Sales support device, sales support method and program

Abstract

In order to more accurately identify other business discussions similar to a given business discussion, this business assistance device (10) comprises: an acquisition unit (11) for acquiring a first document set that includes one or a plurality of first documents in which the content of a first business discussion is written in natural language; and an identification unit (12) for referring to, for each of a plurality of second business discussions that do not include the first business discussion, a storage device for storing a second document set that includes a second document in which the content of the second business discussions is written in natural language, and identifying a second business discussion, among the plurality of business discussions, that is similar to the first business discussion on the basis of the degree of similarity between the first document set and the second document set.

Description

[Technical field]

[0001] The present invention relates to a sales support device, a sales support method, and a program. [Background technology]

[0002] A technology for predicting the outcome of business negotiations has been proposed. Patent Document 1 describes a production planning device that creates a production plan in which production volume allocation is optimized to maximize profits, taking into account the probability of receiving orders for steel products. The order information database described in Patent Document 1 includes past order information (actual received orders) including order information that was not received, and order information that is scheduled to be received (projected received orders). The production planning device refers to the order information stored in the order information database, calculates the similarity between each projected received order data subject to the production plan and the actual received order, and calculates the probability of receiving the projected received order based on the calculated similarity. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2014-109845 A Summary of the Invention [Problem to be solved by the invention]

[0004] Meanwhile, whether a business negotiation is successful or not is influenced by various factors related to the business negotiation, such as, for example, the specific sales method performed by a salesperson. In the technology described in Patent Document 1, the similarity between the order information to be received and the past order information is calculated by referring to the past order information, so it is difficult to calculate the similarity of the business negotiation by taking into account various factors related to the business negotiation.

[0005] One aspect of the present invention has been made in consideration of the above-mentioned problems, and one example of an objective of the present invention is to provide a technology for more accurately identifying other business negotiations similar to a business negotiation. [Means for solving the problem]

[0006] A sales support device according to one aspect of the present invention comprises an acquisition means for acquiring a first document set including one or more first documents describing the contents of a first business negotiation in a natural language, and an identification means for referring to a storage device that stores a second document set including a second document describing the contents of a second business negotiation in a natural language for each of a plurality of second business negotiations that do not include the first business negotiation, and identifying a second business negotiation among the plurality of second business negotiations that is similar to the first business negotiation based on the similarity between the first document set and the second document set.

[0007] A sales support method according to one aspect of the present invention includes a sales support device that acquires a first document set including one or more first documents that describe the contents of a first business negotiation in a natural language, references a storage device that stores a second document set including a second document that describes the contents of a second business negotiation in a natural language for each of a plurality of second business negotiations that do not include the first business negotiation, and identifies a second business negotiation that is similar to the first business negotiation among the plurality of second business negotiations based on the similarity between the first document set and the second document set.

[0008] A program according to one aspect of the present invention is a program for causing a computer to function as a sales support device, the program causing the computer to function as: an acquisition means for acquiring a first document set including one or more first documents describing the contents of a first business negotiation in a natural language; and an identification means for referring to a storage device that stores a second document set including a second document describing the contents of a second business negotiation in a natural language for each of a plurality of second business negotiations not including the first business negotiation, and identifying a second business negotiation among the plurality of second business negotiations that is similar to the first business negotiation based on the similarity between the first document set and the second document set. Effect of the Invention

[0009] According to one aspect of the present invention, it is possible to more appropriately identify a second business deal that has been conducted in the past and is similar to a first business deal that is currently or will be conducted in the future. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a sales support device according to a first exemplary embodiment of the present invention. [Diagram 2] 1 is a flow chart showing the flow of a sales support method according to a first exemplary embodiment of the present invention. [Diagram 3] FIG. 11 is a block diagram showing the configuration of a negotiation management system according to a second exemplary embodiment of the present invention. [Figure 4] FIG. 11 is a diagram showing a specific example of a negotiation history database according to the second exemplary embodiment of the present invention. [Diagram 5] FIG. 11 is a diagram showing a specific example of a contract performance database according to the exemplary embodiment 2 of the present invention. [Figure 6] FIG. 11 is a flow chart showing the flow of a sales support method according to an exemplary embodiment 2 of the present invention. [Figure 7] FIG. 11 is a diagram for explaining a specific example of a similarity calculation process according to the second exemplary embodiment of the present invention. [Figure 8] FIG. 11 is a diagram showing a specific example of information output in the second exemplary embodiment of the present invention. [Figure 9] FIG. 11 is a diagram for explaining a specific example of a similarity calculation process according to the third exemplary embodiment of the present invention. [Figure 10] FIG. 1 is a block diagram showing a configuration of a computer that functions as a sales support device or a user terminal according to first to third exemplary embodiments of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Example 1 A first exemplary embodiment of the present invention will be described in detail with reference to the drawings. This exemplary embodiment is a basic form of the exemplary embodiments described later.

[0012] <Configuration of sales support device> The configuration of a sales support device 10 according to this exemplary embodiment will be described with reference to Fig. 1. 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 and an identification unit 12. The acquisition unit 11 is an example of a configuration that realizes the acquisition means recited in the claims. The identification unit 12 is an example of a configuration that realizes the identification means recited in the claims.

[0013] The acquisition unit 11 acquires a first document set including one or more first documents that describe the contents of a first business negotiation in a natural language. The identification unit 12 refers to a storage device that stores a second document set including a second document that describes the contents of the second business negotiation in a natural language for each of a plurality of second business negotiations that do not include the first business negotiation, and identifies, from among the plurality of second business negotiations, a second business negotiation that has been conducted in the past that is similar to a first business negotiation that will be conducted at present or in the future, based on the similarity between the first document set and the second document set. Note that the document in this specification is, for example, a sales report or minutes of sales activities, but is not particularly limited as long as it is a document that includes the contents of the business negotiation.

