WO2022259512A1 - 営業支援装置、営業支援方法およびプログラム - Google Patents
営業支援装置、営業支援方法およびプログラム Download PDFInfo
- Publication number
- WO2022259512A1 WO2022259512A1 PCT/JP2021/022263 JP2021022263W WO2022259512A1 WO 2022259512 A1 WO2022259512 A1 WO 2022259512A1 JP 2021022263 W JP2021022263 W JP 2021022263W WO 2022259512 A1 WO2022259512 A1 WO 2022259512A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- document
- documents
- negotiation
- business
- cluster
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 63
- 238000004364 calculation method Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 11
- 239000013598 vector Substances 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 101710114762 50S ribosomal protein L11, chloroplastic Proteins 0.000 description 1
- 101710164994 50S ribosomal protein L13, chloroplastic Proteins 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 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
Definitions
- the present invention relates to a sales support device, a sales support method, and a program.
- Patent Literature 1 describes a data analysis system that searches for a combination of explanatory variables for accurately predicting an objective variable.
- the data analysis system described in Patent Document 1 includes explanatory variables including attribute values indicating customer attributes such as the customer's gender, age group, contract period, and whether or not the customer has subscribed to an option, and whether the customer has continued the contract or canceled the contract.
- a combination with an objective variable, which is an attribute value indicating whether or not, is searched for.
- One aspect of the present invention has been made in view of the above problems, and an example of its purpose is to provide a technique for more accurately determining the status of business negotiations.
- a sales support device includes acquisition means for acquiring a first document in which the content of a first business negotiation is written in a natural language, and a plurality of second business negotiations that do not include the first business negotiation. For each, a storage device storing a second document in which the content of the second business negotiation is described in a natural language, information on the cluster to which the second document belongs, and the business negotiation situation indicated by the document belonging to the cluster is referred to. , selecting one of a plurality of clusters obtained by clustering the plurality of second documents, based on the degree of similarity between the first document and part or all of the plurality of second documents. and output means for outputting information indicating the status of negotiations associated with the cluster selected by the selection means.
- a sales support device obtains a first document in which the content of a first business negotiation is written in a natural language, and obtains a plurality of second documents that do not include the first business negotiation.
- a storage device that stores, for each business negotiation, a second document in which the content of the second business negotiation is written in a natural language, information on the cluster to which the second document belongs, and the business negotiation situation indicated by the document belonging to the cluster.
- one of a plurality of clusters obtained by clustering the plurality of second documents based on the degree of similarity between the first document and a part or all of the plurality of second documents; to output information indicating the status of negotiations associated with the cluster selected by the selection means.
- a program is a program for causing a computer to function as a sales support device, and is an acquisition means for acquiring a first document in which the content of a first business negotiation is written in natural language. and, for each of a plurality of second business negotiations that do not include the first business negotiation, a second document describing the content of the second business negotiation in natural language, information on the cluster to which the second document belongs, and the relevant referring to a storage device that stores negotiation situations indicated by the documents belonging to the cluster, and based on the degree of similarity between the first document and each of a part or all of the plurality of second documents; selecting means for selecting one of a plurality of clusters obtained by clustering two documents; and output means for outputting information indicating the status of negotiations associated with the cluster selected by the selecting means. .
- the status of business negotiations can be determined more accurately.
- FIG. 1 is a block diagram showing the configuration of a sales support device according to exemplary Embodiment 1 of the present invention
- FIG. FIG. 2 is a flow diagram showing the flow of the sales support method according to exemplary Embodiment 1 of the present invention
- FIG. 10 is a block diagram showing the configuration of a negotiation management system according to exemplary embodiment 2 of the present invention
- FIG. 10 is a diagram showing a specific example of a negotiation history database according to the second exemplary embodiment of the present invention
- FIG. 10 is a diagram showing a specific example of a description table according to exemplary embodiment 2 of the present invention
- FIG. 11 is a flow chart showing the flow of a sales support method according to exemplary Embodiment 2 of the present invention
- FIG. 10 is a diagram showing a specific example of clusters according to exemplary embodiment 2 of the present invention
- 1 is a block diagram showing the configuration of a computer functioning as a sales support device or a user terminal according to illustrative embodiments 1-4 of the present invention
- FIG. 10 is a diagram showing a specific example of clusters according to exemplary embodiment 2 of the present invention
- 1 is a block diagram showing the configuration of a computer functioning as a sales support device or a user terminal according to illustrative embodiments 1-4 of the present invention
- FIG. 1 is a block diagram showing the configuration of the sales support device 10.
- the sales support device 10 includes an acquisition unit 11 , a selection unit 12 and an output unit 13 .
- the acquisition unit 11 is an example of a configuration that implements the acquisition means described in the claims.
- the selection unit 12 is an example of a configuration that implements the selection means described in the claims.
- the output unit 13 is an example of a configuration that implements output means described in the claims.
- the acquisition unit 11 acquires a first document in which the content of the first business negotiation is written in natural language.
- the selection unit 12 selects a second document describing the content of the second business negotiation in natural language and information on the cluster to which the second document belongs. and the negotiation status indicated by the documents belonging to the cluster, and based on the degree of similarity between the first document and part or all of the plurality of second documents, a plurality of second to select one of a plurality of clusters in which the documents of are clustered.
- the output unit 13 outputs information indicating the status of the negotiation associated with the cluster selected by the selection unit 12 .
- the document in this specification is, for example, a business daily report or minutes of business activities, but is not particularly limited as long as it includes the content of a business negotiation.
- Business negotiations refer to the exchange of various types of information about the target project between the person in charge of providing the service or product, such as a company, store, etc., and the customer.
- Business negotiations may be conducted face-to-face, or may be conducted non-face-to-face via a network, telephone, or the like. If non-face-to-face, the interview may be conducted in real-time (eg, chat, online meeting) or non-real-time (e-mail, etc.).
- the number of persons in charge and customers may be one or more. Also, the person in charge and the customer may be robots, software, or the like.
- the document is the content of the business negotiation written in natural language.
- the document is, for example, a daily report created by a salesperson.
- the natural language is Japanese, Chinese, or English, for example.
- data representing a document will also be simply referred to as a "document" for convenience of description.
- the document is, for example, text data representing a character string representing the content of the negotiation, a file created by predetermined document creation software, a PDF format file, or an HTML format file.
- the document may be, for example, data generated by a user operating an input device or the like.
- a device such as the sales support device 10 may perform voice analysis processing on a voice file representing the content of a business negotiation. It may be generated data.
- Each of the plurality of clusters includes one or more second documents.
- a plurality of second documents may be classified into a plurality of clusters by being pre-clustered.
- FIG. 2 is a flowchart showing the flow of the sales support method S10.
- step S11 acquisition processing
- the acquisition unit 11 acquires a first document in which the content of the first business negotiation is written in natural language.
- the acquisition unit 11 may acquire the first document from a device capable of communicating via a network, or may acquire the first document by reading it from memory.
- step S12 selection processing
- the selection unit 12 stores a second document in which the content of the second negotiations written in natural language is written for each of the plurality of second negotiations that do not include the first negotiations.
