Information processing systems, information processing methods, and programs

Abstract

Based on behavioral logs and customer attribute information of prospective customers, the system generates email templates tailored to each prospective customer and allows customer approach support information for those prospective customers to be reflected in external systems. [Solution] An information processing system having at least one control unit, the control unit acquires behavioral logs and customer attribute information relating to prospective customers from an external system, identifies missing information indicating information that the prospective customer lacks based on the behavioral logs and customer attribute information, determines appeal axes to supplement the missing information, generates an email draft for prospective customers based on the appeal axes, and reflects customer approach support information including the email draft or information corresponding to the appeal axes or missing information in the external system.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] In recent years, behavioral histories, customer attribute information, negotiation histories, etc. regarding prospective customers have been accumulated in a marketing automation system, a customer management system, or a sales support system, and these have been used in sales activities or marketing activities.

[0003] For example, technologies have been proposed for generating content used in a sales approach based on information regarding prospective customers, or for managing information regarding sales activities or negotiations by an external system.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the conventional technologies as described above, although it is possible to manage information regarding prospective customers or generate content used in a sales approach, based on the action logs and customer attribute information for each prospective customer, it is not sufficient to identify the information lacking in the prospective customer, determine an appeal axis for supplementing the lacking information, and generate an email text based on the appeal axis.

[0006] Furthermore, in addition to reflecting the generated email text, appeal points, or information corresponding to missing information into an external system for use in subsequent sales or marketing activities, sufficient consideration was not given to reflecting various customer approach support information obtained based on behavioral logs, customer attribute information, segment classification results, difference analysis results, and other analysis results into an external system. Customer approach support information may include, for example, lead score values, segment classification results, recommended action information, missing information category labels, and approach priority flags. Therefore, the present invention aims to provide an information processing system, information processing method, and program that can identify missing information based on behavioral logs and customer attribute information of prospective customers, determine appeals to supplement the missing information, generate email drafts based on the appeals, and reflect customer approach support information for the prospective customer in an external system. [Means for solving the problem]

[0007] (1) An information processing system, Having at least one control unit, The control unit, We obtain behavioral logs and customer attribute information about prospective customers from an external system. Based on the way the prospective customer interacted with the content included in the behavior log, a content contact status table is generated that associates contact status or response status for each content category. From the aforementioned content contact status table, content categories that the prospective customer has not yet contacted or content categories whose response is below a predetermined standard are extracted as missing candidate categories. The priority of the candidate categories of missing information is adjusted according to the customer attribute information, and the information corresponding to the candidate categories of missing information is identified as missing information indicating that the prospective customer is lacking. Referencing candidate appeal axis information associated with each category of missing information, calculate the appeal suitability score for each candidate appeal axis using the missing information deficiency score and the customer attribute suitability based on the customer attribute information, and determine the appeal axis to supplement the missing information based on the appeal suitability score. Select recommended content corresponding to the aforementioned appeal axis, The system generates instruction information including the missing information, the appeal axis, and the recommended content, and uses the instruction information as input to the text generation model to generate a draft email for the prospective customer. The system generates customer approach support information including the aforementioned email draft, the appeal axis, information corresponding to the missing information, and identification information for the recommended content. The customer approach support information is reflected in the external system. Information processing system. (2) (1) The information processing system described above, The action log includes at least one of a Web page browsing history, a mail delivery history, a mail opening history, a link click history, a document download history, a form submission history, and an online event participation history. Information processing system. (3) The information processing system according to (1), The control unit calculates statistical values ​​of feature quantities derived from the behavioral logs or customer attribute information for each of the customer groups in which the outcome event was achieved and the customer group in which the outcome event was not achieved, calculates a difference index between the statistical values ​​of the customer group in which the outcome event was achieved and the statistical values ​​of the customer group in which the outcome event was not achieved, generates difference feature information based on the difference index, and determines the missing information or the appeal axis based on the difference feature information. Information processing system. (4) The information processing system according to (1), The control unit classifies the prospective customer into a plurality of segments using at least one of the behavior log and the customer attribute information as features. The determination of the appeal axis or the generation of the email text is performed using appeal axis candidate information or instruction information corresponding to the segment to which the prospective customer belongs. Information processing system. (5) The information processing system according to (4), The control unit generates the different appeal axes or the mail copy for each of the segments and Correspond to a segment identifier indicating the aforementioned segment reflects it in the external system. Information processing system. (6) The information processing system according to (1), The text generation model generates the email text, which includes at least one of the following: a subject line, body text, a description of the recommended content, and a call to action, using the missing information, appeal axis, and recommended content included in the instruction information. Information processing system. (7) The information processing system according to (6), The control unit As the instruction information, in addition to the missing information, the appeal axis, and the recommended content, information is generated that includes at least one of the prospective customer's attributes, segment, writing style conditions, character count conditions, and prohibited expression conditions. By inputting the aforementioned instruction information into the text generation model, the email text is generated. Information processing system. (8) The information processing system according to (1), The customer approach support information The following further includes at least one of the following: lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, and recommended content identification information. The recommended action information includes at least one of a type, a priority, and a recommended timing. Information processing system. (9) The information processing system according to (1), The control unit, after reflecting the email draft in the external system, accepts user approval input for the email draft. In response to the aforementioned approval input, the system is instructed to execute a send command to perform the process of sending an email to the prospective customer using the email template. Information processing system. (10) (1) The information processing system described above, The control unit generates explanatory information indicating the missing information, the appeal axis, and the recommended content used in generating the email draft, The above explanatory information Output the email text in correspondence with the aforementioned draft. Information processing system. (11) (1) The information processing system described above, The aforementioned external system has an external database that manages data for each prospective customer, The control unit searches for or specifies a corresponding record from the external database using identification information including a customer ID or email address that identifies the prospective customer, and registers or updates the customer approach support information associated with the corresponding record. Information processing system. (12) An information processing method performed by an information processing system, The process involves obtaining behavioral logs and customer attribute information about prospective customers from an external system. A step of generating a content contact status table that associates contact status or response status for each content category based on the way the prospective customer interacted with content included in the behavior log, The process of extracting content categories that the prospective customer has not yet interacted with or content categories whose response is below a predetermined standard from the content contact status table as missing candidate categories, A step of adjusting the priority of the candidate categories of deficiencies according to the customer attribute information, and identifying the information corresponding to the candidate categories of deficiencies as deficiency information indicating that the prospective customer is lacking information, The process involves referring to candidate appeal axis information associated with each category of missing information, calculating an appeal suitability score for each candidate appeal axis using the missing information deficiency score and the customer attribute suitability based on the customer attribute information, and determining an appeal axis to supplement the missing information based on the appeal suitability score. The process of selecting recommended content corresponding to the aforementioned appeal axis, The process includes generating instruction information including the missing information, the appeal axis, and the recommended content, and using the instruction information as input to a text generation model to generate a draft email text for the prospective customer, A process for generating customer approach support information including the aforementioned email draft, the appeal axis, information corresponding to the missing information, and identification information for the recommended content, A step of reflecting the customer approach support information in the external system, Information processing methods including (13) Computers, A program to function as an information processing system as described in any one of (1) through (11). [Effects of the Invention]

[0008] According to the present invention, based on behavioral logs and customer attribute information of prospective customers, it is possible to identify information that is lacking in the prospective customer, determine appeals to supplement that lacking information, and generate email drafts based on those appeals. Furthermore, according to the present invention, the generated email text, appeal points, information corresponding to missing information, and customer approach support information including lead score values, segment classification results, recommended action information, missing information category labels, and approach priority flags can be reflected in an external system, making it easier to use approach content tailored to each prospective customer in subsequent sales or marketing activities. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of the system configuration of an information processing system. [Figure 2] Figure 2 shows an example of the hardware configuration of an information processing device. [Figure 3] Figure 3 shows an example of the hardware configuration of a terminal device. [Figure 4] Figure 4 is a block diagram showing an example of the functional configuration of an information processing device. [Figure 5] Figure 5 is a flowchart showing an example of the customer approach support information generation, reflection, and transmission control process. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below (including modified examples; the same applies hereinafter) can be combined with each other.