[0014] A business negotiation refers to the exchange of various information regarding a target project between a person in charge of a service or product providing entity, such as a company or store, and a customer. A business negotiation may be conducted face-to-face, or may be conducted non-face-to-face via a network, telephone, etc. If not face-to-face, the interview may be conducted in real time (e.g., chat, online conference) or non-real time (email, etc.). There may be one or more person in charge and customers. Furthermore, the person in charge and the customer may be a robot, software, etc.

[0015] The document is a description of the contents of a business negotiation written in a natural language. An example of the document is a daily report prepared by a salesperson. An example of the natural language is Japanese, Chinese, or English. In the following description, for convenience of explanation, data representing the document is also simply referred to as a "document." An example of the document is text data showing a character string representing the contents of the business negotiation, a file created by a specified document creation software, a PDF file, or an HTML file. The document may be, for example, data generated by a user operating an input device or the like, or may be, for example, data generated by a device such as the sales support device 10 performing a voice analysis process on a voice file representing the contents of the business negotiation.

[0016] <Sales support method flow> The flow of the sales support method S10 according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the sales support method S10.

[0017] (Step S11) In step S11 (acquisition process), the acquisition unit 11 acquires a first document collection including one or more first documents that describe the contents of the first business negotiation in a natural language. As one example, the acquisition unit 11 may acquire the one or more first documents from a device that can communicate via a network, or may acquire the first documents by reading them from a memory.

[0018] (Step S12) In step S12 (identification process), the identification unit 12 refers to a storage device that stores a second document set including a second document describing the content of the second business negotiation in a natural language for each of the multiple second business negotiations that do not include the first business negotiation, and identifies a second business negotiation that is similar to the first business negotiation among the multiple second business negotiations based on the similarity between the first document set and the second document set. The similarity is information that indicates the degree of similarity between the first document set and the second document set.

[0019] As an example, the specification unit 12 calculates the similarity between the first document set and the second document set based on the similarity between each of the first documents included in the first document set and each of the second documents included in the second document set. As a method for determining the similarity between the document sets, the specification unit 12 may use, for example, a method for calculating the distance between words included in the documents in a predetermined feature space. In this case, the specification unit 12 calculates the 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 between the first document and the second document becomes smaller as the distance between the documents becomes larger, and becomes larger as the distance between the documents becomes smaller. In addition, the specification unit 12 calculates the similarity between the first document set and the second document set based on the similarity between each of the first documents included in the first document set and each of the second documents included in the second document set. However, the process for calculating the similarity between the first document set and the second document set is not limited to the above-mentioned process.

[0020] As described above, the sales support device 10 according to this exemplary embodiment is configured to identify a second business negotiation similar to a first business negotiation based on the similarity between a first document set describing the contents of the first business negotiation and a second document set describing the contents of the second business negotiation. By determining the similarity between business negotiations based on the similarity between documents describing the contents of the business negotiations in natural language, the sales support device 10 according to this exemplary embodiment can provide the effect of more accurately identifying a second business negotiation similar to the first business negotiation.

[0021] Exemplary embodiment 2 A second exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the first exemplary embodiment are given the same reference numerals, and the description thereof will not be repeated.

[0022] <System configuration> FIG. 3 is a block diagram showing the configuration of a sales negotiation management system 1 according to this exemplary embodiment. The sales negotiation management system 1 is a system that manages sales negotiations conducted by sales representatives and the like. The sales negotiation management system 1 includes a sales support device 20 and a user terminal 30. The sales support device 20 and the user terminal 30 are communicatively connected via a network N1. Although FIG. 3 shows one user terminal 30, the number of user terminals 30 to which the sales support device 20 is connected is not limited to one. 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. However, the configuration of the network N1 is not limited to these.

[0023] <Configuration of sales support device> The sales support device 20 is a device that outputs information predicting the outcome of a business negotiation. The sales support device 20 includes a control unit 210, a storage unit 220, and a communication unit 230. The control unit 210 includes an acquisition unit 211, a first calculation unit 212, a second calculation unit 213, an identification unit 214, and an output unit 215. The acquisition unit 211 is an example of a configuration that realizes the acquisition means described in the claims. The first calculation unit 212, the second calculation unit 213, and the identification unit 214 are an example of a configuration that realizes the identification means described in the claims. The output unit 215 is an example of a configuration that realizes the first output means and the second output means described in the claims.

[0024] In this exemplary embodiment, the result of the business negotiation indicates the success or failure of the business negotiation. However, the result of the business negotiation is not limited to this. The result of the business negotiation may indicate, for example, the success, partial success, pending, failure, or any of various other results of the business negotiation. Hereinafter, "information regarding the prediction of the result of the business negotiation" will also be described as "information regarding the prediction of whether the business negotiation will be successful." As an example, the success of the business negotiation includes an order for a product or service, or a contract for a service, etc. As an example, the failure of the business negotiation includes a loss of an order for a product or service, or withdrawal or cancellation of a service. Whether the business negotiation will be successful depends on the specific content of the business negotiation, such as the sales content by the salesperson. As an example, the content of the business negotiation includes the content of the materials provided to the customer, or the number of meetings with the executives.

