Support system, support method, and program

Abstract

To provide a support system and the like capable of providing better product plan suggestions.SOLUTION: A support system 100 is a support system for supporting product sales. The support system include: a conversion unit (part of information processing server 40) that acquires conversation voices between a customer and a salesperson and converts the acquired conversation voices between the customer and the salesperson into a piece of text information; an analysis unit (part of information processing server 40) that analyzes the converted text information to generate a piece of preference information of the customer for the product; and an output unit (analysis result output unit 23 and plan output unit 25) that outputs a plan for the product in accordance with the preference information based on the preference information, and displays the same on an information terminal 10.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a support system, a support method, and a program for supporting the sale of products. [Background technology]

[0002] Various technologies relating to the design of buildings have been proposed in the past. Patent Document 1 discloses a method for modifying a dwelling plan that allows for easy and quick calculation of costs associated with modifying a dwelling plan. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-199594 Summary of the Invention [Problem to be solved by the invention]

[0004] Generally, in the design of a building, the selection of equipment (i.e., products) to be installed in the building requires a conversation between the customer and the salesperson to search for a product plan that meets the customer's needs from among available products. In such cases, depending on the conversation skills of at least one of the customer and the salesperson, it may not be possible to propose an appropriate product plan. Therefore, the present disclosure provides a support system or the like for more appropriately proposing product plans. [Means for solving the problem]

[0005] An assistance system according to one aspect of the present disclosure is an assistance system for assisting in the sale of a product, and includes a conversion unit that acquires audio of a conversation between a customer and a salesperson and converts the acquired audio of the conversation between the customer and the salesperson into text information, an analysis unit that analyzes the converted text information and generates preference information of the customer for the product, and an output unit that outputs a plan for the product that is in line with the generated preference information based on the preference information and displays it on an information terminal.

[0006] Furthermore, a support method according to one aspect of the present disclosure is a support method executed by a computer to support the sale of a product, and includes the steps of acquiring audio of a conversation between a customer and a salesperson and converting the acquired audio of the conversation between the customer and the salesperson into text information, analyzing the converted text information to generate preference information of the customer regarding the product, and outputting a plan for the product that is in line with the preference information based on the generated preference information and presenting the plan on an information terminal.

[0007] Furthermore, one aspect of the present disclosure can also be realized as a program for causing a computer to execute the above-described assistance method.

[0008] These comprehensive or specific aspects may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to more appropriately propose product plans. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing a functional configuration of a support system according to an embodiment. [Figure 2] FIG. 2 is a flowchart showing an example of the operation of the support system according to the embodiment. [Figure 3] FIG. 3 is a diagram showing an example of a screen display according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of a screen display according to the embodiment. [Figure 5] FIG. 5 is a diagram showing an example of a screen display according to the embodiment. [Figure 6]FIG. 6 is a diagram showing an example of a screen display according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments will be described in detail with reference to the drawings. Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection configurations, steps, and step order shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not recited in independent claims will be described as optional components. Note that each figure is a schematic diagram and is not necessarily an exact illustration. Furthermore, in each figure, substantially identical components are assigned the same reference numerals, and duplicated descriptions may be omitted or simplified.

[0012] (Embodiment) [composition] First, the configuration of the support system according to the embodiment will be described. Fig. 1 is a block diagram showing the functional configuration of the support system according to the embodiment.

[0013] As shown in FIG. 1 , the support system 100 according to the present embodiment includes an information terminal 10, a UI server 20, an information storage server 30, an information processing server 40, and a recommended plan server 50. The support system 100 is used by a salesperson and is a system for inputting and outputting information to support the salesperson in selling products to customers. More specifically, the support system 100 receives audio of a conversation between a customer and a salesperson and analyzes the audio to output a recommended product plan. As described above, when selling building equipment such as flooring, baseboards, trim, kitchens, sinks, fixtures, wall materials, stairs, storage, stools, toilets, bathroom fixtures, and elevators, the salesperson must select an appropriate product from several options for each product based on the customer's needs. To hear such needs, a conversation takes place between the customer and the salesperson.

