JP2022109776A - Content distribution method, device, and program - Google Patents

Abstract

To automatically distribute a content of great interest to a customer.SOLUTION: A content distribution method, which is executed by an information processing device, includes: acquisition processing of obtaining customer information including text relating to a customer; identification processing of identifying an interest keyword of the customer based on the text; selection processing of selecting a content relating to the interest keyword from among a plurality of preliminarily registered contents; and distribution processing of distributing the selected content.SELECTED DRAWING: Figure 8

Description

The present invention relates to a content delivery method, device, and program.

Conventionally, systems for accumulating and analyzing customer information have been used to support sales activities. Such systems may have the ability to provide sales personnel with useful information during sales. As a method of providing information to a salesperson, a salesperson support computer and a plurality of mobile terminals used by salespersons visiting customers are connected via a wireless communication network, and the salesperson support computer a sales information computer and a salesperson management terminal for providing general-purpose sales information to the said salesperson support computer; When information is provided, while referring to the general-purpose sales information, using a predetermined editing method or analysis method, from the report information, unique sales information about the individual salesperson is generated, and from the portable terminal When receiving a command requesting information necessary for supporting the sales activity of the salesperson at the sales activity site, support information corresponding to the request command is provided using the general-purpose sales information or the unique sales information as an information source. A sales activity support method has been proposed, which is characterized by generating and providing to the portable terminal.

JP-A-2002-99707

In the prior art described above, information requested by a salesperson is provided to the salesperson. In other words, there is a problem that even useful information about sales is not provided to the sales person unless the sales person requests it.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to automatically distribute contents that are of high interest to customers.

A content distribution method according to one embodiment is a content distribution method executed by an information processing apparatus, comprising an acquisition process of acquiring customer information including a text about a customer, and specifying a keyword of interest of the customer based on the text. a selection process of selecting content related to the keyword of interest from a plurality of pre-registered contents; and a distribution process of distributing the selected content.

According to one embodiment, content of high customer interest can be automatically distributed.

It is a figure which shows an example of a structure of a content delivery system. It is a figure which shows an example of the hardware constitutions of an information processing apparatus. It is a figure which shows an example of the functional structure of a content distribution apparatus. It is a figure which shows an example of customer information. It is a figure which shows an example of interest keyword information. It is a figure which shows an example of content information. 6 is a flowchart showing an example of content distribution processing; It is a figure which shows an example of a content display screen. It is a figure which shows the modification of a content delivery system.

Hereinafter, each embodiment of the present invention will be described with reference to the accompanying drawings. Regarding the descriptions of the specifications and drawings according to each embodiment, components having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

<System configuration>
First, an overview of the content distribution system according to this embodiment will be described. A content distribution system according to the present embodiment is a system that automatically distributes content of interest to a customer to a user in charge of the customer. A user is a person who uses the content distribution system, and is, for example, a salesperson in charge of one or more customers. Specifically, when the content distribution system acquires information about the customer input by the user, content that the customer is interested in is automatically selected based on the acquired information, and the selected content is delivered to the user. delivered to. By referring to the distributed content, the user can effectively make proposals to customers and interact with customers.

FIG. 1 is a diagram showing an example of the configuration of a content distribution system according to this embodiment. The content distribution system of FIG. 1 includes a user terminal 1 and a content distribution device 2 that are connected to each other via a network N so as to be able to communicate with each other. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination thereof.

The user terminal 1 is an information processing device used by a user of the content distribution system. The user terminal 1 is, for example, a PC (Personal Computer), a smart phone, or a tablet terminal, but is not limited thereto. The user uses the user terminal 1 to register customer information and receive content distribution. Note that the content delivery system may include two or more user terminals 1 .

The content distribution device 2 is an information processing device that distributes content to users. The content distribution device 2 is, for example, a server, a PC, a smart phone, a tablet terminal, or a combination thereof, but is not limited thereto. Details of the content distribution device 2 will be described later.