[0025] The storage unit 220 is an example of a configuration for realizing the storage device described in the claims. The storage unit 220 stores a negotiation history database DB1 and a contract performance database DB2. The negotiation history database DB1 accumulates negotiation history data representing the history of each of a plurality of negotiations. Hereinafter, "a negotiation whose negotiation history data is accumulated in the negotiation history database DB1" is also simply described as "a negotiation accumulated in the negotiation history database DB1". The plurality of negotiations accumulated in the negotiation history database DB1 includes, as an example, past negotiations or negotiations currently in progress. A past negotiation is, for example, a negotiation whose result has been determined. In this exemplary embodiment, of the plurality of negotiations accumulated in the negotiation history database DB1, a currently ongoing negotiation is applied as the first negotiation. When a plurality of currently ongoing negotiations are accumulated in the negotiation history database DB1, at least one of them is applied as the first negotiation. Furthermore, among the multiple negotiations stored in the negotiation history database DB1, a negotiation other than the first negotiation is applied as a second negotiation. The negotiation history data includes documents in which the content of the negotiation is written in natural language. In other words, the negotiation history database DB1 stores a first document set (negotiation history data of the first negotiation) including one or more first documents in which the content of the first negotiation is written in natural language. Furthermore, the negotiation history database DB1 stores a second document set (negotiation history data of the second negotiation) including one or more second documents in which the content of the second negotiation is written in natural language for each of multiple second negotiations.

[0026] In the following explanation, for convenience, when there is no need to distinguish between the first and second negotiations, they will be referred to simply as "negotiations." Also, when there is no need to distinguish between the first and second documents, they will be referred to simply as "documents."

[0027] The contract record database DB2 accumulates information indicating the results of business negotiations. The information indicating the results of business negotiations is, for example, data indicating whether an order has been placed or not.

[0028] The acquisition unit 211 acquires a first document set including one or more first documents that describe the contents of the first business negotiation in a natural language by reading it from the business negotiation history database DB1. Each of the first documents included in the first document set includes information indicating a date and time. As an example, the information indicating a date and time indicates the date and time when the first document was created, or the date and time when sales, etc., related to the contents described in the first document were conducted. In other words, the one or more first documents that describe the contents of the first business negotiation have an order relationship.

[0029] The first calculation unit 212 refers to the negotiation history database DB1 and calculates the similarity between a first document included in the first document collection and a second document included in the second document collection. The method of calculating the similarity between the first document and the second document will be described in detail later.

[0030] The second calculation unit 213 calculates the similarity between the first document set and the second document set based on the similarity between the first document and the second document calculated by the first calculation unit 212. The similarity between the first document set and the second document set represents the similarity between the first business negotiation and the second business negotiation.

[0031] The identification unit 214 identifies a second business negotiation similar to the first business negotiation from among the multiple second business negotiations based on the similarity calculated by the second calculation unit 213. As an example, the identification unit 214 identifies a second business negotiation whose similarity calculated by the second calculation unit 213 satisfies a predetermined condition. The predetermined condition is, for example, that the calculated similarity is equal to or greater than a predetermined value (threshold value).

[0032] The output unit 215 outputs information related to prediction of whether the first business negotiation will be successful. Specifically, the output unit 215 outputs information indicating the order of similarity between the second document set related to the second business negotiation and the first document set for each of some or all of the multiple second business negotiations. The information indicating the order is, for example, information indicating a descending or ascending order of similarity. In other words, the second business negotiations for which the order of similarity is output may be all or some of the second business negotiations accumulated in the business negotiation history database DB1. Furthermore, the output unit 215 refers to information indicating the results of the multiple second business negotiations registered in the contract performance database DB2, and outputs information predicting the result of the first business negotiation. The information indicating the result is, for example, information indicating the success or failure of the business negotiation, or information (numerical values ​​or icons) indicating the probability of success or failure of the business negotiation.

[0033] The communication unit 230 transmits and receives information to and from the user terminal 30 via the network N1 under the control of the control unit 210. Hereinafter, the transmission and reception of information by the control unit 210 to and from the user terminal 30 via the communication unit 230 will also be simply described as the control unit 210 transmitting and receiving information to and from the user terminal 30.

[0034] <User terminal configuration> The user terminal 30 is a terminal used by a user. The user is, for example, a salesperson conducting business negotiations. For example, the user terminal 30 is a laptop computer, a desktop computer, a tablet terminal, or a smartphone. The user terminal 30 includes an input unit 31, a display unit 32, and a communication unit 33. The user terminal 30 is connected to an input device and a display device (neither of which are shown). The input unit 31 acquires a prediction request for the result of the first business negotiation via the input device. The input unit 31 transmits the acquired prediction request to the sales support device 20. The display unit 32 outputs information related to the prediction of the result of the first business negotiation output by the sales support device 20.

[0035] The communication unit 33 transmits and receives information to and from the sales support device 20 via the network N1. Hereinafter, the communication unit 33 transmitting and receiving information to and from the sales support device 20 will also be simply described as the user terminal 30 transmitting and receiving information to and from the sales support device 20.

[0036] (Example of a business negotiation history database) FIG. 4 is a diagram showing a specific example of the negotiation history database DB1. In the example of FIG. 4, the negotiation history database DB1 stores multiple pieces of negotiation history data, including the fields of "Negotiation ID," "Negotiation Name," "Document ID," "Report Date and Time," and "Body." Of these fields, the "Negotiation ID" field stores the negotiation ID. The negotiation ID is identification information that identifies the negotiation. The "Negotiation Name" field stores text information that identifies the negotiation, such as the name of the customer and the name of the case that are the subject of the negotiation.

[0037] The document ID field stores a document ID. The document ID is identification information that identifies a document that describes the contents of the business negotiation in natural language. The "report date and time" field stores information indicating the date and time when the report was made. As an example, the date and time when the report was made is the date and time when the document describing the contents of the business negotiation was registered in the business negotiation history database DB1.

