WO2022113285A1 - レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 - Google Patents
レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 Download PDFInfo
- Publication number
- WO2022113285A1 WO2022113285A1 PCT/JP2020/044290 JP2020044290W WO2022113285A1 WO 2022113285 A1 WO2022113285 A1 WO 2022113285A1 JP 2020044290 W JP2020044290 W JP 2020044290W WO 2022113285 A1 WO2022113285 A1 WO 2022113285A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- company
- important part
- recommended
- target
- companies
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 106
- 238000000605 extraction Methods 0.000 claims abstract description 77
- 239000000284 extract Substances 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims description 19
- 238000011161 development Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 13
- 239000000470 constituent Substances 0.000 description 12
- 238000004891 communication Methods 0.000 description 11
- 239000013598 vector Substances 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 102220486681 Putative uncharacterized protein PRO1854_S10A_mutation Human genes 0.000 description 5
- 239000003086 colorant Substances 0.000 description 5
- 230000002457 bidirectional effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 102200082907 rs33918131 Human genes 0.000 description 3
- 230000004397 blinking Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 235000021067 refined food Nutrition 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Definitions
- the present invention relates to a technique for presenting a recommended company according to a target company.
- Patent Document 1 describes a technique for presenting a recommended company according to the target company.
- the technique described in Patent Document 1 extracts recommended companies recommended as business partners of the target company based on a matching index such as a profit margin, and presents the extracted recommended companies together with the matching index.
- Non-Patent Document 1 describes techniques applicable when presenting a recommended company. The technique described in Non-Patent Document 1 predicts the evaluation value of the company by analyzing the text that evaluates the company, and presents the important points that contributed to the prediction in the text.
- Patent Document 1 With the technique described in Patent Document 1, the user cannot grasp information other than the matching index for the recommended company. For this reason, the user may not be able to obtain sufficient information about the recommended company presented, and it may be difficult to judge the effectiveness as a business partner.
- the technique described in Non-Patent Document 1 is applied when presenting a recommended company, the important part in the text evaluating the recommended company is an important part for judging the effectiveness as a business partner. Is not always. For this reason, the user may not be able to obtain sufficient information about the recommended company presented, and it may be difficult to judge the effectiveness.
- One aspect of the present invention has been made in view of the above problems. That is, one example of the object of one aspect of the present invention is to provide a technique that allows a user to more easily determine the effectiveness of a recommended company recommended as a candidate for collaboration with a target company.
- the recommendation device includes target company information including desired cooperation contents of the target company and cooperation candidate company information including desired cooperation contents of a plurality of companies that are candidates for cooperation of the target company. Based on this, an extraction means for extracting recommended companies recommended as candidates for cooperation of the target company from the plurality of companies, the first important part in the target company information, and the first in the information on the candidate companies for cooperation regarding the recommended company. (2) A specific means for specifying the important part, a collaboration candidate company information regarding the recommended company, and a presentation means for presenting the first important part and the second important part are provided.
- the recommendation device is a collaboration candidate including the target company information including the desired collaboration content of the target company and the desired collaboration content of a plurality of companies that are candidates for the collaboration destination of the target company.
- the recommended companies recommended as the candidate for cooperation of the target company are extracted from the plurality of companies, and the first important part in the target company information and the information on the candidate companies for cooperation regarding the recommended company are obtained.
- the second important part is specified, and the information on the candidate companies for collaboration regarding the recommended company and the first important part and the second important part are presented.
- the program according to one aspect of the present invention is a program that causes a computer to function as a recommendation device, and the program uses the computer as a target company information including a desired collaboration content of the target company and a business partner of the target company.
- An extraction means for extracting a recommended company recommended as a candidate for cooperation of the target company from the plurality of companies based on the information of the candidate company for cooperation including the desired cooperation contents of the plurality of candidate companies, and the target.
- the storage medium is a storage medium that stores a program that causes a computer to function as a recommendation device, and the program uses the computer as a target company information including a desired collaboration content of the target company.
- the recommended companies recommended as the cooperation destination candidates of the target company are extracted from the plurality of companies.
- the recommendation system includes a recommendation device and a user terminal, and the recommendation device includes target company information including desired collaboration contents of the target company indicated by input information acquired by the user terminal.
- the recommendation device includes target company information including desired collaboration contents of the target company indicated by input information acquired by the user terminal.
- the recommended companies recommended as the cooperation destination candidates of the target company are extracted from the plurality of companies.
- the user terminal includes a presentation means for presenting an important portion and the second important portion to the user terminal, and the user terminal has an input means for acquiring the input information and a display for displaying the information presented by the presentation means. Means and.
- the user can more easily determine the effectiveness of the recommended company recommended as a candidate for collaboration with the target company.
- the recommendation device 100 is a device that presents a recommended company according to the target company.
- the configuration of the recommendation device 100 will be described with reference to FIG.
- FIG. 1 is a block diagram showing the configuration of the recommendation device 100.
- the recommendation device 100 includes an extraction unit 101, a specific unit 102, and a presentation unit 103.
- the extraction unit 101 is configured to realize the extraction means in this exemplary embodiment.
- the specific unit 102 is configured to realize the specific means in this exemplary embodiment.
- the presentation unit 103 is configured to realize the presentation means in this exemplary embodiment.
- the extraction unit 101 is from a plurality of companies based on the target company information including the desired collaboration content of the target company and the collaboration candidate company information including the desired collaboration content of the plurality of companies that are candidates for the target company. , Extract recommended companies recommended as candidates for collaboration with target companies.
- the target company information and the collaboration candidate company information may be stored in the storage device included in the recommendation device 100, or may be stored in an external device communicably connected to the recommendation device 100. ..
- the extraction unit 101 extracts a company whose collaborative candidate company information is similar to the target company information from a plurality of companies as a recommended company.
- a technique for determining the similarity between information a known technique can be adopted.
- the process of extracting recommended companies from a plurality of companies is not limited to the above-mentioned process.
- the desired collaboration content is the business content that a company wants to collaborate with another company.
- the desired collaborative content includes the characteristics of the company sought as a collaborative destination.
- the desired collaboration content may include at least one of the company name, business content, development service, provided product, and corporate philosophy of the company.
- the specifying unit 102 specifies the first important part in the target company information and the second important part in the collaboration candidate company information regarding the recommended company.
- the specifying unit 102 may specify one first important part or may specify a plurality of first important parts.
- the specifying unit 102 may specify one second important part or may specify a plurality of second important parts.
- the specific unit 102 may set the portion of the target company information and the collaboration candidate company information whose importance is equal to or higher than the threshold value as the first important part and the second important part.
- a technique for determining the importance of a part included in information for example, a known technique as described later can be applied.
- the process for specifying the first important part and the second important part is not limited to the above-mentioned process.
- the presentation unit 103 presents information on candidate companies for collaboration regarding recommended companies, and the first important part and the second important part.
- the information presented by the presentation unit 103 will also be referred to as a “recommendation result”.
- the presentation unit 103 presents the recommendation result to the user, for example.
- the presentation unit 103 displays a screen showing the recommendation result on the display device.
- the display device may be included in the recommendation device 100, or may be an external device communicably connected to the recommendation device 100.
- the screen showing the recommendation result includes the target company information and the collaboration candidate company information regarding the recommended company.
- the screen includes the first important part in the target company information and the second important part in the collaboration candidate company information in an emphasized display mode.
- the process of presenting the recommendation result to the user is not limited to the above-mentioned process.
- FIG. 2 is a flow chart showing the flow of the recommendation method S100. As shown in FIG. 2, the recommendation method S100 includes steps S1 to S3.
- Step S1 the extraction unit 101 extracts recommended companies from a plurality of companies based on the target company information and the cooperation candidate company information of the plurality of companies.
- Step S2 the specific unit 102 specifies the first important part in the target company information and the second important part in the collaboration candidate company information.
- step S3 the presentation unit 103 presents the collaborative candidate company information regarding the recommended company and the recommendation result including the first important part and the second important part.
- this exemplary embodiment presents to the user the first important part in the target company information and the second important part in the collaboration candidate company information regarding the recommended company. As a result, the user can recognize the first important part and the second important part in comparison with each other. As a result, by such a comparison, the user can more easily determine the effectiveness of the recommended company recommended as a collaborative candidate of the target company.
- the recommendation system 10 is a system that presents recommended companies according to the target company.
- the configuration of the recommendation system 10 will be described with reference to FIG.
- FIG. 3 is a block diagram showing the configuration of the recommendation system 10.
- the recommendation system 10 includes a recommendation device 1 and a user terminal 3.
- the recommendation device 1 and the user terminal 3 are connected to each other so as to be able to communicate with each other.
- the recommendation device 1 includes an extraction unit 11, a specific unit 12, and a presentation unit 13.
- the extraction unit 11 is configured to realize the extraction means in this exemplary embodiment.
- the specific unit 12 is configured to realize the specific means in this exemplary embodiment.
- the presentation unit 13 is configured to realize the presentation means in this exemplary embodiment.
- the extraction unit 11 is configured in substantially the same manner as the extraction unit 101 in the exemplary embodiment 1, except that it receives input information indicating a target company among a plurality of companies from the user terminal 3. Since other points are configured in the same manner as the extraction unit 101, detailed description will not be repeated.
- the presentation unit 13 is configured in substantially the same manner as the presentation unit 103 in the exemplary embodiment 1, except that the recommendation result is presented to the user terminal 3. Specifically, the presentation unit 13 presents the recommendation result by transmitting it to the user terminal 3. Since other points are configured in the same manner as the presentation unit 103, detailed description will not be repeated.
- the user terminal 3 includes an input unit 31 and a display unit 32.
- the input unit 31 is configured to realize the input means in this exemplary embodiment.
- the display unit 32 is configured to realize the display means in this exemplary embodiment.
- the user terminal 3 is connected to an input device and a display device (both not shown).
- the input unit 31 acquires input information indicating a target company among a plurality of companies via an input device.
- the input unit 31 transmits the acquired input information to the recommendation device 1.
- the display unit 32 displays the recommendation result presented by the recommendation device 1 on the display device.
- FIG. 4 is a flow chart showing the flow of the recommendation method S10. As shown in FIG. 4, the recommendation method S10 includes steps S11 to S15.