<Hardware configuration>
Next, the hardware configuration of the information processing device will be described. FIG. 2 is a diagram showing an example of the hardware configuration of the information processing apparatus 100. As shown in FIG. As shown in FIG. 2, the information processing apparatus 100 includes a processor 101, a memory 102, a storage 103, a communication I/F 104, an input/output I/F 105, and an input It comprises a device 106 , an output device 107 and a drive device 108 .

The processor 101 controls each component of the information processing apparatus 100 and implements the functions of the information processing apparatus 100 by loading the program stored in the storage 103 into the memory 102 and executing the program. The functions of the information processing apparatus 100 are implemented by the processor 101 executing the program. The processor 101 is, for example, a CPU (Central Processing Unit), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit), DSP (Digital Signal Processor), or a combination thereof.

The memory 102 is, for example, ROM (Read Only Memory), RAM (Random Access Memory), or a combination thereof. ROM is, for example, PROM (Programmable ROM), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), or a combination thereof. RAM is, for example, DRAM (Dynamic RAM), SRAM (Static RAM), MRAM (Magnetoresistive RAM), or a combination thereof.

The storage 103 stores programs such as an OS and various data. The storage 103 is, for example, flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), SCM (Storage Class Memories), or a combination thereof.

The communication I/F 104 is an interface for connecting the information processing device 100 to an external device via the network N and controlling communication. The communication I/F 104 is, for example, an adapter conforming to Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), Ethernet (registered trademark), or optical communication (for example, Fiber Channel). , but not limited to.

The input/output I/F 105 is an interface for connecting the input device 106 and the output device 107 to the information processing apparatus 100 .

The input device 106 is a device for receiving an operation by the user U and inputting information corresponding to the received operation to the information processing apparatus 100 . The input device 106 is, for example, a mouse, keyboard, touch panel, microphone, scanner, camera, various sensors, operation buttons, or a combination thereof.

The output device 107 is a device that outputs various information held by the information processing device 100 . Output device 107 is, for example, a display, a projector, a printer, a speaker, a vibrator, or a combination thereof.

The drive device 108 reads and writes data on the disk media 109 . Drive device 108 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or a combination thereof.

The disk medium 109 is a disk-shaped recording medium on which information is recorded. The disk medium 109 is, for example, a CD (Compact Disc), DVD (Digital Versatile Disc), FD (Floppy Disk), MO (Magneto-Optical disk), BD (Blu-ray (registered trademark) Disc), or a combination thereof. is.

In this embodiment, various programs may be written in the memory 102 or the storage 103 at the manufacturing stage of the information processing device 100, or may be provided to the information processing device 100 via the network N, It may be provided to the information processing apparatus 100 via a non-temporary computer-readable recording medium such as the disc medium 109 .

<Functional configuration>
Next, the functional configuration of the content distribution device 2 will be described. FIG. 3 is a diagram showing an example of the functional configuration of the content distribution device 2. As shown in FIG. As shown in FIG. 3 , the content distribution device 2 includes a communication section 21, a storage section 22, and a control section 23.

Communication unit 21 is realized by communication I/F 104 . The communication unit 21 transmits and receives information to and from the user terminal 1 via the network N. FIG. Specifically, the communication unit 21 receives information about customers from the user terminal 1 and transmits (distributes) content to the user terminal 1 .

The storage unit 22 is implemented by the memory 102 and storage 103 . The storage unit 22 stores customer information 221 , interest keyword information 222 , content information 223 and model information 224 .

The customer information 221 is information related to customers for whom the user is in charge. The customer information 221 is registered by, for example, the user himself or another person in charge of the same customer. FIG. 4 is a diagram showing an example of the customer information 221. As shown in FIG. The customer information 221 in FIG. 4 includes “customer ID”, “name”, “address”, “date of birth”, “sex”, “place of work”, “department”, and “memo” as information items. "Customer ID" is an identifier that uniquely identifies a customer. "Name", "address", "date of birth", "sex", and "place of work" are the customer's name, address, date of birth, sex, and place of work, respectively. "Memo" is text about the customer entered by the user. In the "memo", for example, the user inputs arbitrary information about the customer obtained by conversation with the customer or by e-mail as text. “Department” is the department to which the customer belongs at the customer's office. For example, the customer information on the first line in FIG. "2000/1/1", "Gender" is "Male", "Workplace" is "Company A", "Department" is "Department A", and "Memo" is "Recently I bought a car.” Note that the customer information 221 is not limited to the above example. The customer information 221 may include some of the above information items, or may include information items other than the above.

