaluation formula generation unit 116 performs logistic regression using the transaction logs obtained by the transaction log classification unit 113 as positive examples and the transaction logs created at random for companies that do not actually have transactions as negative examples. generates an evaluation expression for each pattern. Note that models and methods other than logistic regression may be used. In this example, the evaluation formula is a linear formula for each variable selected by the variable determination unit 115 in S422, but is not limited to this, and may be a more complicated formula. Also, different models and techniques may be used for each matching pattern.

FIG. 11 shows an example of the pattern-by-pattern evaluation formula information 157 generated by the evaluation formula generation unit 116 . As shown in the figure, the pattern-by-pattern evaluation formula information 157 is composed of one or more records having each item of a matching pattern 1571 , an evaluation formula 1572 , a variable 1573 , a variable description 1574 and a variable 1575 .

Information indicating a matching pattern is set in the matching pattern 1571 . An evaluation formula for the matching pattern is set in the evaluation formula 1572 . In addition, in the example of FIG. 4, for simplicity of explanation, the linear expression of the parameter part of the logistic regression for each matching pattern is used as the pattern-by-pattern evaluation expression information. A variable used in the evaluation formula is set in the variable 1573 . Information describing the variable is set in the variable description 1574 . Note that as many sets of items as variables 1573 and variable descriptions 1754 are included in the record as many as the number of variables used in the evaluation formula 1572 .

This completes the description of the evaluation formula generation processing S400 in FIG.

Subsequently, when the support device 10 receives a matching request from the user via the input device 14, a process of generating the candidate company evaluation list 158 using the evaluation formula for each matching pattern generated in the evaluation formula generation process S400. (hereinafter referred to as “evaluation processing S1200”).

FIG. 12 is a flowchart for explaining the evaluation process S1200. The evaluation processing S1200 will be described below with reference to FIG.

First, the candidate company evaluation unit 117 of the support device 10 receives matching request information from the user (S1211). The matching request information includes the company ID of the requester, information indicating whether the requester is the seller or the buyer, information indicating the matching pattern desired by the user, and the like.

First, the user inputs matching request information. In this example, the case where the requester is the "buyer" and the desired matching pattern is "supplier expansion" will be described as an example.

Subsequently, the candidate company evaluation unit 117 acquires the evaluation formula of the matching pattern specified in the matching request information from the pattern-by-pattern evaluation formula information 157 (S1212). In this example, the candidate company evaluation unit 117 acquires the content of the evaluation formula 1572 of the record in which the matching pattern 1571 of the pattern-by-pattern evaluation formula information 157 in FIG. 11 is "supplier expansion".

The subsequent processing of S1213 is repeatedly performed for each company in the company attribute information 152 . In this process, the candidate company evaluation unit 117 obtains the value of each variable of the evaluation formula obtained in S1212 from the company characteristic matrix 155 and the corporate attribute information 152, and substitutes the obtained values into the evaluation formula obtained in S1212. to obtain the evaluation value. In this example, the evaluation value is assumed to be a probability value obtained from the logistic regression evaluation formula.

When the processing of S1213 is completed for each company, the candidate company evaluation unit 117 determines the evaluation value in S1213. (S1214). For example, taking the variable x1 in FIG. 11 as an example, the candidate company evaluation unit 117 obtains it by multiplying the difference between x1 and the average value of x1 of each company by the coefficient a1. Note that the magnitude of the influence may be obtained by a method different from the above.

Subsequently, the candidate company evaluation unit 117 uses the evaluation value obtained in S1213 and the highly influential co-occurrence rule obtained in S1214 to generate a candidate company evaluation list 158 (S1215).

FIG. 13 shows an example of candidate company evaluation list 158 . As shown in the figure, the candidate company evaluation list 158 is composed of one or more records having each item of a ranking 1581, a company name 1582, an evaluation value 1583, a matching pattern 1584, and a highly influential co-occurrence rule 1585. . Each record corresponds to one candidate company to be matched.