- step S11 the input unit 31 of the user terminal 3 acquires input information indicating a target company among a plurality of companies.
- the input unit 31 transmits the acquired input information to the recommendation device 1.
- Step S12 the extraction unit 11 of the recommendation device 1 extracts recommended companies from a plurality of companies based on the target company information and the cooperation candidate company information of the plurality of companies.
- step S13 the specifying unit 12 specifies a first important part in the target company information and a second important part in the collaboration candidate company information.
- step S14 the presentation unit 13 presents the information on the candidate companies for collaboration regarding the recommended company and the recommendation result including the first important part and the second important part. Specifically, the presentation unit 13 presents the recommendation result to the user terminal 3 by transmitting the recommendation result to the user terminal 3.
- step S15 the display unit 32 of the user terminal 3 displays the recommendation result presented by the recommendation device 1 on the display device.
- the user of the user terminal inputs the information indicating the target company, and the first important part in the target company information and the first important part in the collaboration candidate company information regarding the recommended company. 2 It is possible to recognize by contrasting with the important part. As a result, the user can more easily determine the effectiveness of the recommended company according to the target company.
- the recommendation system 10A is a system that presents a recommended company according to a target company by referring to a need statement registered by each of a plurality of companies.
- the recommendation system 10A presents to the user the recommendation result of recommending the recommended company, including the correspondence between the first important part related to the target company and the second important part related to the recommended company.
- the configuration of the recommendation system 10A will be described with reference to FIG.
- FIG. 5 is a block diagram showing the configuration of the recommendation system 10A.
- the recommendation system 10A includes a recommendation device 1A and a user terminal 3A.
- the recommendation device 1A and the user terminal 3A are communicably connected via the network N1.
- FIG. 5 shows one user terminal 3A, the number of user terminals 3A to which the recommendation device 1A is connected is not limited.
- the network N1 is, for example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination of these networks.
- the configuration of the network N1 is not limited to these.
- the user terminal 3A includes a communication unit 33A in addition to the same configuration as the user terminal 3 in the exemplary embodiment 2.
- the communication unit 33A transmits / receives information to / from the recommendation device 1A via the network N1.
- the communication unit 33A transmits / receives information to / from the recommendation device 1A, and the user terminal 3A simply transmits / receives information to / from the recommendation device 1A.
- the recommendation device 1A includes a control unit 110A, a storage unit 120A, and a communication unit 130A.
- the control unit 110A includes an extraction unit 11A, a specific unit 12A, and a presentation unit 13A.
- the extraction unit 11A is configured to realize the extraction means in this exemplary embodiment.
- the specific unit 12A is configured to realize the specific means in this exemplary embodiment.
- the presentation unit 13A is configured to realize the presentation means in this exemplary embodiment. Details of these functional blocks included in the control unit 110A will be described later.
- the storage unit 120A stores the needs information database DB1. The details of the needs information database DB1 will be described later.
- the storage unit 120A is configured to realize the storage device in this exemplary embodiment.
- the communication unit 130A transmits / receives information to / from the user terminal 3A via the network N1 under the control of the control unit 110A.
- the control unit 110A transmits / receives information to / from the user terminal 3A via the communication unit 130A, and the control unit 110A simply transmits / receives information to / from the user terminal 3A.
- FIG. 6 is a diagram showing a specific example of the needs information database DB1.
- the needs information database DB1 stores information including a need statement for each of a plurality of companies.
- the needs statement of each company in this exemplary embodiment is an example of "target company information" and "cooperation candidate company information” described in the claims.
- the needs statement of each company includes a phrase indicating the characteristics of the business partner required by the company.
- the needs statement of each company may include at least one of the company name, business content, development service, provided product, and corporate philosophy of the company.
- the phrase "I am looking for a manufacturer of processed foods for gifts" included in the needs statement of company A shows an example of the characteristics of the business partner that company A seeks.
- the phrase "I am looking for a sales channel for freeze-dried foods” included in the needs statement related to company B shows an example of the characteristics of the business partner that company B seeks.
- the company in which the information including the needs statement is stored in the needs information database DB1 is also described as "a company in which the needs statement is registered in the needs information database DB1" or simply "a company in which the needs statement is registered”. do.
- the needs statement of a new company may be additionally registered after the start of operation of the recommendation device 1A.
- the already registered needs statement may be modified after the start of operation of the recommendation device 1A.
- the needs statement of the company that has already been registered may be deleted after the start of operation of the recommendation device 1A.
- the “plurality of companies” refers to a plurality of companies in which a need statement is registered in the needs information database DB1.
- Target company refers to one company to be matched among a plurality of companies.
- the target company is designated by the user of the recommendation device 1A.
- the “recommended company” refers to a company that is recommended as a collaborative partner of the target company among a plurality of companies.
- the “candidate company” refers to a company other than the target company among a plurality of companies.
- Candidate companies are companies that are candidates for recommended companies according to the target company.
- a candidate company is a company that is a candidate for collaboration with the target company.
- the extraction unit 11A refers to the needs sentences of each company stored in the needs information database DB 1, and extracts one or more candidate companies having similar needs sentences with the target company as recommended companies. The details of the method for judging the similarity between the needs sentences will be described later.
- the specific unit 12A specifies a phrase related to the business with which the target company wants to collaborate (hereinafter, also referred to as “important phrase”) from each of the needs sentence of the target company and the needs sentence of the recommended company. That is, the specific unit 12A specifies the first important part, which is one or more important phrases in the needs sentence of the target company, and the second important part, which is one or more important phrases in the needs sentence of the recommended company. Further, the specifying unit 12A specifies a correspondence relationship between each first important part and each second important part. Details of each first important part, each second important part, and a method for identifying the correspondence between them will be described later.
- the needs statement of the target company in this exemplary embodiment is an example of the "target company information" described in the claims. Further, the needs statement of the candidate company in this exemplary embodiment is an example of the "cooperation candidate company information" described in the claims.
- the presentation unit 13A presents the recommendation result to the user terminal 3A based on the correspondence relationship specified by the specific unit 12A.
- the recommendation result includes information indicating the correspondence between the first important part and the second important part, in addition to the same contents as the recommendation result in the exemplary embodiment 2.
- FIG. 7 is a flow chart showing the flow of the recommendation method S10A. As shown in FIG. 7, the recommendation method S10A includes steps S101 to S105.
- Step S101 the input unit 31 of the user terminal 3A acquires the input information indicating the target company among the plurality of companies in which the needs statement is registered via the input device.
- the input unit 31 transmits the acquired input information to the recommendation device 1A.
- Step S102 the extraction unit 11A refers to the needs sentence of each company and extracts one or more candidate companies having similar needs sentences from the target company indicated by the input information as recommended companies.
- Specific examples of the method for determining the similarity between the needs sentences include (a) a method based on the inter-word distance, (b) a method based on the inter-document distance, and (c) a method based on a learning model. Details of these methods will be described below. However, the method for judging the similarity between the needs sentences is not limited to these.
- the extraction unit 11A calculates the similarity between the needs sentences of the target company and each candidate company based on the inter-word distance. Specifically, the extraction unit 11A calculates the inter-word distance for each combination between each word included in the needs sentence of the target company and each word included in the needs sentence of the candidate company. Further, the extraction unit 11A calculates the degree of similarity between the needs sentences of the target company and the candidate company by using the calculated inter-word distance. Further, the extraction unit 11A extracts one or more candidate companies whose calculated similarity is equal to or more than the threshold value as recommended companies.
- n and m are natural numbers.
- the extraction unit 11A calculates n ⁇ m inter-word distances.
- the distance between words can be expressed by the angle formed by the two vectors or the Euclidean distance between the vectors.
- the extraction unit 11A calculates the degree of similarity between the needs sentences of the target company and the candidate company by using the statistical value of the distance between words. As a specific example, the extraction unit 11A calculates the similarity so that the smaller the average value of the inter-word distances of all combinations of words w1i and w2j, the larger the degree. Further, as another specific example, the extraction unit 11A calculates the degree of similarity so that the smaller the average value of the predetermined number of inter-word distances is, in order from the one with the shortest inter-word distance among all the combinations.
- the extraction unit 11A calculates the similarity between the needs sentences of the target company and each candidate company based on the distance between documents. Further, the extraction unit 11A extracts one or more candidate companies having a similarity equal to or higher than the threshold value as recommended companies.
- the distance between the documents of the need sentences can be expressed by the angle formed by the two vectors or the Euclidean distance between the vectors.
- a technique for expressing the features of a needs sentence as a vector it is conceivable to use a learning model machine-learned to output a feature vector with the needs sentence as an input.
- a technique such as doc2vec can be applied, but the learning model is not limited to this.
- the extraction unit 11A calculates the similarity so that the smaller the distance between documents, the larger the degree.
- the extraction unit 11A uses a learning model that has been trained by machine learning so as to input the needs sentences of two companies and output information indicating the similarity between the needs sentences.
- the extraction unit 11A inputs the needs sentence of the target company and the needs sentence of the candidate company into the learning model. Further, the extraction unit 11A extracts one or more candidate companies for which "information indicating similarity" is output from the learning model as recommended companies.
- the extraction unit 11A generates a learning model in advance by machine learning as follows.
- the extraction unit 11A uses each need sentence of two companies having actual matching cases as teacher data among a plurality of companies, and learns so that information indicating that they are similar when these needs sentences are input is output. Train the model. Further, for example, the extraction unit 11A trains the learning model so that when inputting the needs sentences of two companies having no matching case, information indicating that they are not similar is output.
- the extraction unit 11A may generate a learning model by performing transfer learning or fine tuning using a pre-trained model. Specific examples of the pre-trained model include, but are not limited to, BERT (Bidirectional Encoder Representations from Transformers).
- the learning model may have been trained to output the degree of similarity instead of outputting information indicating whether or not they are similar. In this case, the extraction unit 11A extracts one or more candidate companies whose similarity equal to or higher than the threshold value is output as recommended companies.