Interested keyword information 222 is information about an interested keyword. Keywords of interest are keywords that the customer is interested in. Keywords of interest include hobbies (soccer, camping, sauna, car, shogi, etc.), brands, life events (childbirth, school entrance, graduation, employment, marriage, etc.), and attributes of people (gender, age, marital status, presence of children). etc.). A plurality of pieces of interest keyword information 222 are registered in advance by, for example, the administrator of the content distribution system. FIG. 5 is a diagram showing an example of the interest keyword information 222. As shown in FIG. The interest keyword information 222 of FIG. 5 includes “keyword ID”, “interest keyword”, and “interest keyword vector” as information items. "Keyword ID" is an identifier that uniquely identifies an interest keyword. "Interested Keyword" is text indicating an interested keyword. The "interest keyword vector" is a vector obtained by vectorizing the interest keyword. When a new keyword of interest is registered in the content distribution system, the specifying unit 232, which will be described later, reads the model information 224, which will be described later, vectorizes the keyword of interest using a natural language processing model, and generates the obtained keyword of interest vector. is associated with the keyword of interest and stored. For example, the keyword-of-interest information 222 on the first line in FIG. 0.01, . . . ”. Note that the interest keyword information 222 is not limited to the above example. The question information 222 may include some of the above information items, or may include information items other than the above.

The content information 223 is information about content. Content is, for example, articles, advertisements, videos, images, music, games, or combinations thereof. The content can be any content selectable by keywords of interest. The content may have tags corresponding to keywords of interest, or may have descriptions (titles, summaries, etc.) searchable by keywords of interest. Also, the content itself may be searchable using keywords of interest. Also, the content may have tags or descriptions that are vectorizable in a manner similar to the keywords of interest, or the content itself may be vectorizable in a manner similar to the keywords of interest. A plurality of pieces of content information are registered in advance by, for example, an administrator of the content distribution system. FIG. 6 is a diagram showing an example of the content information 223. As shown in FIG. The content information 223 in FIG. 6 is content information when the content is an article with tags, and includes "content ID", "content", and "tag" as information items. "Content ID" is an ID for uniquely identifying the content. "Content" is text indicating the content of the article. "Tag" is text indicating a tag attached to the content. For example, in the content information 223 of FIG. 6, the "content ID" is "A001", the "content" is "Company X announced a concept car at a motor show", and the "tag" is "Company X" and It's a "motor show". Note that the content information 223 is not limited to the above example. The content information 223 may include some of the above information items, or may include information items other than the above.

The model information is information about a trained natural language processing model and includes the model and parameter values. A natural language processing model can be any machine learning model that can vectorize text. The natural language processing model is, for example, Word2Vec, BERT (Bidirectional Encoder Representations from Transformers), or USE (Universal Sentence Encoder), but is not limited thereto.

The control unit 23 is implemented by the processor 101 reading and executing a program from the memory 102 and cooperating with other hardware configurations. The control unit 23 includes an acquisition unit 231 , an identification unit 232 , a selection unit 233 and a distribution unit 234 .

The acquisition unit 231 acquires the customer information 221 including the text regarding the customer from the user terminal 1 and stores it in the storage unit 22 .

The identifying unit 232 identifies keywords of interest to the customer based on the text regarding the customer. A method of specifying the keyword of interest will be described later.

The selection unit 233 selects content related to the customer's keyword of interest from a plurality of content registered in advance in the content distribution system. A content selection method will be described later.

The distribution unit 234 distributes the content selected by the selection unit 233 to the user terminal 1 .