- the selection unit 12 may use, for example, a method of calculating the distance in a predetermined feature amount space between words included in the documents. In this case, the selection unit 12 calculates the degree of similarity between the first document and the second document based on the distance between the words included in the first document and the words included in the second document. In this case, the similarity decreases as the distance between documents increases, and increases as the distance between documents decreases.
- the process of calculating the degree of similarity between the first document and the second document is not limited to the process described above.
- the selection unit 12 selects, for example, one or a plurality of second documents whose degree of similarity with the first document satisfies a predetermined condition, and selects a plurality of clusters. may be selected from among the clusters to which part or all of the selected one or more second documents belong. Further, the selection unit 12 may, for example, calculate the degree of similarity between each of a plurality of clusters and the second document, which is the representative of each cluster, and select a cluster based on the calculated degree of similarity for each cluster. .
- the process of selecting clusters is not limited to the process described above.
- Step S13 In step S ⁇ b>13 (output processing), the output unit 13 outputs information indicating the status of the negotiation associated with the cluster selected by the selection unit 12 .
- the output unit 13 may output the information to a device capable of communicating via a network, or may output the information by writing the information into a memory.
- the first document describing the content of the first business negotiation and the second document describing the content of the second business negotiation are generated.
- a configuration is adopted in which one of a plurality of clusters obtained by clustering a plurality of second documents is selected based on the degree of similarity between the two documents, and information associated with the selected cluster is output.
- FIG. 3 is a block diagram showing the configuration of the negotiation management system 1 according to this exemplary embodiment.
- the business negotiation management system 1 is a system for managing business negotiations conducted by sales staff.
- the negotiation management system 1 includes a sales support device 20 and user terminals 30 .
- the sales support device 20 and the user terminal 30 are communicably connected via a network N1.
- 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 sales support device 20 is a device that outputs information about the status of business negotiations.
- Sales support device 20 includes control unit 210 , storage unit 220 and communication unit 230 .
- the control unit 210 includes an acquisition unit 211 , a calculation unit 212 , a selection unit 213 , an output unit 214 , a clustering unit 215 , a reception unit 216 and an information addition unit 217 .
- the acquisition unit 211 is an example of a configuration that implements the acquisition means described in the claims.
- the calculation unit 212 and the selection unit 213 are an example of a configuration that implements the selection means described in the claims.
- the output unit 214 is an example of a configuration that realizes output means described in the claims.
- the clustering unit 215 is an example of a configuration that implements clustering means described in the claims.
- the receiving unit 216 is an example of a configuration that implements the receiving unit described in the claims.
- the information adding unit 217 is an example of a configuration that implements information adding means described in the claims.
- the information indicating the status of the negotiation is information indicating what phase or status the negotiation is in.
- the status of negotiations is "product selection in progress", “project stagnating”, and “requirement mismatch”.
- Selecting a product indicates that the customer is in the phase of selecting a product.
- Project stagnation indicates a situation in which the project is in stagnation.
- Requirement mismatch indicates that the requirements of the customer and the requirements of products that can be provided to the customer are mismatched. How the negotiation proceeds depends on the specific content of the negotiation, such as the sales content of the salesperson.
- the contents of business negotiations include, for example, the contents of materials provided to customers or the number of interviews with executives.
- Recommended actions in negotiations differ depending on the negotiation situation. For example, when the status of the business negotiation is "product selection in progress”, an example of a recommended action is preparation of benchmark materials. Also, for example, when the status of the business negotiation is "project stagnating”, one example of a recommended action is to involve the upper layer. Also, for example, when the status of the negotiation is "requirement mismatch,” an example of a recommended action is to withdraw.
- the storage unit 220 is an example of a configuration that implements the storage device described in the claims.
- Storage unit 220 stores negotiation history database DB1 and description table TB2.
- the business negotiation history database DB1 accumulates business negotiation history data representing the history of each of multiple business negotiations.
- business negotiations whose business negotiation history data is accumulated in the business negotiation history database DB1 will also be simply referred to as "business negotiations accumulated in the business negotiation history database DB1".
- the plurality of business negotiations accumulated in the business negotiation history database DB1 include, for example, past business negotiations or ongoing business negotiations.
- a past business negotiation is, for example, a business negotiation whose result has been finalized.
- the current negotiation among the multiple negotiations accumulated in the negotiation history database DB1 is applied as the first negotiation.
- at least one of them is applied as the first negotiation.
- the business negotiation history data includes documents in which the content of business negotiations is written in natural language.
- the business negotiation history database DB1 stores a set of documents (business negotiation history data of the first business negotiation) including one or a plurality of first documents describing the content of the first business negotiation in natural language.
- the business negotiation history database DB1 stores a set of documents (business negotiation history of the second business negotiations) including one or more second documents describing the content of the second business negotiations in natural language for each of the plurality of second business negotiations. data).
- the description table TB2 stores information on the cluster to which the second document belongs and the negotiation status indicated by the document belonging to the cluster.
- the description table TB2 is, for example, a table that associates cluster types with information on the status of negotiations.
- the information about the status of the negotiation includes, for example, information indicating the status of the negotiation and information indicating recommended actions in that situation.
- the acquisition unit 211 acquires the first document in which the content of the first negotiation is written in natural language by reading it from the negotiation history database DB1.
- the calculation unit 212 refers to the negotiation history database DB1, and calculates the degree of similarity between the first document and part or all of the plurality of second documents for each of the plurality of second negotiations. The details of the method for calculating the degree of similarity between the first document and the second document will be described later.
- the selection unit 213 selects one of a plurality of clusters obtained by clustering a plurality of second documents. The details of the cluster selection method will be described later.
- the output unit 214 outputs information related to the status of negotiations associated with the cluster selected by the selection unit 213 .
- the clustering unit 215 clusters the second documents based on the degree of similarity between the documents to generate a plurality of clusters.
- Accepting unit 216 accepts input of information regarding the status of negotiations for each of the plurality of clusters.
- the information adding unit 217 stores the information received by the receiving unit 216 in the storage unit 220 in association with the information for identifying the cluster.
- the communication unit 230 transmits and receives information to and from the user terminal 30 via the network N1.
- the control unit 210 transmitting/receiving information to/from the user terminal 30 via the communication unit 230 is simply referred to as the control unit 210 transmitting/receiving information to/from the user terminal 30 .
- the user terminal 30 is a terminal used by a user.
- a user is a salesperson who conducts a business negotiation as an example.
- the user terminal 30 is, for example, a laptop computer, desktop computer, tablet terminal, or smart phone.
- the user terminal 30 includes an input section 31 , a display section 32 and a communication section 33 .
- the user terminal 30 is connected to an input device and a display device (both not shown).
- the input unit 31 acquires a request for determining the status of the first negotiation via the input device.
- the input unit 31 transmits the acquired determination request to the sales support device 20 .
- the display unit 32 outputs information about the status of the first business negotiation output by the sales support device 20 .
- the communication unit 33 transmits and receives information to and from the sales support device 20 via the network N1.
- the transmission and reception of information by the communication unit 33 to and from the sales support device 20 is simply referred to as the transmission and reception of information from the user terminal 30 to and from the sales support device 20 .
- FIG. 4 is a diagram showing a specific example of the negotiation history database DB1.