- step S103 the specifying unit 12A identifies one or more first important parts in the needs statement of the target company and one or more second important parts in the needs sentence of each recommended company. Further, the specifying unit 12A specifies a correspondence relationship between each first important part and each second important part. In addition, in order to specify the "correspondence relationship between each first important part and each second important part", the specific unit 12A has a correspondence relationship among the combinations of each first important part and each second important part. Identify combinations with.
- step S102 (D: Method based on interword distance) It is desirable that this method is applied when the extraction unit 11A uses "(a) a method based on the inter-word distance" in step S102.
- the specific unit 12A has each first important part and each first important part based on the inter-word distance between each word included in the needs sentence of the target company and each word included in the needs sentence of the recommended company. Identify each second important part of the recommended company's needs statement.
- the specific unit 12A may refer to the value calculated by the extraction unit 11A in the method (a) for the inter-word distance of each combination.
- the words included in the needs sentence of the target company are regarded as important words in the needs sentences of the target company.
- the words included in the needs sentence of the recommended company are set as important words in the needs sentences of the recommended company.
- the specific unit 12A calculates a score based on the important words included in each constituent unit of the needs sentence of the target company, and the constituent unit whose calculated score is equal to or higher than the threshold value is set as the first important part. Further, for example, the specific unit 12A calculates a score based on the important words included in each constituent unit of the needs sentence of the recommended company, and the constituent unit whose calculated score is equal to or higher than the threshold value is set as the second important portion.
- specific examples of the structural unit include, but are not limited to, phrases or paragraphs.
- Specific examples of the score include, but are not limited to, a value based on the number of important words included.
- the specifying unit 12A specifies, among the combinations of each first important part and each second important part, a combination in which the statistical value of the inter-word distance between the included important words is equal to or less than the threshold value as a combination having a corresponding relationship. do.
- the specific unit 12A identifies each first important part and each second important part based on the importance of each word included in each need sentence of the target company and the recommended company. For example, the specific unit 12A calculates a score based on the importance of each word included in each constituent unit of the needs sentence of the target company, and the constituent unit whose calculated score is equal to or higher than the threshold value is set as the first important portion. Further, for example, the specific unit 12A calculates a score based on the importance of each word included in each constituent unit of the needs sentence of the recommended company, and the constituent unit whose calculated score is equal to or higher than the threshold value is set as the second important portion. ..
- the specific unit 12A specifies that they have a corresponding relationship.
- each first important part and each second important part are regarded as documents and the distance between documents is determined. It may be calculated.
- the specifying unit 12A specifies, among the combinations of each first important part and each second important part, the combination in which the distance between documents is equal to or less than the threshold value as a combination having a corresponding relationship.
- TF-IDF Term Frequency-Inverse Document Frequency
- TF-IDF Term Frequency-Inverse Document Frequency
- the learning model used in "(b) the method based on the distance between documents" or “(c) the method based on the learning model” is input to the target company and the recommended company.
- Each first important part and each second important part are specified based on the part of interest in each needs sentence.
- the specific unit 12A uses the attention mechanism built into the learning model to obtain the degree of attention of each word included in the input needs sentence. Further, the extraction unit 11A calculates a score based on the degree of attention of the included words for each constituent unit of the needs sentence of the target company, and the constituent unit whose calculated score is equal to or higher than the threshold value is set as the first important part. Further, the extraction unit 11A calculates a score based on the degree of attention of the included words for each constituent unit of the needs sentence of the recommended company, and the constituent unit whose calculated score is equal to or higher than the threshold value is set as the second important part.
- the method for specifying the correspondence relationship when the first important part and the second important part are specified one by one is as described in "(e): Method based on the importance of words”. Further, the method for specifying the correspondence relationship when a plurality of parts are specified as one or both of the first important part and the second important part is as described in "(e): Method based on the importance of words”. ..
- Step S104 the presentation unit 13A presents the recommendation result to the user terminal 3A.
- the recommendation result includes information indicating the recommended company, the first important part and the second important part, and the information indicating the correspondence between them.
- the presentation unit 13A generates screen data showing the recommendation result.
- the presentation unit 13A presents the recommendation result to the user terminal 3A by transmitting the screen data to the user terminal 3A.
- the presentation unit 13A generates screen data including the needs statement of the target company and the needs statement of the recommended company. Further, the presentation unit 13A makes the display mode of the first important portion different from the display mode of the portion other than the first important portion in the needs sentence of the target company included in such screen data. Further, the presentation unit 13A makes the display mode of the second important portion different from the display mode of the portion other than the second important portion in the needs statement of the recommended company included in such screen data. Further, the presentation unit 13A may have a display mode in which the first important portion and the second important portion correspond to each other in such screen data. Specifically, the presentation unit 13A may apply different display modes to each combination of the first important part and the second important part having a corresponding relationship. Details of such screen data will be described later.
- Step S105 the display unit 32 of the user terminal 3A displays the recommendation result presented by the recommendation device 1A. Specifically, the display unit 32 displays the screen data received from the recommendation device 1A on the display device. An example of a screen displayed on the user terminal 3A in this step will be described below.
- FIG. 8 shows a screen example G1 of the recommendation result.
- the screen example G1 includes the needs sentence A of the target company A and the needs sentences H, I, L of the recommended companies H, I, L.
- the first important parts p1 to p3 are specified.
- the second important part p4 is specified.
- the second important part p5 is specified.
- the second important part p6 is specified.
- the first important parts p1 to p3 and the second important parts p4 to p6 are displayed in different display modes from the other parts in the corresponding needs sentence, respectively.
- the display mode applied to the important portion is, but is not limited to, the display mode surrounded by a rectangle.
- the first important parts p1 to p3 and the second important parts p4 to p6 have different colors, different background colors, different fonts, different sizes, different brightness, bold characters, italics, etc. It may be displayed in an underlined, blinking, animated display, or a combination of at least two of these.
- different display modes may be applied to each combination of the first important portion and the second important portion having a corresponding relationship.
- the rectangle surrounding the first important part p1 and the second important part p4 is colored red
- the rectangle surrounding the first important part p2 and the second important part p5 is colored blue
- the first important part p3 and the second important part p3 are colored.
- the rectangle surrounding each p6 may be yellow.
- the display mode different from each other for each combination having a corresponding relationship is not limited to this.
- the display mode applied to each combination includes different background colors, different fonts, different sizes, different brightnesses, or at least two combinations thereof.
- the bold words in the needs sentences A, H, I, and L are the words specified as important words in the corresponding needs sentences.
- important words are displayed in a display mode different from other words.
- the display mode applied to important words is not limited to bold.
- important words may have different colors, different background colors, different fonts, different sizes, different brightness, italics, underlining, blinking, animations, borders, or a combination of at least two of these. It may be displayed in a display mode.
- the screen example G1 includes figures f1 to f3 showing a correspondence relationship between each first important part and each second important part.
- the figures f1 to f3 are bidirectional arrows, respectively.
- the figures f1 to f3 are not limited to the bidirectional arrows.
- the figures f1 to f3 may be lines other than arrows, broken lines, alternate long and short dash lines, double lines, curves, free lines, and the like.
- the figure f1 shows that the first important portion p1 and the second important portion p4 have a correspondence relationship.
- the figure f2 shows that the first important portion p2 and the second important portion p5 have a correspondence relationship.
- the figure f3 shows that the first important portion p3 and the second important portion p6 have a correspondence relationship.
- the user can recognize that the first important part p1 in the needs sentence A of the company A corresponds to the second important part p4 in the needs sentence H by the figure f1. Further, it can be recognized from the figure f2 that the second important part p5 in the needs sentence I corresponds to the first important part p2 in the needs sentence A.
- the first important parts p1 and p2 in the needs sentence A indicate the business policy of the company A, and do not sufficiently represent the characteristics of the business partner required by the company A. In this case, the user can easily determine that the companies H and I including the second important parts p4 and p5 corresponding to the first important parts p1 and p2 are less effective as the business partner of the company A. ..
- the user can recognize that the second important part p6 in the needs sentence L corresponds to the first important part p3 in the needs sentence A of the company A by the figure f3.
- the first important part p3 in the needs sentence A fully expresses the characteristics of the business partner required by the company A.
- the user can easily determine that the company L including the second important part p6 corresponding to the first important part p3 is highly effective as a business partner of the company A.
- the screen example G1 does not have to include the figures f1 to f3. In this case, the user can easily recognize the correspondence between them by visually recognizing the second important part of the display mode corresponding to the display mode of the first important part.
- the present exemplary embodiment presents the recommendation result to the user terminal including information indicating the correspondence relationship between each first important part and each second important part.
- the user can recognize which part of the needs statement of the target company corresponds to which part of the needs statement of the recommended company.
- the user can judge that the recommended company corresponding to the first important part of the needs statement of the target company, which more fully expresses the characteristics of the desired business partner, is highly effective as a business partner. can.
- the user can determine that the recommended company corresponding to the first important part of the needs statement of the target company, which does not sufficiently express the characteristics of the desired business partner, is not effective.
- the user can more easily determine the effectiveness of the recommended company according to the target company.
- the recommendation system 10B according to the present exemplary embodiment is a modification of the exemplary embodiment 3.
- the recommendation system 10B presents a company that is unlikely to compete with the target company as a recommended company according to the target company.
- the configuration of the recommendation system 10B will be described with reference to FIG.
- FIG. 9 is a block diagram showing the configuration of the recommendation system 10B.
- the recommendation system 10B is configured in substantially the same manner as the recommendation system 10A according to the exemplary embodiment 3, except that the recommendation device 1B is provided in place of the recommendation device 1A. Other points are the same as those of the recommendation system 10A.
- the recommendation device 1B includes a control unit 110B, a storage unit 120B, and a communication unit 130A.
- the control unit 110B is configured in substantially the same manner as the control unit 110A in the third embodiment, except that the extraction unit 11B is provided in place of the extraction unit 11A. Other points are the same as those of the control unit 110A.
- the storage unit 120B is configured in the same manner as the storage unit 120A in the exemplary embodiment 3, and further includes the company information database DB2.
- FIG. 10 is a diagram showing a specific example of the corporate information database DB2.
- the company information database DB2 stores company information about each of a plurality of companies.
- corporate information includes information indicating an industry.
- information indicating the industry "information and communication" is stored as the company information of the companies A, I, J, and K.