[0011] <Embodiment 1> 1. System Configuration Figure 1 shows an example of the system configuration of the information processing system 1000 according to this embodiment. As shown in Figure 1, the information processing system 1000 includes, as a system configuration, an information processing device 100, a terminal device 110, an external system 120, and a document generation system 130.

[0012] The information processing device 100, terminal device 110, external system 120, and document generation system 130 are connected to each other via a network 150. The network 150 includes a WAN (Wide Area Network), a LAN (Local Area Network), and the Internet, or any combination thereof. The network 150 includes a wired network and a wireless network, or both.

[0013] The information processing system 1000 identifies information lacking for a prospective customer based on their behavioral logs and customer attribute information, determines an appeal strategy to address that lack, generates an email draft based on that appeal strategy, and reflects the email draft, the appeal strategy, or customer approach support information corresponding to the lacking information into the external system 120. This allows for the generation of tailored approach content for each prospective customer, and the results of this generation can be reflected in the external system for use in subsequent sales or marketing activities.

[0014] The information processing device 100 is a device that provides the main functions of the information processing system 1000 and corresponds to a device having a "control unit" in this disclosure. The information processing device 100 acquires behavioral logs and customer attribute information about prospective customers from the external system 120, identifies missing information based on the behavioral logs and customer attribute information, determines the appeal axis, and generates an email draft based on the appeal axis. The information processing device 100 also reflects the generated email draft, appeal axis, information corresponding to the missing information, lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, and other customer approach support information to the external system 120.

[0015] Terminal device 110 is a device used by users of the information processing system 1000. Users of the information processing system 1000 include, for example, marketing personnel, inside sales personnel, sales planning personnel, or sales managers. Through terminal device 110, users can select prospective customers, check segments, review email drafts, enter approvals, issue sending instructions, and view explanatory information.

[0016] External system 120 is an external system that manages data for each prospective customer, and is, for example, a marketing automation system, a customer relationship management system, or a sales support system. External system 120 has an external database that holds behavioral logs and customer attribute information about prospective customers. The external database stores, for example, web page browsing history, email delivery history, email open history, link click history, document download history, form submission history, online event participation history, and customer attribute information such as contact person's name, department, industry, job title, region, and company size.

[0017] The external system 120 provides behavioral logs and customer attribute information in response to requests from the information processing device 100. The external system 120 also receives customer approach support information transmitted from the information processing device 100 and reflects it in the external database. The information reflected here may include, for example, list information associated with prospective customers, segment information, property information, candidate message information for transmission, transmission target flag, lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, etc.

[0018] The text generation system 130 is a system that provides the function of generating email text based on the appeal axis. The text generation system 130 may include a text generation model. The information processing device 100 causes the text generation system 130 to perform text generation based on the determined appeal axis and obtains email text for prospective customers. The text generation system 130 may be a separate system from the information processing device 100, or it may be configured to be built into the information processing device 100.

[0019] The text generation model is a model that generates email text based on a sales pitch or instruction information that includes the sales pitch. The text generation model may be, for example, a natural language processing model, a language generation model, or a generative artificial intelligence model, but is not limited to these. The information processing device 100 may also generate instruction information that includes the sales pitch and cause the text generation model to generate email text based on the instruction information.

[0020] Herein, "customer approach support information" as used in this specification means information used in sales or marketing activities targeting prospective customers. Customer approach support information may include, for example, at least one of the following: email text, appeal axis, information corresponding to missing information, lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, recommended content identification information, approval status information, generation date and time, text version information, regeneration history information, etc.

[0021] The lead score is a numerical value calculated based on prospective customer behavior logs, customer attribute information, differential analysis results, segment information, and relationships with past success events, and may be an indicator of the prospective customer's level of interest, progress in consideration, likelihood of success in a success event, or sales priority.

[0022] Recommended action information is information that indicates the next recommended action to take for a prospective customer, and may include at least one of the following: type (e.g., sending an email, making a phone call, sending materials, presenting comparative materials, presenting case studies, proposing an online meeting, waiting for further contact), priority of that type, and recommended timing.

[0023] The missing information category label is label information indicating the type or category of the identified missing information, and may include, for example, insufficient comparative judgment materials, insufficient understanding of implementation cases, insufficient understanding of cost-effectiveness, insufficient understanding of functionality, insufficient understanding of security, etc. The approach priority flag is information indicating the priority of approaching the prospective customer, and may be a multi-value flag of high, medium, or low, a binary flag indicating whether or not it is above a predetermined threshold, or ranking information.

[0024] Herein, "prospective customer" in this specification refers to a potential customer or an unplaced customer who is the target of sales or marketing activities. "Segment" refers to a group of prospective customers divided according to predetermined classification criteria. "Segment classification result" refers to information indicating the segment to which the prospective customer belongs.

[0025] Herein, "recommended content" in this specification refers to materials that supplement missing information or correspond to the appeal axis, case studies, comparative materials, pricing information, functional description materials, linked content, etc. Furthermore, "information corresponding to the appeal axis or missing information" refers to appeal axis categories, appeal axis identifiers, missing information categories, missing information category labels, recommended content identification information, descriptive information, supplementary information, and other related information.

[0026] Herein, "reflection" as used herein refers to processes including registration, updating, overwriting, appending, or association with corresponding records in an external system.

[0027] Here, the information processing system described in the claims may consist of multiple devices or of one device. If the information processing system described in the claims consists of one device, an example of such device is the information processing device 100. If the information processing system described in the claims consists of multiple devices, an example of such multiple devices is a configuration that includes at least some of the information processing device 100, terminal device 110, external system 120, and document generation system 130.

[0028] In Figure 1, for simplicity, one terminal device 110, one external system 120, and one document generation system 130 are shown, but the number of each is not limited to one. For example, multiple terminal devices 110 may be connected to the information processing device 100, data may be acquired from multiple types of external systems 120, or multiple document generation systems 130 may be used for different purposes.

[0029] Furthermore, the information processing system 1000 is not limited to a configuration that allows for bidirectional data exchange with the external system 120. The system that acquires behavioral logs and customer attribute information may be different from the system that receives the generated results. For example, customer attribute information may be acquired from a customer management system, behavioral logs may be acquired from a marketing automation system, and the generated results may be reflected in a sales support system.

[0030] 2. Hardware Configuration (1) Hardware configuration of the information processing device 100 Figure 2 shows an example of the hardware configuration of the information processing device 100. As shown in Figure 2, the information processing device 100 includes, as a hardware configuration, a control unit 210, a storage unit 220, a communication unit 230, and an internal bus 240. The control unit 210, the storage unit 220, and the communication unit 230 are electrically connected via the internal bus 240.

[0031] The control unit 210 includes at least one of the following: CPU (Central Processing Unit), MPU (Micro Processing Unit), SoC (System on Chip), FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit), GPU (Graphics Processing Unit), or a combination of at least two of these. It controls the entire information processing device 100 and executes various processes according to information input from other devices or information stored in the storage unit 220.

[0032] The storage unit 220 includes at least one of the following: HDD (Hard Disk Drive), ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drive), or a combination of at least two of these, and stores a program and data used by the control unit 210 when executing processing based on the program.

[0033] Examples of data used by the control unit 210 when executing processing based on the program include identification information to identify prospective customers, behavioral logs obtained from the external system 120, customer attribute information, segment information for each prospective customer, missing information, appeal axis, email draft, lead score value, recommended action information, missing information category label, approach priority flag, candidate message information to send, target message flag, information related to approval input, and explanatory information used as the basis for generating the email draft.