[0038] The "Body" field stores data representing the contents of the document. Examples of the data representing the contents of the document include text data, a file created by a specific document creation software, a PDF file, or an HTML file. The "Body" field may also store an address indicating the storage location of the data representing the contents of the document.

[0039] In the example of Figure 4, multiple documents are associated with one business negotiation. Each of these multiple documents is associated with information indicating the 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 a sales transaction related to the content described in the document was conducted. In other words, multiple documents describing the content of one business negotiation have an order relationship.

[0040] (Example of contract performance database) Fig. 5 is a diagram showing a specific example of the contract performance database DB2. In the example of Fig. 5, the contract performance database DB2 stores multiple pieces of contract performance data including the fields of "negotiation ID" and "contract performance". Of these fields, the "negotiation ID" field stores a negotiation ID that identifies the negotiation. The "contract performance" field stores information indicating the outcome of the negotiation. The information indicating the outcome of the negotiation includes, for example, information indicating whether the order was won or lost.

[0041] <Sales support method flow> FIG. 6 is a flow diagram showing the flow of a sales support method S20 executed by the business negotiation management system 1. As an example, the sales support method S20 is started when a user uses an input device to perform an operation to request a prediction of the result of a first business negotiation. For example, the user may specify the first business negotiation by inputting identification information for identifying the first business negotiation using the input device, or may use the input device to perform an operation to specify the first business negotiation as a target from among multiple business negotiations. In this exemplary embodiment, the first business negotiation is a business negotiation registered in the business negotiation history database DB1. However, the first business negotiation may also be a business negotiation that is not registered in the business negotiation history database DB1.

[0042] (Step S21) In step S21, the input unit 31 of the user terminal 30 receives information indicating a prediction request via the input device. The communication unit 33 transmits the prediction request to the sales support device 20 based on the information received by the input unit 31. The prediction request includes identification information for identifying the first negotiation. The acquisition unit 211 of the sales support device 20 receives the prediction request from the user terminal 30.

[0043] (Step S22) In step S22, the acquisition unit 211 of the sales support device 20 acquires negotiation history data (first document set) of the first negotiation that is the subject of the received prediction request. Specifically, the acquisition unit 211 reads one or more first documents included in the first document set from the negotiation history database DB1.

[0044] (Step S23) In step S23, the first calculation unit 212 calculates the similarity between one or more first documents included in the first document set acquired by the acquisition unit 211 and one or more second documents included in each of the negotiation history data (second document set) of a plurality of second negotiations stored in the negotiation history database DB1.

[0045] A specific example of the similarity calculation process performed by the first calculation unit 212 will be described with reference to the drawings. FIG. 7 is a diagram for explaining a specific example of the similarity calculation process performed by the first calculation unit 212. In the example of FIG. 7, the first calculation unit 212 calculates the similarity between each of one or more first documents DT_i (1 ≦ i ≦ nt; nt is a natural number of 1 or more) included in the first document set DT and each of one or more second documents Dj_k (1 ≦ k ≦ nj; nj is a natural number of 1 or more) included in each of the second document sets Dj (1 < j ≦ N; N is a natural number of 2 or more).

[0046] In the example of FIG. 7, specifically, the first calculation unit 212 calculates the similarity between each of the first documents DT_1, DT_2,..., DT_nt included in the first document set DT and each of the second documents D1_1, D1_2,..., D1_n1 included in the second document set D1. Further, the first calculation unit 212 calculates the similarity between each of the first documents DT_1, DT_2,..., DT_nt included in the first document set DT and each of the second documents D2_1, D2_2,..., D2_n2 included in the second document set D2.

[0047] (Method for calculating similarity between first document and second document) As a specific example of the method by which the first calculation unit 212 calculates the 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 for determining the similarity between the first document and the second document is not limited to these.

[0048] (a: Method based on distance between words) When this method is used, the first calculation unit 212 calculates the similarity between the first document and the second document based on the distance between words included in the documents. Specifically, the first 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 first calculation unit 212 performs natural language processing on each document included in the first document set and the second document set, and extracts words included in each document. As an example, the natural language processing is morphological analysis or N-gram analysis.

[0049] For example, the first calculation unit 212 calculates the word distance for each combination of a word w1i (i=1, 2, . . . , n) included in the first document and a word w2j (j=1, 2, . . . , m) included in the second document. Here, n and m are natural numbers. In this case, there are n×m combinations between the word w1i and the word w2j. In other words, the first calculation unit 212 calculates n×m word distances. Here, when the features of each word w1i and w2j are expressed as vectors, the word distance is represented by the angle between the two vectors or the Euclidean distance between the vectors. As a technique for expressing the features of words as vectors, it is considered to use a learning model that has been machine-learned to input words and output feature vectors. As such a learning model, a technique such as word2vec can be applied, but is not limited to this.

[0050] The first calculation unit 212 calculates the similarity between the first document and the second document using the statistical value of the word distance. As an example, the first calculation unit 212 calculates the average value of the word distance of all combinations of the words w1i and w2j as the similarity indicating the degree of similarity between the first document and the second document. In this case, the larger the value of the similarity, the lower the degree of similarity, and conversely, the smaller the value of the similarity, the higher the degree of similarity. In addition, as an example, the first calculation unit 212 may select a predetermined number of combinations in order from the shortest word distance among all combinations of the words w1i and w2j, and use the average value of the word distance for the selected combinations as the similarity between the first document and the second document. In this case, too, the larger the value of the similarity, the lower the degree of similarity, and conversely, the smaller the value of the similarity, the higher the degree of similarity.