- the company information of the company H information indicating the industry "pharmaceutical manufacturing” is stored.
- the company information of the company L information indicating the industry "wholesale of chemical products” is stored.
- the company information may include other information about the company in place of or in addition to the information indicating the type of business.
- the extraction unit 11B refers to the company information database DB2 and extracts one or more candidate companies other than the competitors of the target company as recommended companies according to the target company. The details of the extraction process will be described later.
- FIG. 11 is a flow chart showing the flow of the recommendation method S10B.
- the recommendation method S10B is configured in substantially the same manner as the recommendation method S10A in the exemplary embodiment 3, except that steps S102a to 102c are included instead of step S102.
- steps S102a to S102c will be described. Since the other steps are the same as the recommendation method S10A, the detailed description will not be repeated.
- Step S102a the extraction unit 11B of the recommendation device 1B extracts one or more candidate companies having similar needs sentences with the target company as candidates for the recommended company according to the target company. Since the details of the process of extracting the candidate of the recommended company in this step are the same as the process of extracting the recommended company in step S102 of the exemplary embodiment 3, the detailed description will not be repeated.
- Step S102b the extraction unit 11B refers to the company information database DB2 and estimates one or more competitors that compete with the target company among the candidates for the recommended company.
- the extraction unit 11B refers to the company information database DB2 and estimates, among the candidates for the recommended company, a company in the same industry as the target company as a competitor. For example, in the example of the company information database DB2 shown in FIG. 10, it is assumed that companies H, I, J, K, and L are extracted as candidates for recommended companies of company A. In this case, the extraction unit 11B estimates the companies I, J, and K, whose industry is the same as that of the company A, among the candidates for the recommended company, as competitors.
- the method of estimating competitors by referring to company information is not limited to this.
- the extraction unit 11B may use a learning model trained to output the degree of competition by inputting the company information of two companies.
- the extraction unit 11B inputs the company information of the target company and the company information of the candidate of the recommended company into the learning model, and estimates the candidate whose output competition degree is equal to or more than the threshold as a competitor.
- the input company information includes the business type, business content, focus business content, collaborative destination information, and the like of the company.
- step S102c the extraction unit 11B excludes competitors from the candidates for recommended companies and sets them as recommended companies. In other words, the extraction unit 11B extracts companies other than competitors from the candidates for recommended companies as recommended companies.
- the recommendation system 10B displays the recommendation result on the display device of the user terminal 3A by executing steps S103 to S105.
- FIG. 12 shows a screen example G2 of the recommendation result.
- the screen example G2 includes the needs sentence A of the target company A and the needs sentences H and L of the recommended companies H and L.
- the screen example G2 does not include the needs statement of the company I presumed to be a competitor among the recommended companies H, I, and L included in the screen example G1 in the exemplary embodiment 2.
- the screen example G2 includes figures f1 and f3 showing a correspondence relationship between the first important part p1 in the needs sentence of the target company A and the second important parts p4 and p6 in each of the needs sentences of the recommended companies H and L. ..
- the recommendation result for recommending a recommended company other than the competitors is presented with information indicating the correspondence relationship between each first important part and each second important part.
- each first important part and each second important part The correspondence with the user is not presented to the user. Therefore, the user can more easily determine the effectiveness of the presented recommended company.
- the configuration in which the needs information database DB1 and the company information database DB2 are separate databases has been described.
- the configuration of the database is not limited to that shown in the above-described embodiment. Needs statements and company information may be stored in one database.
- the company information stored in the company information database DB 2 may include a needs statement and information on the type of business.
- the company information of each company stored in the company information database DB2 is an example of the "target company information" and the "cooperation candidate company information" described in the scope of the request.
- the recommendation system 10C is a modification of the exemplary embodiment 4.
- the recommendation system 10C classifies and presents candidates for recommended companies according to the target company into competitors and non-competitors.
- the configuration of the recommendation system 10C will be described with reference to FIG.
- FIG. 13 is a block diagram showing the configuration of the recommendation system 10C.
- the recommendation system 10C includes a recommendation device 1C and a user terminal 3C.
- the recommendation device 1C is configured in substantially the same manner as the recommendation device 1B in the exemplary embodiment 4, except that the control unit 110C is provided in place of the control unit 110B.
- the control unit 110C is configured in substantially the same manner as the control unit 110B in the exemplary embodiment 4, except that the presentation unit 13C is provided in place of the presentation unit 13A.
- Other points are the same as those of the recommendation device 1B.
- the presentation unit 13C classifies the recommended company candidates according to the target company into competitors and non-competitors and presents them to the user terminal 3A. The details of the processing to be classified and presented will be described later.
- the user terminal 3C includes an input unit 31C and a display unit 32C.
- the input unit 31C is configured in the same manner as the input unit 31 in the exemplary embodiment 4, and further transmits input information for designating a recommended company to the recommendation device 1C. The details of the process of transmitting the input information will be described later.
- the display unit 32C further classifies and displays candidates for recommended companies into competitors and non-competitors. The details of the displayed process will be described later.
- FIG. 14 is a flow chart showing the flow of the recommendation method S10C.
- the recommendation method S10C is configured in substantially the same manner as the recommendation method S10B in the exemplary embodiment 4, except that steps S102d to S102f are included instead of step S102c.
- steps S102d to S102f will be described. Since the other steps are the same as those of the recommendation method S10B, the detailed description will not be repeated.
- Step S102d the presentation unit 13C of the recommendation device 1C classifies the candidates of the recommended company into competitors and non-competitors and presents them to the user terminal 3C. Specifically, the presentation unit 13C generates screen data in which the recommended company candidates extracted in step S102a are classified into competitors and non-competitors estimated in step S102b. By transmitting the screen data to the user terminal 3C, the presentation unit 13C classifies them and presents them to the user terminal 3C.
- Step S102e the display unit 32C of the user terminal 3C classifies the candidates of the recommended company according to the target company into competitors and non-competitors and displays them on the display device. Specifically, the display unit 32 displays the screen data received from the recommendation device 1A on the display device.
- Step S102f the input unit 31C of the user terminal 3C acquires the input information for designating the recommended company via the input device.
- the input unit 31C transmits the acquired input information to the recommendation device 1C.
- the user performs an operation of designating one or more of the recommended company candidates displayed in step S102d as the recommended company by using the input device.
- the recommendation system 10C displays the recommendation result on the display device of the user terminal 3C by executing steps S103 to S105.
- FIG. 15 is a screen example G3 of the candidate of the recommended company displayed in step S102e.
- the screen example G3 includes a region R indicating the companies H, I, L, K, and L as candidates for the recommended company of the company A, which is the target company.
- each area R of the companies I, J, and K is surrounded by a frame indicating a competitor.
- the companies H and L are surrounded by a frame indicating a company other than the competitors.
- the companies H, I, L, K, and L which are candidates for the recommended company, are classified into competitors and non-competitors and displayed.
- the frame indicating a competitor and the frame indicating a non-competitor are examples of display modes for classifying competitors and non-competitors, but the present invention is not limited to this.
- the display unit 32C receives screen data indicating such a screen example G3 from the recommendation device 1C, and displays the received screen data on the display device.
- Each area R receives an operation by an input device.
- the user designates the company indicated by each area R as a recommended company by performing an operation of designating one or more of the displayed plurality of areas R using the input device.
- the input unit 31 acquires input information indicating one or more designated recommended companies and transmits it to the recommendation device 1C. In this example, it is assumed that the user performs an operation of designating the company I classified as a competitor and the company H classified as a non-competitor as a recommended company.
- FIG. 16 shows a screen example G4 of the recommendation result displayed in step S105.
- the screen example G4 includes the needs sentence A of the target company A.
- the screen example G4 includes the needs statements of the companies H and I, which are the recommended companies designated by the user.
- the company H is a company classified as a company other than the competitors.
- the company I is a company classified as a competitor.
- the screen example G4 includes figures f1 and f2 showing a correspondence relationship between the first important part p1 in the needs sentence of the company A and the second important parts p4 and p5 in each of the needs sentences of the companies H and I. ..
- the user can specify the company I that he / she wants to consider as a business partner as a recommended company even if it is presumed to be a competitor, and can visually recognize each of these needs statements in comparison.
- this exemplary embodiment shows the correspondence between each first important part and each second important part for the recommended company designated by the user from the candidates of the recommended company and the target company.
- Present information to the user As a result, the user can browse the needs statement in comparison with the company that he / she wants to consider as a collaborative partner even if it is presumed to be a competitor. Therefore, the user can more easily determine the effectiveness of the recommended company.
- Some or all the functions of the recommendation devices 1, 1A, 1B, and 1C may be realized by hardware such as an integrated circuit (IC chip) or by software.
- the recommendation devices 1, 1A, 1B, and 1C are realized by, for example, a computer that executes a program instruction that is software that realizes each function.
- a computer that executes a program instruction that is software that realizes each function.
- An example of such a computer (hereinafter referred to as computer C) is shown in FIG.
- the computer C includes at least one processor C1 and at least one memory C2.
- a program P for operating the computer C as the recommendation devices 1, 1A, 1B, and 1C is recorded in the memory C2.
- the processor C1 reads the program P from the memory C2 and executes it, so that the functions of the recommendation devices 1, 1A, 1B, and 1C are realized.
- Examples of the processor C1 include CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), and PPU (Physics Processing Unit). , Microcontrollers, or combinations thereof.
- the memory C2 for example, a flash memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a combination thereof can be used.
- the computer C may further include a RAM (RandomAccessMemory) for expanding the program P at the time of execution and temporarily storing various data. Further, the computer C may further include a communication interface for transmitting / receiving data to / from another device. Further, the computer C may further include an input / output interface for connecting an input / output device such as a keyboard, a mouse, a display, and a printer.
- RAM RandomAccessMemory
- the computer C may further include a communication interface for transmitting / receiving data to / from another device. Further, the computer C may further include an input / output interface for connecting an input / output device such as a keyboard, a mouse, a display, and a printer.
- the program P can be recorded on a non-temporary tangible recording medium M that can be read by the computer C.
- a recording medium M for example, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used.
- the computer C can acquire the program P via such a recording medium M.
- the program P can be transmitted via a transmission medium.