[0034] The storage unit 220 is an example of a computer-readable non-temporary recording medium (storage medium) on which a program is recorded. In this specification, the data used by the control unit 210 when executing processing based on the program is described as being stored in the storage unit 220, but it may also be stored in the storage unit of another device that can communicate with the information processing device 100. In other words, the data may be stored in the storage unit of any device as long as the control unit 210 can access and / or retrieve it.

[0035] The control unit 210 executes processing based on the program stored in the memory unit 220, thereby realizing the functional configuration of the information processing device 100 shown in Figure 4, which will be described later, and the processing of the flowchart shown in Figure 5, which will be described later.

[0036] The communication unit 230 is a communication interface that connects the information processing device 100 to the network 150 and mediates communication with other devices. The communication unit 230 can be implemented, for example, by a network interface card, LAN (Local Area Network) adapter, optical transceiver, etc., for wired communication, and / or by wireless communication modules such as Wi-Fi, Bluetooth®, 5G (5th generation mobile communication system), LTE (Long Term Evolution), NFC (Near Field Communication), etc., and circuits that control them.

[0037] Based on instructions from the control unit 210, the communication unit 230 performs data transmission and reception processing over the network 150 in accordance with a predetermined communication protocol, such as TCP (Transmission Control Protocol) / IP (Internet Protocol), UDP (User Datagram Protocol), HTTP (Hypertext Transfer Protocol), or HTTPS (Hypertext Transfer Protocol Secure).

[0038] Furthermore, the hardware configurations of the control unit 210, storage unit 220, and communication unit 230 are not limited to one. For example, the information processing device 100 may include multiple CPUs, multiple storage devices, or multiple communication interfaces.

[0039] (2) Hardware configuration of terminal device 110 Figure 3 shows an example of the hardware configuration of the terminal device 110. As shown in Figure 3, the terminal device 110 includes, as a hardware configuration, a control unit 310, a storage unit 320, an input / output unit 330, a communication unit 340, and an internal bus 350. The control unit 310, the storage unit 320, the input / output unit 330, and the communication unit 340 are electrically connected via the internal bus 350.

[0040] The control unit 310 includes at least one of the following: CPU, MPU, SoC, FPGA, ASIC, GPU (Graphics Processing Unit), or at least two combinations thereof, and controls the entire terminal device 110, as well as executing various processes in response to information input from the input / output unit 330 or other devices.

[0041] The storage unit 320 includes at least one of the following: HDD, ROM, RAM, SSD, etc., or at least two combinations thereof, and stores the program and data used by the control unit 310 when executing processing based on the program. The storage unit 320 is an example of a computer-readable non-temporary recording medium (storage medium) on which the program is recorded.

[0042] In this specification, the data used by the control unit 310 when executing processing based on a program is described as being stored in the storage unit 320, but it may also be stored in the storage unit of another device that can communicate with the terminal device 110. The data may be stored in the storage unit of any device as long as the control unit 310 can access and / or retrieve it.

[0043] The control unit 310 executes processing based on the program stored in the storage unit 320, thereby realizing display processing, input reception processing, approval input processing, transmission instruction processing, etc., in the terminal device 110.

[0044] The input / output unit 330 is a device that inputs information to the terminal device 110 in response to user operations, and also outputs information to the user. The input / output unit 330 receives operation inputs made by the user and transfers these operation inputs as command signals to the control unit 310 via the internal bus 350. The input / output unit 330 may also output information as a graphical user interface (GUI) screen that can be operated by the user. Examples of the input / output unit 330 include a touch panel, a combination of a display device and an input device, a keyboard, a mouse, etc. When the input / output unit 330 is implemented as a touch panel, the user can input tap operations, swipe operations, scroll operations, etc. to the input / output unit 330.

[0045] The communication unit 340 is a communication interface that connects the terminal device 110 to the network 150 and mediates communication with other devices. The communication unit 340 can be implemented, for example, by a network interface card, LAN adapter, optical transceiver, etc. that realize wired communication, and / or by wireless communication modules such as Wi-Fi, Bluetooth®, 5G, LTE, NFC (Near Field Communication), etc. that realize wireless communication, and circuits that control them.

[0046] Based on instructions from the control unit 310, the communication unit 340 performs data transmission and reception processing over the network 150 in accordance with a predetermined communication protocol, such as TCP / IP, UDP, HTTP, or HTTPS.

[0047] In this specification, examples of terminal devices 110 include smartphones, tablet devices, and notebook personal computers, but terminal devices 110 are not limited to these and may also include desktop personal computers, thin client terminals, etc.

[0048] (3) Hardware configuration of the external system 120 and the text generation system 130 Since the hardware configurations of the external system 120 and the text generation system 130 are the same as those of the information processing device 100 described above, a detailed explanation will be omitted. That is, the external system 120 and the text generation system 130 may be implemented by a computer configuration including a control unit, a storage unit, a communication unit, etc.

[0049] Furthermore, the control unit of the text generation system 130 may be equipped with a computing device such as a GPU, TPU (Tensor Processing Unit), or NPU (Neural Processing Unit) in addition to, or instead of, the CPU, in order to execute inference processing by the text generation model at high speed.

[0050] 3. Functional Configuration Figure 4 is a block diagram showing an example of the functional configuration of the information processing device 100. As shown in Figure 4, the information processing device 100 includes, for example, an acquisition unit 401, a segment classification unit 402, a missing information identification unit 403, a difference analysis unit 404, an appeal axis determination unit 405, an instruction information generation unit 406, a text draft generation unit 407, a write-back control unit 408, an approval acceptance unit 409, an explanation information generation unit 410, an external linkage unit 411, and a storage control unit 412. These functions may be realized by the control unit 210 executing a program stored in the storage unit 220.

[0051] The acquisition unit 401 acquires behavioral logs and customer attribute information about prospective customers from the external system 120. Behavioral logs may include, for example, web page browsing history, email delivery history, email open history, link click history, document download history, form submission history, online event participation history, etc. Customer attribute information may include, for example, contact person's name, department, industry, job title, region, company size, past contact history, etc.

[0052] The acquisition unit 401 may acquire behavioral logs and customer attribute information for each identification piece of information that identifies a prospective customer via the API of the external system 120. The information acquired by the acquisition unit 401 may be stored in the storage unit 220 via the storage control unit 412.

[0053] The segment classification unit 402 classifies prospective customers into multiple segments based on the behavioral logs and customer attribute information acquired by the acquisition unit 401. Segment classification may be based on at least one of the following: industry, job title, company size, browsing content trends, email response trends, form completion status, etc.

[0054] The segment classification unit 402 may classify prospective customers using a rule-based method, or it may classify them using a statistical model or a machine learning model. For example, prospective customers belonging to a specific industry and having a specific browsing history may be classified into a first segment, and other prospective customers may be classified into a second segment.

[0055] The missing information identification unit 403 identifies missing information that indicates information that the prospective customer is lacking, based on the behavioral logs and customer attribute information acquired by the acquisition unit 401. Missing information refers to information that the prospective customer has not yet acquired or understood in order to reach a success event, and may include things that the customer understands, comparative judgment materials, or reassuring materials.

[0056] The missing information identification unit 403 may identify missing information based, for example, on content that prospective customers have not viewed, appeal items with low response rates, unanswered form items, or missing explanatory information in their contact history. Alternatively, the missing information identification unit 403 may identify different missing information for each segment by referring to the classification results from the segment classification unit 402.

[0057] The difference analysis unit 404 analyzes the differences between the customer group in which an outcome event occurred and the customer group in which an outcome event did not occur. An outcome event may include, for example, email replies, business negotiations, appointment setting, document requests, applications, or orders. The difference analysis unit 404 may extract differences between the two customer groups in terms of behavioral logs, customer attribute information, segment information, etc.