[0051] (b: Method based on document distance) When this method is used, the first calculation unit 212 calculates the similarity between the first document and the second document based on the distance between the documents. Here, when the document features are expressed as vectors, the inter-document distance between the first document and the second document is expressed by the angle between the two vectors or the Euclidean distance between the vectors. As a technique for expressing the document features as vectors, it is possible to use a learning model that has been machine-learned to input a document and output a feature vector. As such a learning model, a technique such as doc2vec can be applied, but is not limited to this.

[0052] The first calculation unit 212 may calculate the similarity between the first document and the second document based on the distance between the first document and the second document, and may use the distance between the first document and the second document as the similarity between the first document and the second document. When the distance between the first document and the second document is used as the similarity, a larger value of the similarity indicates a lower degree of similarity, and conversely, a smaller value indicates a higher degree of similarity.

[0053] (Step S24) In step S24 of FIG. 6, the second calculation unit 213 calculates the similarity between the first document set and each of the plurality of second document sets based on the similarity calculated by the first calculation unit 212.

[0054] In the example of FIG. 7, the first calculation unit 212 identifies, among the second documents D1_1, D1_2, …, D1_n1 included in the second document set D1, the one with the highest degree of similarity to the first document DT_1. The second calculation unit 213 sets the similarity of the identified second document as the similarity d1_1 between the first document DT_1 and the second document set D1. Similarly, the first calculation unit 212 identifies, among the second documents D2_1, D2_2, …, D2_n2 included in the second document set D2, the one with the highest degree of similarity to the first document DT_2. The first calculation unit 212 sets the similarity of the identified second document as the similarity d1_2 between the first document DT_2 and the second document set D2. In this way, the first calculation unit 212 calculates the similarity di_j between the document DT_i (1 ≦ i ≦ nt) and the second document set Dj (1 < j ≦ N).

[0055] The second calculation unit 213 calculates the similarity between the first document set DT and the second document set Dj based on the similarity di_j. As an example, the second calculation unit 213 sets the total value Σ(di_1) of the similarity di_1, or the average value {Σ(di_1)} / nt of the similarity di_1, as the similarity between the first document set DT and the second document set D1. In this way, the second calculation unit 213 calculates the similarity dj between the first document set DT and the second document set Dj by, for example, the following formula (1) or formula (2). Note that the method for calculating the similarity between the first document set DT and the second document set Dj is not limited to these, and the second calculation unit 213 may calculate the similarity by other methods.

Number

Number

[0056] (Step S25) In step S25 of Fig. 6, the identification unit 214 identifies one or more second business negotiations similar to the first business negotiation based on the similarity calculated by the second calculation unit 213 in step S24. As an example, the identification unit 214 identifies the top M (M is an integer of 2 or more) second business negotiations from among the multiple second business negotiations in order of the degree of similarity. Also, as an example, the identification unit 214 may determine whether the multiple second business negotiations are similar to the first business negotiation using a predetermined threshold value.

[0057] (Step S26) In step S26, the output unit 215 generates information on a predicted outcome of the first business negotiation based on the similarity calculated by the second calculation unit 213 and one or both of the one or more second business negotiations identified by the identification unit 214, and outputs the generated information to the user terminal 30. As an example, the output unit 215 outputs information indicating the order of similarity between the second document set and the first document set related to the second business negotiation for some or all of the multiple second business negotiations stored in the business negotiation history database DB1. Also, as an example, the output unit 215 references information indicating the outcome of the second business negotiation identified by the identification unit 214 and outputs information predicting the outcome of the first business negotiation.

[0058] The information output by the output unit 215 may be, for example, data representing a screen showing the results of sorting multiple second business negotiations by similarity, a screen in which the color or shape of the information representing the second business negotiations is varied depending on the similarity, or an image including a figure (graph, etc.) showing the similarity of each of the multiple second business negotiations.

[0059] Moreover, the information output by the output unit 215 is, for example, the probability that the first business negotiation will succeed or the probability that the first business negotiation will fail. In other words, the output unit 215, for example, references information indicating the result of the second business negotiation identified by the identification unit 214, and outputs the probability that the first business negotiation will succeed or the probability that the first business negotiation will fail.

[0060] As one example, the output unit 215 calculates the probability R / N that the first business negotiation will be successful using the number M of one or more second business negotiations identified by the identification unit 214 and the number R of successful business negotiations among the M second business negotiations. Also, as one example, the output unit 215 calculates the probability L / N that the first business negotiation will fail using the number M of one or more second business negotiations identified by the identification unit 214 and the number L of unsuccessful business negotiations among the M second business negotiations.

[0061] (Step S27) The user terminal 30 receives information from the sales support device 20. In step S27, the user terminal 30 outputs the information received from the sales support device 20. As an example, the user terminal 30 displays a screen represented by the screen data received from the sales support device 20 on a display device.

[0062] <Screen example> Fig. 8 is a diagram showing a specific example of information output by the user terminal 30 in step S26. A plurality of second negotiations are displayed in descending order of the degree of similarity with the first negotiation in the example screen SC11 in Fig. 8. The example screen SC11 also displays the results of the plurality of second negotiations (won / lost, etc.).

[0063] The user can easily predict whether the first business negotiation will be successful by displaying the results (won / lost, etc.) of the second business negotiation similar to the first business negotiation on the example screen SC11. Also, the second business negotiations are sorted and ranked by the degree of similarity on the example screen SC11, making it easier for the user to properly understand the second business negotiation to use as reference.

[0064] <Advantages of this exemplary embodiment> As described above, according to this exemplary embodiment, the sales support device 20 is configured to output information indicating the order of similarity between the second document set and the first document set. Therefore, the sales support device 20 according to this exemplary embodiment makes it easy for a user to understand a second business negotiation that is similar to a first business negotiation.