[0014] If a salesperson lacks the conversational skills to listen, they may not be able to properly hear the customer's requests and may not be able to propose an appropriate product plan. Alternatively, if there are multiple salespersons and a salesperson is replaced during a conversation, the necessary handover may not be possible, and an appropriate product plan may not be proposed. The support system 100 of this embodiment acquires and analyzes the audio of the conversation between the customer and the salesperson, making it possible to analyze the customer's requests from the audio and use it to propose an appropriate product plan. In particular, by performing the above analysis using large-scale language models, a technology that has been rapidly advancing in recent years, it is possible to make it less likely that implicit requests contained in the customer's casual utterances will be overlooked, potentially enabling more appropriate product plans to be proposed.

[0015] In addition to the above-mentioned equipment, this embodiment can be applied to any type of product that requires a conversation between the customer and the salesperson to select an appropriate product based on the customer's needs. Examples of such products include custom-made products and products with several options for equipment, such as clothing and vehicles.

[0016] The information terminal 10 is a terminal device used by a salesperson, and may be realized as a smartphone, tablet terminal, PC, or the like. The information terminal 10 is used by the salesperson to access the UI server 20. In addition, the information terminal 10 is often equipped with a sound pickup device, which can be used to capture audio of a conversation between a customer and the salesperson. If an information terminal 10 without a sound pickup device is used, a sound pickup device capable of outputting picked-up audio to the information terminal 10 may be used. One sound pickup device is shared between the customer and the salesperson, but a sound pickup device may also be provided for each customer and salesperson. The information terminal 10 is preferably a portable terminal device so that the salesperson can use it when visiting a customer. In this case, it is preferable that communication between the information terminal 10 and the UI server 20 be performed via mobile communication or wireless communication such as wireless LAN.

[0017] The UI server 20 relays information between the information terminal 10, the information storage server 30, the information processing server 40, and the recommended plan server 50, and has a function of generating presentation information for proposing product plans. The UI server 20 is, for example, an edge server installed in a store where a salesperson works. The UI server 20 includes an input receiving unit 21, a voice acquiring unit 22, an analysis result output unit 23, a plan search unit 24, and a plan output unit 25.

[0018] The input receiving unit 21 is a processing unit that receives input from a customer from the information terminal 10 or a customer's terminal device (not shown) via a network such as the Internet. Customer input from the customer's terminal device (not shown) includes, for example, information entered into a reservation form when the customer visits a store. Such input includes customer information related to the customer's attributes. The customer information includes personal information about the customer that may be related to the product. For example, if the product is equipment, the customer information includes the family structure of the customer who may use the equipment and the age of the building in which the equipment will be installed. Furthermore, for example, the customer information includes the customer's age group for estimating the customer's budget for the product. In other words, customer attributes are a concept that includes the customer and people, things, and events related to the customer, such as the customer's family structure, the age of the building owned by the customer, and the customer's age group.

[0019] The voice acquisition unit 22 is a processing unit that acquires the voice of conversation from a sound pickup device. The voice acquisition unit 22 is also a processing unit that transmits the acquired voice to the information processing server 40. The voice acquisition unit 22 acquires voice continuously in the time domain (in other words, at multiple consecutive points in time) and sequentially transmits the acquired voice to the information processing server 40. Therefore, the information processing server 40 sequentially processes the transmitted voice and sequentially outputs the corresponding processing results.

[0020] The information processing server 40 is a server device for executing a process of analyzing voice and generating an analysis result. The information processing server 40 has a so-called speech-to-text conversion function for converting voice into text information. In other words, the information processing server 40 is an example of a conversion unit. When converting voice into text information, the information processing server 40 distinguishes between the customer's speech and the salesperson's speech from a single voice picked up and acquired by a single sound pickup device, and converts each of the spoken voices into text information for use.

[0021] The information processing server 40 also has a function of so-called generation AI, which generates an output corresponding to a pre-given prompt as an analysis result for text information. That is, the information processing server 40 is equipped with a large-scale language model, and can analyze text information using the large-scale language model in accordance with an instruction given as a prompt and generate a result. In this embodiment, the prompt is an instruction to generate customer preference information from text information, and a salesperson or a system is configured to automatically search for a product plan corresponding to the preference information. The customer information is subjected to processing by the generation AI in the information processing server 40. That is, a prompt is designed for the information processing server 40 to analyze text information taking into account the customer information.

[0022] The preference information generated in the information processing server 40 is output to the information terminal 10 by the analysis result output unit 23. The output preference information is presented to the salesperson so that the salesperson can confirm it. In this way, the analysis result output unit 23 is part of the function of the output unit.