- the negotiation history database DB1 stores a plurality of negotiation history data including items of "negotiation ID”, “negotiation name”, "document ID”, “date and time”, “text” and “cluster ID”. .
- the negotiation ID is stored in the item “negotiation ID”.
- the negotiation ID is identification information that identifies the negotiation.
- the item "name of negotiation” stores text information that identifies the negotiation, such as the name of the customer and the name of the project that is the target of the negotiation.
- the document ID is stored in the document ID item.
- the document ID is identification information that identifies a document in which the content of the business negotiation is written in natural language.
- the item "report date and time” stores information indicating the date and time when the report was made. The date and time when the report was made is, for example, the date and time when the document representing the content of the negotiation was registered in the negotiation history database DB1.
- the "text” item stores data representing the content of the document.
- the data representing the content of the document is, for example, text data, a file created by predetermined document creation software, a PDF format file, or an HTML format file. Note that an address indicating a storage location of data representing the contents of a document may be stored in the item "text".
- the "cluster ID” item stores identification information that identifies which cluster the second document belongs to. Identification information for identifying a cluster is also called a “cluster ID”.
- multiple documents are associated with one business negotiation.
- Each of these multiple documents is associated with information indicating date and time.
- the information indicating the date and time indicates, for example, the date and time when the document was created, or the date and time when the business described in the document was conducted.
- a plurality of documents describing the content of one business negotiation have an order relationship.
- FIG. 5 is a diagram showing a specific example of the explanation table TB2.
- the description table TB2 includes items of "cluster ID” and "description". Among these items, the item “cluster ID” stores identification information (cluster ID) for identifying a cluster.
- the “Description” field stores information about the status of negotiations associated with the cluster.
- Information about the status of negotiations includes, for example, information indicating the status or phase of negotiations, such as "product selection in progress”, “project stagnating”, and “requirements mismatch”.
- the information regarding the status of the negotiation includes information indicating recommended actions in that status.
- the information indicating the action includes, for example, "prepare benchmark material", “involve upper layer”, or "withdraw”.
- FIG. 6 is a flowchart showing the flow of the sales support method S20 executed by the negotiation management system 1.
- the sales support method S20 is a method of determining the status of the first negotiation specified by the user.
- the sales support method S20 is started when the user performs an operation for requesting determination of the status of the first negotiation using the input device.
- the user may specify the first negotiation by inputting identification information for identifying the first negotiation using the input device, and may select a target from a plurality of negotiations using the input device.
- An operation to designate a certain first negotiation may be performed.
- the first negotiation is a negotiation registered in the negotiation history database DB1.
- the first negotiation may be a negotiation that is not registered in the negotiation history database DB1.
- Step S21 The input unit 31 of the user terminal 30 receives information indicating the determination request via the input device.
- the communication unit 33 transmits a determination request to the sales support device 20 based on the information received by the input unit 31 .
- the determination request includes identification information that identifies the first negotiation.
- the acquisition unit 211 of the sales support device 20 receives the determination request from the user terminal 30 .
- step S22 the acquisition unit 211 of the sales support device 20 acquires the first document describing the content of the first negotiation that is the target of the received discrimination request. Specifically, the acquisition unit 211 reads the first document corresponding to the identification information included in the determination request from the negotiation history database DB1.
- step S23 the calculation unit 212 determines the relationship between the first document acquired by the acquisition unit 211 and each of a part or all of the plurality of second documents included in the negotiation history data accumulated in the negotiation history database DB1. Calculate the similarity. As an example, the calculation unit 212 calculates the distance in a predetermined feature amount space between the first document and each of the plurality of second documents as the degree of similarity.
- Method for calculating similarity between first document and second document As specific examples of the method by which the calculation unit 212 calculates the degree of similarity between the first document and the second document, (a) a method based on the distance between words and (b) a method based on the distance between documents will be described. However, the method of determining the similarity between the first document and the second document is not limited to these.
- the calculation unit 212 calculates the degree of similarity between the first document and the second document based on the distance between words included in the documents. Specifically, the calculation unit 212 calculates the distance between words for each combination of each word included in the first document and each word included in the second document. As an example, the calculation unit 212 performs natural language processing on each of the first document and the second document, and extracts words contained in each document. Natural language processing is, for example, morphological analysis or N-gram analysis.
- n and m are natural numbers.
- the calculator 212 calculates n ⁇ m inter-word distances.
- the inter-word distance is represented by the angle formed by the two vectors or the Euclidean distance between the vectors.
- word2vec As a technique for representing word features as vectors, it is conceivable to use a machine-learned learning model that takes words as input and outputs feature vectors. A technique such as word2vec can be applied as such a learning model, but it is not limited to this.
- the calculation unit 212 calculates the degree of similarity between the first document and the second document using the statistical value of the distance between words. As an example, the calculation unit 212 calculates the average value of inter-word distances of all combinations of words w1i and w2j as the degree of similarity indicating the degree of similarity between the first document and the second document. In this case, the larger the similarity value, the lower the degree of similarity, and conversely, the smaller the value, the higher the degree of similarity.
- the calculation unit 212 selects a predetermined number of combinations in descending order of the distance between words from among all combinations of words w1i and w2j, and calculates the average value of the distances between words for the selected combinations as the first document and the second document. Also in this case, the larger the similarity value, the lower the degree of similarity, and conversely, the smaller the value, the higher the degree of similarity.
- the calculation unit 212 calculates the degree of similarity between the first document and the second document based on the distance between the documents.
- the inter-document distance between the first document and the second document is represented by the angle formed by the two vectors or the Euclidean distance between the vectors.
- a technique such as doc2vec can be applied as such a learning model, but it is not limited to this.
- the calculation unit 212 may calculate the degree of similarity between the first document and the second document based on the distance between the first document and the second document in a predetermined feature amount space.
- the distance between the document and the second document in a predetermined feature amount space may be used as the degree of similarity between the first document and the second document.
- a larger value indicates a lower degree of similarity
- a smaller value indicates a higher degree of similarity.
- Step S24 the selection unit 213 selects a plurality of clusters obtained by clustering the plurality of second documents based on the degree of similarity between the first document and the plurality of second documents calculated by the calculation unit 212. Choose one of
- Cluster selection method Specific examples of the method by which the selection unit 213 selects clusters include (c) a method based on one or more second documents whose similarity satisfies a predetermined condition; A method based on document similarity will be explained. However, the method by which the selection unit 213 selects clusters is not limited to these.
- the selection unit 213 selects one or more second documents whose degree of similarity with the first document satisfies a predetermined condition from among the plurality of second documents, and selects a plurality of clusters. from among the clusters to which some or all of the selected one or more second documents belong.
- the predetermined condition is, for example, a condition that the degree of similarity with the first document is the highest, a condition that the degree of similarity with the first document is equal to or greater than a predetermined threshold, or a condition that the degree of similarity with the first document is The condition is that the ranking of the degree of similarity is equal to or higher than a predetermined threshold.
- the selection unit 213 selects the second document with the highest degree of similarity to the first document from among the plurality of second documents. Further, the selection unit 213 selects a cluster to which the selected second document belongs by referring to the negotiation history database DB1.