[0065] According to the present exemplary embodiment, the sales support device 20 is configured to output information predicting the outcome of the first business negotiation based on information indicating the outcome of the second business negotiation similar to the first business negotiation. Therefore, the sales support device 20 according to the present exemplary embodiment can predict the outcome of the first business negotiation with higher accuracy.

[0066] According to the present exemplary embodiment, the sales support device 20 is configured to output the probability of success of the first business negotiation based on information indicating the result of the second business negotiation similar to the first business negotiation. Therefore, the sales support device 20 according to the present exemplary embodiment can predict the result of the first business negotiation with higher accuracy.

[0067] Furthermore, according to the present exemplary embodiment, the sales support device 20 calculates the similarity between the first case and the second case based on the similarity between the first document and the second document, which allows the sales support device 20 to more appropriately calculate the similarity between the first case and the second case.

[0068] <Modification> In this exemplary embodiment, the output unit 215 may output information indicating that the probability of the first business negotiation being successful is equal to or lower than a predetermined threshold. As an example, the output unit 215 may display a first business negotiation having a loss probability equal to or higher than a threshold in a screen showing a list of a plurality of first business negotiations in a different manner from the display manner of the other first business negotiations. By the output unit 215 outputting information indicating that the probability of the business negotiation being successful is equal to or lower than a predetermined threshold, it becomes easier for a user or the like to understand that the probability of the business negotiation being successful is low.

[0069] In the present exemplary embodiment, the acquisition unit 211 may acquire the first document set stored in a storage device different from the negotiation history database DB1, instead of reading the first document set from the negotiation history database DB1. Such 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. In addition, instead of reading the first document set from the negotiation history database DB1, the acquisition unit 211 may acquire text information or the like inputted via an input device as the first document set. In this case, the prediction request inputted from the user terminal 30 in step S21 includes one or more first documents describing the contents of the first negotiation in a natural language. In addition, in step S22, the acquisition unit 211 acquires, as an example, one or more first documents included in the received prediction request.

[0070] Exemplary embodiment 3 Exemplary embodiment 3 of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in exemplary embodiments 1 and 2 are denoted by the same reference numerals, and the description thereof will not be repeated.

[0071] In this exemplary embodiment, the first document set includes a plurality of first documents stored in chronological order. The second document set includes a plurality of second documents stored in chronological order. The second calculation unit 213 also refers to a second document similar to any of the first documents included in the first document set among the second documents included in the second document set, and a second document newer than the second document, to calculate a similarity between the first document set and a newer set of second documents.

[0072] The first document and the second document according to this exemplary embodiment are arranged in chronological order by information indicating date and time, for example. Note that the order relationship of the first document and the order relationship of the second document are not limited to be determined by information indicating date and time. The order relationship of the first document and the order relationship of the second document may be determined by file names, for example, or may be determined by file storage addresses, for example.

[0073] 9 is a diagram for explaining a specific example of the similarity calculation process performed by the first calculation unit 212 and the second calculation unit 213 according to the present exemplary embodiment. In the example of FIG. 9, the first calculation unit 212 first calculates the similarity between the first document DT_1 included in the first document set DT and each of the second documents D1_1, D1_2, ..., D1_n1 included in the second document set D1, and identifies the document with the highest degree of similarity. Here, the second document in the second document set D1 that has the highest degree of similarity to the first document DT_1 is set as the second document D1_k. The first calculation unit 212 sets the similarity of the identified second document D1_k as the similarity d1_1 between the first document DT_1 and the second document set D1.

[0074] Next, the first calculation unit 212 calculates the similarity between each of the second documents D1_k+1, D1_k+2, ..., D1_n1, which are in the second document set D1 after the second document D1_k, and the first document DT_2, and identifies the document with the highest similarity. In the following, the second document D1_k+1, D1_k+2, ..., D1_n1, which has the highest similarity to the first document DT_2, is referred to as the second document D1_k2. The first calculation unit 212 determines the similarity of the identified second document D1_k2 as the similarity d2_1 between the first document DT_2 and the second document set D1.

[0075] Next, the first calculation unit 212 calculates the similarity between each of the second documents D1_k2+1, D1_k2+2, ..., D1_n1, which are in the second document set D1 after the second document D1_k2, and the first document DT_3, and identifies the document with the highest similarity. In the following, the second document D1_k2+1, D1_k2+2, ..., D1_n1, which has the highest similarity to the first document DT_3, is defined as the second document D1_k3. The first calculation unit 212 defines the similarity of the identified second document D1_k3 as the similarity d3_1 between the first document DT_3 and the second document set D1.

[0076] In this manner, the first calculation unit 212 determines, as the similarity di_j between the first document DT_i and the second document set Dj, the similarity of the second document having the highest degree of similarity to the first document DT_i among the second documents that are ranked later than the second document Dj_k(i-1). Here, the second document Dj_k(i-1) is the document that the first calculation unit 212 has determined to have the highest degree of similarity to the first document DT_(i-1) in the second document set Dj.

[0077] The second calculation unit 213 calculates the similarity dj between the first document set DT and the second document set Dj based on the similarity di_j. As an example, the second calculation unit 213 calculates the similarity dj between the first document set DT and the second document set Dj by formula (1) or formula (2) shown in the above-mentioned exemplary embodiment 2.

[0078] According to this exemplary embodiment, the sales support device 20 refers to a second document similar to any of the first documents included in the first document set among the second documents included in the second document set, and one or more second documents newer than the second document, to calculate the similarity between the first document set and the new second document set. This allows the sales support device 20 to more appropriately calculate the similarity between the first document set and the second document set.