[0023] The preference information is calculated, for example, as a score indicating the degree of customer preference for each of the preset evaluation items, i.e., the degree of agreement with the customer's preference. Each evaluation item is set in advance to correspond to a product attribute, and the higher the score, the higher the evaluation score (the more evaluation points are assigned) for the product attribute corresponding to that evaluation item. The higher the evaluation points assigned for each product attribute, the more likely the product is to be recommended. Therefore, the prompts provided to the information processing server 40 are designed to be able to calculate such scores for each evaluation item.

[0024] Some products have multiple attributes, and in such cases, the sum of the evaluation points for each attribute becomes the evaluation point for that product. Note that with this setting, the more attributes a product has, the more easily it is recommended, so in order to adjust the sum of evaluation points for products with many attributes and those without, a correlation coefficient is set for each product between each attribute and the corresponding evaluation item. Therefore, the evaluation point for one attribute of a certain product is the score obtained by multiplying the score of the evaluation item by the correlation coefficient, and the sum of the evaluation points after multiplying by this correlation coefficient corresponds to the degree to which the product is recommended.

[0025] Here, the conversation may be insufficient to calculate the score for each evaluation item. In other words, the conversation required to calculate the evaluation points may not be obtained. Therefore, the analysis result output unit 23 may also generate supplemental information to guide the conversation between the customer and the salesperson so that the necessary audio can be obtained to supplement the text information required to calculate the score (in other words, the text information insufficient to calculate the score). For example, the information processing server 40 may design a prompt to flag evaluation items for which a score cannot be calculated as being unrated (for example, by assigning a score of "-" in the example described below). The analysis result output unit 23 may then infer an appropriate topic and output it as supplemental information so that the conversation can be switched to one that is easy to understand for the evaluation items with such a flag.

[0026] The plan search unit 24 is a processing unit for making an inquiry to the recommended plan server 50 based on the sum of the evaluation points as described above. The plan search unit 24 is configured to make an inquiry to the recommended plan server 50 based on the operation of a salesperson or automatically by the system. The recommended plan server 50 has a recommended plan DB 51, in which a plurality of recommended plans are stored. The recommended plan server 50 replies with a recommended plan, i.e., a product plan, that corresponds to the inquired conditions. Note that customer information is also provided in inquiries to the recommended plan server 50. For example, the plan search unit 24 operates so that constraints based on the customer information are included in the inquiry.

[0027] Then, the plan output unit 25 outputs the product plan returned from the recommended plan server 50 to the information terminal 10. At this time, a product form can be output as the product plan. For example, if the recommended plan server 50 returns multiple plans as plans for a product that meets the conditions, a list of the returned plans is displayed, and when the salesperson selects one of them, a product form for the selected plan is output as the product plan.

[0028] The salesperson can then input into the output form whether or not the customer made a purchase. The input information about the purchase is stored in the information storage server 30, linked to, for example, text information, preference information from the analysis results, and a list of plans that can be answered in response to inquiries based on the preference information. Such information stored in the information storage server 30 may be used, for example, to improve the prompts used in the information processing server 40, to adjust the theoretical formula for responses in the recommended plan server 50, or as other reference information outside the system.

[0029] [Operation] Next, a description will be given of the operation of the support system 100. Fig. 2 is a flowchart showing an example of the operation of the support system according to the embodiment. Figs. 3 to 6 are diagrams showing examples of screen displays according to the embodiment.

[0030] 2, first, the voice acquisition unit 22 acquires the voice of a conversation between a customer and a salesperson (S11). The voice acquisition unit 22 transmits the acquired voice to the information processing server 40. The information processing server 40 then converts the transmitted voice into text information (S12). Then, within the information processing server 40, the prompt and the converted text information are subjected to processing as a generation AI and analyzed (S13).

[0031] Below is an example of a prompt and the converted text information.

[0032] You are a showroom planner at Panasonic.

[0033] From the conversation below, please describe what the client's current preferences are regarding "cooking," "efficiency," "cleaning," "safety," and "design," adhering to the following requirements.