- the selection unit 213 may select clusters by the k-nearest neighbor method. In this case, as an example, the selection unit 213 identifies the k closest second documents to the first document in a predetermined feature amount space, and selects a Select the cluster with the highest number.
- the calculation unit 212 calculates the degree of similarity between the first document and a second document representing a plurality of clusters, and the selection unit 213 calculates the degree of similarity calculated by the calculation unit 212. Select any cluster by referring to it.
- the second document representing each cluster is, for example, the second document with the smallest total distance to other second documents included in the cluster, that is, the second document located at or near the center of the cluster. 2 document.
- the selection unit 213 based on the degree of similarity calculated by the calculation unit 212, the selection unit 213 refers to the negotiation history database DB1 and selects the cluster to which the second document with the highest degree of similarity belongs.
- Step S25 In step S ⁇ b>25 , the output unit 214 outputs information indicating the status of the negotiation associated with the cluster selected by the selection unit 213 .
- the information output by the output unit 214 may include information indicating recommended actions in the situation in addition to information indicating the situation of the negotiation.
- Step S26 The user terminal 30 receives information from the sales support device 20 .
- step S ⁇ b>26 the user terminal 30 outputs the information received from the sales support device 20 .
- the user terminal 30 displays the screen represented by the screen data received from the sales support device 20 on the display device. Displaying the determination result of the situation of the first negotiation makes it easy for the user to grasp the current situation of the first negotiation. In addition, by displaying recommended actions in the relevant situation, it is easy for the user to grasp what action should be taken to advance the negotiation to the next phase.
- the clustering unit 215 clusters the plurality of second documents based on the degree of similarity between the documents to generate a plurality of clusters.
- the clustering unit 215 performs clustering prior to performing the sales support method S20 described above.
- the clustering unit 215 clusters the second documents based on the distance between the second documents when the plurality of second documents are mapped in a predetermined feature amount space.
- the clustering unit 215 performs clustering by, for example, a hierarchical method such as the shortest distance method or a non-hierarchical method such as the k-means method.
- the method of clustering the second documents is not limited to these.
- FIG. 7 is a diagram showing a specific example of clusters obtained by clustering performed by the clustering unit 215.
- the clustering unit 215 generates clusters CL11 to CL13 by clustering the plurality of second documents.
- Clusters CL11-CL13 each include a plurality of second documents.
- the reception unit 216 receives input of information regarding the status of business negotiations for each of the plurality of clusters generated by the clustering unit 215 .
- the reception unit 216 may receive input of information from a device (for example, the user terminal 30) connected via a network.
- the accepting unit 216 When accepting input of information from the user terminal 30, the accepting unit 216 transmits information indicating the result of clustering by the clustering unit 215 to the user terminal 30, and the user terminal 30 presents information indicating the result of clustering to the user.
- the information indicating the result of clustering indicates, as an example, a plurality of clusters generated by the clustering unit 215 and the second documents included in each cluster.
- the user uses the user terminal 30 to input information regarding the status of negotiations to be associated with each cluster.
- a user who inputs information is, for example, an expert who has knowledge about negotiations.
- the user terminal 30 transmits the input information to the sales support device 20, and the reception unit 216 receives the information from the user terminal 30, thereby accepting the input of the information.
- the information adding unit 217 stores the information received by the receiving unit 216 in the description table TB2 in association with the information identifying the cluster. Information for each cluster is accumulated in the explanation table TB2 by a user such as an expert registering information on the status of negotiations for a plurality of clusters. The information registered in the explanation table TB2 is referred to in the sales support method S20 described above.
- the sales support device 20 employs a configuration that clusters a plurality of second documents based on the degree of similarity between the documents to generate a plurality of clusters.
- the sales support device 20 selecting a cluster based on the similarity between the first document and the second document, the sales support device 20 according to this exemplary embodiment can more accurately determine the status of the negotiation. can do.
- the sales support device 20 receives input of information regarding the status of negotiations for each of the plurality of clusters, associates the received information with the cluster ID, and registers it in the description table TB2.
- the sales support device 20 According to this, the processing cost required for adding information can be reduced.
- the acquisition unit 211 may acquire the first document stored in a storage device different from the business negotiation history database DB1 instead of reading the first document from the business negotiation history database DB1.
- a storage device may be communicably connected to the sales support device 20 via a network, or may be a portable storage medium readable by the sales support device 20, for example.
- the acquisition unit 211 may acquire text information or the like input via an input device as the first document instead of reading the first document from the negotiation history database DB1.
- the determination request input from the user terminal 30 in step S21 includes the first document describing the content of the first negotiation in natural language.
- the acquisition unit 211 acquires, for example, the first document included in the received determination request.
- the acquisition unit 211 acquires a first set of documents in which the content of the first business negotiation is written in natural language.
- the first document set includes the first document describing the content of the first business negotiation and the other document describing the content of the first business negotiation, which is written in the past from the first document. or contains multiple documents.
- the obtaining unit 211 further obtains the third document created earlier than the first document regarding the first negotiation.
- the documents included in the first document set have an order relationship, and include, for example, information indicating date and time.
- the information indicating the date and time indicates, for example, the date and time when the document was created, or the date and time when the sales, etc. described in the first document were conducted.
- the selection unit 213 selects one of a plurality of clusters clustered by mapping the second document set including the second document to a predetermined feature amount space.
- Each of the plurality of clustered second document sets includes one or more documents, and the one or more documents included in the second document set have an order relationship.
- One or more documents included in the second document set include, for example, information indicating date and time.
- the second set of documents to be clustered is the second document describing the content of the second business negotiation and the other documents describing the content of the second business negotiation. and one or more documents written prior to the second document.
- the plurality of second documents refer to each second document and a fourth document created prior to the second document for the same second business negotiation as the second document. are clustered together.
- the selection unit 213 compares the degree of similarity between the first document and the second document to the first document set containing the first document and the second document set containing the second document. It is calculated based on the degree of similarity with the set. In other words, the selection unit 213 determines the degree of similarity between the first document and each of the second documents by comparing the first document set including the first document and the third document with the second document and the fourth document. is calculated based on the degree of similarity with the second set of documents including the documents.
- the selection unit 213 selects a second A degree of similarity between the first set of documents and the second set of documents is calculated. As an example, the selection unit 213 calculates the average value of similarity between each of the documents included in the first document set and each of the documents included in the second document set. It may be calculated as a degree of similarity with the set.
- the sales support device 20 based on the degree of similarity between the first document set containing the first document and the second document set containing the second document, A degree of similarity with the second document is calculated.
- the sales support device 20 can more accurately determine the status of negotiations.
- the clustering unit 215 clusters the plurality of second documents based on attributes.
- the attributes indicate, for example, the business type of the customer company, the size of the customer company, the price range of the product, the position of the participant on the customer side, the reaction of the customer, or the measures taken by the company.
- the clustering unit 215 maps the second document to a predetermined feature amount space based on a plurality of features including attributes of the second document, and clusters the plurality of second documents in the feature amount space.
- the sales support device 20 clusters the plurality of second documents based on their attributes. As a result, the sales support device 20 can more accurately determine the status of the negotiation.
- sales support device 10 and 20 and the user terminal 30 may be realized by hardware such as an integrated circuit (IC chip), or by software. may be realized by
- the sales support device 10 and the like are realized, for example, by a computer that executes instructions of a program, which is software that realizes each function.