<Content distribution processing>
Next, content distribution processing executed by the content distribution device 2 according to this embodiment will be described. FIG. 7 is a flowchart illustrating an example of content distribution processing.

(Step S101)
A user of the content distribution system inputs customer information 221 regarding his or her customer to the user terminal 1 at a desired timing. The user terminal 1 transmits the input customer information 221 to the content distribution device 2 . When the content distribution device 2 receives the customer information 221, the acquisition unit 231 acquires the customer information 221 and stores it in the storage unit 22 (step S101). The process of step S101 is executed at any timing by each user with respect to each customer.

(Step S102)
When a user desires to view content that a customer is interested in, the user transmits a content distribution request to the content distribution device 2 via the user terminal 1 . The distribution request includes the identification information of the requesting user and the customer ID. If the content distribution device 2 does not receive the content distribution request (step S102: NO), the process ends. On the other hand, if the content distribution device 2 receives a content distribution request (step S102: YES), the process proceeds to step S103.

(Step S103)
The specifying unit 232 refers to the customer information 221 and reads the text regarding the customer corresponding to the customer ID included in the distribution request. The specifying unit 232 also reads the model information 224 . The identifying unit 232 then vectorizes the text regarding the customer using a natural language processing model. As a result, a customer text vector is generated by vectorizing the text about the customer.

(Step S104)
The specifying unit 232 reads the interest keyword information 222 and calculates the degree of association between the interest keyword vector corresponding to each interest keyword and the customer text vector (step S104). The degree of relevance is, for example, Euclidean distance or cosine similarity between the keyword vector of interest and the customer text vector, or a value obtained by subjecting the keyword vector of interest and the customer text vector to matrix transformation processing, but is not limited thereto. .

(Step S105)
The identifying unit 232 selects an interest keyword that the customer is interested in from among a plurality of interest keywords registered in advance based on the degree of association calculated in step S104 (step S105). The degree of relevance between the interest keyword vector and the customer text vector is calculated such that the higher the degree of relevance between the interest keyword and the customer text, the greater the degree of relevance. Therefore, the specifying unit 232 selects an interest keyword having a high degree of relevance to the customer text (that is, an interest keyword corresponding to the interest keyword vector having a high degree of relevance to the customer text vector) from among a plurality of interest keywords registered in advance. Select as customer interest keywords. The specifying unit 232 may select all keywords of interest having a degree of relevance to the customer text equal to or greater than a threshold value as keywords of interest to the customer, or may select one keyword of interest having the highest degree of relevance to the customer text as the keyword of interest to the customer. may be selected as

(Step S106)
The selection unit 233 refers to the content information 223 and selects content related to the keyword of interest identified in step S105 (step S106). When the content is tagged, the selection unit 233 may select the content tagged with the keyword of interest as the content related to the keyword of interest. In addition, when the content is accompanied by a description, the selection unit 233 may select the content to which the description including the interest keyword is attached as the content related to the interest keyword. If the content is accompanied by a description, the selection unit 233 vectorizes the description in the same manner as in step S103, calculates the degree of relevance between the obtained vector and the vector of interest, and Alternatively, content that is above the threshold may be selected as content related to the keyword of interest. Moreover, when the content is an article, the selection unit 233 may select an article including the interest keyword as the content related to the interest keyword. Further, when the content is an article, the selection unit 233 vectorizes the article by the same method as in step S103, calculates the degree of relevance between the obtained vector and the interest keyword vector, and determines whether the degree of relevance is the maximum or is equal to or greater than the threshold. Articles may be selected as content related to keywords of interest. In addition, the selection unit 233 may use customer information (information such as address, date of birth, gender, place of work, department, etc.) other than the text regarding the customer as an additional keyword of interest.

(Step S107)
If the selection unit 233 cannot select content related to the keyword of interest (step S107: NO), the process ends. On the other hand, if the selection unit 233 can select content related to the interest keyword (step S107: YES), the process proceeds to step S108.

(Step S108)
The distribution unit 234 reads the content information 224 of the content selected in step S107, and transmits (distributes) the read content information to the user terminal 1 (step S108).