[0079] Exemplary embodiment 4 A fourth exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the first to third exemplary embodiments are denoted by the same reference numerals, and the description thereof will not be repeated.

[0080] In this exemplary embodiment, the second calculation unit 213 calculates the similarity between a first document in a first document set having a specified attribute and a second document in a second document set having the same attribute as the similarity between the first document set and the second document set.

[0081] Examples of the attributes include the industry of the client company, the size of the client company, the price range of the product, the job title of the client's participant, the client's response, and the client's own policy. As an example, the second calculation unit 213 calculates the similarity between one or more first documents in the first document set, which have an attribute indicating the client's response as "good", and one or more second documents in the second document set, which have an attribute indicating the client's response as "good", as the similarity between the first document set and the second document set. The method for calculating the similarity between the first document and the second document is the method described in the above-mentioned exemplary embodiment 2.

[0082] According to this exemplary embodiment, the sales support device 20 calculates the similarity between a first document and a second document having a predetermined attribute as the similarity between the first document set and the second document set, which allows the sales support device 20 to more appropriately calculate the similarity between the first document set and the second document set.

[0083] [Software implementation example] Some or all of the functions of the sales support devices 10, 20 and the user terminal 30 (hereinafter referred to as "sales support devices 10, etc.") may be realized by hardware such as an integrated circuit (IC chip), or may be realized by software.

[0084] In the latter case, the sales support device 10 etc. is realized, for example, by 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. 10. The computer C has at least one processor C1 and at least one memory C2. The memory C2 stores a program P for operating the computer C as the sales support device 10 etc. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing each function of the sales support device 10 etc.

[0085] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a microcontroller, or a combination of these. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination of these.

[0086] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may further include a communication interface for transmitting and receiving data to and from other devices. The computer C may further include an input / output interface for connecting input / output devices such as a keyboard, a mouse, a display, and a printer.

[0087] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can obtain the program P via such a recording medium M. Furthermore, the program P can be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also obtain the program P via such a transmission medium.

[0088] [Additional Note 1] The present invention is not limited to the above-described embodiment, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the above-described embodiment are also included in the technical scope of the present invention.

[0089] [Additional Note 2] Some or all of the above-described embodiments can be described as follows. However, the present invention is not limited to the following described aspects.

[0090] (Appendix 1) An acquisition means for acquiring a first document set including one or more first documents each describing the content of a first business negotiation in a natural language; a means for referring to a storage device that stores a second document set including a second document describing the content of each of a plurality of second business negotiations not including the first business negotiation, and for identifying a second business negotiation similar to the first business negotiation among the plurality of second business negotiations based on the similarity between the first document set and the second document set; A sales support device equipped with the above.

[0091] According to the above configuration, the sales support device identifies a second business negotiation similar to the first business negotiation based on the similarity between a first document set describing the contents of the first business negotiation and a second document set describing the contents of the second business negotiation. This allows the sales support device to more appropriately identify a second business negotiation similar to the first business negotiation.

[0092] (Appendix 2) The sales support device described in Appendix 1, further comprising a first output means for outputting information representing an order of similarity between the second document set related to each of the second business negotiations and the first document set for some or all of the multiple second business negotiations.

[0093] According to the above configuration, the sales support device outputs information indicating the order of similarity with the first document set, making it easier for users to understand a second business negotiation that is similar to the first business negotiation.

[0094] (Appendix 3) A sales support device as described in Appendix 1 or 2, further comprising a second output means for outputting information predicting the result of the first sales negotiation by referring to information indicating the result of the second sales negotiation identified by the identification means.

[0095] According to the above configuration, the sales support device can more accurately predict the outcome of the first business negotiation by outputting information predicting the outcome of the first business negotiation based on information indicating the outcome of a second business negotiation that is similar to the first business negotiation.

[0096] (Appendix 4) The sales support device according to claim 3, wherein the second output means outputs the probability that the first sales negotiation will be successful by referring to information indicating the result of the second sales negotiation identified by the identification means.

[0097] According to the above configuration, the sales support device outputs the probability that the first business negotiation will be successful based on the result of the second business negotiation that is similar to the first business negotiation, thereby enabling the sales support device to more accurately predict the result of the first business negotiation.

[0098] (Appendix 5) The sales support device according to any one of appendices 1 to 4, wherein the identification means calculates a similarity between the first document set and the second document set based on a similarity between each of the first documents included in the first document set and each of the second documents included in the second document set.

[0099] According to the above configuration, the sales support device calculates the similarity between the first case and the second case based on the similarity between the first document and the second document, thereby enabling the sales support device to more appropriately calculate the similarity between the first case and the second case.

[0100] (Appendix 6) the first document collection includes a plurality of the first documents stored in chronological order; the second document set includes a plurality of the second documents stored in chronological order; The sales support device of any one of Appendices 1 to 5, wherein the identification means refers to a second document included in the second document set that is similar to any first document included in the first document set and a second document that is newer than the second document, and calculates a similarity between the first document set and the newer second document set.

[0101] According to the above configuration, the sales support device refers to a second document similar to any of the first documents included in the first document set among the second documents included in the second document set, and a second document newer than the second document, to calculate the similarity between the first document set and the new second document set. This allows the sales support device to more appropriately calculate the similarity between the first document set and the new second document set.

[0102] (Appendix 7) The sales support device according to any one of appendices 1 to 6, wherein the identification means calculates a similarity between a first document in the first document set, the first document having a predetermined attribute, and a second document in the second document set, the second document having the predetermined attribute, as a similarity between the first document set and the second document set.

[0103] According to the above configuration, the sales support device calculates the similarity between a first document and a second document having a predetermined attribute as the similarity between the first document set and the second document set. This allows the sales support device to more appropriately calculate the similarity between the first document set and the second document set.