- a transmission medium for example, a communication network, a broadcast wave, or the like can be used.
- the computer C can also acquire the program P via such a transmission medium.
- the first important part in the target company information and the second important part in the collaboration candidate company information regarding the recommended company are presented to the user.
- the user can recognize the first important part and the second important part in comparison with each other.
- the user can more easily determine the effectiveness of the recommended company recommended as a collaborative candidate of the target company.
- the specifying means identifies the correspondence between the first important part and the second important part.
- the presenting means further presents information indicating the correspondence.
- the user can recognize the correspondence between the first important part and the second important part, so that the effectiveness of the recommended company recommended as a collaborative candidate of the target company becomes easier. You can judge.
- the content of the collaboration includes at least one of the company name, business content, development service, provided product, and corporate philosophy of the company.
- the user can more easily determine the effectiveness of the recommended company as a collaborative destination of the target company as a collaborative destination candidate.
- the specific means identifies the first important part and the second important part based on the inter-word distance between each word included in the target company information and each word included in the collaboration candidate company information.
- the recommendation device according to any one of Supplementary note 1 to 3, characterized in that.
- the user can be presented with the first important part and the second important part specified by reflecting the inter-word distance between the target company information and the collaboration candidate company information.
- the specific means identifies the first important part and the second important part based on the importance of each word included in each of the target company information and the collaboration candidate company information.
- the recommendation device according to any one of Supplementary note 1 to 3, characterized in that.
- the user can be presented with the first important part and the second important part specified by reflecting the importance in each information.
- the extraction means extracts the recommended company by referring to the information output from the learning model that inputs the target company information and the collaboration candidate company information.
- the specific means identifies the first important part and the second important part based on the parts of the learning model that the learning model pays attention to in each of the target company information and the collaboration candidate company information.
- the recommendation device according to any one of Supplementary note 1 to 3, characterized in that.
- the extraction means refers to the company information of each of the plurality of companies, and extracts a company other than the competitors of the target company as the recommended company.
- the recommendation device according to any one of Supplementary Provisions 1 to 6, characterized in that.
- the first important part and the second important part are presented to the user for the companies that are likely to be competitors even if the contents of collaboration with the target company are similar. There is no. Therefore, the user can more easily determine the effectiveness of the presented recommended company.
- the presenting means displays the target company information and the collaboration candidate company information on a display device, and displays the first important part and the part other than the first important part in the target company information in different display modes.
- the collaboration candidate company information the second important part and the part other than the second important part are displayed in different display modes.
- the recommendation device according to any one of Supplementary note 1 to 7, wherein the recommendation device is described.
- the user can more easily recognize that the first important part and the second important part are important parts different from the other parts.
- the presenting means displays the first important portion and the second important portion on a display device in display modes corresponding to each other.
- the recommendation device according to any one of Supplementary Provisions 1 to 8, characterized in that.
- each first important part and each second important part can be more easily associated and recognized by the user.
- the recommendation device is Based on the target company information including the desired collaboration content of the target company and the collaboration candidate company information including the desired collaboration content of the plurality of companies that are candidates for the cooperation destination of the target company, the target from the plurality of companies. Extract recommended companies that are recommended as potential business partners Identify the first important part in the target company information and the second important part in the collaboration candidate company information regarding the recommended company. Information on collaborative candidate companies regarding the recommended company, and the first important part and the second important part are presented. A recommendation method characterized by that.
- a program that makes a computer function as a recommendation device The program is the computer. Based on the target company information including the desired collaboration content of the target company and the collaboration candidate company information including the desired collaboration content of the plurality of companies that are candidates for the cooperation destination of the target company, the target from the plurality of companies.
- An extraction method for extracting recommended companies that are recommended as potential business partners Specific means for specifying the first important part in the target company information and the second important part in the collaboration candidate company information regarding the recommended company, and It functions as a presentation means for presenting the collaborative candidate company information regarding the recommended company and the first important part and the second important part.
- a storage medium that stores a program that makes a computer function as a recommendation device.
- the program is the computer.