[0034] -Evaluate the strength of each item on a scale of 100 -Please also include the basis for each evaluation in approximately 100 characters. If it is not possible to determine from the conversation, a "-" will be entered instead of a score. -The following is the conversation- "Usually next to the stove." "Oh, that's right. *** Are you thinking of getting a gas or induction stove?" "Well, I'm using gas now, so, *I somehow feel like gas is easier to use,*** but will that change?" "Well, to be honest, the unit price of the product itself doesn't change much. However, the price range really does vary depending on the product, and for both induction and gas, yes. For gas, the list price ranges from around 100,000 yen to around 400,000 yen, and the same goes for induction, with the price varying from the upper 100,000 yen range to around 400,000 yen, so it really does depend on the product." "***." "Well, it depends. Also, with this side-by-side type, there isn't much difference. However, we also have side-by-side induction cooktops that are cheaper." "Have you ever used induction cooking anywhere?" *My parents' house has an induction cooktop. "Have you ever used it before and understand it from a practical standpoint?" "***Strength and things like that aren't easy to understand numerically***." "The drawback of induction is that the pots you can use are limited. It does have its advantages, though." "*Just get it all together*." "That's right." "If you want to cook using a wok or something similar, and you want to cook while slightly roasting the food, I recommend gas. But even if you don't want to use gas, if you value the ease of maintenance and safety of not having to use a flame, I would recommend induction. What do you think now?" "Right now, I use the wok quite a bit." "Oh, yes. Oh, I see. In that case, I highly recommend a gas stove that is lined up next to the stove. The handles of the pots and pans are lined up next to each other, so they don't hit your body. That's a great idea." "***that's why." "That's right. When you're boiling pasta, making sauce, or making soup in the back, that's what happens. It ends up looking like this. Yes, this is Panasonic's most popular product, and I'll tell you about it later if you stand a little further forward and try it out for yourself. The sink is also a little strange on this ceiling, and it's quite close to the gas, but if you move it to the side, you can get the full space, yes." "Um, it's *right." "Please sit here and wait for a moment. I'll go and make a copy. Thank you." "thank you."

[0035] The following is an example of an analysis result generated for the above prompt and converted character information.

[0036] Cooking ability: 80 The client prefers the ease of use of a gas stove and often uses a wok. He feels that a gas stove is more suitable for using a wok, so he has a certain level of preference for cooking.

[0037] Efficiency: 80 The client wanted to cook multiple dishes at the same time, so he preferred side-by-side stoves, emphasizing efficiency by making pasta, sauces, and soups at the same time.

[0038] Cleanability: 40 There was no specific mention of cleanability, but there was an explanation about the ease of maintenance of the 1H. However, since the priority is on using the wok, it is possible that cleanability was not a major concern.

[0039] Safety: 40 Although they are aware of the safety of induction cooktops, it is assumed that safety is not given much importance as cooking style takes priority.

[0040] Design:- Since there is no specific mention of the design, it is not possible to evaluate the client's particularities.

[0041] Next, the analysis result output unit 23 outputs the generated preference information and supplemental information (S14). For example, as shown in FIG. 3, as preference information, scores are assigned to several evaluation items ("Top Customer Preferences" in the figure). Furthermore, the reasons for the scores are summarized in about one line and written alongside. Also, topic suggestions to guide the conversation are included. The support system 100 queries the recommended plan server 50 in the background and obtains a response regarding the plan of the recommended product. As a result, in the figure, three plans, Plan 1 to Plan 3, can be output for such preference information.

[0042] When the salesperson selects one of the three plans, a pop-up display 10a is displayed so that the salesperson can check an outline of the selected plan, as shown in FIG. 4, for example. By pressing "Cancel" in the pop-up display 10a, the salesperson can return to the screen shown in FIG. 3, and by pressing "Print report," the salesperson can transition to a screen showing product plans to be presented to the customer. By pressing "Print report," it is determined that an instruction to print the plan shown in FIG. 2 has been made (Yes in S15). Then, a product plan corresponding to the selected plan is output (S16).

[0043] If the salesperson does not select any of the three plans, or selects a plan but does not press "Print Report," it is determined that there was no instruction to print the plan shown in Figure 2 (No in S15), and the process returns to step S11, where the same processing is continued for the continuous voice. Therefore, the preference information and supplemental information presented at one point in time are updated to different preference information and supplemental information at the next point in time, and the salesperson can roughly check the plans that can be printed on the pop-up display 10a, and change the conversation while checking the supplemental information until an appropriate plan is printed.

[0044] Then, by pressing "Report Output" in the pop-up display 10a, the plan output unit 25 outputs a product plan including a 3D layout of the product, detailed specifications, and an estimate as a report to be presented to the customer, as shown in Figures 5 and 6. The salesperson can show the customer the screens shown in Figures 5 and 6, or can press "Print" in the figures to present a printout output from a printer or the like to the customer. In addition, as the basis for such a proposal, information corresponding to the "Basis" column shown in Figure 3 may be included in the product plan to be output.