Among the above items, in the rank 1581, the rank (in descending order of evaluation value) of candidate companies to which matching is requested is set. The company name 1582 is set with the company ID of the candidate company to which the matching is requested. The evaluation value obtained in S1213 of FIG. 12 is set in the evaluation value 1583. FIG. Information indicating the matching pattern specified in the matching request information received in S1211 of FIG. 12 is set in the matching pattern 1584 . Information indicating one or more highly influential variables identified in S1214 of FIG. 12 is set in the highly influential co-occurrence rule 1585 .

As described above, the support device 10 of the present embodiment automatically collects information about companies from the company information providing device, and automatically analyzes the factors of contract closing for each matching pattern based on the collected information. An evaluation formula is generated for each matching pattern, and an evaluation value of a company that is a candidate for a matching destination of a requesting company received from a user is provided using the evaluation formula, so highly accurate and useful information for business matching. can be provided to the user. In addition, since the support device 10 obtains an evaluation value in consideration of company characteristics such as owned facilities, management philosophy, and policies, it becomes possible to accurately search for long-term business partners such as new product development. Moreover, when using the support device 10, the user only needs to set the matching pattern classification rule 154 at the minimum, and the user can use the support device 10 easily and simply.

[Second embodiment]
Next, a second embodiment will be described. The support device 10 of the second embodiment generates an evaluation formula based on the transaction log that meets the needs of the matching requesting company, and accurately identifies the company that meets the needs as a matching candidate.

The configuration and basic operation of the information processing system 1 of the second embodiment are the same as those of the first embodiment. The following description will focus on the portions that are different from the first embodiment.

FIG. 14 shows a process of generating a candidate company evaluation list 158 when the support device 10 of the second embodiment receives a matching request from a user via the input device 14 (hereinafter referred to as "evaluation process S1400"). It is a flowchart explaining. The evaluation process S1400 is based on the evaluation process S1200 of the first embodiment, but generates an evaluation formula based on information that matches the conditions received from the user (hereinafter referred to as "company extraction conditions"). This differs from the evaluation process S1200 of the first embodiment in that an evaluation value is obtained using an evaluation formula.

In S1411, the support device 10 receives matching request information and company extraction conditions from the user.

FIG. 15 is an example of company extraction conditions. The example company extraction conditions 1500 include a condition 1511 for limiting candidate companies and a condition 1512 for regarding companies as being similar to the requesting company. Also, as shown in the figure, these conditions include a company attribute condition 1513 and a text condition 1514, respectively. These conditions are similar to the corporate attribute condition 1543 and the text condition 1544 in the matching pattern classification rule 154 shown in FIG. is. In the example of FIG. 15, a condition 1511 for limiting candidate companies is set as a text condition 1514 that "the machine value (TF-IDF value) of the company feature matrix 155 is greater than 0.5". As for the condition 1512 for regarding the company as being similar to the requesting company, the company attribute condition 1513 is set as "the business type is retail and the number of employees is 300 or less".

Returning to FIG. 14, subsequently, the support device 10 extracts the transaction logs of the transaction log information 153 that match the corporate attribute condition received in S1411 (S1412).

Subsequently, the support device 10 performs the process of S412 in FIG. 4 on the extracted transaction logs, and classifies the transaction logs by matching pattern (S1413). Note that the support device 10 classifies transaction logs that satisfy the condition 1512 regarding companies that are similar to the requesting company for each matching pattern.

Subsequently, the support device 10 performs the processing of S421 to S423 in FIG. 4 on the transaction log of the matching pattern of the matching request information received in S1411 to generate an evaluation formula (S1414).

Subsequently, the support device 10 extracts companies that match the company extraction conditions received in S1411 as candidate companies from the company attribute information 152 (S1415).

Subsequently, the support device 10 repeatedly executes the process of S1213 in FIG. 12 for each company extracted in S1415 to obtain an evaluation value (S1416).