[0058] The difference analysis unit 404 may, based on the results of the difference analysis, correct the identification of missing information by the missing information identification unit 403, or generate difference feature information used by the appeal axis determination unit 405 to determine the appeal axis. For example, it may extract the difference between the content group that is frequently viewed in the group where the success event occurred and the content group that is not viewed in the group where the success event did not occur, and reflect this difference in the determination of missing information or the appeal axis. The difference analysis unit 404 may also calculate a lead score value for each prospective customer based on the behavior log, customer attribute information, difference feature information, or segment information.

[0059] The appeal axis determination unit 405 determines an appeal axis to supplement the missing information identified by the missing information identification unit 403. The appeal axis may be information that indicates the value, benefits, implementation effects, comparative advantages, or case studies that should be presented to prospective customers in an emphasis.

[0060] The appeal axis determination unit 405 may determine an appeal axis for each prospective customer, or it may determine an appeal axis for each segment based on the classification results of the segment classification unit 402. Alternatively, the appeal axis determination unit 405 may use the analysis results of the difference analysis unit 404 to preferentially determine an appeal axis corresponding to explanatory elements characteristic of the group in which the outcome event occurred.

[0061] The instruction information generation unit 406 generates instruction information that includes the appeal axis determined by the appeal axis determination unit 405. The instruction information is information used by the text generation unit 407 when generating a text draft, and includes at least the appeal axis, and may include, as necessary, the attributes of prospective customers, segments, recommended content, writing style conditions, character count conditions, prohibited expression conditions, etc.

[0062] The text generation unit 407 generates email text for prospective customers based on the appeal axis determined by the appeal axis determination unit 405. The text generation unit 407 may generate email text using a text generation model built into the information processing device 100, or it may send a text generation request to the text generation system 130 via the external cooperation unit 411 and obtain an email text in response.

[0063] The text generation unit 407 may generate email text based on the instruction information generated by the instruction information generation unit 406. For example, it may generate email text as candidate text information for sending based on instruction information that includes prospective customer segments, appeal points, recommended content, writing style conditions, etc.

[0064] The text generation unit 407 may generate different email templates for each segment according to the classification results from the segment classification unit 402. Alternatively, the text generation unit 407 may generate multiple candidate email templates for a single prospective customer.

[0065] The write-back control unit 408 reflects customer approach support information, including the email draft generated by the draft generation unit 407, appeal axis, information corresponding to missing information, lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, etc., to the external system 120. The write-back control unit 408 may identify the record corresponding to the prospective customer based on identification information that identifies the prospective customer, and reflect the information in association with that corresponding record.

[0066] The information reflected by the write-back control unit 408 may include, for example, list information, segment information, property information, candidate message information, target flag, lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, or auxiliary information corresponding to missing information or appeal axis. The write-back control unit 408 may reflect the email draft itself, or it may reflect reference information or summary information of the email draft.

[0067] The approval receiving unit 409 accepts user approval input for the email text generated by the text generation unit 407. The approval receiving unit 409 may accept approval input, modification input, return input, or send instruction input via the screen of the terminal device 110.

[0068] The approval receiving unit 409 may accept approval input for the email draft after the email draft has been reflected in the external system 120 by the write-back control unit 408. The approval receiving unit 409 may also issue a transmission execution instruction to the external system 120 in response to the approval input.

[0069] The explanatory information generation unit 410 generates explanatory information indicating missing information, appeal points, and recommended content as the basis for generating the email draft. The explanatory information may include, for example, "Since the prospective customer has not yet viewed comparative materials, comparative advantage was selected as the appeal point," or "Since this segment shows a high response to case studies, case study content was recommended."

[0070] The explanatory information generation unit 410 may output the generated explanatory information to the terminal device 110 in association with the email draft. This allows the user to approve or modify the email draft while understanding the reasons why it was generated.

[0071] The external linkage unit 411 performs linkage processing with the external system 120 or the document generation system 130. The external linkage unit 411 may send and receive information acquisition requests from the acquisition unit 401, document generation requests from the document generation unit 407, reflection requests from the write-back control unit 408, transmission execution instructions from the approval acceptance unit 409, etc., in accordance with a predetermined communication protocol and API specifications.

[0072] The storage control unit 412 stores the following in the storage unit 220: behavioral logs and customer attribute information acquired by the acquisition unit 401, classification results by the segment classification unit 402, differential feature information and lead score values ​​by the differential analysis unit 404, missing information and missing information category labels by the missing information identification unit 403, appeal axis by the appeal axis determination unit 405, email text by the text generation unit 407, recommended action information, approach priority flag, approval status by the approval acceptance unit 409, and explanatory information by the explanatory information generation unit 410, and reads them out as needed and provides them to each functional unit.

[0073] In Figure 4, for the sake of explanation, each function is shown as a separate functional block, but these functions do not need to be physically separate and may be implemented by one or more program modules. Furthermore, at least some of the functions of the information processing device 100 may be executed in cooperation with the terminal device 110, the external system 120, or the document generation system 130.

[0074] 4. Information Processing (1) Overview of the process The acquisition unit 401 acquires behavioral logs and customer attribute information about prospective customers from the external system 120. The segment classification unit 402 may classify prospective customers into segments based on the acquired behavioral logs and customer attribute information. The difference analysis unit 404 analyzes the difference between the group of customers who achieved a success event and the group of customers who did not, and may calculate a lead score value as necessary. The missing information identification unit 403 identifies missing information that indicates the information that the prospective customer lacks to reach a success event, based on the acquired behavioral logs and customer attribute information, and as necessary, segment information and difference analysis results. The appeal axis determination unit 405 determines appeal axes such as value proposition, implementation effect, comparative advantage, or implementation case studies that correspond to the identified missing information. The text generation unit 407 generates a draft email to send to prospective customers based on the instruction information including the appeal axes. Furthermore, the information processing device 100 may generate recommended action information, missing information category labels, or approach priority flags as necessary.

[0075] Specifically, the acquisition unit 401 acquires behavioral logs such as web page browsing history, email open history, click history, document download history, and event participation history for each prospective customer, as well as customer attribute information such as industry, job title, and company size. The missing information identification unit 403 identifies missing information based on the behavioral logs and customer attribute information, such as content that the prospective customer has not viewed, explanatory matters that they may not fully understand, or information for comparative judgment. The appeal axis determination unit 405 determines appeal axes, such as value propositions, implementation effects, comparative advantages, or case studies, corresponding to the identified missing information. The text generation unit 407 generates a draft email to send to the prospective customer based on the instruction information including the appeal axes.

[0076] The write-back control unit 408 associates the generated email draft, appeal axis, information corresponding to missing information, lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, etc., with identification information that identifies prospective customers and reflects it in the external system 120. This makes the customer approach support information available for use in email distribution processing, sales support processing, or marketing strategy processing in the external system 120.

[0077] Through this process, it is possible to identify appeal points that supplement the information lacking for a prospective customer, based on their behavioral logs and customer attribute information, and to generate email templates based on those appeal points. As a result, it becomes possible to automatically generate email templates with content tailored to the prospective customer's situation.

[0078] Furthermore, by reflecting the generated email draft, appeal axis, or information corresponding to missing information, as well as lead score values, segment classification results, recommended action information, missing information category labels, approach priority flags, etc., in the external system 120, the generated email draft and related customer approach support information can be easily used for email distribution processing or sales activities while coordinating with existing marketing automation systems or sales support systems.

[0079] (2) Details of the process Next, the details of the processing performed by the information processing device 100 will be described. Figure 5 is a flowchart showing an example of the customer approach support information generation, reflection, and transmission control processing in this embodiment. This processing is achieved when the control unit 210 of the information processing device 100 executes a program stored in the storage unit 220.

[0080] First, the acquisition unit 401 acquires behavioral logs and customer attribute information related to the target prospective customer from the external system 120 (step S501). Behavioral logs may include, for example, web page browsing history, email open history, link click history, document download history, form submission history, online event participation history, etc. Customer attribute information may include, for example, industry, company size, job title, department, location, past contact history, etc.