[0045] If a purchase is subsequently made for such a product plan, the salesperson will input this information, which will then be stored in the information storage server 30 in association with other information, making it possible to use the information for other purposes.

[0046] As described above, by supporting the conversation between the customer and the salesperson using the support system 100, the customer's requests obtained from the voice of the conversation with the customer can be visualized as preference information, which can lead to the salesperson presenting an appropriate product plan. Therefore, the support system 100 makes it possible to propose more appropriate product plans.

[0047] [Effects, etc.] As described above, the support system 100 according to the first embodiment is a support system 100 that supports the sale of products, and includes a conversion unit (part of the information processing server 40) that acquires audio of a conversation between a customer and a salesperson and converts the acquired audio of the conversation between the customer and the salesperson into text information, an analysis unit (part of the information processing server 40) that analyzes the converted text information and generates product preference information of the customer, and an output unit (analysis result output unit 23 and plan output unit 25) that outputs a product plan that is in line with the generated preference information based on the generated preference information and displays it on the information terminal 10.

[0048] Such a support system 100 can acquire and analyze the audio of a conversation between a customer and a salesperson, thereby analyzing the customer's requests from the audio and proposing an appropriate product plan. In particular, by performing the above analysis using the analysis unit, it is less likely that implicit requests contained in the customer's casual utterances will be overlooked, making it possible to propose a more appropriate product plan. Therefore, the support system 100 can propose a more appropriate product plan.

[0049] In addition, the support system 100 according to the second aspect is the support system 100 according to the first aspect, and the preference information includes a score indicating the degree of match with the customer's preferences for each of one or more pre-set evaluation items corresponding to the attributes of the product.

[0050] According to this, a score indicating the degree of agreement between the customer's preferences and each of one or more pre-set evaluation items corresponding to the product attributes can be generated and used as customer preference information.

[0051] The support system 100 according to a third aspect is the support system 100 according to the second aspect, in which the product attributes and the evaluation items correspond to each other by correlation coefficients.

[0052] This allows for the estimation of recommended products using the corresponding attributes based on the scores of the degree of agreement with the customer's preferences for each evaluation item and the correlation coefficient.

[0053] Furthermore, the support system 100 according to the fourth aspect is the support system 100 according to the third aspect, and the output unit multiplies the score for each evaluation item by a correlation coefficient with the corresponding attribute of the product to calculate an evaluation score for the attribute, calculates a sum of the evaluation scores for each product, and outputs a product plan based on the calculated sum of the evaluation scores.

[0054] This allows the system to calculate an evaluation score for each product attribute by multiplying the score of the degree of match with the customer's preferences for each evaluation item by the correlation coefficient with the corresponding product attribute, and then estimate which products should be recommended based on the total sum of the calculated evaluation scores.

[0055] Furthermore, the support system 100 according to the fifth aspect is the support system 100 according to any one of the first to fourth aspects, and acquires customer information relating to customer attributes generated based on customer input, and the output unit outputs a plan based on the preference information and the customer information.

[0056] This allows the customer information to be used as one of the pieces of information used to output the plan.

[0057] Furthermore, the support system 100 according to a sixth aspect is the support system 100 according to any one of the first to fifth aspects, and the output unit further outputs supplemental information for guiding the conversation between the customer and the salesperson so as to obtain the audio necessary to supplement the text information that is insufficient for generating preference information.

[0058] This allows the conversation between the customer and the salesperson to be guided so that the necessary voice information can be obtained to compensate for insufficient text information.

[0059] Furthermore, the support system 100 according to a seventh aspect is the support system 100 according to any one of the first to sixth aspects, and the conversion unit distinguishes between speech by a customer and speech by a salesperson and converts each of the spoken voices into text information.

[0060] This makes it possible to distinguish between customer speech and salesperson speech and convert each of the speeches into text information.

[0061] In addition, the support method according to the eighth aspect is a support method for supporting the sale of products, which is executed by a computer, and includes the steps of acquiring audio of a conversation between a customer and a salesperson and converting the acquired audio of the conversation between the customer and the salesperson into text information, analyzing the converted text information to generate product preference information for the customer, and outputting a product plan that is in line with the generated preference information based on the preference information and displaying it on an information terminal.

[0062] This makes it possible to achieve the same effects as the support system 100 described above.