- a computer that executes instructions of a program, which is software that realizes each function.
- An example of such a computer (hereinafter referred to as computer C) is shown in FIG.
- Computer C comprises at least one processor C1 and at least one memory C2.
- a program P for operating the computer C as the sales support device 10 or the like is recorded in the memory C2.
- the processor C1 reads the program P from the memory C2 and executes it, thereby realizing each function of the sales support device 10 and the like.
- processor C1 for example, CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), PPU (Physics Processing Unit) , a microcontroller, or a combination thereof.
- memory C2 for example, a flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof can be used.
- the computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and temporarily storing various data.
- Computer C may further include a communication interface for sending and receiving data to and from other devices.
- Computer C may further include an input/output interface for connecting input/output devices such as a keyboard, mouse, display, and printer.
- the program P can be recorded on a non-temporary tangible recording medium M that is readable by the computer C.
- a recording medium M for example, a tape, disk, card, semiconductor memory, 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 or broadcast waves can be used.
- Computer C can also obtain program P via such a transmission medium.
- (Appendix 1) Acquisition means for acquiring a first document in which the content of the first business negotiation is written in natural language; For each of a plurality of second business negotiations that do not include the first business negotiation, a second document describing the content of the second business negotiation in a natural language, information on the cluster to which the second document belongs, and information on the cluster referring to a storage device that stores the negotiation status indicated by the document to which it belongs, and based on the degree of similarity between the first document and each of a part or all of the plurality of second documents, a plurality of the second documents; selecting means for selecting one of a plurality of clusters in which documents are clustered; and output means for outputting information indicating the status of negotiations associated with the cluster selected by the selection means.
- the sales support device selects a cluster based on the similarity between documents in which the contents of business negotiations are written in natural language. This makes it possible to more accurately determine the status of the negotiation.
- (Appendix 2) 1. The sales support apparatus according to claim 1, further comprising: clustering means for clustering the plurality of documents accumulated in the storage device based on the degree of similarity between the documents to generate the plurality of clusters.
- the sales support device clusters a plurality of second documents based on the degree of similarity between the documents to generate a plurality of clusters. Select clusters based on similarity to documents. As a result, the sales support device can more accurately determine the status of business negotiations.
- the sales support device selects one of the clustered clusters based on the attributes of the second document.
- the sales support device can more accurately determine the situation in consideration of the attributes of the second document.
- Appendix 4 receiving means for receiving input of information indicating the status of the negotiation for each of the plurality of clusters; information providing means for storing the information received by the receiving means in a storage device in association with the information for identifying the cluster; 4.
- the sales support device according to any one of Appendices 1 to 3, further comprising:
- the sales support device receives input of information indicating the status of business negotiations for each of the plurality of clusters, associates the received information with information identifying the cluster, and stores the information in the storage device.
- Appendix 5 The business according to any one of Appendices 1 to 4, wherein the selection means calculates a distance in a predetermined feature amount space between the first document and each of the plurality of second documents as the degree of similarity. support equipment.
- the sales support device can more accurately determine the status of business negotiations by selecting a cluster based on the distance between documents in a predetermined feature amount space.
- the selection means selects one or a plurality of second documents whose degree of similarity satisfies a predetermined condition from among the plurality of second documents; 6.
- the sales support device according to any one of appendices 1 to 5, wherein a cluster to which part or all of the selected one or more second documents belong is selected from among the plurality of clusters.
- the sales support device selects, from among the plurality of clusters, the cluster to which the second document whose degree of similarity with the first document satisfies a predetermined condition belongs. As a result, the sales support device can more accurately determine the status of the negotiations in the first document.
- the selecting means calculates a degree of similarity between the document acquired by the acquiring means and a second document that is a representative of each of the plurality of clusters, and refers to the calculated degree of similarity to select one of the clusters. 7.
- the sales support device according to any one of appendices 1 to 6, selecting
- the sales support device selects a cluster based on the degree of similarity between the first document and the second document representing each cluster. As a result, the sales support device can more accurately determine the status of the negotiations in the first document.
- the acquisition means further acquires a third document created earlier than the first document regarding the first negotiation,
- the plurality of second documents refer to each second document and a fourth document created earlier than the second document for the same second business negotiation as the second document are clustered and
- the selection means selects the degree of similarity between the first document and each of the second documents for a set of documents including the first document and the third document, the second document and the fourth document.
- the sales support device according to any one of appendices 1 to 7, which is calculated based on the degree of similarity with a set of documents containing
- the sales support device calculates the degree of similarity between the first document and the second document based on the degree of similarity between the document set containing the first document and the document set containing the second document. calculate.
- the sales support device Acquire a first document in which the content of the first business negotiation is written in natural language, For each of a plurality of second business negotiations that do not include the first business negotiation, a second document describing the content of the second business negotiation in a natural language, information on the cluster to which the second document belongs, and information on the cluster referring to a storage device that stores the negotiation status indicated by the document to which it belongs, and based on the degree of similarity between the first document and each of a part or all of the plurality of second documents, a plurality of the second documents; select one of the clusters in which the documents are clustered; A sales support method characterized by outputting information indicating the status of negotiations associated with a selected cluster.
- a program for causing a computer to function as a sales support device comprising: Acquisition means for acquiring a first document in which the content of the first business negotiation is written in natural language; For each of a plurality of second business negotiations that do not include the first business negotiation, a second document describing the content of the second business negotiation in a natural language, information on the cluster to which the second document belongs, and information on the cluster referring to a storage device that stores the negotiation status indicated by the document to which it belongs, and based on the degree of similarity between the first document and each of a part or all of the plurality of second documents, a plurality of the second documents; selecting means for selecting one of a plurality of clusters in which documents are clustered; and output means for outputting information indicating the status of negotiations associated with the cluster selected by the selection means.
- said processor comprising: Acquisition processing for acquiring a first document in which the content of the first business negotiation is written in natural language; For each of a plurality of second business negotiations that do not include the first business negotiation, a second document describing the content of the second business negotiation in a natural language, information on the cluster to which the second document belongs, and information on the cluster referring to a storage device that stores the negotiation status indicated by the document to which it belongs, and based on the degree of similarity between the first document and each of a part or all of the plurality of second documents, a plurality of the second documents; a selection process for selecting one of a plurality of clusters in which documents are clustered; and an output process for outputting information indicating the status of negotiations associated with the cluster selected in the selection process.