[0081] The acquisition unit 401, for example, specifies a customer ID or email address that identifies a prospective customer and calls the API of the external system 120 to acquire behavioral logs and customer attribute information associated with that prospective customer. The acquired information is stored in the storage unit 220 via the storage control unit 412.

[0082] Next, the segment classification unit 402 classifies prospective customers into one of several segments based on the acquired behavioral logs and customer attribute information (step S502). For example, prospective customers may be classified into segments such as "information gathering segment," "comparison and evaluation segment," and "implementation consideration segment" based on industry, job title, company size, type of content viewed, email response history, etc.

[0083] The segment classification process may be performed based on predefined classification rules, or it may be performed using a classification model that uses behavioral logs and customer attribute information as features. The segment classification unit 402 generates a segment identifier as a classification result and stores it in the storage unit 220 in association with the prospective customer.

[0084] Next, the difference analysis unit 404 analyzes the difference between the customer group in which an outcome event occurred and the customer group in which an outcome event did not occur (step S503). An outcome event may include, for example, email replies, appointment setting, business negotiations, document requests, applications, orders, etc.

[0085] The difference analysis unit 404, for example, refers to past customer data and calculates the frequency or average value of features derived from behavioral logs or customer attribute information for the group where the outcome event was successful and the group where it was not, and evaluates the differences between them. For example, it may extract materials with a high viewing rate in the successful group, links with a high click-through rate in the successful group, or content categories that are frequently viewed in the successful group.

[0086] The differential analysis unit 404 may calculate a lead score value for each target prospective customer in addition to the differential analysis results. For example, the differential analysis unit 404 may use the behavioral log, customer attribute information, segment information, and differential feature information to calculate a lead score value that indicates the level of interest, progress of consideration, or likelihood of a success event occurring for the prospective customer. The calculated lead score value is stored in the storage unit 220 and may be used to determine subsequent recommended action information, set approach priority flags, or reflect them in the external system 120.

[0087] Next, the missing information identification unit 403 identifies the information that the prospective customer is missing based on the behavior log, customer attribute information, segment information, and differential analysis results (step S504). Missing information refers to information that the prospective customer has not yet acquired or understood in order to reach a success event, and may include, for example, an understanding of product functions, an understanding of cost-effectiveness, an understanding of implementation cases, or comparative information with other companies.

[0088] For example, if prospective customers have not viewed the comparison materials, and the difference analysis shows that the rate of viewing the comparison materials is high among the group that achieved the outcome event, the missing information identification unit 403 may identify "lack of comparison material" as missing information.

[0089] Next, the appeal axis determination unit 405 determines an appeal axis to supplement the missing information identified by the missing information identification unit 403 (step S505). The appeal axis may be from perspectives such as the value presented to prospective customers, the effects of implementation, comparative advantages, and case studies.

[0090] For example, if the missing information is "insufficient comparative data," the appeal axis may be determined to be "appealing comparative advantages," and if the missing information is "insufficient understanding of case studies," the appeal axis may be determined to be "appealing case studies." The appeal axis determination unit 405 may also adjust the priority of the appeal axes by considering segment information or customer attribute information.

[0091] Next, the instruction information generation unit 406 generates instruction information including the determined appeal axis (step S506). In addition to the appeal axis, the instruction information may also include prospective customer attribute information, affiliated segment, recommended content, email style conditions, character count conditions, etc.

[0092] Next, the text generation unit 407 generates an email draft for prospective customers based on the instruction information (step S507). The text generation unit 407 may generate the email draft using a text generation model (for example, a generation AI model), or it may send instruction information to the text generation system 130 via the external cooperation unit 411 and receive the email draft in response.

[0093] The generated email draft may include, for example, a subject line, a greeting, the body of the email, a description of recommended content, a call to action, etc. The draft generation unit 407 may generate a single draft or may generate multiple candidate drafts.

[0094] As an example of the difference analysis processing performed by the difference analysis unit 404, the difference analysis unit 404 may calculate the difference features by following the procedure below.

[0095] First, the differential analysis unit 404 obtains label information indicating whether or not a success event occurred for past prospective customer data, and based on this label information, divides the prospective customer group into two groups: a group where a success event occurred and a group where a success event did not occur. Success events may include, for example, email replies, appointment setting, business negotiations, requests for materials, trial applications, requests for quotations, or orders.

[0096] Next, the difference analysis unit 404 generates multiple features for each prospective customer based on the behavioral log and customer attribute information. These features may include, for example, the following values: (a) Number of web page views within a specified period (b) Number of views of specific category pages (case studies, comparison materials, pricing information, etc.) (c) Number of emails opened or open rate (d) Number of link clicks or click-through rate (e) Number of document downloads (f) Number of form submissions (g) Number of online event participations (h) Frequency of appearance of browsing content categories (i) Attribute features such as company size code, industry code, and job title code

[0097] The difference analysis unit 404 calculates statistical values ​​for each feature for both the group where the outcome event occurred and the group where the outcome event did not occur. Examples of statistical values ​​that may be calculated include the mean, median, frequency of occurrence, probability of occurrence, proportion, or distribution value.

[0098] Next, the difference analysis unit 404 calculates a difference index between the group where the outcome event occurred and the group where the outcome event did not occur. For example, one or more of the following can be used as the difference index. (a) Average difference (b) Ratio difference (c) Odds ratio (d) Correlation coefficient (e) Information gain (f) Statistical test value (e.g., t-test value or chi-squared value)

[0099] The difference analysis unit 404 calculates a difference score for each feature based on the calculated difference index. For example, if the probability of occurrence in the set group is P1 and the probability of occurrence in the set group is P0, the difference score S is S = |P1 - P0| It is acceptable to calculate it as follows.

[0100] Furthermore, the difference analysis unit 404 may apply a predetermined thresholding process or ranking process to the difference score. For example, it can extract features whose difference score is equal to or greater than a predetermined threshold, or select the top N features with the highest difference scores as difference features.

[0101] Furthermore, the difference analysis unit 404 may refer to the classification results by the segment classification unit 402 and perform difference analysis processing for each segment. In this case, the difference analysis unit 404 generates groups of successful and unsuccessful outcome events targeting only prospective customers belonging to each segment, and calculates difference features for each segment.

[0102] The difference analysis unit 404 generates difference feature information associated with the difference score as a result of the difference analysis, and stores the difference feature information in the storage unit 220. The difference feature information may include, for example, a feature identifier, a difference score, statistics for the group that is successful, statistics for the group that is not successful, and related content identification information.

[0103] The differential analysis unit 404 may calculate a lead score value for each prospective customer based on the behavior log, customer attribute information, differential feature information, and segment information. The lead score value may be calculated using, for example, the number of times a web page is viewed, the number of times a specific category page is viewed, the email open rate, the link click rate, the number of times a document is downloaded, the number of times a form is submitted, the number of times an online event is attended, the differential score, and the customer attribute fit.

[0104] For example, the difference analysis unit 404 may normalize each feature to a predetermined range and then calculate the read score value L by weighted sum. L = a1 × View Score + a2 × Open Score + a3 × Click Score + a4 × Download Score + a5 × Difference Fit Score + a6 × Attribute Fit Score The calculation may be performed as follows: Here, a1 to a6 are weight coefficients. The difference analysis unit 404 may store the calculated read score value in the storage unit 220 and use it for reflection to the external system 120 by the write-back control unit 408.

[0105] The missing information identification unit 403 can refer to the differential feature information and identify content categories or information categories corresponding to features with high differential scores as information that is missing for prospective customers.

[0106] As an example of the missing information identification process by the missing information identification unit 403, the missing information identification unit 403 may identify the information missing for a prospective customer by following the procedure below.