[0104] (Appendix 8) The sales support device according to claim 4, wherein the second output means outputs information indicating that the certainty is equal to or lower than a predetermined threshold value.

[0105] According to the above configuration, the sales support device outputs information indicating that the probability is equal to or lower than the threshold, making it easier for the user to understand that the probability of success in the negotiation is low.

[0106] (Appendix 9) Sales support device, A first document set including one or more first documents describing the content of a first business negotiation in a natural language is obtained; refer to a storage device that stores a second document set including a second document describing the content of the second business negotiation in a natural language for each of the second business negotiations not including the first business negotiation, and identify, from among the second business negotiations, a second business negotiation that is similar to the first business negotiation based on the similarity between the first document set and the second document set; A sales support method comprising:

[0107] (Appendix 10) A program for causing a computer to function as a sales support device, the program comprising: An acquisition means for acquiring a first document set including one or more first documents each describing the content of a first business negotiation in a natural language; A program characterized by functioning as an identification means that, for each of a plurality of second business negotiations not including the first business negotiation, refers to a storage device that stores a second document set including a second document describing the content of the second business negotiation in a natural language, and identifies a second business negotiation that is similar to the first business negotiation among the plurality of second business negotiations based on the similarity between the first document set and the second document set.

[0108] [Additional Note 3] A part or all of the above-described embodiments can be further expressed as follows.

[0109] At least one processor, the processor comprising: an acquisition process for acquiring a first document set including one or more first documents each describing the content of a first business negotiation in a natural language; A sales support device that executes an identification process for identifying, for each of a plurality of second business negotiations not including the first business negotiation, a second business negotiation that is similar to the first business negotiation among the plurality of second business negotiations based on the similarity between the first document set and the second document set, by referring to a storage device that stores a second document set including a second document that describes the content of the second business negotiation in a natural language.

[0110] The sales support device may further include a memory that stores a program for causing the processor to execute the acquisition process and the identification process. The program may be recorded in a computer-readable, non-transitory, tangible recording medium. [Explanation of symbols]

[0111] 1. Sales negotiation management system 10, 20 Sales support equipment 11, 211 Acquisition Department 12, 214 Specific part 30 User terminal 31 Input section 32 Display section 33, 230 Communications Department 210 Control section 212 First Calculation Section 213 Second Calculation Section 215 Output section 220 Storage section S10, S20 sales support method

Claims

1. an acquisition means for acquiring a first document set including one or more first documents each describing the content of a first business negotiation in a natural language; a means for referring to a storage device that stores a second document set including a second document describing the content of each of a plurality of second business negotiations not including the first business negotiation, and for identifying a second business negotiation similar to the first business negotiation among the plurality of second business negotiations based on the similarity between the first document set and the second document set; Equipped with the first document collection includes a plurality of the first documents stored in chronological order; the second document set includes a plurality of the second documents stored in chronological order; The specifying means refers to a second document similar to any one of the first documents included in the first document set, among the second documents included in the second document set, and a second document newer than the second document, to calculate a similarity between the first document set and the new second document set. Sales support device.

2. The sales support device of claim 1, further comprising a first output means for outputting information representing an order of similarity between the second document set and the first document set relating to each of some or all of the multiple second sales negotiations.

3. 3. The sales support device according to claim 1, further comprising a second output means for outputting information predicting the result of the first sales negotiation by referring to information indicating the result of the second sales negotiation identified by the identification means.

4. 4. The sales support device according to claim 3, wherein the second output means outputs the probability that the first sales negotiation will be successful by referring to information indicating the result of the second sales negotiation identified by the identification means.

5. 3. The sales support device according to claim 1, wherein the identification means calculates a similarity between the first document set and the second document set based on a similarity between each of the first documents included in the first document set and each of the second documents included in the second document set.

6. 3. The sales support device according to claim 1, wherein the identification means calculates a similarity between a first document in the first document set having a predetermined attribute and a second document in the second document set having the same attribute as a similarity between the first document set and the second document set.

7. The sales support device according to claim 4 , wherein the second output means outputs information indicating that the certainty is equal to or lower than a predetermined threshold value when the certainty is equal to or lower than a predetermined threshold value.

8. Sales support device, A first document set including one or more first documents describing the content of the first business negotiation in a natural language is obtained; For each of a plurality of second business negotiations not including the first business negotiation, refer to a storage device that stores a second document set including a second document describing the content of the second business negotiation in a natural language, and identify, among the plurality of second business negotiations, a second business negotiation that is similar to the first business negotiation based on the similarity between the first document set and the second document set; the first document collection includes a plurality of the first documents stored in chronological order; the second document set includes a plurality of the second documents stored in chronological order; In the identification, a second document similar to any one of the first documents included in the first document set and a second document newer than the second document among the second documents included in the second document set are referenced to calculate a similarity between the first document set and the new second document set. A sales support method comprising:

9. A program for causing a computer to function as a sales support device, the program comprising: an acquisition means for acquiring a first document set including one or more first documents each describing the content of a first business negotiation in a natural language; and functioning as an identification means for identifying, for each of a plurality of second business negotiations not including the first business negotiation, a second document set including a second document describing the content of the second business negotiation in a natural language, among the plurality of second business negotiations, a second business negotiation that is similar to the first business negotiation based on the similarity between the first document set and the second document set; the first document collection includes a plurality of the first documents stored in chronological order; the second document set includes a plurality of the second documents stored in chronological order; The specifying means refers to a second document similar to any one of the first documents included in the first document set, among the second documents included in the second document set, and a second document newer than the second document, to calculate a similarity between the first document set and the new second document set. A program characterized by:

Images