When receiving the content information from the content distribution device 2, the user terminal 1 displays the content display screen D on the display device. FIG. 8 is a diagram showing an example of the content display screen D. As shown in FIG. The content display screen D of FIG. 8 includes a customer image Im, customer information C, and articles A1 and A2. The customer image Im is an image of the customer. Articles A1 and A2 are contents in which customers are interested. In the example of FIG. 8, articles A1 and A2 related to cars are displayed as content of interest to the customer. Note that the content display screen D is not limited to the above example. The content display screen D may include some of the above information items, or may include information items other than the above.

<Summary>
As described above, according to this embodiment, a customer's keyword of interest is specified based on the text about the customer registered by the user, content related to the customer's keyword of interest is selected, and automatically delivered to the user. . Since the distributed content is of interest to the customer, the user can effectively make suggestions to the customer and interact with the customer by referring to this content. As described above, according to the present embodiment, it is possible to provide (distribute) useful information (contents of interest to customers) to the user during sales without the user's request.

Further, according to this embodiment, the customer's interest keyword is specified based on the degree of relevance to the text regarding the customer. Therefore, even if the keyword included in the customer-related text and the pre-registered interest keyword do not match, if the two are close in meaning, the interest keyword corresponding to the keyword included in the customer-related text is identified. be. As a result, the influence of fluctuations in notation when the user inputs text can be suppressed, and the accuracy of identifying keywords of interest to customers can be improved.

The content distribution system according to this embodiment can also be used as a marriage activity support system that matches registered users. In this case, the content distribution system according to the present embodiment can be used as a system for automatically distributing content that one user is interested in to other users who are matched with one user. Specifically, when the content distribution system acquires information about oneself input by one user, content in which the one user is interested is automatically selected based on the acquired information, and the selected content is , is delivered to other users that match the one user. Other users can effectively interact with one user by referring to the distributed content.

<Modification>
FIG. 9 is a diagram showing a modification of the content delivery system. The content distribution system of FIG. 9 includes a user terminal 1, a content distribution device 2, a sales support system 3, and a content management system 4, which are connected to each other via a network N so as to be able to communicate with each other.

The sales support system 3 is an external system in which customer information 221 is registered by a salesperson, and is operated by a business operator different from the content distribution apparatus 2 . The sales support system 3 is, for example, a CRM (Customer Relationship management) system or an SFA (Sales Force Automation) system, but is not limited thereto. A user accesses the sales support system 3 via the user terminal 1 .

The content management system 4 is an external system that accumulates and distributes the content information 223, and is operated by a business operator (newspaper company, publisher, television station, etc.) different from the content distribution device 2. FIG.

In the example of FIG. 9, the content distribution device 2 cooperates with the sales support system 3 and the content management system 4 to realize a content distribution system. Specifically, the acquisition unit 231 of the content distribution device 2 acquires the customer information 221 from the sales support system 3 and acquires the content information 223 from the content management system 4 . The specifying unit 232 specifies the customer's interest keyword based on the customer information 221 and the interest keyword information 222 acquired by the acquisition unit 231 . The selection unit 233 selects content that the customer is interested in based on the content information 223 and the customer's interest keyword. The distribution unit 234 distributes the selected content from the content management system 4 to the sales support system 3 . A user accesses the sales support system 3 from the user terminal 1 and views the content delivered from the content management system 4 . As a result, the modified example can realize the functions and effects of the content distribution system according to the present embodiment. In addition, in the example of FIG. 9, the content management system 4 may include the selection unit 233 and the distribution unit 234 .

<Appendix>
This embodiment includes the following disclosure.

(Appendix 1)
A content distribution method executed by an information processing device,
a retrieval process for retrieving customer information including text about the customer;
an identification process of identifying keywords of interest to the customer based on the text;
a selection process of selecting content related to the keyword of interest from a plurality of pre-registered content;
a distribution process for distributing the selected content;
content delivery methods, including;

(Appendix 2)
The content distribution method according to appendix 1, wherein the identifying process identifies, from among a plurality of keywords of interest registered in advance, keywords of interest having a degree of association with the text about the customer equal to or greater than a threshold as keywords of interest of the customer. .