[0107] First, the missing information identification unit 403 reads out the behavioral logs and customer attribute information acquired by the acquisition unit 401, the segment identifier assigned by the segment classification unit 402, and the differential feature information generated by the differential analysis unit 404 for the target prospective customer.

[0108] Next, the missing information identification unit 403 may generate a content contact status table to identify information that a prospective customer has already contacted and information that they have not yet contacted. The content contact status table may be, for example, a table that associates content identifier, content category, contact status, number of contacts, last contact date and time, contact method, and response status. Here, the contact method may include viewing, opening, clicking, downloading, watching, or form submission.

[0109] Next, the missing information identification unit 403 extracts content categories that prospective customers have not yet interacted with, or content categories that have been interacted with but whose response is below a predetermined standard, based on the content contact status table. For example, if the contact status for a comparison material category is "none," or if the number of interactions is 1 and the click-through rate or download rate is below a predetermined threshold, that category may be extracted as a candidate missing information category.

[0110] Furthermore, the missing information identification unit 403 refers to the difference feature information generated by the difference analysis unit 404 and extracts content categories or information categories with high difference scores in the group of successful outcome events. For example, it may extract comparison material categories, case study categories, pricing information categories, or function description categories that are frequently viewed in the successful outcome group.

[0111] The missing information identification unit 403 may compare candidate missing categories with high-difference categories based on differential feature information, and determine categories that match or have a predetermined degree of relevance as information categories missing for prospective customers. In other words, categories that prospective customers have not contacted or have shown little response to, and that are of high importance in the group where an outcome event has occurred, can be preferentially identified as missing information.

[0112] Furthermore, the missing information identification unit 403 may adjust the priority of missing information according to customer attribute information or segment information. For example, for prospective customers belonging to management, the priority of the cost-effectiveness category or the implementation effectiveness category may be increased, while for prospective customers belonging to field personnel, the priority of the function description category or the ease of operation category may be increased.

[0113] The information deficiency identification unit 403 may calculate a deficiency score for each candidate deficiency category. The deficiency score may be calculated, for example, as a weighted sum of (a) non-contact score, (b) difference score, (c) attribute fit score, and (d) segment fit score. For example, the deficiency score U may be calculated as U = α × Uncontact score + β × Difference score + γ × Attribute fit + δ × Segment fit It can be calculated as follows. Here, α, β, γ, and δ are weighting coefficients.

[0114] The information deficiency identification unit 403 may identify the category with the highest deficiency score as the information deficiency, or it may identify multiple top categories as a group of information deficiencies. The information deficiency identification unit 403 may also generate information deficiency data for the identified information deficiency, associating it with information deficiency identifiers, categories, scores, and justification information, and store it in the storage unit 220.

[0115] The missing information identification unit 403 may, if necessary, generate a missing information category label for the identified missing information. The missing information category label may be used as part of the customer approach support information written back to the external system 120.

[0116] The supporting information may include, for example, content identifiers that have not been accessed, behavioral logs where the response is below a predetermined standard, referenced differential features, and customer attribute items used to calculate attribute fit. This makes it possible to track how the missing information was identified based on the information processing.

[0117] Next, as an example of the appeal axis determination process by the appeal axis determination unit 405, the appeal axis determination unit 405 may determine the appeal axis corresponding to the missing information by following the procedure below.

[0118] First, the appeal axis determination unit 405 reads the missing information data generated by the missing information identification unit 403 and refers to the appeal axis candidate information associated with each missing information category. The appeal axis candidate information may be configured, for example, as a table that defines the correspondence between missing information categories and appeal axis candidates that are effective in supplementing those categories.

[0119] For example, for the category of missing information, "lack of comparative data," "appealing to comparative advantages" and "appealing to competitive differences" can be used as potential appeal axes. For the category of missing information, "lack of understanding of implementation cases," "appealing to implementation cases" and "appealing to the success of similar companies" can be used as potential appeal axes. Furthermore, for the category of missing information, "lack of understanding of cost-effectiveness," "appealing to cost-effectiveness" or "appealing to return on investment" can be used.

[0120] Next, the appeal axis determination unit 405 may calculate an appeal suitability score for each appeal axis candidate. The appeal suitability score may be calculated, for example, as a weighted sum of (a) deficiency score, (b) difference score, (c) customer attribute suitability, (d) segment suitability, and (e) recommended content presence.

[0121] For example, if the appeal relevance score is A, A = λ × deficiency score + μ × difference score + ν × customer attribute suitability + ξ × segment suitability + ρ × recommended content presence It may be calculated as follows: Here, λ, μ, ν, ξ, and ρ are weighting coefficients. The recommended content availability may be a value indicating the degree to which materials, case studies, linked content, etc. that can be associated with the appeal axis are available.

[0122] In terms of customer attribute suitability, for example, if the prospective customer is in management, a high value may be assigned to the cost-effectiveness appeal, and if the prospective customer is a field worker, a high value may be assigned to the functional explanation appeal or the ease of operation appeal. In terms of segment suitability, a high value may be assigned to the comparative advantage appeal in the comparison segment, and a high value may be assigned to the implementation consideration segment to the case study appeal or the short-term implementation appeal.

[0123] The appeal axis determination unit 405 may rank each appeal axis candidate based on the calculated appeal suitability score and determine the appeal axis candidate with the highest score as the appeal axis for that prospective customer. Alternatively, it may combine multiple appeal axis candidates having scores above a predetermined threshold to determine a composite appeal axis.

[0124] For example, if a prospective customer has not yet viewed comparative materials, belongs to management, and has a high rate of viewing cost-effectiveness and comparative materials within the established group of the same segment, the appeal axis determination unit 405 may determine a composite appeal axis that combines "comparative advantage appeal" and "cost-effectiveness appeal."

[0125] The appeal axis determination unit 405 may generate appeal axis data that associates the determined appeal axis with an appeal axis identifier, appeal axis category, appeal suitability score, and decision basis information, and store it in the storage unit 220. The decision basis information may include, for example, the referenced missing information category, differential feature quantity, attribute suitability, segment suitability, and recommended content identifier.

[0126] The appeal axis determination unit 405 or the write-back control unit 408 may determine recommended action information for prospective customers based on the missing information category, appeal axis, lead score value, segment classification result, customer attribute information, and past response history. Recommended action information may include, for example, types such as sending an email, making a phone call, sending materials, presenting comparative materials, presenting case studies, proposing an online business meeting, or re-contacting the customer after a certain period of time.

[0127] For example, the appeal axis determination unit 405 or the write-back control unit 408 may decide to recommend presenting comparative materials or sending an email appealing for comparative advantage as recommended action information if the missing information category is insufficient comparative judgment material and the lead score value is above a predetermined threshold. In addition, if the missing information category is insufficient understanding of implementation cases, the unit may decide to recommend presenting implementation cases or sending similar company case studies as recommended action information. Furthermore, the priority and timing of the recommended action information may be determined based on the lead score value, past response history, segment classification results, or the likelihood of a success event occurring.

[0128] Furthermore, the write-back control unit 408 may set an approach priority flag for each prospective customer based on the lead score value, recommended action information, priority, or recommended timing. For example, a high priority flag may be set if the lead score value is above the first threshold and the recommended timing is immediate; a medium priority flag may be set if the lead score value is above the second threshold but below the first threshold; and a low priority flag may be set if it is below the second threshold. The approach priority flag may be used in the external system 120 for prospective customer extraction, distribution target selection, or assignment of personnel.

[0129] The instruction information generation unit 406 may refer to the appeal axis data and generate instruction information to be used for generating email drafts according to the determined appeal axis or composite appeal axis. This allows the draft generation unit 407 to generate email drafts that reflect the perspective of supplementing the information lacking for prospective customers.