Subsequently, the support device 10 performs the same processing as S1214 and S1215 of FIG. 12 to generate the candidate company evaluation list 158 (S1417, S1418).

As described above, the support device 10 of the second embodiment uses the transaction log that satisfies the company extraction conditions received from the user for selecting the variables of the evaluation formula and generating the evaluation formula, so that the requester's needs are used as matching destination candidates. It is possible to accurately identify companies that meet the requirements and present them to the user.

Although the embodiments have been described in detail above, it goes without saying that the present invention is not limited to the above-described embodiments, and that various modifications can be made without departing from the gist of the present invention. For example, the above embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the described configurations. Moreover, it is possible to add, delete, or replace a part of the configuration of the above embodiment with another configuration.

Further, each of the above configurations, functional units, processing units, processing means, and the like may be realized by hardware, for example, by designing a part or all of them using an integrated circuit. Moreover, each of the above configurations, functions, etc. may be realized by software by a processor interpreting and executing a program for realizing each function. Information such as programs, tables, files, etc. that realize each function can be stored in memory, hard disks, recording devices such as SSDs (Solid State Drives), ICs, etc.
It can be placed on a recording medium such as a card, SD card, or DVD.

Further, in each of the above drawings, control lines and information lines are those considered necessary for explanation, and not all control lines and information lines for implementation are necessarily shown. For example, it may be considered that almost all structures are interconnected in practice.

Moreover, the arrangement form of various functional units, various processing units, and various databases of each information processing apparatus described above is merely an example. The arrangement form of various functional units, various processing units, and various databases can be changed to an optimum arrangement form from the viewpoint of the performance, processing efficiency, communication efficiency, etc. of hardware and software provided in these devices.

Also, the configuration of the database (schema, etc.) that stores the various data described above can be flexibly changed from the viewpoints of efficient use of resources, improvement of processing efficiency, improvement of access efficiency, improvement of search efficiency, and the like.

1 information processing system 2 web server 3 company information server 4 transaction information server 5 communication network 10 support device 110 storage unit 111 data acquisition unit 112 company feature vector generation unit 113 transaction log classification unit 114 Pattern-by-pattern co-occurrence rule extraction unit 115 variable determination unit 116 evaluation formula generation unit 117 candidate company evaluation unit 151
Company text information, 152 Company attribute information, 153 Transaction log information, 154 Matching pattern classification rule, 155 Company feature matrix, 156 Co-occurrence rule for each pattern, 157
Evaluation formula information for each pattern 158 Candidate company evaluation list S400 Evaluation formula generation process S411 Company feature matrix generation process S1200 Evaluation process 1500 Company extraction conditions

Claims (10)