- the sales support device may further include a memory, and the memory stores a program for causing the processor to execute the acquisition process, the selection process, and the output process. good too. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (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営業支援装置10の構成について、図1を参照して説明する。図1は、営業支援装置10の構成を示すブロック図である。営業支援装置10は、取得部11、選択部12および出力部13を備える。取得部11は、請求の範囲に記載した取得手段を実現する構成の一例である。選択部12は、請求の範囲に記載した選択手段を実現する構成の一例である。出力部13は、請求の範囲に記載した出力手段を実現する構成の一例である。
本例示的実施形態に係る営業支援方法S10の流れについて、図2を参照して説明する。図2は、営業支援方法S10の流れを示すフロー図である。
ステップS11(取得処理)において、取得部11は、第1の商談の内容を自然言語で記した第1の文書を取得する。取得部11は、一例として、ネットワークを介して通信可能な装置から第1の文書を取得してもよく、また、メモリから第1の文書を読み込むことにより取得してもよい。
ステップS12(選択処理)において、選択部12は、第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書を記憶した記憶装置を参照し、第1の文書と複数の第2の文書の一部または全部の各々との類似度に基づいて、複数の第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する。
ステップS13(出力処理)において、出力部13は、選択部12が選択したクラスタに関連付けられた、商談の状況を示す情報を出力する。出力部13は、一例として、ネットワークを介して通信可能な装置に情報を出力してもよく、また、メモリに情報を書き込むことにより出力してもよい。
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。
図3は、本例示的実施形態に係る商談管理システム1の構成を示すブロック図である。商談管理システム1は、営業員等が行う商談を管理するシステムである。商談管理システム1は、営業支援装置20およびユーザ端末30を含む。営業支援装置20とユーザ端末30とは、ネットワークN1を介して通信可能に接続される。なお、図3には、1つのユーザ端末30を示しているが、営業支援装置20が接続されるユーザ端末30の数は1に限定されない。ネットワークN1は、例えば無線LAN(Local Area Network)、有線LAN、WAN(Wide Area Network)、公衆回線網、モバイルデータ通信網、またはこれらのネットワークの組み合わせである。ただし、ネットワークN1の構成はこれらに限定されない。
営業支援装置20は、商談の状況に関する情報を出力する装置である。営業支援装置20は、制御部210、記憶部220および通信部230を含む。制御部210は、取得部211、算出部212、選択部213、出力部214クラスタリング部215、受付部216および情報付与部217を備える。取得部211は、請求の範囲に記載した取得手段を実現する構成の一例である。算出部212および選択部213は、請求の範囲に記載した選択手段を実現する構成の一例である。出力部214は、請求の範囲に記載した出力手段を実現する構成の一例である。クラスタリング部215は、請求の範囲に記載したクラスタリング手段を実現する構成の一例である。受付部216は、請求の範囲に記載した受付手段を実現する構成の一例である。情報付与部217は、請求の範囲に記載した情報付与手段を実現する構成の一例である。
ユーザ端末30は、ユーザが利用する端末である。ユーザは、一例として、商談を行う営業員である。ユーザ端末30は、一例として、ラップトップコンピュータ、デスクトップコンピュータ、タブレット端末、またはスマートフォンである。ユーザ端末30は、入力部31、表示部32、および通信部33を備える。ユーザ端末30は、入力装置および表示装置(何れも不図示)に接続される。入力部31は、第1の商談の状況の判別要求を、入力装置を介して取得する。入力部31は、取得した判別要求を営業支援装置20に送信する。表示部32は、営業支援装置20が出力した、第1の商談の状況に関する情報を出力する。
図4は、商談履歴データベースDB1の具体例を示す図である。図4の例で、商談履歴データベースDB1は、「商談ID」、「商談名」、「文書ID」、「日時」、「本文」および「クラスタID」の項目を含む商談履歴データを複数記憶する。これらの項目のうち、「商談ID」の項目には商談IDが格納される。商談IDは、商談を識別する識別情報である。「商談名」の項目には、商談の対象である顧客名および案件名等、商談を識別するテキスト情報が格納される。
図5は、説明テーブルTB2の具体例を示す図である。図5の例で、説明テーブルTB2は、「クラスタID」および「説明」の各項目を含む。これらの項目のうち、「クラスタID」の項目には、クラスタを識別する識別情報(クラスタID)が格納される。「説明」の項目には、当該クラスタに関連付けられた、商談の状況に関する情報が格納される。
図6は、商談管理システム1が実行する営業支援方法S20の流れを示すフロー図である。営業支援方法S20は、ユーザが指定した第1の商談の状況を判別する方法である。営業支援方法S20は、一例として、ユーザが入力装置を用いて第1の商談の状況の判別を要求するための操作を行うことを契機として開始される。ユーザは例えば、入力装置を用いて第1の商談を識別する識別情報を入力することにより、第1の商談を指定してもよく、また、入力装置を用いて複数の商談の中から対象である第1の商談を指定する操作を行ってもよい。本例示的実施形態では、第1の商談は、商談履歴データベースDB1に登録されている商談である。ただし、第1の商談は、商談履歴データベースDB1に登録されていない商談であってもよい。
ユーザ端末30の入力部31は、入力装置を介して判別要求を示す情報を受け付ける。ステップS21において、通信部33は、入力部31が受け付けた情報に基づき、判別要求を営業支援装置20に送信する。判別要求は、第1の商談を識別する識別情報を含む。営業支援装置20の取得部211は、ユーザ端末30から判別要求を受信する。
ステップS22において、営業支援装置20の取得部211は、受信した判別要求の対象である第1の商談の内容を記した第1の文書を取得する。具体的には、取得部211は、判別要求に含まれる識別情報に対応する第1の文書を商談履歴データベースDB1から読み出す。
ステップS23において、算出部212は、取得部211が取得した第1の文書と、商談履歴データベースDB1に蓄積された商談履歴データに含まれる複数の第2の文書の一部または全部の各々との類似度を算出する。算出部212は、一例として、第1の文書と複数の第2の文書の各々との所定の特徴量空間における距離を類似度として算出する。
算出部212が第1の文書と第2の文書との類似度を算出する手法の具体例として、(a)単語間距離に基づく手法、および(b)文書間距離に基づく手法を説明する。ただし、第1の文書と第2の文書との類似性を判別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、算出部212は、第1の文書と第2の文書との類似度を、文書に含まれる単語間の距離に基づいて算出する。具体的には、算出部212は、第1の文書に含まれる各単語と、第2の文書に含まれる各単語との各組み合わせについて単語間の距離を算出する。算出部212は、一例として、第1の文書および第2の文書のそれぞれに対して自然言語処理を行い、各文書に含まれる単語を抽出する。自然言語処理は、一例として、形態素解析またはN-gram解析である。
この手法を用いる場合、算出部212は、第1の文書と第2の文書との類似度を、文書間の距離に基づいて算出する。ここで、文書の特徴をベクトルとして表現する場合、第1の文書と第2の文書との文書間距離は、2つのベクトルのなす角度またはベクトル間のユークリッド距離により表わされる。文書の特徴をベクトルとして表す技術としては、文書を入力として特徴ベクトルを出力するよう機械学習された学習モデルを用いることが考えられる。そのような学習モデルとしては、doc2vec等の技術を適用可能であるが、これに限られない。
図6のステップS24において、選択部213は、算出部212が算出した第1の文書と複数の第2の文書との類似度に基づいて、複数の第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する。
選択部213がクラスタを選択する手法の具体例として、(c)類似度が所定の条件を満たす1または複数の第2の文書に基づく手法、および(d)各クラスタの代表である第2の文書との類似度に基づく手法、を説明する。ただし、選択部213がクラスタを選択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、選択部213は、複数の第2の文書の中から、第1の文書との類似度が所定の条件を満たす1または複数の第2の文書を選択し、複数のクラスタの中から、選択した1または複数の第2の文書の一部または全部が属するクラスタを選択する。所定の条件は、一例として、第1の文書との類似の度合いが最も高いという条件、第1の文書との類似の度合いが所定の閾値以上であるという条件、または、第1の文書との類似の度合いの順位が所定の閾値以上であるという条件、である。