[0130] The calculation of the lead score value by the difference analysis unit 404, the generation of missing information category labels by the missing information identification unit 403, the determination of recommended action information by the appeal axis determination unit 405 or the write-back control unit 408, and the setting of the approach priority flag by the write-back control unit 408 may be performed between steps S503 and S508.

[0131] Next, the write-back control unit 408 reflects customer approach support information, including the generated email text, appeal axis, information corresponding to missing information, lead score value, segment classification result, recommended action information, missing information category label, and approach priority flag, to the external system 120 (step S508). Based on the identification information that identifies the prospective customer, the write-back control unit 408 identifies the corresponding record on the external system 120.

[0132] The write-back control unit 408 may register, for example, segment information, missing information, appeal axis, candidate message information, target flag, lead score value, segment classification result, recommended action information, missing information category label, or approach priority flag in association with the corresponding record. This allows the external system 120 to use the email message and related customer approach support information for email distribution processing or sales support processing.

[0133] Next, the approval reception unit 409 receives approval input for the email draft from the user via the terminal device 110 (step S509). The user can review the generated email draft and perform operations such as approval, modification, or return.

[0134] When user approval input is received, the external linkage unit 411 sends an email sending command to the external system 120 (step S510). This allows the external system 120 to execute the email sending process using the email text.

[0135] Through the above processing, missing information can be identified based on prospective customer behavior logs and customer attribute information, email drafts based on appeals that address that missing information can be generated, and these email drafts or related information can be reflected and used in external systems. In addition to email drafts, customer approach support information including lead score values, segment classification results, recommended action information, missing information category labels, and approach priority flags can also be reflected and used in external systems.

[0136] The information processing device 100 can acquire behavioral logs and customer attribute information about prospective customers from the external system 120, identify missing information indicating that the prospective customer lacks information based on the behavioral logs and customer attribute information, determine appeal axes to supplement the missing information, generate email drafts for prospective customers based on the appeal axes, and reflect customer approach support information including the email drafts, appeal axes, or information corresponding to the missing information back into the external system 120. This makes it possible to generate email drafts tailored to the prospective customer's situation and to easily utilize the generation results and related information for subsequent sales or marketing activities.

[0137] The information processing device 100 can utilize behavioral logs that include at least one of the following: web page browsing history, email delivery history, email open history, link click history, document download history, form submission history, and online event participation history. This makes it easier to comprehensively understand the information contact status or interest level of prospective customers, and to identify missing information and improve the suitability of email drafts.

[0138] The information processing device 100 can determine missing information or appeal axes based on the difference between the customer group where the outcome event occurred and the customer group where the outcome event did not occur. This makes it easier to set appeal content that reflects characteristics or information elements that are likely to lead to results, and improves the appropriateness of the approach to prospective customers.

[0139] The information processing device 100 can classify prospective customers into multiple segments and perform the determination of appeal axes or the generation of email templates for each segment. This makes it easier to set appeal content or wording according to the attributes or behavioral tendencies of prospective customers, and to take an approach that is tailored to the tendencies of each prospective customer.

[0140] The information processing device 100 can generate different appeals or email templates for each segment and reflect them in the external system 120 in association with that segment. This makes it easier to manage different measures on a segment-by-segment basis in the external system 120, and improves the operational efficiency of marketing or sales measures.

[0141] The information processing device 100 can generate email templates based on the appeal axis using a template generation model. This makes it easier to efficiently create templates that reflect the appeal perspective and streamlines the process of generating email templates tailored to each prospective customer.

[0142] The information processing device 100 can generate instruction information including the appeal axis and generate an email draft based on said instruction information. This makes it easier to reflect prospective customer attributes, segments, recommended content, and other conditions in addition to the appeal axis when generating the draft, thereby improving the consistency and ease of adjustment of the email draft content.

[0143] The information processing device 100 can reflect the information in the external system 120 in a manner that updates at least one of the following: list information, segment information, property information, candidate message information for transmission, transmission target flag, lead score value, segment classification result, recommended action information, missing information category label, or approach priority flag associated with prospective customers. This makes it easier to use the generated results according to the management items on the external system 120, and facilitates smooth coordination with subsequent distribution processing or sales support processing.

[0144] The information processing device 100 can, after reflecting the email draft in the external system 120, accept user approval input for the email draft and issue a transmission command to the external system 120 in response to the approval input. This makes it easier to proceed to transmission after human review while the generated email draft is retained in the external system 120, thus making it easier to balance operational efficiency with the appropriateness of the transmitted content.

[0145] The information processing device 100 can generate explanatory information indicating missing information, key selling points, and recommended content as the basis for generating the email draft, and output it in association with the email draft. This makes it easier for users to understand the reasons for generating the email draft, and to review, approve, or revise it, thereby improving their satisfaction with the generated result.

[0146] The information processing device 100 can associate customer approach support information with corresponding records in an external database, based on identification information that identifies prospective customers. This makes it easier to appropriately manage the generated results for each prospective customer and to use them in subsequent processing without misidentifying the target.

[0147] (Variation 1) In this embodiment, an example of generating an entire email draft has been described, but the objects to be generated are not limited to this. The draft generation unit 407 may generate multiple elements that constitute the email draft individually. For example, the draft generation unit 407 may individually generate at least one of the following: subject, greeting, body, recommended content introduction, call to action, and signature. Furthermore, the draft generation unit 407 may generate the subject and then the body, or it may generate only the body and select the subject from a template.

[0148] This modified version allows for flexible changes to the generation method for each component of the email draft, thereby increasing the flexibility of the email creation process. Furthermore, because the subject line generation process and the body generation process can be executed independently, it is possible to improve email open rates or increase the efficiency of the email draft generation process.

[0149] (Modification 2) In this embodiment, a lack of understanding regarding comparative decision materials or implementation examples is given as an example of missing information, but it is not limited to this. The missing information identification unit 403 may identify at least one of the following as missing information: a lack of understanding regarding product functions, a lack of understanding regarding cost-effectiveness, a lack of understanding regarding implementation procedures, a lack of understanding regarding security measures, a lack of understanding regarding legal compliance, a lack of understanding regarding operational burden, a lack of understanding regarding support systems, a lack of information regarding internal approval documents, or a lack of understanding regarding contract terms or pricing structures.

[0150] This modified approach allows for addressing the diverse information gaps faced by potential customers, enabling flexible decision-making regarding messaging tailored to each customer's situation. As a result, email content becomes more easily aligned with the potential customer's interests or challenges, leading to improved email response rates or conversion rates.

[0151] (Variation 3) In this embodiment, comparative advantage appeals or case study appeals are given as examples of appeal axes, but the invention is not limited to these. The appeal axis determination unit 405 may determine at least one of the following as an appeal axis: cost-effectiveness appeal, short-term implementation appeal, peace of mind appeal, support system appeal, ease of operation appeal, security appeal, legal compliance appeal, or approval support appeal. Alternatively, it may determine a composite appeal axis that combines multiple appeal axes.

[0152] This modified version allows for the selection of diverse appeal points depending on the attributes or stage of consideration of the prospective customer, thereby increasing the suitability of the appeal content included in the email draft.

[0153] (Modification 4) In this embodiment, an example of reflecting information corresponding to the email draft, appeal axis, or missing information to the external system 120 has been described, but the items to be reflected are not limited to this. The write-back control unit 408 may also reflect lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, segment information, recommended content identification information, approval status information, generation date and time, draft version information, or regeneration history information in association with the corresponding record.

[0154] According to this modification, in addition to historical information related to the email draft generation process, various types of information used for approaching potential customers can be stored in an external system, making it easier to analyze and improve marketing strategies or sales activities.

[0155] (Variation 5) In this embodiment, an example has been described in which a transmission execution instruction is given after receiving approval input from the user, but the embodiment is not limited to this. The approval reception unit 409 may be configured to automatically execute transmission for prospective customers who meet predetermined conditions, or to require user approval for prospective customers who do not meet the predetermined conditions.