- the recommendation device is Based on the target company information including the desired collaboration content of the target company indicated by the input information acquired by the user terminal, and the collaboration candidate company information including the desired collaboration content of a plurality of companies that are candidates for the cooperation destination of the target company. Then, from the plurality of companies, an extraction means for extracting recommended companies recommended as potential business partners of the target company, and Specific means for specifying the first important part in the target company information and the second important part in the collaboration candidate company information regarding the recommended company, and A collaborative candidate company information regarding the recommended company and a presentation means for presenting the first important part and the second important part to the user terminal are provided.
- the user terminal is An input means for acquiring the input information and A display means for displaying information presented by the presentation means, and the like.
- a recommendation system that features that.
- It comprises at least one processor, said processor.
- the target company information including the desired collaboration content of the target company and the collaboration candidate company information including the desired collaboration content of the plurality of companies that are candidates for the cooperation destination of the target company
- the target from the plurality of companies.
- Extraction processing to extract recommended companies recommended as potential business partners
- the presentation process for presenting the collaborative candidate company information regarding the recommended company and the first important part and the second important part.
- a recommendation device that runs.
- the recommendation device may further include a memory, even if the memory stores a program for causing the processor to execute the pre-extraction process, the specific process, and the present process. good.
- the program may also be recorded on a computer-readable, non-temporary, tangible recording medium.
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
本発明の第1の例示的実施形態について、図面を参照して詳細に説明する。本例示的実施形態は、後述する例示的実施形態の基本となる形態である。
本例示的実施形態に係るレコメンド装置100は、対象企業に応じた推奨企業を提示する装置である。レコメンド装置100の構成について、図1を参照して説明する。図1は、レコメンド装置100の構成を示すブロック図である。
以上のように構成されたレコメンド装置100が実行するレコメンド方法S100の流れについて、図2を参照して説明する。図2は、レコメンド方法S100の流れを示すフロー図である。図2に示すように、レコメンド方法S100は、ステップS1~S3を含む。
ステップS1において、抽出部101は、対象企業情報と、複数の企業の協業候補企業情報とに基づいて、複数の企業から推奨企業を抽出する。
ステップS2において、特定部102は、対象企業情報における第1重要部分と、協業候補企業情報における第2重要部分と、を特定する。
ステップS3において、提示部103は、推奨企業に関する協業候補企業情報と、第1重要部分および第2重要部分とを含むレコメンド結果を提示する。
以上のように、本例示的実施形態は、対象企業情報における第1重要部分と、推奨企業に関する協業候補企業情報における第2重要部分とをユーザに提示する。これにより、ユーザは、第1重要部分と第2重要部分とを対比して認識することができる。その結果、このような対比により、ユーザは、対象企業の協業先候補として推奨される推奨企業の有効性をより容易に判断することができる。
本発明の第2の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を繰り返さない。
本例示的実施形態に係るレコメンドシステム10は、対象企業に応じた推奨企業を提示するシステムである。レコメンドシステム10の構成について、図3を参照して説明する。図3は、レコメンドシステム10の構成を示すブロック図である。
図3に示すように、レコメンド装置1は、抽出部11と、特定部12と、提示部13とを備える。抽出部11は、本例示的実施形態において抽出手段を実現する構成である。特定部12は、本例示的実施形態において特定手段を実現する構成である。提示部13は、本例示的実施形態において提示手段を実現する構成である。
図3に示すように、ユーザ端末3は、入力部31と、表示部32とを備える。入力部31は、本例示的実施形態において入力手段を実現する構成である。表示部32は、本例示的実施形態において表示手段を実現する構成である。ユーザ端末3は、入力装置および表示装置(何れも不図示)に接続される。
以上のように構成されたレコメンドシステム10が実行するレコメンド方法S10の流れについて、図4を参照して説明する。図4は、レコメンド方法S10の流れを示すフロー図である。図4に示すように、レコメンド方法S10は、ステップS11~S15を含む。
ステップS11において、ユーザ端末3の入力部31は、複数の企業のうち対象企業を示す入力情報を取得する。入力部31は、取得した入力情報をレコメンド装置1に送信する。
ステップS12において、レコメンド装置1の抽出部11は、対象企業情報と、複数の企業の協業候補企業情報とに基づいて、複数の企業から推奨企業を抽出する。
ステップS13において、特定部12は、対象企業情報における第1重要部分と、協業候補企業情報における第2重要部分と、を特定する。
ステップS14において、提示部13は、推奨企業に関する協業候補企業情報と、第1重要部分および第2重要部分とを含むレコメンド結果を提示する。具体的には、提示部13は、レコメンド結果をユーザ端末3に送信することにより、ユーザ端末3に提示する。
ステップS15において、ユーザ端末3の表示部32は、レコメンド装置1から提示されたレコメンド結果を表示装置に表示する。
以上の構成により、本例示的実施形態によれば、ユーザ端末のユーザは、対象企業を示す情報を入力することにより、対象企業情報における第1重要部分と、推奨企業に関する協業候補企業情報における第2重要部分とを対比して認識することができる。その結果、ユーザは、対象企業に応じた推奨企業の有効性をより容易に判断することができる。
本発明の第3の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1~2にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を繰り返さない。
本例示的実施形態に係るレコメンドシステム10Aは、複数の企業の各々によって登録されたニーズ文を参照して、対象企業に応じた推奨企業を提示するシステムである。レコメンドシステム10Aは、推奨企業を推奨するレコメンド結果に、対象企業に係る第1重要部分と、推奨企業に係る第2重要部分との対応関係を含めてユーザに提示する。レコメンドシステム10Aの構成について、図5を参照して説明する。図5は、レコメンドシステム10Aの構成を示すブロック図である。
図5に示すように、ユーザ端末3Aは、例示的実施形態2におけるユーザ端末3と同様の構成に加えて、通信部33Aを備える。
図5に示すように、レコメンド装置1Aは、制御部110Aと、記憶部120Aと、通信部130Aとを含む。制御部110Aは、抽出部11Aと、特定部12Aと、提示部13Aとを備える。抽出部11Aは、本例示的実施形態において抽出手段を実現する構成である。特定部12Aは、本例示的実施形態において特定手段を実現する構成である。提示部13Aは、本例示的実施形態において提示手段を実現する構成である。制御部110Aに含まれるこれらの機能ブロックの詳細については後述する。
ニーズ情報データベースDB1の構成について、図6を参照して説明する。図6は、ニーズ情報データベースDB1の具体例を示す図である。図6に示すように、ニーズ情報データベースDB1は、複数の企業の各々についてニーズ文を含む情報を格納する。本例示的実施形態における各企業のニーズ文は、請求の範囲に記載した「対象企業情報」および「協業候補企業情報」の一例である。各企業のニーズ文は、当該企業が求める協業先の特徴を示すフレーズを含む。また、各企業のニーズ文は、当該企業の企業名、事業内容、展開サービス、提供製品、及び企業理念、の少なくとも一つを含んでいてもよい。
以降、ニーズ情報データベースDB1にニーズ文を含む情報が格納される企業を、「ニーズ情報データベースDB1にニーズ文が登録された企業」、または、単に、「ニーズ文が登録された企業」、とも記載する。新たな企業のニーズ文が、レコメンド装置1Aの運用開始後に追加して登録される場合もあり得る。また、既に登録されたニーズ文が、レコメンド装置1Aの運用開始後に修正される場合もあり得る。また、既に登録された企業のニーズ文が、レコメンド装置1Aの運用開始後に削除される場合もあり得る。
「複数の企業」とは、ニーズ情報データベースDB1にそれぞれニーズ文が登録されている複数の企業を指す。
「対象企業」とは、複数の企業のうち、マッチングの対象となる1の企業を指す。対象企業は、レコメンド装置1Aのユーザにより指定される。
「推奨企業」とは、複数の企業のうち、対象企業の協業先として推奨する企業を指す。
「候補企業」とは、複数の企業のうち、対象企業以外の企業を指す。候補企業は、対象企業に応じた推奨企業の候補となる企業である。換言すると、候補企業とは、対象企業の協業先候補となる企業である。1つの対象企業に対して、1以上の候補企業が存在する。
抽出部11Aは、ニーズ情報データベースDB1に格納された各企業のニーズ文を参照して、対象企業との間でニーズ文同士が類似する1以上の候補企業を、推奨企業として抽出する。ニーズ文同士の類似性を判断する手法の詳細については後述する。
特定部12Aは、対象企業のニーズ文及び推奨企業のニーズ文それぞれから、該対象企業が協業したいビジネスに関するフレーズ(以下、「重要フレーズ」ともいう。)を特定する。すなわち、特定部12Aは、対象企業のニーズ文における1以上の重要フレーズである第1重要部分と、推奨企業のニーズ文における1以上の重要フレーズである第2重要部分と、を特定する。また、特定部12Aは、各第1重要部分と各第2重要部分との間の対応関係を特定する。各第1重要部分、各第2重要部分、およびそれらの間の対応関係を特定する手法の詳細については後述する。
提示部13Aは、特定部12Aが特定した対応関係に基づいて、レコメンド結果をユーザ端末3Aに提示する。レコメンド結果は、例示的実施形態2におけるレコメンド結果と同様の内容に加えて、第1重要部分と第2重要部分との間の対応関係を示す情報を含む。
以上のように構成されたレコメンドシステム10Aが実行するレコメンド方法S10Aの流れについて、図7を参照して説明する。図7は、レコメンド方法S10Aの流れを示すフロー図である。図7に示すように、レコメンド方法S10Aは、ステップS101~S105を含む。
ステップS101において、ユーザ端末3Aの入力部31は、ニーズ文が登録された複数の企業のうち対象企業を示す入力情報を、入力装置を介して取得する。入力部31は、取得した入力情報をレコメンド装置1Aに送信する。
ステップS102において、抽出部11Aは、各企業のニーズ文を参照して、入力情報が示す対象企業との間で、ニーズ文同士が類似する1以上の候補企業を、推奨企業として抽出する。ニーズ文同士の類似性を判断する手法の具体例としては、(a)単語間距離に基づく手法、(b)文書間距離に基づく手法、または、(c)学習モデルに基づく手法が挙げられる。これらの手法の詳細について以下に説明する。ただし、ニーズ文同士の類似性を判断する手法は、これらに限定されない。
この手法を用いる場合、抽出部11Aは、対象企業および各候補企業のニーズ文同士の類似度を、単語間距離に基づいて算出する。具体的には、抽出部11Aは、対象企業のニーズ文に含まれる各単語と、当該候補企業のニーズ文に含まれる各単語との間の各組み合わせについて、単語間距離を算出する。また、抽出部11Aは、算出した単語間距離を用いて、対象企業および候補企業のニーズ文同士の類似度を算出する。また、抽出部11Aは、算出した類似度が閾値以上となる1以上の候補企業を、推奨企業として抽出する。
この手法を用いる場合、抽出部11Aは、対象企業および各候補企業のニーズ文同士の類似度を、文書間距離に基づいて算出する。また、抽出部11Aは、類似度が閾値以上の1以上の候補企業を、推奨企業として抽出する。
この手法を用いる場合、抽出部11Aは、2つの企業のニーズ文を入力として、当該ニーズ文同士の類似性を示す情報を出力するよう機械学習により学習済みの学習モデルを用いる。抽出部11Aは、対象企業のニーズ文と候補企業のニーズ文とを学習モデルに入力する。また、抽出部11Aは、学習モデルから「類似することを示す情報」が出力された1以上の候補企業を、推奨企業として抽出する。
ステップS103において、特定部12Aは、対象企業のニーズ文における1以上の第1重要部分と、各推奨企業のニーズ文における1以上の第2重要部分とを特定する。また、特定部12Aは、各第1重要部分と各第2重要部分との間の対応関係を特定する。なお、特定部12Aは、「各第1重要部分と各第2重要部分との間の対応関係」を特定するために、各第1重要部分と各第2重要部分との組み合わせのうち対応関係を有する組み合わせを特定する。