この手法を用いる場合、算出部212は、第1の文書と、複数のクラスタの代表である第2の文書との類似度を算出し、選択部213は、算出部212が算出した類似度を参照して何れかのクラスタを選択する。各クラスタの代表である第2の文書は、一例として、クラスタに含まれる他の第2の文書との距離の合計が最小となる第2の文書、すなわちクラスタの中心または中心付近に位置する第2の文書である。
ステップS25において、出力部214は、選択部213が選択したクラスタに関連付けられた、商談の状況を示す情報を出力する。出力部214が出力する情報は、商談の状況を示す情報に加えて、当該状況において推奨されるアクションを示す情報を含んでもよい。
ユーザ端末30は、営業支援装置20から情報を受信する。ステップS26において、ユーザ端末30は、営業支援装置20から受信した情報を出力する。一例として、ユーザ端末30は、営業支援装置20から受信した画面データの表す画面を表示装置に表示する。ユーザは、第1の商談の状況の判別結果が表示されることにより、第1の商談が現在どのような状況であるかを把握し易い。また、当該状況において推奨されるアクションが表示されることにより、ユーザが商談を次のフェーズに進めるためにどのようなアクションをとればよいかを把握し易い。
次いで、クラスタリング部215が行うクラスタリング、および説明テーブルへの情報の登録処理について説明する。クラスタリング部215は、複数の第2の文書を、文書間の類似度に基づきクラスタリングして複数のクラスタを生成する。本例示的実施形態では、クラスタリング部215は、上述の営業支援方法S20が実行されるのに先立ってクラスタリングを実行する。
以上のように、本例示的実施形態によれば、営業支援装置20は、複数の第2の文書を文書間の類似度に基づきクラスタリングして複数のクラスタを生成する構成が採用されている。営業支援装置20が第1の文書と第2の文書との類似性に基づきクラスタを選択することにより、本例示的実施形態に係る営業支援装置20によれば、商談の状況をより精度よく判別することができる。
本例示的実施形態において、取得部211は、第1の文書を商談履歴データベースDB1から読み込む代わりに、商談履歴データベースDB1とは異なる記憶装置に記憶された第1の文書を取得してもよい。そのような記憶装置は、例えば、ネットワークを介して営業支援装置20と通信可能に接続されていてもよいし、営業支援装置20によって読取可能な可搬型の記憶媒体であってもよい。また、取得部211は、第1の文書を商談履歴データベースDB1から読み込む代わりに、入力装置を介して入力されるテキスト情報等を第1の文書として取得してもよい。この場合、ステップS21においてユーザ端末30から入力される判別要求は、第1の商談の内容を自然言語で記した第1の文書を含む。また、ステップS22において、取得部211は、一例として、受信した判別要求に含まれる第1の文書を取得する。
本発明の第3の例示的実施形態について詳細に説明する。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、同じ符号を付記し、その説明を繰り返さない。
本発明の例示的実施形態4について詳細に説明する。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、同じ符号を付記し、その説明を繰り返さない。
営業支援装置10、20およびユーザ端末30(以下、「営業支援装置10等」という)の一部または全部の機能は、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または全部は、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。
第1の商談の内容を自然言語で記した第1の文書を取得する取得手段と、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する選択手段と、
前記選択手段が選択したクラスタに関連付けられた、商談の状況を示す情報を出力する出力手段と、を備えた営業支援装置。
前記記憶装置が蓄積した複数の文書を文書間の類似度に基づきクラスタリングして前記複数のクラスタを生成するクラスタリング手段、を更に備える付記1に記載の営業支援装置。
前記クラスタリング手段は、複数の前記第2の文書を当該第2の文書の属性に基づきクラスタリングする、付記2に記載の営業支援装置。
前記複数のクラスタの各々について、前記商談の状況を示す情報の入力を受け付ける受付手段と、
前記受付手段が受け付けた情報を、前記クラスタを識別する情報と関連付けて記憶装置に記憶する情報付与手段と、
を更に備える付記1から3の何れか1つに記載の営業支援装置。
前記選択手段は、前記第1の文書と複数の前記第2の文書の各々との所定の特徴量空間における距離を前記類似度として算出する、付記1から4の何れか1つに記載の営業支援装置。
前記選択手段は、複数の前記第2の文書の中から、前記類似度が所定の条件を満たす1または複数の第2の文書を選択し、
前記複数のクラスタの中から、選択した1または複数の第2の文書の一部または全部が属するクラスタを選択する、付記1から5の何れか1つに記載の営業支援装置。
前記選択手段は、前記取得手段が取得した文書と、前記複数のクラスタの各々に含まれる代表である第2の文書との類似度を算出し、算出した類似度を参照して何れかのクラスタを選択する、付記1から6の何れか1つに記載の営業支援装置。
前記取得手段は、前記第1の商談について前記第1の文書より過去に作成された第3の文書をさらに取得し、
複数の前記第2の文書は、各第2の文書と、当該第2の文書と同一の前記第2の商談について当該第2の文書より過去に作成された第4の文書とを参照してクラスタリングされており、
前記選択手段は、前記第1の文書と各第2の文書との類似度を、前記第1の文書および前記第3の文書を含む文書集合と、当該第2の文書と前記第4の文書を含む文書集合との類似度に基づき算出する、付記1から7の何れか1つに記載の営業支援装置。
営業支援装置が、
第1の商談の内容を自然言語で記した第1の文書を取得し、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択し、
選択したクラスタに関連付けられた、商談の状況を示す情報を出力する、ことを特徴とする営業支援方法。
コンピュータを営業支援装置として機能させるためのプログラムであって、前記コンピュータを、
第1の商談の内容を自然言語で記した第1の文書を取得する取得手段と、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する選択手段と、
前記選択手段が選択したクラスタに関連付けられた、商談の状況を示す情報を出力する出力手段と、として機能させるプログラム。
上述した実施形態の一部または全部は、更に、以下のように表現することもできる。
第1の商談の内容を自然言語で記した第1の文書を取得する取得処理と、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する選択処理と、
前記選択処理において選択したクラスタに関連付けられた、商談の状況を示す情報を出力する出力処理と、を実行する営業支援装置。
10、20 営業支援装置
11、211 取得部
12、213 選択部
13、214 出力部
30 ユーザ端末
31 入力部
32 表示部
33、230 通信部
210 制御部
212 算出部
215 クラスタリング部
216 受付部
217 情報付与部
220 記憶部
S10、S20 営業支援方法
Claims (10)
- 第1の商談の内容を自然言語で記した第1の文書を取得する取得手段と、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する選択手段と、
前記選択手段が選択したクラスタに関連付けられた、商談の状況を示す情報を出力する出力手段と、を備えた営業支援装置。 - 複数の前記第2の文書を文書間の類似度に基づきクラスタリングして前記複数のクラスタを生成するクラスタリング手段、を更に備える請求項1に記載の営業支援装置。
- 前記クラスタリング手段は、複数の前記第2の文書を当該第2の文書の属性に基づきクラスタリングする、請求項2に記載の営業支援装置。
- 前記複数のクラスタの各々について、前記商談の状況を示す情報の入力を受け付ける受付手段と、
前記受付手段が受け付けた情報を、前記クラスタを識別する情報と関連付けて記憶装置に記憶する情報付与手段と、
を更に備える請求項1から3の何れか1項に記載の営業支援装置。 - 前記選択手段は、前記第1の文書と複数の前記第2の文書の各々との所定の特徴量空間における距離を前記類似度として算出する、請求項1から4の何れか1項に記載の営業支援装置。
- 前記選択手段は、複数の前記第2の文書の中から、前記類似度が所定の条件を満たす1または複数の第2の文書を選択し、
前記複数のクラスタの中から、選択した1または複数の第2の文書の一部または全部が属するクラスタを選択する、請求項1から5の何れか1項に記載の営業支援装置。 - 前記選択手段は、前記第1の文書と、前記複数のクラスタの各々に含まれる代表である第2の文書との類似度を算出し、算出した類似度を参照して何れかのクラスタを選択する、請求項1から6の何れか1項に記載の営業支援装置。