(Appendix 3)
3. The content distribution method according to appendix 2, wherein the degree of association is calculated based on a customer text vector obtained by vectorizing text relating to the customer and an interest keyword vector obtained by vectorizing the interest keyword.

(Appendix 4)
3. The content distribution method according to any one of appendices 1 to 3, wherein the content is an article.

(Appendix 5)
4. The content distribution method according to any one of appendices 1 to 4, wherein the interest keyword includes a keyword relating to at least one of hobby, brand, life event, and person's attribute.

(Appendix 6)
The acquisition process acquires the customer information from a sales support system,
The content distribution method according to any one of appendices 1 to 5, wherein the distribution process distributes the content to the sales support system.

(Appendix 7)
an acquisition unit for acquiring customer information including text about the customer;
an identifying unit that identifies keywords of interest to the customer based on the text;
a selection unit that selects content related to the keyword of interest from a plurality of pre-registered content;
a distribution unit that distributes the selected content;
content delivery system including;

(Appendix 8)
information processing equipment,
a retrieval process for retrieving customer information including text about the customer;
an identification process of identifying keywords of interest to the customer based on the text;
a selection process of selecting content related to the keyword of interest from a plurality of pre-registered content;
a distribution process for distributing the selected content;
A program for executing a content distribution method including

The embodiments disclosed this time are illustrative in all respects and should be considered not restrictive. The scope of the present invention is indicated by the scope of the claims rather than the above-described meaning, and is intended to include all modifications within the scope and meaning equivalent to the scope of the claims. In addition, the present invention is not limited to the above-described embodiments, but can be modified in various ways within the scope of the claims, and can be obtained by appropriately combining technical means disclosed in different embodiments. Embodiments are also included in the technical scope of the present invention.

1: User terminal 2: Content distribution device 3: Sales support system 4: Content management system 21: Communication unit 22: Storage unit 23: Control unit 221: Customer information 222: Interest keyword information 223: Content information 224: Model information 231: Acquisition unit 232: Identification unit 233: Selection unit 234: Distribution unit 100: Information processing device 101: Processor 102: Memory 103: Storage 104: Communication I/F
105: Input/output I/F
106: Input device 107: Output device 108: Drive device 109: Disk media

Claims (8)

A content distribution method executed by an information processing device,
a retrieval process for retrieving customer information including text about the customer;
an identification process of identifying keywords of interest to the customer based on the text;
a selection process of selecting content related to the keyword of interest from a plurality of pre-registered content;
a distribution process for distributing the selected content;
content delivery methods, including; 2. The content distribution according to claim 1, wherein said identifying process identifies, as said customer's keyword of interest, said keyword of interest having a degree of relevance to said customer's text that is equal to or greater than a threshold, from among a plurality of keywords of interest registered in advance. Method. 3. The content distribution method according to claim 2, wherein the degree of association is calculated based on a customer text vector obtained by vectorizing the text relating to the customer and an interest keyword vector obtained by vectorizing the interest keyword. 4. The content delivery method according to any one of claims 1 to 3, wherein said content is an article. 5. The content delivery method according to any one of claims 1 to 4, wherein said interest keyword includes a keyword relating to at least one of hobby, brand, life event, and person's attribute. The acquisition process acquires the customer information from a sales support system,
6. The contents distribution method according to claim 1, wherein said distribution process distributes said contents to said sales support system. an acquisition unit for acquiring customer information including text about the customer;
an identifying unit that identifies keywords of interest to the customer based on the text;
a selection unit that selects content related to the keyword of interest from a plurality of pre-registered content;
a distribution unit that distributes the selected content;
content delivery system including; information processing equipment,
a retrieval process for retrieving customer information including text about the customer;
an identification process of identifying keywords of interest to the customer based on the text;
a selection process of selecting content related to the keyword of interest from a plurality of pre-registered content;
a distribution process for distributing the selected content;
A program for executing a content distribution method including

Images