この手法は、ステップS102において抽出部11Aが「(a)単語間距離に基づく手法」を用いている場合に適用することが望ましい。この手法を用いる場合、特定部12Aは、対象企業のニーズ文に含まれる各単語と、推奨企業のニーズ文に含まれる各単語との間の単語間距離に基づいて、各第1重要部分および推奨企業のニーズ文における各第2重要部分を特定する。ここで、特定部12Aは、各組み合わせの単語間距離については、抽出部11Aが手法(a)において算出した値を参照すればよい。
この手法は、ステップS102において、抽出部11Aが「(b)文書間距離に基づく手法」または「(c)学習モデルに基づく手法」を用いている場合に適用することが望ましい。
この手法は、ステップS102において、抽出部11Aが「(b)文書間距離に基づく手法」または「(c)学習モデルに基づく手法」を用いている場合に適用することが望ましい。
ステップS104において、提示部13Aは、レコメンド結果をユーザ端末3Aに提示する。レコメンド結果は、推奨企業を示す情報と、第1重要部分および第2重要部分と、これらの間の対応関係を示す情報とを含む。具体的には、提示部13Aは、レコメンド結果を示す画面データを生成する。提示部13Aは、画面データをユーザ端末3Aに送信することにより、レコメンド結果をユーザ端末3Aに提示する。
ステップS105において、ユーザ端末3Aの表示部32は、レコメンド装置1Aから提示されたレコメンド結果を表示する。具体的には、表示部32は、レコメンド装置1Aから受信した画面データを表示装置に表示する。本ステップでユーザ端末3Aに表示される画面例について、以下に説明する。
レコメンドシステム10AがステップS105において表示する画面例について、図8を参照して説明する。図8は、レコメンド結果の画面例G1を示す。図8に示すように、画面例G1は、対象企業である企業Aのニーズ文Aと、推奨企業である企業H、I、Lのニーズ文H、I、Lとを含む。
以上のように、本例示的実施形態は、レコメンド結果に、各第1重要部分と各第2重要部分との対応関係を示す情報を含めてユーザ端末に提示する。これにより、ユーザは、対象企業のニーズ文のどの部分と推奨企業のニーズ文のどの部分とが対応しているかを認識することができる。その結果、ユーザは、対象企業のニーズ文のうち、求める協業先の特徴をより充分に表している第1重要部分に対応する推奨企業は、協業先としての有効性が高いと判断することができる。また、ユーザは、対象企業のニーズ文のうち、求める協業先の特徴を充分に表していない第1重要部分に対応する推奨企業は、有効性が低いと判断することができる。このように、本例示的実施形態を用いることにより、ユーザは、対象企業に応じた推奨企業の有効性をより容易に判断することができる。
本発明の第4の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1~3にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を繰り返さない。
本例示的実施形態に係るレコメンドシステム10Bは、例示的実施形態3を変形した態様である。レコメンドシステム10Bは、対象企業に応じた推奨企業として、対象企業と競合しない可能性が高い企業を提示する。レコメンドシステム10Bの構成について、図9を参照して説明する。図9は、レコメンドシステム10Bの構成を示すブロック図である。
図9に示すように、レコメンド装置1Bは、制御部110Bと、記憶部120Bと、通信部130Aとを含む。
企業情報データベースDB2の構成について、図10を参照して説明する。図10は、企業情報データベースDB2の具体例を示す図である。図10に示すように、企業情報データベースDB2は、複数の企業の各々に関する企業情報を格納する。例えば、企業情報は、業種を示す情報を含む。図10の例では、企業A、I、J、Kの企業情報として、業種「情報通信」を示す情報が格納される。また、企業Hの企業情報として、業種「医薬品製造」を示す情報が格納される。また、企業Lの企業情報として、業種「化学製品卸売」を示す情報が格納される。なお、企業情報は、業種を示す情報に代えて、または加えて、企業に関するその他の情報を含んでいてもよい。
以上のように構成されたレコメンドシステム10Bが実行するレコメンド方法S10Bの流れについて、図11を参照して説明する。図11は、レコメンド方法S10Bの流れを示すフロー図である。図11に示すように、レコメンド方法S10Bは、例示的実施形態3におけるレコメンド方法S10Aとほぼ同様に構成されるが、ステップS102に代えてステップS102a~102cを含む点が異なる。以下では、ステップS102a~S102cについて説明する。その他のステップについては、レコメンド方法S10Aと同様であるため、詳細な説明を繰り返さない。
ステップS102aにおいて、レコメンド装置1Bの抽出部11Bは、対象企業に応じた推奨企業の候補として、対象企業との間でニーズ文同士が類似する1以上の候補企業を抽出する。本ステップにおいて推奨企業の候補を抽出する処理の詳細は、例示的実施形態3のステップS102において推奨企業を抽出する処理と同様であるため、詳細な説明を繰り返さない。
ステップS102bにおいて、抽出部11Bは、企業情報データベースDB2を参照して、推奨企業の候補のうち対象企業と競合する1以上の競合企業を推定する。
具体的には、抽出部11Bは、企業情報データベースDB2を参照して、推奨企業の候補のうち、対象企業との間で業種が同一の企業を、競合企業として推定する。例えば、図10に示した企業情報データベースDB2の例において、企業Aの推奨企業の候補として、企業H、I、J、K、Lが抽出されていたとする。この場合、抽出部11Bは、推奨企業の候補のうち業種が企業Aと同一の「情報通信」である企業I、J、Kを、競合企業として推定する。
ステップS102cにおいて、抽出部11Bは、推奨企業の候補から、競合企業を除外して推奨企業とする。換言すると、抽出部11Bは、推奨企業の候補のうち競合企業以外の企業を、推奨企業として抽出する。
レコメンドシステム10BがステップS105において表示する画面例について、図12を参照して説明する。図12は、レコメンド結果の画面例G2を示す。図12に示すように、画面例G2は、対象企業である企業Aのニーズ文Aと、推奨企業である企業H、Lのニーズ文H、Lとを含む。画面例G2は、例示的実施形態2における画面例G1に含まれる推奨企業H、I、Lのうち、競合企業として推定された企業Iのニーズ文を含まない。画面例G2は、対象企業Aのニーズ文における第1重要部分p1と、推奨企業H、Lの各ニーズ文における第2重要部分p4、p6との間の対応関係を示す図形f1、f3を含む。
以上のように、本例示的実施形態は、競合企業以外の推奨企業を推奨するレコメンド結果に、各第1重要部分と各第2重要部分との対応関係を示す情報を含めて提示する。これにより、本例示的実施形態は、対象企業との間でニーズ文同士が類似する企業であっても競合企業である可能性が高い企業については、各第1重要部分と各第2重要部分との対応関係をユーザに提示することがない。したがって、ユーザは、提示された推奨企業の有効性をより容易に判断することができる。
本発明の第5の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1~4にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を繰り返さない。
本例示的実施形態に係るレコメンドシステム10Cは、例示的実施形態4を変形した態様である。レコメンドシステム10Cは、対象企業に応じた推奨企業の候補を、競合企業と競合以外とに分類して提示する。レコメンドシステム10Cの構成について、図13を参照して説明する。図13は、レコメンドシステム10Cの構成を示すブロック図である。
図13に示すように、レコメンド装置1Cは、例示的実施形態4におけるレコメンド装置1Bとほぼ同様に構成されるが、制御部110Bに代えて制御部110Cを備える点が異なる。制御部110Cは、例示的実施形態4における制御部110Bとほぼ同様に構成されるが、提示部13Aに代えて提示部13Cを備える点が異なる。その他の点については、レコメンド装置1Bと同様に構成される。
図13に示すように、ユーザ端末3Cは、入力部31Cおよび表示部32Cを備える。
以上のように構成されたレコメンドシステム10Cが実行するレコメンド方法S10Cの流れについて、図14を参照して説明する。図14は、レコメンド方法S10Cの流れを示すフロー図である。図14に示すように、レコメンド方法S10Cは、例示的実施形態4におけるレコメンド方法S10Bとほぼ同様に構成されるが、ステップS102cに代えてステップS102d~S102fを含む点が異なる。以下では、ステップS102d~S102fについて説明する。その他のステップについては、レコメンド方法S10Bと同様であるため、詳細な説明を繰り返さない。
ステップS102dにおいて、レコメンド装置1Cの提示部13Cは、推奨企業の候補を、競合企業と競合以外とに分類してユーザ端末3Cに提示する。具体的には、提示部13Cは、ステップS102aで抽出した推奨企業の候補を、ステップS102bで推定した競合企業と競合以外とに分類した画面データを生成する。提示部13Cは、画面データをユーザ端末3Cに送信することにより、これらを分類してユーザ端末3Cに提示する。
ステップS102eにおいて、ユーザ端末3Cの表示部32Cは、対象企業に応じた推奨企業の候補を、競合企業と競合以外とに分類して表示装置に表示する。具体的には、表示部32は、レコメンド装置1Aから受信した画面データを表示装置に表示する。
ステップS102fにおいて、ユーザ端末3Cの入力部31Cは、推奨企業を指定する入力情報を、入力装置を介して取得する。入力部31Cは、取得した入力情報をレコメンド装置1Cに送信する。例えば、ユーザは、入力装置を用いて、ステップS102dで表示された推奨企業の候補のうち1以上を推奨企業として指定する操作を行う。
レコメンドシステム10CがステップS102eおよびステップS105において表示する画面例について、図15、図16を参照して説明する。
図15は、ステップS102eにおいて表示される推奨企業の候補の画面例G3である。図15に示すように、画面例G3は、対象企業である企業Aの推奨企業の候補として、企業H、I、L、K、およびLをそれぞれ示す領域Rを含む。このうち、企業I、J、Kの各領域Rは、競合企業を示す枠で囲まれている。また、企業H、Lは、競合以外の企業を示す枠で囲まれている。これにより、推奨企業の候補である企業H、I、L、K、およびLは、競合企業と競合以外とに分類して表示される。なお、競合企業を示す枠および競合以外の企業を示す枠は、競合企業および競合以外を分類する表示態様の一例であるが、これに限られない。
図16は、ステップS105において表示されるレコメンド結果の画面例G4を示す。図16に示すように、画面例G4は、対象企業である企業Aのニーズ文Aを含む。また、画面例G4は、ユーザによって指定された推奨企業である企業H、Iの各ニーズ文を含む。ここで、企業Hは、競合以外に分類された企業である。また、企業Iは、競合企業に分類された企業である。また、画面例G4は、企業Aのニーズ文における第1重要部分p1と、企業H、Iの各ニーズ文における第2重要部分p4、p5との間の対応関係を示す図形f1、f2を含む。これにより、ユーザは、競合企業として推定されていても、協業先として考慮したい企業Iを推奨企業として指定することができ、これらの各ニーズ文を対比して視認することができる。
以上のように、本例示的実施形態は、対象企業に応じた推奨企業の候補を、競合企業と競合以外とに分類して表示する。その上で、本例示的実施形態は、推奨企業の候補の中からユーザが指定した推奨企業と、対象企業とについて、各第1重要部分と各第2重要部分との間の対応関係を示す情報をユーザに提示する。これにより、ユーザは、競合企業として推定されていても協業先として考慮したい企業については、ニーズ文を対比して閲覧することができる。したがって、ユーザは、推奨企業の有効性をより容易に判断することができる。
レコメンド装置1、1A、1B、1Cの一部又は全部の機能は、集積回路(ICチップ)等のハードウェアによって実現してもよいし、ソフトウェアによって実現してもよい。
本発明は、上述した実施形態に限定されるものでなく、請求項に示した範囲で種々の変更が可能である。例えば、上述した実施形態に開示された技術的手段を適宜組み合わせて得られる実施形態についても、本発明の技術的範囲に含まれる。
上述した実施形態の一部又は全部は、以下のようにも記載され得る。ただし、本発明は、以下の記載する態様に限定されるものではない。
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示手段と、
を備えたことを特徴とするレコメンド装置。
前記特定手段は、前記第1重要部分と前記第2重要部分との間の対応関係を特定し、
前記提示手段は、前記対応関係を示す情報をさらに提示する、
ことを特徴とする付記1に記載のレコメンド装置。
前記協業内容は、当該企業の企業名、事業内容、展開サービス、提供製品、及び企業理念、の少なくとも一つを含む、
ことを特徴とする付記1または2に記載のレコメンド装置。
前記特定手段は、前記対象企業情報に含まれる各単語と、前記協業候補企業情報に含まれる各単語との間の単語間距離に基づいて、前記第1重要部分および前記第2重要部分を特定する、
ことを特徴とする付記1から3の何れか1つに記載のレコメンド装置。
前記特定手段は、前記対象企業情報および前記協業候補企業情報のそれぞれに含まれる各単語の重要度に基づいて、前記第1重要部分および前記第2重要部分を特定する、
ことを特徴とする付記1から3の何れか1つに記載のレコメンド装置。
前記抽出手段は、前記対象企業情報および前記協業候補企業情報を入力とする学習モデルから出力される情報を参照して前記推奨企業を抽出し、
前記特定手段は、前記学習モデルが前記対象企業情報および前記協業候補企業情報のそれぞれにおいて注目した部分に基づいて、前記第1重要部分および前記第2重要部分を特定する、
ことを特徴とする付記1から3の何れか1つに記載のレコメンド装置。
前記抽出手段は、前記複数の企業の各々の企業情報を参照して、前記対象企業の競合企業以外の企業を前記推奨企業として抽出する、
ことを特徴とする付記1から6の何れか1つに記載のレコメンド装置。
前記提示手段は、前記対象企業情報および前記協業候補企業情報を表示装置に表示し、前記対象企業情報において前記第1重要部分と前記第1重要部分以外の部分とを異なる表示態様で表示し、前記協業候補企業情報において前記第2重要部分と前記第2重要部分以外の部分とを異なる表示態様で表示する、
ことを特徴とする付記1から7の何れか1つに記載のレコメンド装置。
前記提示手段は、前記第1重要部分および前記第2重要部分を、互いに対応する表示態様で表示装置に表示する、
ことを特徴とする付記1から8の何れか1つに記載のレコメンド装置。
レコメンド装置が、
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出し、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定し、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する、
ことを特徴とするレコメンド方法。
コンピュータをレコメンド装置として機能させるプログラムであって、
前記プログラムは、前記コンピュータを、
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示手段と、として機能させる、
ことを特徴とするプログラム。
コンピュータをレコメンド装置として機能させるプログラムを記憶した記憶媒体であって、
前記プログラムは、前記コンピュータを、
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示手段と、として機能させる、
ことを特徴とするプログラムを記憶した記憶媒体。
レコメンド装置と、ユーザ端末とを含み、
前記レコメンド装置は、