- 前記取得手段は、前記第1の商談について前記第1の文書より過去に作成された第3の文書をさらに取得し、
複数の前記第2の文書は、各第2の文書と、当該第2の文書と同一の前記第2の商談について当該第2の文書より過去に作成された第4の文書とを参照してクラスタリングされており、
前記選択手段は、前記第1の文書と各第2の文書との類似度を、前記第1の文書および前記第3の文書を含む文書集合と、当該第2の文書と前記第4の文書を含む文書集合との類似度に基づき算出する、請求項1から7の何れか1項に記載の営業支援装置。 - 営業支援装置が、
第1の商談の内容を自然言語で記した第1の文書を取得し、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択し、
選択したクラスタに関連付けられた、商談の状況を示す情報を出力する、ことを特徴とする営業支援方法。 - コンピュータを営業支援装置として機能させるためのプログラムであって、前記コンピュータを、
第1の商談の内容を自然言語で記した第1の文書を取得する取得手段と、
前記第1の商談を含まない複数の第2の商談の各々について、当該第2の商談の内容を自然言語で記した第2の文書と当該第2の文書が属するクラスタの情報と当該クラスタに属する文書が示す商談状況とを記憶した記憶装置を参照し、前記第1の文書と複数の前記第2の文書の一部または全部の各々との類似度に基づいて、複数の前記第2の文書がクラスタリングされた複数のクラスタのうちのいずれかを選択する選択手段と、
前記選択手段が選択したクラスタに関連付けられた、商談の状況を示す情報を出力する出力手段と、として機能させるプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/022263 WO2022259512A1 (ja) | 2021-06-11 | 2021-06-11 | 営業支援装置、営業支援方法およびプログラム |
JP2023526796A JPWO2022259512A1 (ja) | 2021-06-11 | 2021-06-11 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/022263 WO2022259512A1 (ja) | 2021-06-11 | 2021-06-11 | 営業支援装置、営業支援方法およびプログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022259512A1 true WO2022259512A1 (ja) | 2022-12-15 |
Family
ID=84425133
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/022263 WO2022259512A1 (ja) | 2021-06-11 | 2021-06-11 | 営業支援装置、営業支援方法およびプログラム |
Country Status (2)
Country | Link |
---|---|
JP (1) | JPWO2022259512A1 (ja) |
WO (1) | WO2022259512A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005149489A (ja) * | 2003-10-24 | 2005-06-09 | Toshiba Solutions Corp | プログラム及び営業活動支援システム並びに方法 |
JP2019008530A (ja) * | 2017-06-23 | 2019-01-17 | 株式会社日立製作所 | 営業支援システム、営業支援方法、及び営業支援プログラム |
JP2020119128A (ja) * | 2019-01-22 | 2020-08-06 | 株式会社三菱総合研究所 | 情報処理装置、情報処理方法及びプログラム |
-
2021
- 2021-06-11 WO PCT/JP2021/022263 patent/WO2022259512A1/ja active Application Filing
- 2021-06-11 JP JP2023526796A patent/JPWO2022259512A1/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005149489A (ja) * | 2003-10-24 | 2005-06-09 | Toshiba Solutions Corp | プログラム及び営業活動支援システム並びに方法 |
JP2019008530A (ja) * | 2017-06-23 | 2019-01-17 | 株式会社日立製作所 | 営業支援システム、営業支援方法、及び営業支援プログラム |
JP2020119128A (ja) * | 2019-01-22 | 2020-08-06 | 株式会社三菱総合研究所 | 情報処理装置、情報処理方法及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022259512A1 (ja) | 2022-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10504120B2 (en) | Determining a temporary transaction limit | |
CN112733042B (zh) | 推荐信息的生成方法、相关装置及计算机程序产品 | |
CN108701155B (zh) | 社交网络中的专家检测 | |
WO2020242622A1 (en) | Remote validation of machine-learning models for data imbalance | |
CN110909222A (zh) | 基于聚类的用户画像建立方法、装置、介质及电子设备 | |
US9298780B1 (en) | Method and system for managing user contributed data extraction templates using weighted ranking score analysis | |
WO2017203672A1 (ja) | アイテム推奨方法、アイテム推奨プログラムおよびアイテム推奨装置 | |
WO2023229737A1 (en) | Method and system of discovering templates for documents | |
CN115271931A (zh) | 一种信用卡产品的推荐方法、装置、电子设备和介质 | |
US20120185476A1 (en) | Multi-function searching and search-related tools and techniques for improved search results and enhanced analysis and decision-making | |
WO2022245469A1 (en) | Rule-based machine learning classifier creation and tracking platform for feedback text analysis | |
JP7481181B2 (ja) | 計算機システムおよび貢献度計算方法 | |
WO2021042541A1 (zh) | 新零售模式下的商品导购方法、装置、设备及存储介质 | |
WO2022259512A1 (ja) | 営業支援装置、営業支援方法およびプログラム | |
CN114169418B (zh) | 标签推荐模型训练方法及装置、标签获取方法及装置 | |
CN116451074A (zh) | 目标对象的画像生成方法、装置、计算机设备、存储介质 | |
JP6026036B1 (ja) | データ分析システム、その制御方法、プログラム、及び、記録媒体 | |
JP2020194204A (ja) | 機械学習ベースのマッチング装置およびマッチング方法 | |
CN115827994A (zh) | 一种数据处理方法、装置、设备、存储介质 | |
US20230100716A1 (en) | Self-optimizing context-aware problem identification from information technology incident reports | |
WO2022259511A1 (ja) | 営業支援装置、営業支援方法およびプログラム | |
JPWO2022259512A5 (ja) | ||
CN114049637A (zh) | 一种目标识别模型的建立方法、系统、电子设备及介质 | |
JP6039057B2 (ja) | 文書分析装置及び文書分析プログラム | |
JP6970527B2 (ja) | コンテンツ選択方法及びコンテンツ選択プログラム |
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: 21945186 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18567139 Country of ref document: US Ref document number: 2023526796 Country of ref document: JP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21945186 Country of ref document: EP Kind code of ref document: A1 |