[0063] A program according to a ninth aspect is a program for causing a computer to execute the support method according to the eighth aspect.

[0064] According to this, by causing a computer to execute the process, it is possible to achieve the same effects as the support system 100 described above.

[0065] (Other embodiments) Although the embodiments have been described above, the present invention is not limited to the above-described embodiments.

[0066] For example, the order of processes described in the flowcharts of the above embodiments is an example. The order of multiple processes may be changed, or multiple processes may be executed in parallel. In the above embodiments, processes executed by a specific processing unit may be executed by another processing unit.

[0067] Furthermore, the communication method between the devices in the above-described embodiments is not particularly limited. Wireless communication or wired communication may be performed between the devices. Furthermore, wireless communication and wired communication may be combined between the devices. Furthermore, when two devices communicate in the above-described embodiments, a relay device (not shown) may be interposed between the two devices.

[0068] In the above-described embodiments, each component may be realized by executing a software program suitable for that component. Each component may be realized by a program execution unit such as a CPU (Central Processing Unit) or a processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

[0069] Furthermore, each component may be realized by hardware. For example, each component may be a circuit (or integrated circuit). These circuits may form a single circuit as a whole, or each may be a separate circuit. Furthermore, each of these circuits may be a general-purpose circuit or a dedicated circuit.

[0070] In the above embodiment, the assistance system is realized by a plurality of devices, but it may be realized as a single device. When the assistance system is realized by a plurality of devices, the components of the assistance system may be distributed among the plurality of devices in any manner.

[0071] As described above, it is possible to realize a support system with an arrangement different from that of the above embodiment at the level of each component or at the level of one function of the component.

[0072] Furthermore, the general or specific aspects of the present invention may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a computer-readable recording medium such as a CD-ROM. Also, the present invention may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium. For example, the present invention may be realized as a computer-readable non-transitory recording medium on which a calculation program according to the above-described embodiment is recorded.

[0073] In addition, the present invention also includes forms obtained by applying various modifications to each embodiment that a person skilled in the art would think of, or forms realized by arbitrarily combining the components and functions of each embodiment within the scope of the present invention. [Explanation of symbols]

[0074] 10 Information terminals 10a Pop-up display 20 UI Server 21 Input reception section 22 Voice acquisition unit 23 Analysis result output section 24 Plan Search Department 25 Plan output section 30 Information storage server 40 Information Processing Server 50 Recommended Plan Servers 51 Recommended Plan DB 100 Support System

Claims

1. A support system for supporting product sales, a conversion unit that acquires a voice of a conversation between a customer and a salesperson and converts the acquired voice of the conversation between the customer and the salesperson into text information; an analysis unit that analyzes the converted character information and generates preference information of the customer regarding the product; an output unit that outputs a product plan that conforms to the generated preference information based on the preference information and displays the plan on an information terminal. Support system.

2. The preference information includes a score indicating a degree of agreement with the customer's preference for each of one or more pre-defined evaluation items corresponding to the attributes of the product. The assistance system according to claim 1 .

3. The product attributes and the evaluation items correspond to each other by a correlation coefficient. The assistance system according to claim 2 .

4. The output unit multiplying the score for each evaluation item by a correlation coefficient with the corresponding attribute of the product to calculate an evaluation score for the attribute; Calculating the sum of the evaluation points for each of the products, and outputting a plan for the product based on the calculated sum of the evaluation points. The assistance system according to claim 3 .

5. acquiring customer information relating to attributes of the customer, generated based on the customer's input; The output unit outputs the plan based on the preference information and the customer information. The assistance system according to claim 1 .

6. The output unit further outputs supplemental information for guiding a conversation between the customer and the salesperson so that the voice necessary to supplement the character information that is insufficient for generating the preference information can be obtained. The assistance system according to claim 1 .

7. The conversion unit distinguishes between the customer's speech and the salesperson's speech and converts each of the speeches into the text information. The assistance system according to claim 1 .

8. 1. A computer-implemented method for supporting the sale of goods, comprising: acquiring a voice of a conversation between a customer and a salesperson, and converting the acquired voice of the conversation between the customer and the salesperson into text information; analyzing the converted character information to generate preference information of the customer regarding the product; and a step of outputting a plan for the product in accordance with the generated preference information based on the preference information and displaying the plan on an information terminal. How to help.

9. A method for causing the computer to execute the support method according to claim 8. program.

Images