[0156] This modified version allows for a flexible balance between automated email sending and human review, thus enabling a combination of operational efficiency and the quality of the sent content.

[0157] (Experimental variation 6) In this embodiment, an example of generating email text based on a sales pitch has been described, but in addition, the sales pitch determination unit 405 may select recommended content corresponding to the sales pitch. The text generation unit 407 may include links or reference information to the recommended content in the email text.

[0158] This modified version allows for the presentation of materials or content that supplements the information that potential customers lack, thereby promoting their understanding.

[0159] (Example 7) In this embodiment, an example of generating a single email draft has been described, but the draft generation unit 407 may generate multiple candidate drafts. The approval reception unit 409 may reflect the candidate draft selected by the user to the external system 120.

[0160] This modified version allows for the optimization of email marketing strategies by enabling the selection of the final message by comparing multiple drafts.

[0161] (Variation 8) In this embodiment, an example using a generation AI model has been described, but it is not limited to this. The text generation unit 407 may generate email text using a template method, a rule-based method, a statistical language model, or the like.

[0162] This modified version allows for the selection of an appropriate text generation method depending on the system environment, thereby improving processing stability.

[0163] (Extreme variation 9) In this embodiment, the post-email sending process is not particularly limited, but the open history, click history, reply history, or whether a success event occurred after sending the email may be reacquired and reflected in the next differential analysis process, missing information identification process, or appeal axis determination process.

[0164] This modified version allows for feedback-based marketing processing that reflects past sending results, thus enabling continuous improvement of email marketing strategies.

[0165] (Variation 10) In this embodiment, an example has been described in which the difference analysis unit 404 analyzes the difference between the successful group and the unsuccessful group, but it is not limited to this. The difference analysis unit 404 may also analyze the difference between the successful group and the unsuccessful group by industry, job title, company size, or segment.

[0166] This modified version allows for differential analysis based on customer attributes, enabling more accurate identification of missing information and determination of key selling points.

[0167] (Variation 11) In this embodiment, an example of sending a message via email has been described, but the sending medium is not limited to this. For example, a message may be sent using communication methods such as SMS, chat messages, messaging apps, or SNS direct messages.

[0168] This modified version allows for customer contact strategies that support multiple communication channels, thereby expanding touchpoints with potential customers.

[0169] Although embodiments have been described above, these are presented as examples and are not intended to limit the scope of the invention. Novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of symbols]

[0170] 100: Information Processing Device 110: Terminal device 120: External Systems 130: Text generation system 150: Network 210: Control Unit 220: Storage section 230: Communications Department 1000: Information Processing System

Claims

1. An information processing system, Having at least one control unit, The control unit, We obtain behavioral logs and customer attribute information about prospective customers from an external system. Based on the way the prospective customer interacted with the content included in the behavior log, a content contact status table is generated that associates contact status or response status for each content category. From the aforementioned content contact status table, content categories that the prospective customer has not yet contacted or content categories whose response is below a predetermined standard are extracted as missing candidate categories. The priority of the candidate categories of missing information is adjusted according to the customer attribute information, and the information corresponding to the candidate categories of missing information is identified as missing information indicating that the prospective customer is lacking. Referencing candidate appeal axis information associated with each category of missing information, calculate the appeal suitability score for each candidate appeal axis using the missing information deficiency score and the customer attribute suitability based on the customer attribute information, and determine the appeal axis to supplement the missing information based on the appeal suitability score. Select recommended content corresponding to the aforementioned appeal axis, The system generates instruction information including the missing information, the appeal axis, and the recommended content, and uses the instruction information as input to the text generation model to generate a draft email for the prospective customer. The system generates customer approach support information including the aforementioned email draft, the appeal axis, information corresponding to the missing information, and identification information for the recommended content. The customer approach support information is reflected in the external system. Information processing system.

2. In the information processing system described in claim 1, The aforementioned activity log includes at least one of the following: web page browsing history, email delivery history, email open history, link click history, document download history, form submission history, and online event participation history. Information processing system.

3. In the information processing system described in claim 1, The control unit calculates statistical values ​​of feature quantities derived from the behavioral logs or customer attribute information for each of the customer groups in which the outcome event was achieved and the customer group in which the outcome event was not achieved, calculates a difference index between the statistical values ​​of the customer group in which the outcome event was achieved and the statistical values ​​of the customer group in which the outcome event was not achieved, generates difference feature information based on the difference index, and determines the missing information or the appeal axis based on the difference feature information. Information processing system.

4. In the information processing system described in claim 1, The control unit classifies the prospective customer into a plurality of segments using at least one of the behavior log and the customer attribute information as features. The determination of the appeal axis or the generation of the email text is performed using appeal axis candidate information or instruction information corresponding to the segment to which the prospective customer belongs. Information processing system.

5. In the information processing system described in claim 4, The control unit generates different appeal axes or email templates for each segment. The segment identifier representing the aforementioned segment is associated with the external system and reflected in the external system. Information processing system.

6. In the information processing system described in claim 1, The text generation model generates the email text, which includes at least one of the following: a subject line, body text, a description of the recommended content, and a call to action, using the missing information, appeal axis, and recommended content included in the instruction information. Information processing system.

7. In the information processing system described in claim 6, The control unit, As the instruction information, in addition to the missing information, the appeal axis, and the recommended content, information is generated that includes at least one of the prospective customer's attributes, segment, writing style conditions, character count conditions, and prohibited expression conditions. By inputting the aforementioned instruction information into the text generation model, the email text is generated. Information processing system.

8. In the information processing system described in claim 1, The customer approach support information further includes at least one of the following: lead score value, segment classification result, recommended action information, missing information category label, approach priority flag, and recommended content identification information. The aforementioned recommended action information includes at least one of the type, priority, and recommended timing. Information processing system.

9. In the information processing system described in claim 1, The control unit, after reflecting the email draft in the external system, accepts user approval input for the email draft. In response to the aforementioned approval input, the system is instructed to execute a send command to perform the process of sending an email to the prospective customer using the email template. Information processing system.

10. In the information processing system described in claim 1, The control unit generates explanatory information indicating the missing information, the appeal axis, and the recommended content used in generating the email draft, The explanatory information is output in correspondence with the email text. Information processing system.

11. In the information processing system described in claim 1, The aforementioned external system has an external database that manages data for each prospective customer, The control unit searches for or specifies a corresponding record from the external database using identification information including a customer ID or email address that identifies the prospective customer, and registers or updates the customer approach support information associated with the corresponding record. Information processing system.

12. An information processing method performed by an information processing system, The process involves obtaining behavioral logs and customer attribute information about prospective customers from an external system. A step of generating a content contact status table that associates contact status or response status for each content category based on the way the prospective customer interacted with content included in the behavior log, The process of extracting content categories that the prospective customer has not yet interacted with or content categories whose response is below a predetermined standard from the content contact status table as missing candidate categories, A step of adjusting the priority of the candidate categories of deficiencies according to the customer attribute information, and identifying the information corresponding to the candidate categories of deficiencies as deficiency information indicating that the prospective customer is lacking information, The process involves referring to candidate appeal axis information associated with each category of missing information, calculating an appeal suitability score for each candidate appeal axis using the missing information deficiency score and the customer attribute suitability based on the customer attribute information, and determining an appeal axis to supplement the missing information based on the appeal suitability score. The process of selecting recommended content corresponding to the aforementioned appeal axis, The process includes generating instruction information including the missing information, the appeal axis, and the recommended content, and using the instruction information as input to a text generation model to generate a draft email text for the prospective customer, A process for generating customer approach support information including the aforementioned email draft, the appeal axis, information corresponding to the missing information, and identification information for the recommended content, A step of reflecting the customer approach support information in the external system, Information processing methods including

13. It is a program, A program for causing a computer to function as an information processing system according to any one of claims 1 to 11.

Images