A business matching support device for supporting business matching between companies,
configured using an information processing device,
a data acquisition unit that acquires data describing information about each of a plurality of companies;
A company feature vector generation unit that extracts words that indicate the features of each company from the data and generates a company feature vector that vectorizes the features of each company based on the appearance frequency of the extracted words in the data;
A transaction log, which is a history of transactions between the companies obtained from the data, is classified according to a matching pattern classification rule, which is a condition for classifying the reasons for requesting matching by matching patterns for each matching pattern. a transaction log classifier,
Each pattern, which is information obtained by extracting a co-occurrence rule, which is a combination of words co-occurring between companies that have transactions, for each matching pattern based on the transaction log and the company feature vector for each matching pattern a co-occurrence rule extraction unit for each pattern, which generates co-occurrence rules;
an evaluation formula generation unit that generates an evaluation formula for generating an evaluation value indicating a high contract rate between companies for each of the matching patterns;
a variable determination unit that determines a variable to be used in the evaluation formula by specifying a factor that affects the presence or absence of a transaction for each matching pattern ;
a candidate company evaluation unit that receives information on a matching request source company and the specification of the matching pattern, obtains an evaluation value using the evaluation formula corresponding to the matching pattern, and outputs the obtained evaluation value for each company;
with
The candidate company evaluation unit outputs the variable whose magnitude of influence on the evaluation value exceeds a preset threshold.
Business matching support device. The business matching support device according to claim 1,
The matching pattern classification rule includes at least one of conditions related to past transaction trends between companies, conditions related to the attributes of each company that has conducted transactions, and conditions related to the description content of the data for each company that has conducted transactions. including,
Business matching support device. The business matching support device according to claim 1,
The variable determination unit determines the variable according to an information criterion;
Business matching support device. The business matching support device according to claim 1,
Furthermore, a condition for limiting candidates of companies to which the matching is requested is received, and the transaction log classification unit classifies the transaction logs satisfying the condition for each matching pattern.
Business matching support device. The business matching support device according to claim 1,
Furthermore, a condition for considering the company to be similar to the matching request source company is received, and the transaction log classification unit classifies the transaction logs that satisfy the condition for each matching pattern,
Business matching support device. The business matching support device according to claim 1,
The company feature vector generation unit generates the company feature vector using TF-IDF,
Business matching support device. A business matching support device for supporting business matching between companies,
configured using an information processing device,
a data acquisition unit that acquires data describing information about each of a plurality of companies;
A company feature vector generation unit that extracts words that indicate the features of each company from the data and generates a company feature vector that vectorizes the features of each company based on the appearance frequency of the extracted words in the data;
A transaction log, which is a history of transactions between the companies obtained from the data, is classified according to a matching pattern classification rule, which is a condition for classifying the reasons for requesting matching by matching patterns for each matching pattern. a transaction log classifier,
Each pattern, which is information obtained by extracting a co-occurrence rule, which is a combination of words co-occurring between companies that have transactions, for each matching pattern based on the transaction log and the company feature vector for each matching pattern a co-occurrence rule extraction unit for each pattern, which generates co-occurrence rules;
an evaluation formula generation unit that generates an evaluation formula for generating an evaluation value indicating a high contract rate between companies for each of the matching patterns;
a variable determination unit that determines a variable to be used in the evaluation formula by specifying a factor that affects the presence or absence of a transaction for each matching pattern;
with
The data acquisition unit acquires the data from another information processing device connected via a communication network at predetermined intervals,
generation of a company feature vector by the company feature vector generation unit and classification of the transaction log by the transaction log classification unit when the difference between the previous acquisition of the data and the current acquisition of the data exceeds a preset threshold; generating the pattern-based co-occurrence rule by the pattern-based co-occurrence rule extraction unit, determining the variable by the variable determination unit, and generating the evaluation formula by the evaluation formula generation unit;
Business matching support device. The business matching support device according to claim 1,
Communicatively connected to a web server via the Internet,
the data acquisition unit acquires the data from the web server via the Internet;
Business matching support device. The business matching support device according to claim 1,
the data is text data;
Business matching support device. A method for supporting business matching between companies,
The information processing device
obtaining data describing information about each of the plurality of companies;
a step of extracting words indicating the characteristics of each company from the data, and generating a company characteristic vector by vectorizing the characteristics of each company based on the frequency of appearance of the extracted words in the data;
A transaction log, which is a history of transactions between the companies obtained from the data, is classified according to a matching pattern classification rule, which is a condition for classifying the reasons for requesting matching by matching patterns for each matching pattern. step,
Each pattern, which is information obtained by extracting a co-occurrence rule, which is a combination of words co-occurring between companies that have transactions, for each matching pattern based on the transaction log and the company feature vector for each matching pattern generating co-occurrence rules;
a step of generating an evaluation formula for generating an evaluation value indicating a high contract rate between companies for each of the matching patterns ;
determining variables to be used in the evaluation formula by identifying factors affecting the presence or absence of transactions for each of the matching patterns;
a step of receiving information on a matching request source company and the specification of the matching pattern, obtaining an evaluation value using the evaluation formula corresponding to the matching pattern, and outputting the obtained evaluation value for each company;
outputting the variable whose magnitude of influence on the evaluation value exceeds a preset threshold;
run the
Business matching support method.

Images