前記ユーザ端末が取得した入力情報が示す対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを前記ユーザ端末に提示する提示手段と、を備え、
前記ユーザ端末は、
前記入力情報を取得する入力手段と、
前記提示手段によって提示される情報を表示する表示手段と、を備える、
ことを特徴とするレコメンドシステム。
上述した実施形態の一部又は全部は、更に、以下のように表現することもできる。
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出処理と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定処理と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示処理と、
を実行するレコメンド装置。
10、10A、10B レコメンドシステム
3、3A、3C ユーザ端末
11、11A、11B、101 抽出部
12、12A、102 特定部
13、13A、13C、103 提示部
31、31C 入力部
32、32C 表示部
Claims (13)
- 対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示手段と、
を備えたことを特徴とするレコメンド装置。 - 前記特定手段は、前記第1重要部分と前記第2重要部分との間の対応関係を特定し、
前記提示手段は、前記対応関係を示す情報をさらに提示する、
ことを特徴とする請求項1に記載のレコメンド装置。 - 前記協業内容は、当該企業の企業名、事業内容、展開サービス、提供製品、及び企業理念、の少なくとも一つを含む、
ことを特徴とする請求項1または2に記載のレコメンド装置。 - 前記特定手段は、前記対象企業情報に含まれる各単語と、前記協業候補企業情報に含まれる各単語との間の単語間距離に基づいて、前記第1重要部分および前記第2重要部分を特定する、
ことを特徴とする請求項1から3の何れか1項に記載のレコメンド装置。 - 前記特定手段は、前記対象企業情報および前記協業候補企業情報のそれぞれに含まれる各単語の重要度に基づいて、前記第1重要部分および前記第2重要部分を特定する、
ことを特徴とする請求項1から3の何れか1項に記載のレコメンド装置。 - 前記抽出手段は、前記対象企業情報および前記協業候補企業情報を入力とする学習モデルから出力される情報を参照して前記推奨企業を抽出し、
前記特定手段は、前記学習モデルが前記対象企業情報および前記協業候補企業情報のそれぞれにおいて注目した部分に基づいて、前記第1重要部分および前記第2重要部分を特定する、
ことを特徴とする請求項1から3の何れか1項に記載のレコメンド装置。 - 前記抽出手段は、前記複数の企業の各々の企業情報を参照して、前記対象企業の競合企業以外の企業を前記推奨企業として抽出する、
ことを特徴とする請求項1から6の何れか1項に記載のレコメンド装置。 - 前記提示手段は、前記対象企業情報および前記協業候補企業情報を表示装置に表示し、前記対象企業情報において前記第1重要部分と前記第1重要部分以外の部分とを異なる表示態様で表示し、前記協業候補企業情報において前記第2重要部分と前記第2重要部分以外の部分とを異なる表示態様で表示する、
ことを特徴とする請求項1から7の何れか1項に記載のレコメンド装置。 - 前記提示手段は、前記第1重要部分および前記第2重要部分を、互いに対応する表示態様で表示装置に表示する、
ことを特徴とする請求項1から8の何れか1項に記載のレコメンド装置。 - レコメンド装置が、
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出し、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定し、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する、
ことを特徴とするレコメンド方法。 - コンピュータをレコメンド装置として機能させるプログラムであって、
前記プログラムは、前記コンピュータを、
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示手段と、として機能させる、
ことを特徴とするプログラム。 - コンピュータをレコメンド装置として機能させるプログラムを記憶した記憶媒体であって、
前記プログラムは、前記コンピュータを、
対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを提示する提示手段と、として機能させる、
ことを特徴とするプログラムを記憶した記憶媒体。 - レコメンド装置と、ユーザ端末とを含み、
前記レコメンド装置は、
前記ユーザ端末が取得した入力情報が示す対象企業の所望の協業内容を含む対象企業情報と、前記対象企業の協業先候補である複数の企業の所望の協業内容を含む協業候補企業情報とに基づいて、前記複数の企業から、前記対象企業の協業先候補として推奨される推奨企業を抽出する抽出手段と、
前記対象企業情報における第1重要部分と、前記推奨企業に関する協業候補企業情報における第2重要部分と、を特定する特定手段と、
前記推奨企業に関する協業候補企業情報と、前記第1重要部分および前記第2重要部分とを前記ユーザ端末に提示する提示手段と、を備え、
前記ユーザ端末は、
前記入力情報を取得する入力手段と、
前記提示手段によって提示される情報を表示する表示手段と、を備える、
ことを特徴とするレコメンドシステム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2020/044290 WO2022113285A1 (ja) | 2020-11-27 | 2020-11-27 | レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 |
JP2022564948A JP7452701B2 (ja) | 2020-11-27 | 2020-11-27 | レコメンド装置、レコメンドシステム、レコメンド方法およびプログラム |
US18/038,966 US20240005224A1 (en) | 2020-11-27 | 2020-11-27 | Recommendation device, recommendation system, recommendation method, program and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2020/044290 WO2022113285A1 (ja) | 2020-11-27 | 2020-11-27 | レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022113285A1 true WO2022113285A1 (ja) | 2022-06-02 |
Family
ID=81755436
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/044290 WO2022113285A1 (ja) | 2020-11-27 | 2020-11-27 | レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20240005224A1 (ja) |
JP (1) | JP7452701B2 (ja) |
WO (1) | WO2022113285A1 (ja) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007079963A (ja) * | 2005-09-14 | 2007-03-29 | Nec Corp | 企業間提携支援システム、企業間提携支援方法、及び企業間提携支援プログラム |
JP2011138306A (ja) * | 2009-12-28 | 2011-07-14 | National Institute Of Information & Communication Technology | 文書要約装置、文書処理装置、文書要約方法、文書処理方法、及びプログラム |
JP2019057068A (ja) * | 2017-09-20 | 2019-04-11 | 株式会社野村総合研究所 | 情報処理装置およびコンピュータプログラム |
JP2020013413A (ja) * | 2018-07-19 | 2020-01-23 | 株式会社日立製作所 | 判断支援装置および判断支援方法 |
JP2020071869A (ja) * | 2018-10-29 | 2020-05-07 | バク ヒョクゼPark Hyuck−jae | 動画基盤求人求職マッチングサーバーおよび方法 |
-
2020
- 2020-11-27 WO PCT/JP2020/044290 patent/WO2022113285A1/ja active Application Filing
- 2020-11-27 JP JP2022564948A patent/JP7452701B2/ja active Active
- 2020-11-27 US US18/038,966 patent/US20240005224A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007079963A (ja) * | 2005-09-14 | 2007-03-29 | Nec Corp | 企業間提携支援システム、企業間提携支援方法、及び企業間提携支援プログラム |
JP2011138306A (ja) * | 2009-12-28 | 2011-07-14 | National Institute Of Information & Communication Technology | 文書要約装置、文書処理装置、文書要約方法、文書処理方法、及びプログラム |
JP2019057068A (ja) * | 2017-09-20 | 2019-04-11 | 株式会社野村総合研究所 | 情報処理装置およびコンピュータプログラム |
JP2020013413A (ja) * | 2018-07-19 | 2020-01-23 | 株式会社日立製作所 | 判断支援装置および判断支援方法 |
JP2020071869A (ja) * | 2018-10-29 | 2020-05-07 | バク ヒョクゼPark Hyuck−jae | 動画基盤求人求職マッチングサーバーおよび方法 |
Also Published As
Publication number | Publication date |
---|---|
US20240005224A1 (en) | 2024-01-04 |
JPWO2022113285A1 (ja) | 2022-06-02 |
JP7452701B2 (ja) | 2024-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Conway et al. | Machine learning for hackers | |
US11599808B2 (en) | Artificial intelligence assisted hybrid enterprise/candidate employment assistance platform | |
US9753916B2 (en) | Automatic generation of a speech by processing raw claims to a set of arguments | |
US8650143B2 (en) | Determination of document credibility | |
US9141729B2 (en) | Display-data generating apparatus and display-data generating method | |
CN111651996A (zh) | 摘要生成方法、装置、电子设备及存储介质 | |
CN112188312B (zh) | 用于确定新闻的视频素材的方法和装置 | |
MXPA04011788A (es) | Aprendizaje y uso de patrones de cadena generalizados para extraccion de informacion. | |
WO2019159986A1 (ja) | 情報提供装置、情報提供方法、およびプログラム | |
CN109582788A (zh) | 垃圾评论训练、识别方法、装置、设备及可读存储介质 | |
US20240221404A1 (en) | Method of training text quality assessment model and method of determining text quality | |
JP2021047817A (ja) | 出力装置、及び出力プログラム | |
CN113157871B (zh) | 应用人工智能的新闻舆情文本处理方法、服务器及介质 | |
JP2006323517A (ja) | テキスト分類装置およびプログラム | |
Addepalli et al. | A proposed framework for measuring customer satisfaction and product recommendation for ecommerce | |
US20190073682A1 (en) | Evaluation apparatus, evaluation method, noise removal apparatus, and program | |
WO2022113286A1 (ja) | レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 | |
WO2022113285A1 (ja) | レコメンド装置、レコメンドシステム、レコメンド方法、プログラムおよび記憶媒体 | |
US20210374198A1 (en) | Interactive suggestions for directed content copy using a deep learning model | |
Conway et al. | Machine learning for email: spam filtering and priority inbox | |
WO2020121638A1 (ja) | 情報処理装置、情報処理システム、および情報処理方法、並びにプログラム | |
JPWO2022113286A5 (ja) | ||
KR102422844B1 (ko) | 인공지능에 기반하여 영상 컨텐츠의 언어 위기를 관리하는 방법 | |
US20200257763A1 (en) | Visual storyline generation from text story | |
US20190155906A1 (en) | Enhancing a computer to match emotion and tone in text with the emotion and tone depicted by the color in the theme of the page or its background |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20963549 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022564948 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18038966 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20963549 Country of ref document: EP Kind code of ref document: A1 |